JP2739386B2 - Method and apparatus for determining radiation image reading conditions and / or image processing conditions - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a radiation image reading condition for obtaining an image signal for obtaining an image signal based on an image signal representing a radiation image, an image processing condition for performing image processing on the image signal, and / or Alternatively, the present invention relates to a method and apparatus for determining image processing conditions.

[0002]

2. Description of the Related Art A recorded radiographic image is read to obtain an image signal, and the image signal is subjected to appropriate image processing.
Reproduction and recording of images are performed in various fields. For example, an X-ray image is recorded using an X-ray film having a low gamma value designed to be compatible with the subsequent image processing, and the X-ray image is read from the film on which the X-ray image is recorded, and is converted into an electric signal. After converting and subjecting the electric signal (image signal) to image processing, the electric signal (image signal) is reproduced as a visible image in a copy photograph or the like, thereby obtaining a reproduced image having excellent image quality performance such as contrast, sharpness, and graininess. (See Japanese Patent Publication No. 61-5193).

[0003] Further, the applicant of the present invention has proposed that radiation (X-ray, α
Radiation, β-rays, γ-rays, electron beams, ultraviolet rays, etc.), a portion of this radiation energy is accumulated, and then, when irradiated with excitation light, such as visible light, the accumulated light shows stimulated emission according to the accumulated energy. Using stimulable phosphor (stimulable phosphor)
The radiation image information of a subject such as a human body is temporarily recorded on a sheet-shaped stimulable phosphor, and the stimulable phosphor sheet is scanned with an excitation light such as a laser beam to generate stimulated emission light. A radiation image recording / reproducing system has already been proposed in which the emitted light is photoelectrically read to obtain an image signal, and a radiation image of the subject is output as a visible image to a recording material such as a photographic material or a CRT based on the image data. (JP-A-55-12429, JP-A-56-11395, JP-A-55-163472, and JP-A-56-1)
04645, 55-116340, etc.).

[0004] This system has the practical advantage of being able to record images over a very wide radiation exposure area compared to conventional radiographic systems using silver halide photography. That is, in the case of the stimulable phosphor, it has been recognized that the amount of emitted light that is stimulated by excitation after accumulation is proportional to the radiation exposure amount over an extremely wide range. Even if fluctuates considerably, the amount of the stimulating light emitted from the stimulable phosphor sheet is read by the photoelectric conversion means with the reading gain set to an appropriate value and converted into an electric signal. Recording materials such as photographic photosensitive materials using
By outputting a radiation image as a visible image on a display device such as a CRT, it is possible to obtain a radiation image that is not affected by a change in radiation exposure.

[0005] In the above system, before the image signal is obtained by reading under the optimum reading conditions in accordance with the dose of the radiation applied to the stimulable phosphor sheet or the like, the stimulable phosphor sheet is previously irradiated with a low-level light beam. Perform a pre-read to scan and read the outline of the radiation image recorded on this sheet, analyze the pre-read image signal obtained by this pre-read,
After that, there is a system configured to scan the sheet by irradiating the sheet with a high-level light beam and read the radiation image under optimum reading conditions to obtain an image signal to perform a main reading.

Here, the reading condition is a general term for various conditions that affect the relationship between the amount of stimulated emission light in reading and the output of the reading device. It means the scale factor or the power of the excitation light in reading.

[0007] The high level / low level of the light beam means the magnitude of the energy of the light beam applied per unit area of the sheet or the energy of the photostimulated light emitted from the sheet, respectively. When it depends on the wavelength of the light beam (has a wavelength sensitivity distribution), the weight of the energy of the light beam irradiated per unit area of the sheet is weighted by the wavelength sensitivity. In other words, the method of changing the level of the light beam includes a method of using light beams of different wavelengths, a method of changing the intensity of a light beam emitted from a laser light source or the like, and inserting and removing an ND filter or the like on an optical path of the light beam. Known methods such as a method of changing the intensity of the light beam, a method of changing the scanning density by changing the beam diameter of the light beam, and a method of changing the scanning speed The method of people can be used.

[0008] Regardless of whether the system performs the pre-reading or the system which does not perform the pre-reading, the obtained image signal (including the pre-reading image signal) is analyzed, and the optimum image when the image signal is subjected to the image processing is analyzed. In some systems, processing conditions are determined. Here, the image processing condition is a general term for various conditions when a process that affects the gradation and sensitivity of a reproduced image based on an image signal is performed on the image signal. The method for determining the optimum image processing conditions based on this image signal is not limited to a system using a stimulable phosphor sheet, and obtains an image signal from a radiation image recorded on a recording sheet such as a conventional X-ray film. It is also applied to the system.

The calculation for obtaining the reading conditions and / or image processing conditions (hereinafter referred to as reading conditions, etc.) based on the image signals (including the pre-read image signals) is performed by statistically processing a large number of radiation images in advance. The algorithm has been determined from the results obtained (for example, Japanese Patent Laid-Open No. 60-185944,
See JP-A-61-280163).

As one of the conventionally employed algorithms, there is known a method of obtaining a histogram of an image signal and obtaining reading conditions and the like based on the histogram. The method of obtaining reading conditions and the like based on this histogram is subdivided into two parts. The maximum value and the minimum value of the range required as image information are obtained from the histogram of the image signal, and are sandwiched between the maximum value and the minimum value. (See Japanese Patent Application Laid-Open No. 60-156055), for example, obtains only the maximum value from the above-mentioned histogram, and determines a predetermined value from the maximum value. A method in which the subtracted value is set to a minimum value, and a range sandwiched between the maximum value and the minimum value is set as a range of necessary image information (see Japanese Patent Application Laid-Open No. 60-185944). A method in which a value obtained by adding a predetermined value to the minimum value is set as a maximum value, and a range sandwiched between the minimum value and the maximum value is set as a necessary image information range (see Japanese Patent Application Laid-Open No. 61-280163). Difference histogram (See JP-A-63-233658), a method using a cumulative histogram (see JP-A-61-170730), and a method of dividing a histogram into a plurality of small areas based on a discrimination criterion (see JP-A-63-233658). Two
A method is known in which a necessary range of image information is obtained by using a number of methods, and the reading conditions and the like are determined based on the obtained range.

On the other hand, in recent years, the concept of a neural network has appeared and is being applied to various fields.

This neural network inputs information (teacher signal) indicating whether an output signal output when a certain input signal is given is a correct signal or an erroneous signal. It is equipped with an error reverse propagation learning (back propagation) function that corrects the weight of the connection between units (the weight of the synaptic connection). When a new signal is input by repeatedly 'learning' Can increase the probability of outputting a correct answer.

Using this neural network,
It is possible to determine the above-described reading conditions and the like by using the image data of the radiation image as input.

That is, by inputting the image data of the radiation image to the neural network and outputting reading conditions and the like, and by repeatedly "learning" the neural network in advance, the correct reading conditions and the like can be gradually obtained. can do.

[0015]

However, in the above-described method based on histogram analysis for obtaining reading conditions and the like based on the histogram of image signals, various characteristic values are calculated by performing threshold processing and local analysis. For this reason, the local feature of the histogram may be given too much importance to give an incorrect result.

Further, the method of obtaining the reading conditions and the like using the above-described neural network is not a local analysis, so that it is possible to prevent an erroneous result from giving too much emphasis to the local features. In order to repeat the learning by inputting as it is, it is necessary to spend an enormous amount of time on the learning, which is not realistic.

Accordingly, the present invention solves both the disadvantages of the method using a histogram and the method using a neural network, and uses a neural network that can make a global judgment, while reducing the learning amount and improving efficiency. It is an object of the present invention to provide a method and an apparatus for determining radiation image reading conditions and / or image processing conditions with high accuracy.

[0018]

According to one aspect of the present invention, there is provided a pre-reading system using the above-described stimulable phosphor sheet. That is, the first radiation image reading condition and / or image processing condition determination method of the present invention is as follows.
Based on a first image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet on which the radiation image is recorded with excitation light and reading the stimulated emission light emitted from the stimulable phosphor sheet. Reading conditions for irradiating the stimulable phosphor sheet with excitation light again, reading the stimulated emission light emitted from the stimulable phosphor sheet to obtain a second image signal representing the radiation image, and / or In a method for determining a radiation image reading condition and / or an image processing condition for obtaining an image processing condition when performing image processing on the obtained second image signal, the method comprises: (1) inputting a histogram of the first image signal to a neural network; And outputting the reading condition and / or the image processing condition from the neural network.

The second method for determining a radiation image reading condition and / or an image processing condition according to the present invention is the method for determining a radiation image reading condition and / or an image processing condition as described above. And the additional information on the radiation image recorded on the stimulable phosphor sheet are input to a neural network, and the neural network outputs the reading condition and / or the image processing condition. Things.

Further, the third method for determining a radiation image reading condition and / or an image processing condition according to the present invention comprises the following steps: (1) irradiating the stimulable phosphor sheet on which the radiation image is recorded with excitation light, Based on the first image signal representing the radiation image obtained by reading the emitted stimulating light, the stimulable phosphor sheet was again irradiated with excitation light and emitted from the stimulable phosphor sheet. Radiation image reading for obtaining reading conditions for obtaining a second image signal representing the radiation image by reading the stimulated emission light and / or image processing conditions for performing image processing on the obtained second image signal In the method for determining conditions and / or image processing conditions, the value of the image signal indicating the maximum light emission amount of the histogram of the first image signal excluding the through-hole corresponding to the direct radiation part is defined as the maximum value; value After normalizing the maximum frequency of the histogram between a minimum value of said first image signal,
Inputting the normalized histogram to the neural network such that a predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is always input to the same input unit of the neural network; Outputting the reading condition and / or the image processing condition from the neural network; correcting the reading condition and / or the image processing condition output from the neural network based on the predetermined value; It is characterized in that reading conditions and / or image processing conditions are determined.

Further, a fourth method for determining a radiation image reading condition and / or an image processing condition according to the present invention is a method for determining a radiation image reading condition and / or an image processing condition as described above. Of the histogram, the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation part is the maximum value, the histogram between the maximum value and the minimum value of the first image signal. After normalization at the maximum frequency, the normalized histogram and the additional information for the radiation image recorded on the stimulable phosphor sheet are stored in a neural network, and the maximum value and minimum value of the normalized histogram image signal are stored. A predetermined value between the input value and the input value is always input to the same input unit of the neural network. And outputting the reading condition and / or the image processing condition, and correcting the reading condition and / or the image processing condition output from the neural network based on the predetermined value, to obtain a final reading condition and / or The image processing condition is determined.

The radiographic image reading condition and / or image processing condition determining apparatus according to the present invention for carrying out the above method firstly irradiates the stimulable phosphor sheet on which the radiographic image is recorded with excitation light. Based on a first image signal representing the radiation image obtained by reading the stimulated emission light emitted from the stimulable phosphor sheet, the stimulable phosphor sheet is again irradiated with excitation light to irradiate the stimulable phosphor sheet with the stimulable phosphor. Reading conditions when reading the stimulated emission light emitted from the body sheet to obtain a second image signal representing the radiation image and / or image processing when performing image processing on the obtained second image signal In a radiation image reading condition and / or image processing condition determining device for obtaining a condition, {histogram calculating means for calculating and outputting a histogram of the first image signal; Enter a more output histogram, the reading conditions and on the basis of the histogram /
Or a neural network for outputting the image processing conditions.

Second, in order to further increase the accuracy, in the above apparatus, in addition to the histogram calculating means for calculating and outputting the histogram of the first image signal, the histogram recorded on the stimulable phosphor sheet is added. Further, using additional information output means for outputting additional information such as patient information or a radiographing method concerning the radiation image, the histogram output by the histogram calculation means and the additional information output by the additional information output means are neurally connected. And inputting the reading condition and / or the neural network based on the histogram and the additional information.
Alternatively, image processing conditions are output.

Third, the radiation image obtained by irradiating the stimulable phosphor sheet on which the radiation image is recorded with excitation light and reading the stimulated emission light emitted from the stimulable phosphor sheet. A second image representing the radiation image by reading the stimulable light emitted from the stimulable phosphor sheet again by irradiating the stimulable phosphor sheet with excitation light based on the first image signal representing the radiation image. A radiation image reading condition and / or an image processing condition determining device for obtaining a reading condition when obtaining a signal and / or an image processing condition when performing image processing on the obtained second image signal; Calculate the histogram of the image signal, from the histogram, detect the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation part, the value of the detected image signal as the maximum value, The maximum Calculating means for normalizing and outputting the histogram with the maximum frequency between the minimum value of the first image signal and the output value; and ◆ an image signal of the normalized histogram output from the normalized histogram output from the calculating means. A predetermined value between the maximum value and the minimum value is input to the same input unit, and the reading condition and / or the image processing condition are output based on the normalized histogram. And a correction means for correcting the reading conditions and / or the image processing conditions output from the neural network based on the predetermined value.

Further, an apparatus for performing the fourth method includes:
Based on a first image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet on which the radiation image is recorded with excitation light and reading the stimulated emission light emitted from the stimulable phosphor sheet. Reading conditions for irradiating the stimulable phosphor sheet with excitation light again, reading the stimulated emission light emitted from the stimulable phosphor sheet to obtain a second image signal representing the radiation image, and / or In a radiation image reading condition and / or image processing condition determination device for obtaining image processing conditions when performing image processing on the obtained second image signal, a histogram of the first image signal is calculated, and From, the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation portion is detected, the detected image signal value is set to the maximum value, the maximum value and the first image signal Minimum of Calculating means for normalizing and outputting the histogram at the maximum frequency, output information outputting means for outputting additional information relating to the radiation image recorded on the stimulable phosphor sheet, output from the arithmetic means. The normalized histogram and the additional information output by the additional information output means are input to an input unit in which a predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is always the same. And a neural network that outputs the reading condition and / or the image processing condition based on the normalized histogram; and ◆ the reading condition output from the neural network based on the predetermined value. And / or correction means for correcting the image processing conditions.

Another method according to the present invention is not limited to the stimulable phosphor sheet, but determines image processing conditions. That is, the fifth radiographic image processing condition determining method is a radiographic image processing condition determining method for obtaining an image processing condition when performing image processing on the image signal based on the image signal representing the radiographic image. The histogram is input to a neural network, and the image processing conditions are output from the neural network.

Further, the apparatus for implementing the fifth method is a radiographic image processing condition determining apparatus for obtaining an image processing condition for performing image processing on the image signal based on the image signal representing the radiographic image. A histogram calculating means for calculating and outputting a histogram of the image signal; and a histogram output by the histogram calculating means,
And a neural network that outputs image processing conditions based on the histogram.

Further, in the sixth method, that is, in the image processing condition determining method, additional information regarding the radiographic image is input to the neural network in addition to the histogram of the image signal as described above, and the neural network transmits the additional information. The image processing conditions are output.

Further, the apparatus for carrying out the sixth method is the same as the apparatus for carrying out the fifth method, wherein in addition to the histogram calculating means for calculating and outputting the histogram of the image signal, patient information relating to the radiation image and the like are obtained. Using an additional information output unit that outputs additional information such as a photographing method, the histogram output by the histogram calculation unit and the additional information output by the additional information output unit are input to a neural network, and the neural network The image processing conditions are output based on the histogram and the additional information.

A seventh method is a radiographic image processing condition determining method for obtaining image processing conditions for performing image processing on an image signal based on the image signal representing the radiographic image. The maximum value is the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation portion, and the histogram is normalized at the maximum frequency between the maximum value and the minimum value of the image signal. After that, the normalized histogram is input to the neural network such that a predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is always input to the same input unit of the neural network. Input, output the image processing condition from the neural network, and output from the neural network based on the predetermined value. Performs correction of the image processing condition, and is characterized in determining the final image processing conditions.

An apparatus for implementing the seventh method is a radiation image processing condition determining apparatus for obtaining image processing conditions for performing image processing on an image signal based on the image signal representing the radiation image. A histogram of the signal is calculated, and from the histogram, a value of an image signal indicating a maximum light emission amount excluding a penetration part corresponding to a direct radiation part is detected, and a value of the detected image signal is set to a maximum value. Calculating means for normalizing and outputting the histogram at the maximum frequency between the maximum value and the minimum value of the image signal; and ◆ a normalized histogram output from the calculating means, and an image signal of the normalized histogram. A predetermined value between the maximum value and the minimum value is input so as to be always input to the same input unit, and the image processing condition is output based on the normalized histogram. And a neural network that,
A correction means for correcting the image processing conditions output from the neural network based on the predetermined value.

An eighth method is the image processing condition determining method, wherein:
After maximizing the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation portion and normalizing the histogram at the maximum frequency between the maximum value and the minimum value of the image signal The normalized histogram and the additional information for the radiation image recorded on the stimulable phosphor sheet are stored in a neural network in a predetermined manner between the maximum value and the minimum value of the image signal of the normalized histogram. Values are input so as to be always input to the same input unit of the neural network, the image processing conditions are output from the neural network, and the image processing conditions output from the neural network are output based on the predetermined value. And the final image processing conditions are determined.

Further, the apparatus for implementing the eighth method is a radiographic image processing condition determining apparatus for obtaining image processing conditions for performing image processing on the image signal based on the image signal representing the radiographic image. A histogram of the signal is calculated, and from the histogram, a value of an image signal indicating a maximum light emission amount excluding a penetration part corresponding to a direct radiation part is detected, and a value of the detected image signal is set to a maximum value. Calculating means for normalizing and outputting the histogram at a maximum frequency between a maximum value and a minimum value of the image signal; and additional information for outputting additional information regarding the radiation image recorded on the stimulable phosphor sheet. Output means, and を the normalized histogram output from the arithmetic means and the additional information output from the additional information output means, A neural network that inputs a predetermined value between the maximum value and the minimum value of the image signal so as to be always input to the same input unit, and outputs the image processing condition based on the normalized histogram, ◆
Correction means for correcting the image processing conditions output from the neural network based on the predetermined value.

Here, there is a "predetermined value between the maximum value and the minimum value of the normalized histogram image signal", and the predetermined value is between the maximum value and the minimum value of the image signal. Any value may be used as long as a predetermined value such as a maximum value, a minimum value, or an intermediate value between the maximum value and the minimum value of the image signal is used. To input the predetermined value so as to be always input to the same input unit of the neural network means that the value of the image signal changes and the predetermined value always changes even if the predetermined value changes. That is, a value other than the predetermined value of the image signal is input to a predetermined unit, and is sequentially input to a unit next to the certain predetermined unit based on the predetermined value.

[0035]

One of the radiographic image reading condition and / or image processing condition determining devices according to the present invention inputs a histogram of an image signal or a signal obtained by adding additional information such as patient information and an imaging method to a neural network. Since the reading conditions and / or the image processing conditions are output by a neural network based on the histogram or a result of adding the additional information to the histogram, only the histogram is used by a neural network capable of globally judging. In this case, it is possible to prevent an error due to local analysis, which is a drawback in the case where an error occurs, and reduce the amount of learning of the neural network, thereby efficiently and accurately determining the image reading condition and / or the image processing condition.

Another embodiment of the radiation image reading condition and / or image processing condition determining apparatus according to the present invention is an image signal showing a maximum light emission amount of a histogram of an image signal excluding a through portion corresponding to a direct radiation portion. Is the maximum value, and the reading conditions and / or the image processing conditions are obtained and corrected based on the histogram normalized between the maximum value and the minimum value of the image signal, so that the correction does not depend on the escape portion. In addition, stable reading conditions and / or image processing conditions can be obtained from the histogram of the image signal of only the subject portion.

Further, a constant image signal is not always obtained in a radiographic image, and the sensitivity changes due to the difference in radiation dose, and the value of the image signal also changes. That is, the minimum value of the image signal of the histogram and the maximum value of the image signal excluding the unplugged portion also change due to the change in the sensitivity. However, the other one of the radiation image reading conditions and / or the image processing condition determination device of the present invention includes: Even if the sensitivity changes, a predetermined value between the maximum value and the minimum value of the normalized histogram image signal is always input to the same input unit of the neural network, and the reading conditions and / or the image output by the neural network are output. By correcting the processing conditions based on a predetermined value between the maximum value and the minimum value of the normalized histogram image signal, stable image reading conditions and / or image processing conditions independent of the sensitivity of the radiation image can be obtained. Obtainable.

Further, another one of the radiation image reading condition and / or image processing condition determining apparatus according to the present invention uses the above-described normalized histogram or a histogram obtained by adding additional information such as patient information and an imaging method to a neural network. Since the image data is input to a network, the reading conditions and / or image processing conditions are output by a neural network based on the normalized histogram or a value obtained by adding additional information to the histogram, and correction is performed based on the predetermined value. Similarly to one of the above-described radiation image reading conditions and / or image processing conditions according to the present invention, a neural network capable of making a global judgment prevents errors due to local analysis, which is a drawback when only histograms are used. At the same time, reduce the amount of learning of the neural network,
Image reading conditions and / or image processing conditions can be determined efficiently and with high accuracy.

[0039]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing the basic concept of the first embodiment of the present invention. That is, the basic concept of the method according to the first embodiment of the present invention is to calculate the histogram 2 of the image signal 1 representing the radiographic image and use it alone or in combination with the patient information or the radiographing method for the radiographic image. The additional information 3 is added and input to the neural network 4.
Alternatively, the image processing condition 5 is output.

Next, an X-ray image reading apparatus including a computer system to which a method for determining radiation image reading conditions and / or image processing conditions according to the first embodiment of the present invention is applied will be described in detail.

FIG. 2 is a perspective view showing a computer system including an X-ray image reading apparatus and a radiation image reading condition and / or image processing condition determining apparatus according to the first embodiment of the present invention. This system uses the above-described stimulable phosphor sheet to perform pre-reading.

In an X-ray imaging apparatus (not shown), an X-ray image of the subject is stored and recorded on the stimulable phosphor sheet. The stimulable phosphor sheet 11 on which the X-ray image is recorded is first scanned by a weak light beam to emit only a part of the radiation energy stored in the sheet 11 and read by the pre-reading means 100 for pre-reading. Set to position. The stimulable phosphor sheet 11 set at this predetermined position is conveyed (sub-scanning) in the direction of arrow Y by sheet conveying means 13 such as an endless belt driven by a motor 12. On the other hand, the weak light beam 15 emitted from the laser light source 14 is reflected and deflected by the rotating polygon mirror 16 driven by the motor 23 and rotated at high speed in the direction of the arrow, passes through the focusing lens 17 such as an fθ lens, Is changed, and the light is incident on the sheet 11 and is main-scanned in an arrow X direction substantially perpendicular to the sub-scanning direction (arrow Y direction). From the portion of the sheet 11 to which the light beam 15 has been irradiated, a stimulating luminescent light 19 of a light amount corresponding to the accumulated and recorded radiation image information is diverged, and the stimulating luminescent light 19 is guided by a light guide 20. , Are photoelectrically detected by a photomultiplier (photomultiplier tube) 21. The light guide 20 is formed by molding a light-guiding material such as an acrylic plate, and is arranged such that a linear incident end face 20a extends along a main scanning line on the stimulable phosphor sheet 11. The light receiving surface of the photomultiplier 21 is connected to the emission end face 20b formed in an annular shape. The stimulated emission light 19 entering the light guide 20 from the incident end face 20a is
The light is emitted from the emission end face 20b and received by the photomultiplier 21, and the amount of photostimulated light 19 representing the radiation image is determined by the photomultiplier 21.
Is converted into an electric signal.

The analog output signal S output from the photomultiplier 21 is logarithmically amplified by a logarithmic amplifier 26,
It is digitized by the A / D converter 27, and the pre-read image signal S _P
Is obtained. The pre-reading signal level of the image signal S _P is proportional to the amount of the logarithm of the photostimulated luminescence light emitted from each pixel of the sheet 11.

In the pre-reading, the reading conditions, that is, the voltage value applied to the photomultiplier 21 and the amplification factor of the logarithmic amplifier 26 are set so that the radiation energy stored in the stimulable phosphor sheet 11 can be read over a wide area. Etc. are defined.

The preliminary read-out image signals S _P obtained is input to the computer system 40. This computer system
Numeral 40 denotes an example of the radiation image reading condition and / or image processing condition determining apparatus of the present invention. The main unit 41 includes a CPU and an internal memory, and a floppy disk as an auxiliary memory is inserted and driven. The system comprises a drive unit 42, a keyboard 43 for an operator to input necessary instructions and the like to the computer system 40, and a CRT display 44 for displaying necessary information.

[0047] In the computer system 40 within are recognized division pattern and the irradiation field is needed based on the inputted pre-reading image signals S _P, then the histogram is determined based on the preliminary read-out image signals S _P On the basis of this histogram, the neural network determines the reading conditions at the time of book reading, that is, the sensitivity Sk and latitude Gp at the time of book reading, and according to the determined sensitivities Sk and latitude Gp, for example, a photomultiplier.
The voltage value applied to 21 'and the amplification factor of logarithmic amplifier 26' are controlled.

Here, the latitude Gp corresponds to the light amount ratio of the strongest stimulated emission light to the weakest stimulated emission light converted into an image signal at the time of main reading.
The sensitivity Sk is a photoelectric conversion rate that determines a level of an image signal of a predetermined amount of stimulated emission light.

The stimulable phosphor sheet 11 'for which pre-reading has been completed
Is set at a predetermined position of the main reading means 100 ', the sheet 11' is scanned by a light beam 15 'stronger than the light beam used for the pre-reading, and an image signal is obtained according to the reading conditions determined as described above. However, since the configuration of the main reading means 100 'is substantially the same as the configuration of the pre-reading means 100, the components corresponding to the components of the pre-reading means 100 are provided with the pre-reading means 10'.
The numbers used in 0 are shown with dashes, and the description is omitted.

The A / D converter 27 image signals S _Q obtained by being digitized 'is inputted again to the computer system 40. Appropriate image processing on the image signal S _Q is a computer system 40 within are subjected, the image signal subjected to the image processing is sent to a not-shown reproducing apparatus, X-rays image is reproduced and displayed based on the image signal in the playback device Is done.

[0051] In the computer system 40, on the basis of the preliminary read-out image signals S _P, a histogram is calculated, the image on an image signal obtained by reading condition and / or reading at the time of real reading by the neural network on the basis of the histogram Image processing conditions for performing the processing are determined.

[0052] pre-reading image signals S _P is input to the first arithmetic unit for implementing a method for determining read conditions and / or image processing conditions in accordance with an embodiment of the present invention provided in the computer system 40. In this embodiment, a combination of hardware and software for realizing a function corresponding to each unit of the present invention in the computer system 40 is considered as each unit.

[0053] Figure 3 is a diagram showing a histogram of the preliminary read-out image signals S _P. In the figure, the horizontal axis represents the value of the preliminary read-out image signals S _P, the vertical axis (upward) is pre-reading image signal S having the value
(Each preliminary readout image signals S _P corresponding to each pixel of the X-ray image 1 count bracts) _P frequency of represent. The vertical axis of FIG. (Lower) shows the value of the image signals S _Q obtained by real reading.

[0054] and the mountains A corresponding to the subject image roughly in the histogram 70, which corresponds to a direct X-ray unit, there is a mountain B in the large positional value of the preliminary read-out image signals S _P than mountain A I do. Here searches the position at which the frequency of the histogram 70 is T from the smallest value of the preliminary read-out image signals S _P to the larger value, the first position a the frequency is T and the next position b
Is pre-reading image signals S _P1, S _P2 corresponding to the demanded. It is determined that the range between the two pre-read image signals S _P1 and S _P2 obtained in this way corresponds to the subject image on the X-ray image. So when to perform the real reading, the preliminary read-out image signals S _P1, S emitted light, each image signal emitted from the position on the corresponding X-ray image to _P2 S _Q minimum S _Q1 of
The reading condition is determined so as to be converted into the maximum value S _Q2 , that is, the straight line G1 shown in FIG. 3, and the main reading is performed according to the reading condition. Here, the reading conditions are
The position of the straight line G1 in the horizontal direction in FIG. 3 (sensitivity Sk) and the inclination of the straight line G1 (latency Gp) are determined.

However, when the histogram 70 has irregularities that cross the threshold value T, for example, as in a histogram 70 'shown in FIG. 3, a straight line corresponding to the reading condition is erroneously obtained as a straight line G1'. a pre-reading image signals S _P1, S _P2 '(corresponding to the region on the histogram a) region sandwiched' portion only carries the image signals S _Q of the object image when performing real reading on the basis of the reading conditions In this case, for example, it is necessary to perform re-photographing.

Therefore, in the present invention, the data of the histogram is input to the neural network so that the straight line G1 in FIG.
The neural network learns the correct reading conditions corresponding to the histogram by learning, and outputs the correct reading conditions by the neural network.

In order to further improve the accuracy of condition determination in addition to the histogram, additional information on the radiation image is input to the neural network, and reading conditions are output according to the combination of the additional information and the histogram. You may. Thereby, the accuracy of condition determination by the neural network can be greatly improved. As the additional information, for example, patient information such as a patient name and an imaging part, and an imaging method such as a simple imaging, a contrast imaging, and a tomography can be used.

Next, an X-ray image reading apparatus including a computer system to which a method for determining radiation image reading conditions and / or image processing conditions according to a second embodiment of the present invention is applied will be described.

FIG. 4 is a block diagram showing the basic concept of the second embodiment of the present invention. The Figure 5 is pre-reading image signals S _P
FIG. 3 is a diagram simply showing an example of a histogram obtained by normalizing the histogram of FIG. 1 and a neural network according to the present invention. That is, the basic concept of the method according to the second embodiment of the present invention is that the histogram 52 of the image signal 51 representing the radiographic image is calculated by the calculating means 59 and the assembling part corresponding to the radiological part is directly removed from the histogram 52. The value of the image signal indicating the maximum light emission amount is detected, the image signal Smax1 is set to the maximum value, the histogram 52 is normalized between the maximum value Smax1 and the minimum value Smin of the image signal 51, and the normalized histogram 54 is used alone. Or additional information 58 relating to the radiation image is output to the neural network 55. As shown in FIG. 5, a predetermined value between the maximum value Smax1 and the minimum value Smin of the image signal of the normalized histogram 54 is provided to the neural network 55. Is input so that the maximum value Smax1 is always input to the same input unit (here, the lower input unit) of the neural network 55. The sensitivity correction is performed on the image reading conditions and / or image processing conditions output from the network 55, and the optimum image reading conditions and / or image processing conditions 57 are output.

An X-ray image reading apparatus and a computer system to which the method for determining radiation image reading conditions and / or image processing conditions according to the second embodiment of the present invention are applied are described. Except for X according to the first embodiment of the present invention shown in FIG.
Since they are the same as the line image reading device and the radiation image reading condition and / or the image processing condition determining device, the detailed description is omitted here, and the radiation image reading condition and / or image processing according to the second embodiment of the present invention will be described below. A computer system to which the condition determination method is applied will be described.

[0061] In the second embodiment the computer system 40 in FIG. 2 in the example of the present invention, the division pattern and the irradiation field as needed based on the inputted pre-reading image signals S _P are recognized, and then the pre-reading histogram is determined based on the image signal S _P, and detects the value of the image signal indicative of the maximum light emission amount, excluding be missing portion corresponding to the radiation unit directly from the histogram, the maximum value S value of the image signal
and max1, between the minimum value Smin of the maximum value Smax1 and preliminary readout image signal S _P, the histogram is normalized, the normalized histogram, as shown in FIG. 5, the image signal of the histogram normalized Are input to the neural network such that the maximum values Smax1 and S'max1 are always input to the same input unit (lower unit in FIG. 5) even when the values of The reading conditions at the time of the main reading, that is, the sensitivity Sk 'and the latitude Gp' at the time of the main reading are obtained, the sensitivity Sk 'and the latitude Gp' are corrected based on the maximum value Smax1, and according to the corrected sensitivity Sk and the latitude Gp. For example, the voltage value applied to the photomultiplier 21 'and the amplification factor of the logarithmic amplifier 26' are controlled.

Next, the main reading is performed by the main reading means 100 'in FIG. 2 in the same manner as in the first embodiment of the present invention under the reading conditions determined as described above, and an image signal is obtained.

[0063] A / D converter 27 image signals S _Q obtained by being digitized 'is inputted again to the computer system 40. Appropriate image processing on the image signal S _Q is a computer system 40 within are subjected, the image signal subjected to the image processing is sent to a not-shown reproducing apparatus, X-rays image is reproduced and displayed based on the image signal in the playback device Is done.

[0064] In the computer system 40, on the basis of the preliminary read-out image signals S _P, the histogram is calculated, detecting the value of the image signal indicative of the maximum light emission amount, excluding be missing portion corresponding to the radiation section directly from this histogram The value of the image signal is set to the maximum value Smax1, and the histogram is normalized between the maximum value Smax1 and the minimum value Smin of the image signal. The normalized histogram is such that the maximum value Smax1 is always the same as shown in FIG. Input unit (lower unit)
Is input to the neural network so as to be input to the neural network. Based on the normalized histogram, the neural network determines reading conditions at the time of main reading and / or image processing conditions at the time of performing image processing on an image signal obtained by reading. And the normalized maximum value Smax1 of the histogram
The image processing conditions are corrected based on the maximum value Smax1, which is a predetermined value between the maximum value Smin and the minimum value Smin, and the optimum image processing conditions for the read X-ray image are determined.

[0065] pre-reading image signals S _P is input to the second arithmetic unit for implementing a method for determining read conditions and / or image processing conditions in accordance with an embodiment of the present invention provided in the computer system 40. In this embodiment, a combination of hardware and software for realizing a function corresponding to each unit of the present invention in the computer system 40 is considered as each unit.

Next, a method for normalizing the histogram according to the second embodiment of the present invention will be described.

[0067] Figure 6 is a diagram showing a histogram of the preliminary read-out image signals S _P. In the figure, the horizontal axis represents the value of the preliminary read-out image signals S _P, the vertical axis (upward) is pre-reading image signal S having the value
(Each preliminary readout image signals S _P corresponding to each pixel of the X-ray image 1 count bracts) _P frequency of represent.

[0068] and mountain C corresponding to the object image roughly in this histogram 80 shows to missing portion corresponding to the straight line X-ray unit, is in the large positional value of the preliminary read-out image signals S _P than mountain C Mountain D exists. Here, the value of the pre-read image signal indicating the maximum light emission amount excluding the unplugged portion of the histogram 80 is detected, and this value is set as the maximum value Smax1. Also histogram
The value of the minimum of the preliminary read-out image signals at 80 and the minimum value Smin, the normalization of the histogram 80 with a maximum frequency of pre-reading image signals S _P between the minimum value Smin and Smax1 the preliminary readout image signal S _P. That is, the normalized histogram is a normalized histogram corresponding only to the subject image, not depending on the unattended portion.

However, when the histogram 80 shows a value of the pre-read image signal different from the histogram 80 due to the change in the X-ray irradiation amount, that is, a histogram 80 'shown in FIG. , The minimum value of the image signal Smin
And the value of the maximum value Smax1 also changes, and the value of the normalized histogram image signal input to the neural network is wide. Therefore, inputting this value as it is to the neural network requires an enormous amount of time for learning. And the accuracy of outputting correct image reading conditions and / or image processing conditions decreases.

Therefore, in the second embodiment of the present invention, a stable and highly accurate image reading condition and / or image processing condition independent of the sensitivity is output even in such a case as shown in FIG. A predetermined value (the maximum value Smax1 in FIGS. 5 and 6) between the maximum value Smax1 and the minimum value Smin of the image signal of the histogram thus normalized is always input to the same input unit of the neural network. Even if the image signal value of the normalized histogram input to the neural network changes, almost the same condition is always maintained, and a predetermined value (for the reading condition and / or the image processing condition output from the neural network) In FIGS. 5 and 6, correction is performed based on the maximum value Smax1), and reading conditions and / or image processing conditions suitable for an image are output.

The maximum value S is defined as a predetermined value between the maximum value and the minimum value of the normalized histogram image signal.
Although max1 was used, this value may be any value between the maximum value and the minimum value of the normalized histogram image signal, for example, the minimum value of the image signal, or an intermediate value between the maximum value and the minimum value. May be used. In this case, when the predetermined value is the minimum value, the predetermined value is input to the upper input unit shown in FIG.
What is necessary is just to make it input into the input unit located in the middle of the input unit shown in FIG.

When a predetermined value (here, the maximum value Smax1) of the image signal of the normalized histogram is input to a certain input unit which is always the same in the neural network, if a predetermined value of the image signal other than this predetermined value is input. The value is sequentially input to an input unit adjacent to a predetermined input unit based on a predetermined value. For example, in the present invention, when the maximum value Smax1 is input to the lower input unit as shown in FIG. 5, the normalized histogram image signal from the maximum value Smax1 to the minimum value Smin is transmitted from the lower input unit to the upper input unit. They are sequentially input. Therefore, when the predetermined value is set to the minimum value, the input unit at the upper end is sequentially shifted to the input unit at the lower end. When the predetermined value is set to an intermediate value between the maximum value and the minimum value, the input unit shown in FIG. Input is performed sequentially from the input unit toward the upper and lower input units.

In addition to the above-described normalized histogram, in order to further improve the accuracy of condition determination, additional information relating to the radiation image is input to a neural network, and reading conditions are output according to the combination of the additional information and the histogram. You may make it do. Thereby, the accuracy of condition determination by the neural network can be greatly improved.

Hereinafter, a method of repeating learning by a neural network and outputting correct reading conditions by the neural network will be described in detail.

FIG. 7 is a diagram showing an example of a neural network having an error back propagation learning (back propagation) function. Error backpropagation learning (backpropagation) is, as described above, by comparing the output of the neural network with the correct answer (teacher signal) to sequentially connect weights (weights of synaptic connections) from the output side to the input side. Is a “learning” algorithm that modifies

[0076] As shown, the first layer of the neural network (input layer), second layer (intermediate layer), a third layer (output layer) is _one n respectively, _two n, two of the units (Neurons). Each of the signals F ₁ , F ₂ ,..., F _n1 input to the first layer (input layer) is a histogram calculated based on a pre-read image signal corresponding to each pixel of the X-ray image, or is normalized. It is a signal representing a histogram, and includes two outputs Y3,1 from a third layer (output layer).
Y3,2 are signals corresponding to sensitivity and latitude, respectively, at the time of main reading. Let the i-th unit in the k-th layer be U
k, i, each input to the unit Uk, i is Xk, i, each output is Yk, i, and the weight of the connection from Uk, i to Uk + 1, j is Wk, i; k +
1, j, and each unit Uk, j has the same characteristic function.

[0077]

(Equation 1)

It is assumed that At this time, the input Xk, j and the output Yk, j of each unit Uk, j are

[0079]

(Equation 2)

[0080]

(Equation 3)

Is obtained. However, each input F ₁ , F ₂ ,... To each unit U 1, i (i = 1, 2,..., N ₁ ) constituting the input layer
.., F _n1 are not weighted and each unit U1, i
(i = 1, 2,..., n ₁ ). The input n ₁ signals F ₁ , F ₂ ,..., F _n1 are weights Wk, i; k + 1,
final output Y3,1, Y, weighted by j
The reading conditions (sensitivity and latitude) at the time of the main reading are obtained by this.

Here, a method of determining the weights Wk, i; k + 1, j of the respective connections will be described. First, the initial value of the weight Wk, i; k + 1, j of each connection is given by a random number. In this case, even if the input F ₁ to F _n1 is varied to maximize the output Y3,1, so Y3,2 is a value or a value close thereto within a predetermined range in advance to limit the scope of the random number Is preferred.

[0083] optimal reading condition is known X-ray image is read out as the stimulable phosphor sheet that has been recorded has numerous above, this preliminary readout image signal S _P obtained by is thinned above n ₁ number of input _{F 1, F 2, ...,} F n1 is required. The n ₁ inputs F ₁ , F ₂ ,..., F _n1 are input to the neural network shown in FIG.
The output Yk, i of k, i is monitored.

When the outputs Yk, i are obtained, final outputs Y3,1, Y3,2 and teacher signals (sensitivity "Y3,1" and latitude "Y3,1") as correct reading conditions for this image are obtained. 2 ") squared error

[0085]

(Equation 4)

[0086]

(Equation 5)

Is obtained. The weights Wk, i; k + 1, j of the respective connections are corrected as follows so that the square errors E ₁ and E ₂ are minimized. The output of Y3,1 is described below, and Y3,2 is the same as Y3,1 and will not be described here.

To minimize the square error E ₁ , this E ₁
Is a function of Wk, i; k + 1, j

[0089]

(Equation 6)

As described above, the weight Wk, i; k + 1, j of each connection is corrected. Here, η is a coefficient called a learning coefficient.

Here,

[0092]

(Equation 7)

From the equation (2),

[0094]

(Equation 8)

Thus, equation (7) is

[0096]

(Equation 9)

## EQU10 ##

Here, from equation (4),

[0099]

(Equation 10)

By transforming equation (10) using equation (3),

[0101]

[Equation 11]

Here, from equation (1),

[0103]

(Equation 12)

Therefore,

[0105]

(Equation 13)

The following is obtained.

In equation (9), k = 2, and equation (11), (1
Substituting equation (3) into equation (9) gives

[0108]

[Equation 14]

By substituting equation (14) into equation (6),

[0110]

(Equation 15)

Is obtained. According to the equation (15), W2, i; 3,1
The weight of each connection (i = 1, 2,..., n ₁ ) is corrected.

Next,

[0113]

(Equation 16)

Therefore, by substituting equations (2) and (3) into equation (16),

[0115]

[Equation 17]

Here, from equation (12),

[0117]

(Equation 18)

Therefore, the equation (18), the equation (11) and the equation (13)
Substituting equation into equation (17),

[0119]

[Equation 19]

In equation (9), k = 1 is set, and equation (19) is
Substituting into equation (9) gives

[0121]

(Equation 20)

By substituting equation (20) into equation (6), k = 1
And put

[0123]

(Equation 21)

W2, i; 3,1 (i =
, N ₁ ) are substituted into this equation (21), and W1, i; 2, j (i =
_{1,2, ..., n 1; j} = 1,2, ..., n 2) is modified.

It should be noted that, theoretically, by using equations (15) and (21), the learning coefficient η is made sufficiently small and the number of times of learning is made sufficiently large, so that the weight Wk, i; k + 1 of each connection is obtained. , j can be converged to a predetermined value, but making the learning coefficient η too small is not practical because it slows down the progress of learning. On the other hand, if the learning coefficient η is increased, the learning may oscillate (the weight of the connection does not converge to a predetermined value). Therefore, in practice, vibration is suppressed by adding an inertia term such as the following equation to the correction amount of the weight of the connection, and the learning coefficient η is set to a relatively large value. (E.g., DERumelhart, GEHinton and RJWil
liams: Learninginternal representations by error pr
opagation In Parallel Distributed Processing, Volum
e 1, JLMcClelland, DERumelhart and The PDP Resea
rch Group, MIT Press, 1986b ")

[0126]

(Equation 22)

Here, ΔWk, i; k + 1, j (t) is obtained from the modified connection weight Wk, i; k + 1, j in the t-th learning and the weight Wk, i; Represents the correction amount after subtracting k + 1, j. Α is a coefficient called an inertia term.

As the inertia term α and the learning coefficient η, for example, α =
Correction (learning) of the weight Wk, i; k + 1, j of each connection is performed, for example, 200,000 times using 0.9 and η = 0.25. Thereafter, the weight Wk, i; k + 1, j of each connection is Fixed to the final value. At the end of this learning, the two outputs Y3,1 and Y3,2 are signals that correctly represent the sensitivity and latitude, respectively, in the main reading.

Therefore, after the learning is completed, a histogram or a normalized histogram is obtained from a pre-read image signal representing an X-ray image at the time of pre-read, and this is input to the neural network shown in FIG. The outputs Y3,1 and Y3,2 obtained by the above become signals representing the reading conditions (sensitivity and latitude) of the main reading for the X-ray image. Since this signal is obtained after the learning as described above, the signal accurately represents the reading condition at the time of the main reading.

The neural network is not limited to a three-layer structure, but may have a multilayer structure. The number of units of each layer may, it is also capable of constituting the respective layers in any number of units in accordance with the accuracy of reading condition that the number of pixels of the preliminary readout image signal S _P is input, required.

Next, a sensitivity correction method according to the second embodiment of the present invention will be described. In the second embodiment of the present invention, as shown in FIG. 5, a normalized histogram is always input to the same input unit as the maximum value Smax1 to the neural network, and the sensitivity of the normalized histogram image signal value changes. Since the reading condition is not dependent on the sensitivity, the reading condition (sensitivity and latitude) output by the neural network is output not as an absolute value but as relative position information. Here, the latitude corresponds to the light amount ratio of the strongest stimulated emission light to the weakest stimulated emission light converted into an image signal as described above. That is, the latitude corresponds to the ratio between the minimum value Smin and the maximum value Smax1. Since the ratio of the minimum value Smin to the maximum value Smax1 is output from the neural network as latitude, it is not necessary to correct the latitude. In the second embodiment of the present invention, the sensitivity is the minimum value Smin and the maximum value Smax1.
Percentage sensitivity position between the maximum value Smax1 sensitivity of viewed from the minimum value Smin of the preliminary read-out image signals S _P output histogram normalized (hatched portion in FIG. 5) position information, i.e., areas requiring between Is output from the neural network as represented by. The minimum value Smin and the maximum value S
Since max1 is known, sensitivity correction is performed according to the following equation.

[0132]

## EQU23 ## Sensitivity Sk = Smax1- (Smax1-Smin) .times.S
k1 (%) (23) Sensitivity correction is performed by equation (23), and final image reading conditions (sensitivity and latitude) are determined.

As described above, the voltage applied to the photomultiplier 21 'of the main reading means 100' and the amplification factor of the amplifier 26 'are controlled in accordance with the reading conditions obtained by the neural network and the sensitivity correction means. The actual reading is performed according to the controlled conditions.

In the first and second embodiments,
It has been described apparatus for determining a reading condition when the real reading a computer system 40, when the real reading is a reading at a predetermined reading condition regardless preliminary readout image signal S _P, the computer system 40, pre-reading image signals based on S _P, may be calculated image processing conditions for performing image processing on the image signal S _Q, also may be obtained both the read condition and the image processing conditions in the computer system 40 .

Further, the first and second embodiments have the following features.
Although the radiation image reading apparatus that performs pre-reading has been described, the present invention can also be applied to a radiation image reading apparatus that performs reading equivalent to the main reading without performing pre-reading. In this case, at the time of reading, an image signal is obtained by reading under a predetermined reading condition, and an image processing condition is obtained in the computer system 40 based on the image signal, and the image signal is obtained in accordance with the obtained image processing condition. Is subjected to image processing.

[Brief description of the drawings]

FIG. 1 is a diagram showing image reading conditions and / or conditions according to a first embodiment of the present invention.
Or a block diagram showing a basic configuration of an image processing condition determining method.

FIG. 2 is a perspective view showing an example of an X-ray image reading apparatus including a computer system for implementing the method of the present invention.

FIG. 3 is a graph showing an example of a histogram of an image signal read from a stimulable phosphor sheet;

FIG. 4 shows an image reading condition and / or an image reading condition according to a second embodiment of the present invention.
Or a block diagram showing a basic configuration of an image processing condition determining method.

FIG. 5 is a diagram schematically showing a histogram obtained by normalizing a histogram of a pre-read image signal and an example of a neural network according to the present invention.

FIG. 6 is a graph showing another example of a histogram of an image signal read from a stimulable phosphor sheet.

FIG. 7 is a diagram showing an example of a neural network used in the method of the present invention.

[Explanation of symbols]

11, 11 'stimulable phosphor sheet 19, 19' emitted light 21, 21 'photomultiplier 26, 26' logarithmic amplifier 27, 27 'A / D converter 40 the computer system 100' present reader in stage S _P prefetching Image signal

Claims (16)

(57) [Claims] 1. A stimulable phosphor sheet on which a radiation image is recorded is irradiated with excitation light, and the stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or an image processing condition determination method for obtaining an image processing condition when performing image processing on a reading condition and / or an obtained second image signal, the histogram of the first image signal may be set to be neural. A radiographic image reading condition and / or an image processing condition which are input to a network and output the reading condition and / or the image processing condition from the neural network. Decision method. 2. A stimulable phosphor sheet on which a radiation image has been recorded is irradiated with excitation light, and a stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or image processing condition determining device for obtaining image processing conditions for performing image processing on the reading condition and / or the obtained second image signal, a histogram of the first image signal is calculated. And a histogram calculation unit to be output, and a histogram output by the histogram calculation unit, and input the reading condition and / or the image processing condition based on the histogram. And / or a neural network for outputting.
Alternatively, an image processing condition determining device. 3. A first image representing the radiation image obtained by irradiating the stimulable phosphor sheet on which the radiation image is recorded with excitation light and reading the stimulated emission light emitted from the stimulable phosphor sheet. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or an image processing condition determination method for determining an image processing condition when performing image processing on a reading condition and / or the obtained second image signal, a histogram of the first image signal; Additional information about the radiation image recorded on the stimulable phosphor sheet is input to a neural network, and the reading condition and / or
Alternatively, a method for determining a radiation image reading condition and / or an image processing condition, wherein the method outputs the image processing condition. 4. A stimulable phosphor sheet on which a radiation image has been recorded is irradiated with excitation light, and the stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or image processing condition determining device for obtaining image processing conditions for performing image processing on the reading condition and / or the obtained second image signal, a histogram of the first image signal is calculated. A histogram calculating means for outputting, additional information outputting means for outputting additional information relating to the radiation image recorded on the stimulable phosphor sheet, and a histogram calculating means. A neural network that inputs the input histogram and the additional information output by the additional information output unit, and outputs the reading condition and / or the image processing condition based on the histogram and the additional information. A radiation image reading condition and / or image processing condition determining device, characterized in that: 5. A radiation image processing condition determining method for determining image processing conditions when performing image processing on an image signal based on the image signal representing the radiation image, wherein a histogram of the image signal is input to a neural network,
A method for determining a radiation image processing condition, comprising outputting the image processing condition from the neural network. 6. A radiation image processing condition determining apparatus for determining an image processing condition for performing image processing on an image signal based on the image signal representing the radiation image, wherein the histogram of the image signal is calculated and output. A radiation image processing condition determining apparatus, comprising: a calculating unit; and a neural network that inputs the histogram output by the histogram calculating unit and outputs image processing conditions based on the histogram. 7. A radiographic image processing condition determining method for obtaining image processing conditions when performing image processing on an image signal based on the image signal representing the radiographic image, the method comprising the steps of: A method for determining a radiation image processing condition, comprising: inputting information to a neural network; and outputting the image processing condition from the neural network. 8. A radiation image processing condition determining apparatus for obtaining image processing conditions for performing image processing on an image signal based on the image signal representing the radiation image, wherein a histogram of the image signal is calculated and output. Calculating means, additional information output means for outputting additional information relating to the radiographic image, a histogram output by the histogram calculating means, and additional information output by the additional information output means; A radiation image processing condition determining apparatus comprising: a neural network that outputs the image processing condition based on additional information. 9. A stimulable phosphor sheet on which a radiation image has been recorded is irradiated with excitation light, and a stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or an image processing condition determination method for determining an image processing condition when performing image processing on the reading condition and / or the obtained second image signal, the histogram of the first image signal may be The value of the image signal indicating the maximum light emission amount excluding the penetrating part corresponding to the direct radiation part is the maximum value, and the histogram is normalized at the maximum frequency between the maximum value and the minimum value of the first image signal. Conversion After that, the normalized histogram is input to the neural network so that a predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is always input to the same input unit of the neural network. Inputting and outputting the reading condition and / or the image processing condition from the neural network;
Correcting the reading condition and / or the image processing condition output from the neural network based on the predetermined value to determine final reading condition and / or image processing condition; A method for determining reading conditions and / or image processing conditions. 10. A stimulable phosphor sheet on which a radiation image has been recorded is irradiated with excitation light, and the stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or image processing condition determining device for obtaining image processing conditions for performing image processing on the reading condition and / or the obtained second image signal, a histogram of the first image signal is calculated. Then, from the histogram, detect the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation portion, set the value of the detected image signal to the maximum value, and determine the maximum value and the One painting Calculating means for normalizing and outputting the histogram at the maximum frequency between the minimum value of the image signal and the maximum value and the minimum value of the image signal of the normalized histogram And a neural network for inputting a predetermined value between the input unit and the input unit so that the reading condition and / or the image processing condition are output based on the normalized histogram. A radiation image reading condition and / or image processing condition determining apparatus, comprising: a correction unit configured to correct the reading condition and / or the image processing condition output from the neural network based on the value. 11. A stimulable phosphor sheet on which a radiation image has been recorded is irradiated with excitation light and a stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or an image processing condition determination method for determining an image processing condition when performing image processing on the reading condition and / or the obtained second image signal, the histogram of the first image signal may be The value of the image signal indicating the maximum light emission amount excluding the penetrating part corresponding to the direct radiation part is the maximum value, and the histogram is normalized at the maximum frequency between the maximum value and the minimum value of the first image signal. After the normalization, the normalized histogram and the additional information for the radiation image recorded on the stimulable phosphor sheet are stored in a neural network between the maximum value and the minimum value of the image signal of the normalized histogram. Is input so as to be always input to the same input unit of the neural network, and the reading condition and / or the image processing condition are output from the neural network. A radiation image reading condition and / or image processing condition determination, wherein the reading condition and / or the image processing condition output from the network are corrected to determine the final reading condition and / or image processing condition. Method. 12. A stimulable phosphor sheet on which a radiation image is recorded is irradiated with excitation light, and the stimulable light emitted from the stimulable phosphor sheet is read to represent the radiation image. A second image signal representing the radiation image obtained by irradiating the stimulable phosphor sheet with excitation light again based on the image signal and reading the stimulated emission light emitted from the stimulable phosphor sheet; In a radiation image reading condition and / or image processing condition determining device for obtaining image processing conditions for performing image processing on the reading condition and / or the obtained second image signal, a histogram of the first image signal is calculated. Then, from the histogram, detect the value of the image signal indicating the maximum light emission amount excluding the penetrating portion corresponding to the direct radiation portion, set the value of the detected image signal to the maximum value, and determine the maximum value and the One painting Calculating means for normalizing and outputting the histogram with the maximum frequency between the minimum value of the image signal and output; additional information output means for outputting additional information on the radiation image recorded on the stimulable phosphor sheet; The normalized histogram output from the arithmetic unit and the additional information output by the additional information output unit are set such that a predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is always the same. A neural network that is input as input to the input unit and outputs the reading condition and / or the image processing condition based on the normalized histogram; and a neural network that is output from the neural network based on the predetermined value. A radiographic image comprising correction means for correcting the reading conditions and / or the image processing conditions. Preparative conditions and / or the image processing condition determining apparatus. 13. A radiation image processing condition determining method for determining an image processing condition when performing image processing on an image signal based on the image signal representing the radiation image, wherein the histogram of the image signal corresponds to a direct radiation part. The value of the image signal indicating the maximum light emission amount excluding the soak portion is set to the maximum value,
After normalizing the histogram at the maximum frequency between the maximum value and the minimum value of the image signal, the normalized histogram is supplied to a neural network, and the maximum value and the minimum value of the image signal of the normalized histogram are obtained. Is input so that the same value is always input to the same input unit of the neural network, the image processing condition is output from the neural network, and the predetermined value is output from the neural network based on the predetermined value. Correcting the image processing conditions to determine final image processing conditions. 14. A radiation image processing condition determining apparatus for determining image processing conditions for performing image processing on an image signal based on the image signal representing the radiation image, wherein a histogram of the image signal is calculated, and Detects the value of the image signal indicating the maximum light emission amount excluding the penetrating part corresponding to the direct radiation part, sets the value of the detected image signal to the maximum value, and determines the maximum value and the minimum value of the image signal. Between the maximum value and the minimum value of the normalized histogram image signal, and a calculating means for normalizing and outputting the histogram at the maximum frequency during the interval, and outputting the normalized histogram output from the calculating means. A neural network that inputs values so as to be always input to the same input unit and outputs the image processing condition based on the normalized histogram; Correction means for correcting the image processing conditions output from the neural network based on the predetermined value. 15. A radiation image processing condition determining method for obtaining an image processing condition when performing image processing on an image signal based on an image signal representing the radiation image, wherein the histogram of the image signal corresponds to a direct radiation part. The value of the image signal indicating the maximum light emission amount excluding the soak portion is set to the maximum value,
After normalizing the histogram at the maximum frequency between the maximum value and the minimum value of the image signal, the normalized histogram and additional information for the radiation image recorded on the stimulable phosphor sheet, A predetermined value between the maximum value and the minimum value of the image signal of the normalized histogram is input to the neural network such that the predetermined value is always input to the same input unit of the neural network. A method for determining a radiation image processing condition, comprising: outputting a processing condition; correcting the image processing condition output from the neural network based on the predetermined value; and determining a final image processing condition. 16. A radiation image processing condition determining apparatus for determining an image processing condition for performing image processing on an image signal based on the image signal representing the radiation image, wherein a histogram of the image signal is calculated, and Detects the value of the image signal indicating the maximum light emission amount excluding the penetrating part corresponding to the direct radiation part, sets the value of the detected image signal to the maximum value, and determines the maximum value and the minimum value of the image signal. And a calculating means for normalizing and outputting the histogram at the maximum frequency, an additional information outputting means for outputting additional information on the radiation image recorded on the stimulable phosphor sheet, and an output from the calculating means. The normalized histogram and the additional information output by the additional information output means are set in a location between the maximum value and the minimum value of the image signal of the normalized histogram. A neural network that inputs a constant value to be always input to the same input unit and outputs the image processing condition based on the normalized histogram, and a neural network that outputs the image processing condition based on the predetermined value. A radiographic image processing condition determining apparatus, comprising: a correcting means for correcting the image processing conditions.