JPH0486820A - Method for determining radiation image reading condition and/or image processing condition - Google Patents

Abstract

PURPOSE:To stably reproduce a specific concern region at an adequate density between plural reproduced radiation images by utilizing the radiation image photographed with the specific concern region in a subject and the processing conditions and/or image processing conditions optimized with this concern region. CONSTITUTION:The previously read image signal Sp obtd. in a previous reading means 100 is inputted to a neural network consisting of a computer system 200 to obtain the prescribed concern region. The previously read image signal Sp' in which only the concern region is extracted is sent to a histogram analyzing section 201 which determines the reading conditions in accordance with the histogram of this signal Sp'. Reading is executed under the prescribed reading conditions in a regular reading means 100', by which the image signal SQ is obtd. The optimum image processing conditions are determined in accordance with the image signal SQ in the computer system 210 constituting the neural network. The image processing conditions obtd. in the above-mentioned manner are optimized for the concern region by utilizing the radiation image photographed with the specific concern region in order to learn the neural network at this time as well.

Description

DETAILED DESCRIPTION OF THE INVENTION (Industrial Application Field) The present invention relates to a method for determining radiation image reading conditions and/or image processing conditions for determining reading conditions and image processing conditions based on an image signal representing a radiation image.
Or it relates to a method for determining image processing conditions.

(Prior Art) It is practiced in various fields to read a recorded radiation image to obtain an image signal, perform appropriate image processing on the image signal, and then reproduce and record the image. For example, an X-ray image is recorded using an X-ray film with a low gamma value designed to be compatible with later image processing, and the X-ray image is read from the film on which it is recorded and converted into an electrical signal. By performing image processing on this electrical signal (image signal) and then reproducing it as a visible image in a photocopy, etc., a reproduced image with good image quality performance such as contrast sharpness and graininess can be obtained. (Tokuko Showa 6)
1-5193).

Also, when radiation (X-rays, alpha-rays, beta-rays, gamma-rays, electron beams, ultraviolet light, etc.) is irradiated, a portion of this radiation energy is accumulated, and when excitation light such as visible light is then irradiated, the accumulated energy is Accordingly, radiation image information of a subject such as a human body is partially recorded on a sheet-like stimulable phosphor using a stimulable phosphor that exhibits stimulated luminescence. The sheet is scanned with excitation light such as a laser beam to produce stimulated luminescence light, the resulting stimulated luminescence light is read photoelectrically to obtain an image signal, and based on this image data, a radiation image of the subject is photographically exposed. The applicant has already proposed a radiation image recording and reproducing system that outputs a visible image to a recording material such as a CRT (Japanese Unexamined Patent Application Publication No. 55-12).
No. 429, No. 56-11395.

No. 55-163472, No. 56-104645, No. 55-116340, etc.).

In the above system, the stimulable phosphor sheet is scanned in advance with a low-level light beam before obtaining an image signal by reading it under optimal reading conditions depending on the dose of radiation applied to the stimulable phosphor sheet. Pre-reading is performed to read the outline of the radiation image recorded on this sheet, the pre-read image signal obtained by this pre-reading is analyzed, and then the sheet is irradiated with a high-level light beam and scanned, and this radiation image is It has also been considered to perform actual reading in which image signals are obtained by reading under optimal reading conditions.

Here, reading conditions are a general term for various conditions that affect the relationship between the amount of stimulated luminescence light and the output of the reading device during reading, such as reading gain, scale factor, or , the power of excitation light during reading, etc.

It is also being considered to analyze the obtained image signal (including the prefetched image signal) regardless of whether or not this prefetching is performed, and to determine the optimal image processing conditions when performing image processing on the image signal. . The term "image processing conditions" as used herein is a general term for various conditions when applying processing to an image signal that affects the gradation, sensitivity, etc. of a reproduced image based on the image signal. The method of determining the optimal image processing conditions based on this image signal is not limited to systems using stimulable phosphor sheets, and for example, image signals are obtained from radiation images recorded on recording sheets such as conventional X-ray films. It is also applied to the system.

Calculations for determining reading conditions and/or image processing conditions (hereinafter referred to as reading conditions, etc.) based on the above image signals (including pre-read image signals) are based on the results of statistically processing a large number of radiographic images in advance. The algorithm has been defined (for example, see Japanese Patent Laid-Open No. 60-185944 and Japanese Patent Laid-Open No. 61-280163).

This conventionally adopted algorithm calculates a histogram of the image signal on the ship, and calculates various values such as the maximum value, minimum value, and value of the image signal at the point where the frequency of appearance of the image signal is maximum on the histogram. The feature points are determined, and the reading conditions, etc. are determined based on the feature points.

(Problems to be Solved by the Invention) The above method is effective in many cases, but on the other hand, it may cause inconveniences depending on the photographing conditions of the subject. This point will be explained in detail below using a radiographic image of a shoulder joint as an example.

Figures 1A and 1B are both radiographic images of the shoulder joint 5. In the image of Figure 1B, the body 6 is also imprinted, whereas in the image of Figure 1A, it is not. The difference is that it is not included. On the other hand, the histograms of the image signals carrying the radiographic images shown in FIGS. 1A and 1B are as shown in FIGS. 2A and 2B, respectively.

As shown in the figure, the shapes of both histograms are roughly the same, but since the above-mentioned difference exists between the two radiographic images, the range of the image signal responsible for the shoulder joint, which is the region of interest, is different for both. In the histogram, K1 part and K2 part respectively.
The parts become different from each other. Therefore, if the reading conditions or image processing conditions for reproducing radiographic images such as those shown in FIGS. 1A and 1B are determined based on each histogram, the density and contrast of the two reproduced radiographic images are the same histogram, so Since the same conditions are calculated, the density of the shoulder joint, which is the region of interest, becomes unstable.

If this happens, it becomes difficult to observe the region of interest of the liver and kidneys in the reconstructed radiographic image, and when comparing multiple radiographic images to observe the progress of an abnormal area, for example,
There is also the possibility of making an incorrect diagnosis.

The present invention has been made in view of the above-mentioned circumstances, and provides radiation image reading conditions and/or the like so that a specific region of interest can be stably reproduced at an appropriate density among a plurality of reproduced radiation images. Another object of the present invention is to provide a method for determining image processing conditions.

(Means for Solving the Problems) The present invention as set forth in claim 1 is applied to a system that performs so-called pre-reading using the above-mentioned stimulable phosphor sheet.

In other words, this method for determining radiation image reading conditions and/or image processing conditions involves, as described above, irradiating a stimulable phosphor sheet on which a radiation image is recorded with excitation light, and at that time stimulating the stimulable phosphor sheet emitted from the sheet. The forward light is read to obtain a first image signal representing the radiographic image, the stimulable phosphor sheet is irradiated with excitation light again, and the stimulated luminescence light emitted from the sheet is read at that time to obtain the radiographic image. The reading conditions for obtaining a second image signal representing the image signal and/or the image processing conditions for performing image processing on the obtained second image signal are determined based on the first image signal. In the method for determining radiation image reading conditions and/or image processing conditions, the conditions are determined by a neural network that uses the first image signal as input and outputs the reading conditions and/or image processing conditions, and determines appropriate reading conditions. and/or when training the neural network to output image processing conditions, a radiation image in which a specific region of interest in the subject is captured, and reading conditions and/or image processing optimized for the region of interest; This feature is characterized by the use of conditions.

The present invention described in claim 2 is also applied to a system that uses a stimulable phosphor sheet and performs so-called pre-reading.

That is, this radiation image reading condition and/or image processing condition determining method obtains first and second image signals in the same manner as the invention described in claim 1, and sets the reading conditions when obtaining the second image signal. and/or in a radiation image reading condition and/or image processing condition determining method for determining image processing conditions for performing image processing on the second image signal based on the first image signal, the first image signal; A neural network whose input is a specific region of interest in the subject is used to extract a first image signal related to the region of interest, and based on this extracted first image signal, read conditions and/or This method is characterized by determining image processing conditions.

On the other hand, the present invention as set forth in claim 3 does not limit the object to stimulable phosphor sheets, and specifically seeks image processing conditions.

That is, this method for determining radiation image processing conditions is a method for determining image processing conditions for performing image processing on an image signal based on an image signal representing a radiation image, using the image signal as input; Conditions are determined by a neural network that outputs image processing conditions, and when the neural network is trained to output appropriate image processing conditions, a radiation image of a specific region of interest in the subject and its This method is characterized by using image processing conditions that are optimized for the region of interest.

The present invention as set forth in claim 4 is also not limited to stimulable phosphor sheets, and specifically seeks image processing conditions.

In other words, this radiation image processing condition determining method is defined in claim 3.
Similar to the invention described in the above, in a radiation image processing condition determining method for determining image processing conditions for performing image processing on an image signal based on an image signal representing a radiation image, the image signal is used as an input, and a subject is An image signal related to the region of interest is extracted by a neural network whose output is a specific region of interest, and image processing conditions are determined based on the extracted image signal.

(Operation and Effects of the Invention) The above-mentioned neural network has the ability to
It is equipped with an error back propagation learning function that corrects the connection weights (synaptic connection weights) between each unit within the neural network, and by repeatedly “learning” new signals can be generated. It is possible to increase the probability of outputting the correct answer when input (for example, rD, E, Rumelhart,
G.E.

Hinton and R,Jilliams:Le
earning representatives by
back-propagating errors,
Nature, 323-9.533-356.1988
aJ, r Hideki Aso: Backpropagation Co
1putrol No. 2453-60J, R. Kinzoku-Sachi, Neural Computer, Tokyo Denki University Press).

As in the invention described in claim 1 or 3, when the neural network is used to determine reading conditions, etc., by repeatedly "learning" it in advance,
Gradually, it becomes possible to find correct reading conditions, etc.

When training a neural network, if a radiation image in which a specific region of interest in a subject is captured and reading conditions or image processing conditions that are optimized for that region of interest are used, it is possible to No matter what is being imaged in addition to the region of interest, reading conditions and the like are determined to be appropriate for the region of interest.

Further, as in the invention described in claim 2 or 4, by repeatedly training the neural network in advance, it becomes possible to gradually and correctly recognize the region of interest in the radiation image. If reading conditions, etc. are determined based on the image signal related to the region of interest recognized in this way, the reading conditions, etc. will basically be unaffected by image information other than the region of interest, that is, appropriate for the region of interest. Become.

Note that in determining the reading conditions etc. based on the image signal related to the recognized region of interest, a histogram analysis method may be used, or a neural network different from that for recognizing the region of interest may be used. You can do it like this.

(Example) Hereinafter, an example of the present invention will be described with reference to the drawings. Here, the above-mentioned stimulable phosphor sheet was used,
An example of handling an X-ray image of a shoulder joint of a human body as a region of interest will be described.

FIG. 4 is a schematic diagram of an example of an X-ray imaging apparatus.

X-rays 3 are irradiated from the X-ray source 2 of the X-ray imaging device 1 toward the shoulder 4a of the human body 4, and the X-rays 3a that have passed through the human body 4 are irradiated onto the stimulable phosphor sheet 11. A transmitted X-ray image of the shoulder 4a of the human body is accumulated and recorded on the stimulable phosphor sheet 11.

1A and 1B show examples of shoulder X-ray images accumulated and recorded on the stimulable phosphor sheet 11 as described above.
FIG.

FIG. 5 is a perspective view showing an example of an X-ray image reading device and an example of a computer system that implements the method of the present invention. This system handles the stimulable phosphor sheet 11 described above and performs pre-reading.

The stimulable phosphor sheet 11 on which an X-ray image has been recorded is first scanned with a weak light beam to emit only a portion of the radiation energy stored in the stimulable phosphor sheet 11, thereby performing pre-reading. 100 predetermined positions. The stimulable phosphor sheet 11 set in this predetermined position
is transported (sub-scanning) in the direction of arrow Y by a sheet transport means 13 such as an endless belt driven by a motor 12.

On the other hand, a weak light beam 1 emitted from a laser light source 14
5 is reflected and deflected by a rotating polygon mirror 16 that is driven by a motor 23 and rotates at high speed in the direction of the arrow, passes through a focusing lens 17 such as an fθ lens, and then changes its optical path by a mirror 18 and enters the stimulable phosphor sheet 11. Main scanning is then performed in the direction of arrow X, which is substantially perpendicular to the direction of sub-scanning (direction of arrow Y).

Stimulated luminescence light 19 is emitted from a portion of the stimulable phosphor sheet 11 irradiated with the light beam 15 in an amount corresponding to the radiation image information stored and recorded.

This stimulated luminescence light 19 is guided by a light guide 20 and photoelectrically detected by a photomultiplier (photomultiplier tube) 21. The light guide 20 is made by molding a light-guiding material such as an acrylic plate, and is arranged so that the linear entrance end surface 20a extends along the main scanning line on the stimulable phosphor sheet 11. The light receiving surface of the photomultiplier 21 is coupled to the annularly formed exit end surface 20b. The light guide 20 from the incident end surface 20a
The stimulated luminescent light 19 that has entered the light guide 20 travels through the interior of the light guide 20 through repeated total reflection, exits from the exit end face 20b, and is received by the photomultiplier 21, where the stimulated luminescent light 19 representing a radiation image is generated. Light intensity is photo multiplier 2
1 into an electrical signal.

The analog output signal S output from the photomultiplier 21 is logarithmically amplified by the logarithmic amplifier 2B, and digitized by the A/D converter 27 to obtain a pre-read image signal Sp. The signal level of this pre-read image signal Sp is
It is proportional to the logarithm of the amount of stimulated luminescence light emitted from each pixel of 1.

In the above-mentioned pre-reading, reading conditions, such as the voltage value applied to the photomultiplier 21 and the amplification factor of the logarithmic amplifier 26, are determined so that the radiation energy accumulated in the stimulable phosphor sheet 11 can be read over a wide range. It is being

The obtained pre-read image signal Sp is sent to the computer system 4
It is input to 0. This computer system 40 is
Main body section 41 with built-in PU and internal memory. A drive section 42 into which a floppy disk as auxiliary memory is inserted and driven. It consists of a keyboard 43 for an operator to input necessary instructions to the computer system 40, and a CRT display 44 for displaying necessary information.

In this computer system 40, the reading conditions for main reading, that is, the sensitivity and contrast for main reading are determined as will be described later, and according to the sensitivity and contrast, for example, the voltage value or logarithm value to be applied to the photomultiplier 21' is determined. The amplification factor etc. of the amplifier 26' are controlled.

Contrast here corresponds to the light intensity ratio of the strongest stimulated luminescence light to the weakest stimulated luminescence light that is converted into an image signal during main reading, and sensitivity corresponds to the ratio of the luminous intensity of the most intense stimulated luminescence light to the weakest stimulated luminescence light that is converted into an image signal during main reading. This refers to the photoelectric conversion rate that determines what level of image signal the emitted light is converted to.

The stimulable phosphor sheet 11' for which pre-reading has been completed is set at a predetermined position in the main reading means 100', and the sheet 11' is scanned by a light beam 15' which is stronger than the light beam used for the above-mentioned pre-reading, and the pre-read image signal is detected. An image signal is obtained under the reading conditions determined based on Sp. Incidentally, since the configuration of this main reading means 100' is different from the structure of the above-mentioned pre-reading means 100, the components corresponding to the respective components of the pre-reading means 100 are the same as those of the pre-reading means 00. The same numbers are indicated with a dash, and the explanation is omitted.

The image signal SO obtained by digitizing with the A/D converter 27' is input to the computer system 40. Appropriate image processing is performed on the image signal SQ within the computer system 40, and the image signal subjected to this image processing is sent to a playback device (not shown), where the X-ray image represented by this image signal is played back and displayed. Ru.

Next, in the computer system 40, the pre-read image signal Sp
Based on this, we will explain how to find the reading conditions for main reading.

FIG. 3 is a diagram showing an example of a neural network equipped with an error backpropagation learning (pack propagation) function. Error backpropagation learning (pack propagation) is, as mentioned above, by comparing the output of the neural network with the correct answer (teacher signal), and sequentially calculating connection weights (synaptic connection weights) from the output side to the input side. It is a “learning” algorithm that corrects the

As shown in the figure, the first layer (input layer), second layer (middle layer), and third layer (output layer) of this neural network are composed of 01 units, n2 units, and 2 units, respectively. Each signal F1 r F input to the first layer (input layer)
2, ......+ Fol is the pre-read image signal Sp corresponding to each pixel of the X-ray image, and the two outputs y:, yz from the third layer (output layer) are the respective signals at the time of main reading. This is a signal corresponding to sensitivity and contrast. 1st layer
The th unit is ui1 Each input to the unit U:
? , each output as y? , u: to k+l is the weight of the connection W? ':'' and each unit u: has the same characteristic function.In this case, the input x of each unit 7
:, the output y: becomes xi-8w7-' 7 y (4) Y: -f (X7) (5). However, each unit configuring the input layer u)(i-
1+2+・-, nl) Each human power F1 + F2
, "Ffi," are inputted as they are to each unit u+ (i-L2...+rll) without being weighted.The input 01 signals F1 + F2 r "'+
F nt is weighted by the weight Wkk+1 of each connection and the final output Y:+! The reading conditions (sensitivity and contrast) for actual reading are determined by this.

Here, a method for determining the weight Wbi+1 of each of the above-mentioned connections will be explained. First, the weight of each connection Wk k +
An initial value of 1 is given. At this time, input F1~
It is preferable to limit the range of the random number so that even if Fnl fluctuates to a maximum, the output Y:+F2 becomes a value within a predetermined range or a value close to this.

A large number of stimulable phosphor sheets in which the optimal reading conditions are known and shoulder joints 5 (see FIGS. 1A and 1B) are recorded are read as described above to obtain a pre-read image signal Sp. The above n1 inputs F1°Fz, . . . +Fal are obtained. As a feature of the present invention, the above-mentioned optimal reading conditions are those in which the shoulder joint 5 in particular is shown with optimal density in the X-ray image.

These 01 inputs Fl, F2 . ..., Fゎ, are input to the neural network shown in FIG. 3, and the output y7 of each unit u7 is monitored.

Each output? is asked, the final output is )'?
The square error between l F2 and the teacher signal (sensitivity y1 and contrast F2) as correct reading conditions for this image is determined. These squared errors E1. The weight w of each connection is set as follows so that E2 is minimized.
k k + l is modified. The output of y: will be described below, and the output of Yz will be described as y? Since it is the same as , it is omitted here.

To minimize the squared error El, this El should be W f: +1
The weight Wi"H" of each connection is modified as if it were a function of . Here, η is a coefficient called a learning coefficient.

here, From equation (4), +l−ΣW+, +・ ...(4)' Therefore, equation (9) is becomes.

Here, from equation (6), if we transform equation (11) using equation (5), we get (from equation 3, f' (x) -f (x) (1-f (x)
), so...(13) f' (x: ) -Y: (I Y'r)
−(14).

In equation (10), set -2 to (12), (1
Substituting equation (4) into equation (10), = (ydayy\')・Y"1 (1y:) y ... (15) Substituting equation (15) into equation (8), W?: -w
? ? -η・(V? d)・yl(1)′+) 1 y (16). , :(7) According to equation (18), W? ',
The weight of each connection of (1-1, 2, -nt) is modified.

Next, since , we substitute equations (4) and +5) into equation (17), and from equation (13), we get f' (x?) - y (1 - y)...・(1
9), so this equation (19) and (12), (
14) Substitute equation (18) and get ・y? (1y+)・W”1 ...(20)(1
0), and by substituting equation (20) into equation (10), we get -(yl-cao)・)'+ (1-)/? )・)'+(
IV D)・Wll・yl...(21) Substituting this equation (21) into equation (8), replacing it with k-1, we get W: ? -W: ? -η・(V: V:)・y
:(1-yl)・Y? (1y?) ・ylaw
j.

...(22), and W? corrected by formula (I6)? ? (i-1,
2,...nl) is substituted into this equation (22), W:
? (i-1,2゜..., rD ;j-1,2
,..., n2) are corrected.

Theoretically, by using equations (16) and (22) and setting the learning coefficient η sufficiently small and increasing the number of times of learning, the weight W? of each connection can be calculated. :" can be converged to a predetermined value, but making the learning coefficient η too small is not realistic because it slows down the progress of learning. On the other hand, if the learning coefficient η is made too large, learning will oscillate (the above coupling weights may not converge to a predetermined value.
An inertia term as shown in the following equation is added to the correction amount of the connection weight to suppress vibration, and the learning coefficient η is set to a somewhat large value.

(e.g., D, E, RuIIelhart, G, E, H
lnton and R, JJi11iaa+s:Le
earning 1internal representative
ations by error propagatto
n In para++e+ Distributed
Processing, Volume 1. J.L.
, McClelland, D.E., Rumelhart.
and The PDP Re5earch Gro
up, HIT Press, 1986bJ) ΔW muff: (t+1)-α・ΔW77” (t)
+ However, ΔWt+ (t) is the modified connection weight W in the second learning? 7" represents the amount of modification obtained by subtracting the weight of the connection before modification W??" from 1. Also, α
is a coefficient called the inertia term.

For example, α-0, 9η-0 as the inertia term α and the learning coefficient η.
, 25 to modify (learning) the weight of each connection w: 7”
For example, 200,000 times, and then the weight of each connection w
k k "l is fixed at the final value. At the end of this learning, the two outputs y:, yz properly represent the sensitivity and contrast, respectively, during reading (that is, in the X-ray image, the shoulder joint 5 portion is reproduced at a predetermined, stable density) signal.

After the learning is completed, the pre-read image signal Sp representing the X-ray image is input to the neural network shown in Fig. 3 in order to find the appropriate reading conditions for actual reading, and the output obtained thereby )'ll y2 becomes a signal representing the reading conditions (sensitivity and contrast) for the actual reading of the X-ray image. Since this signal is obtained after learning as described above, it accurately represents the optimal reading conditions for actual reading.

It should be noted that the neural network described above is not limited to a three-layer structure, and it goes without saying that it may have even more layers. Further, the number of units in each layer can be set to any number depending on the number of pixels of the input pre-read image signal sp, the accuracy of the required reading conditions, etc.

The voltage applied to the photomultiplier 21' of the main reading means 100', the amplification factor of the amplifier 26', etc. are controlled according to the reading conditions determined by the neural network as described above, and the main reading is performed according to the controlled conditions. It will be done.

In the above embodiment, the pre-reading means 100 and the main reading means 100
' are constructed separately, but as mentioned above, the structure of the pre-reading means 100 and the main reading means 100' is between the two, so the pre-reading means 100 and the main reading means 100' can be integrated. May be used for both purposes. In this case, after pre-reading, the stimulable phosphor sheet 11 may be moved back once and then scanned again to perform main reading.

When the pre-reading means and the main reading means are used, it is necessary to switch the intensity of the light beam between the pre-reading and the main reading, but the method for this switching is to switch the light intensity itself from the laser light source. Various methods can be used.

Furthermore, in the above embodiment, a method for obtaining reading conditions for book reading using the computer system 40 was explained.
During actual reading, reading is performed under predetermined reading conditions regardless of the pre-read image signal Sp, and the computer system 40 sets the image processing conditions when performing image processing on the image signal SQ based on the pre-read image signal Sp. Alternatively, the computer system 40 may obtain both the reading conditions and the image processing conditions.

Further, as shown in FIG. 6, the pre-reading means 10
The pre-read image signal Sp obtained in step 0 is input to a neural network consisting of a computer system 200 to obtain a predetermined region of interest, and the pre-read image signal SP extracted only for this region of interest is sent to the histogram analysis unit 201. , the reading conditions can also be determined based on the histogram of the signal Sp. In this case, since the reading conditions are determined only for the region of interest, the reading conditions can always be optimal for the region of interest.

Therefore, the information C indicating this reading condition is sent to the main reading means 100'.
If the reading conditions for the actual reading are set as indicated by the information C, it is possible to reproduce a radiographic image with a stable density in the region of interest.

Regarding the above-mentioned histogram analysis, for example, the above-mentioned Japanese Patent Application Laid-Open No. 60-185944 and Japanese Patent Application Laid-open No. 61-2
Detailed descriptions are given in Japanese Patent No. 801B3, etc., and the conventionally known histogram analysis method can be used in the present invention as well.

Note that even when a predetermined region of interest is determined using a neural network in this manner, it is possible to determine appropriate image processing conditions through histogram analysis.

Furthermore, instead of the histogram analysis unit 201 described above, a neural network may be used to determine the reading conditions or image processing conditions.

Furthermore, although the above embodiment applies the present invention to a radiation image reading method that performs pre-reading, the present invention is also applicable to a radiation image reading method that performs reading equivalent to the above-mentioned main reading without pre-reading. FIG. 7 shows a schematic configuration of a system for doing so.

In this case, the reading means 100' performs reading under predetermined reading conditions to obtain an image signal SQ, and the computer system 210 forming the neural network determines appropriate image processing conditions based on the image signal S0. . In this case, in order to train the neural network, the image processing conditions determined as described above are optimized for the region of interest by using radiation images taken of a specific region of interest. be able to.

Information indicating the optimal image processing conditions thus determined is input to the image processing device 211, and the image processing device 211
, the input image signal SQ is subjected to image processing such as gradation processing under the optimum image processing conditions described above.

Further, as shown in FIG. 8, the book reading means 10
The image signal SQ obtained at 0' is input to a neural network consisting of a computer system 220 to obtain a predetermined region of interest, and the image signal S,l extracted only for this region of interest is sent to the histogram analysis section 221. Image processing conditions can also be determined based on the histogram of the signal SQ'. In this case, since the image processing conditions are determined only for the region of interest, the image processing conditions can always be optimal for the region of interest.

Therefore, by sending information E indicating this image processing condition to the image processing device 211 and setting the image processing condition as indicated by the information E, it becomes possible to reproduce a radiographic image with a stable density in the region of interest.

In this case as well, instead of the histogram analysis section 221 described above, a neural network may be used to obtain the image processing conditions.

[Brief explanation of drawings]

FIGS. 1A and 1B are explanatory diagrams showing X-ray images of the shoulder joint, respectively. FIGS. 2A and 2B are respectively the above-mentioned FIG. 1A. FIG. 1B is a graph showing a schematic pattern of a histogram of an image signal carrying an X-ray image, FIG. 3 is a schematic diagram showing an example of a neural network, and FIG. 4 is an example of an X-ray imaging device. A schematic diagram of FIG.
A perspective view showing an example of a line image reading device and an example of a computer system implementing the present invention. FIGS. 6.7 and 8 are respectively schematic configuration diagrams of systems implementing further different methods of the present invention. 1... X-ray imaging device 2... X-ray source 5... Shoulder joint 11, 11'... Storable phosphor sheet 19, 19'.
... Stimulated luminescent light 21, 21' ... Photomultiplier 26, 26
'... Logarithmic amplifiers 27, 27'... A/D converter 40.200.210.220... Computer system 100... Pre-reading means 100'... Main reading means 201.221...・Histogram analysis section 211
...Image processing device

Claims (4)

[Claims] (1) A first image signal representing the radiation image by irradiating a stimulable phosphor sheet on which a radiation image is recorded with excitation light and reading the stimulated luminescence light emitted from the stimulable phosphor sheet at that time. and irradiating the stimulable phosphor sheet with excitation light again and reading the stimulated luminescence light emitted from the stimulable phosphor sheet to obtain a second image signal representing the radiation image. In a method for determining radiation image reading conditions and/or image processing conditions, in which reading conditions and/or image processing conditions for performing image processing on the obtained second image signal are determined based on the first image signal. , a neural network that receives the first image signal as an input and outputs the reading conditions and/or image processing conditions determines the conditions, and outputs the appropriate reading conditions and/or image processing conditions. Radiographic image reading characterized in that a radiographic image in which a specific region of interest in a subject is photographed and reading conditions and/or image processing conditions optimized for the region of interest are used when training a network. Conditions and/or method for determining image processing conditions. (2) A first image signal representing the radiation image by irradiating a stimulable phosphor sheet on which a radiation image is recorded with excitation light and reading the stimulated luminescence light emitted from the stimulable phosphor sheet at that time. and irradiating the stimulable phosphor sheet with excitation light again and reading the stimulated luminescence light emitted from the stimulable phosphor sheet to obtain a second image signal representing the radiation image. In a method for determining radiation image reading conditions and/or image processing conditions, in which reading conditions and/or image processing conditions for performing image processing on the obtained second image signal are determined based on the first image signal. , extracting a first image signal related to the region of interest using a neural network that uses the first image signal as input and outputs a specific region of interest in the subject, and based on the extracted first image signal. A method for determining radiation image reading conditions and/or image processing conditions, characterized in that the reading conditions and/or image processing conditions are determined by: (3) A radiation image processing condition determining method for determining image processing conditions for performing image processing on an image signal based on an image signal representing a radiation image, wherein the image signal is input and the image processing condition is output. When training the neural network to determine conditions and output appropriate image processing conditions, a radiological image in which a specific region of interest in the subject is photographed and the optimal image for that region of interest are determined. A method for determining radiation image processing conditions, characterized in that the image processing conditions are determined using the following image processing conditions. (4) A radiation image processing condition determining method for determining image processing conditions for performing image processing on an image signal based on an image signal representing a radiation image, the image signal being input, and specifying a specific region of interest in a subject. A method for determining radiation image processing conditions, comprising: extracting an image signal related to the region of interest using a neural network that outputs the image signal, and determining the image processing condition based on the extracted image signal.