CN111991704B - Operation method based on photodynamic therapy system and photodynamic therapy system - Google Patents
Operation method based on photodynamic therapy system and photodynamic therapy system Download PDFInfo
- Publication number
- CN111991704B CN111991704B CN202010893496.5A CN202010893496A CN111991704B CN 111991704 B CN111991704 B CN 111991704B CN 202010893496 A CN202010893496 A CN 202010893496A CN 111991704 B CN111991704 B CN 111991704B
- Authority
- CN
- China
- Prior art keywords
- fluorescence image
- area
- point
- photodynamic therapy
- underexposed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/06—Radiation therapy using light
- A61N5/0613—Apparatus adapted for a specific treatment
- A61N5/062—Photodynamic therapy, i.e. excitation of an agent
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0071—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by measuring fluorescence emission
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/06—Radiation therapy using light
- A61N2005/0626—Monitoring, verifying, controlling systems and methods
- A61N2005/0627—Dose monitoring systems and methods
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Processing (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The invention discloses a treatment method based on a photodynamic treatment system and the photodynamic treatment system, wherein the method comprises the following steps: acquiring a fluorescence image generated when the photosensitizer on the tissue to be treated is irradiated; calculating the fluorescence image according to a fluorescence image processing algorithm, and determining an overexposed area and an underexposed area of the fluorescence image; analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolution neural network model, and determining the required excitation light dose of each point of the fluorescence image; and generating treatment light intensity according to the excitation light dose required by each point of the fluorescence image for treatment. By implementing the invention, the fluorescence image marked with the overexposed area and the underexposed area can be input into the preset convolution neural network model, and the excitation light parameters required by each point when the optimal fluorescence image is obtained can be determined through the output of the preset convolution neural network model. Optimal imaging is achieved with a minimum number of exposures. The fluorescence bleaching caused by excessive exposure times of the photosensitizer is reduced.
Description
Technical Field
The invention relates to the technical field of photodynamic diagnosis and treatment equipment, in particular to a treatment method based on a photodynamic treatment system and the photodynamic treatment system.
Background
Photodynamic therapy requires light to excite a photosensitizer, and the photosensitizer generates a photosensitization effect to kill pathological tissues. Because the light itself is controllable in the intensity, time and area of irradiation, and the photosensitizer has little effect on the non-irradiated area, the photodynamic therapy becomes an ideal precise treatment method. Meanwhile, the photosensitizer can be used for fluorescence imaging, so that the photosensitizer distribution and other information obtained by the photosensitizer fluorescence imaging is used for guiding photodynamic irradiation, and accurate photodynamic therapy is realized, and the technology has a great clinical application prospect.
At present, in fluorescence imaging performed by using a photosensitizer, due to different regions where the photosensitizer is distributed and different properties of biological tissues, when a light source with uniform irradiation power is used for fluorescence imaging of the photosensitizer, some regions are often over-exposed, and other regions are under-exposed, so that the acquisition of imaging information is greatly reduced. And the multiple exposure superposition mode is adopted, so that the fluorescence of the photosensitizer is bleached, and an ideal imaging effect cannot be obtained. Therefore, how to adjust the light source irradiation power in each area in real time according to the difference of the concentration distribution area of the photosensitizer and obtain the optimal imaging effect by using the minimum exposure times has important significance on the clinical diagnosis and treatment integration of the photodynamic therapy.
Disclosure of Invention
In view of this, embodiments of the present invention provide a treatment method based on a photodynamic therapy system and a photodynamic therapy system, so as to solve the problem that in the prior art, when a photodynamic therapy system is used for treatment, a multiple exposure superposition manner is adopted, which often causes bleaching of photosensitizer fluorescence, and an ideal imaging effect cannot be obtained.
The technical scheme provided by the invention is as follows:
in a first aspect, embodiments of the present invention provide a method of treatment based on a photodynamic therapy system, the method of treatment comprising: acquiring a fluorescence image generated when the photosensitizer on the tissue to be treated is irradiated; calculating the fluorescence image according to a fluorescence image processing algorithm, and determining an overexposed area and an underexposed area of the fluorescence image; analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolutional neural network model, and determining the required excitation light dose of each point of the fluorescence image; and generating treatment light intensity according to the required excitation light dose of each point of the fluorescence image for treatment.
Further, calculating the fluorescence image according to a fluorescence image processing algorithm, and determining an overexposed area and an underexposed area of the fluorescence image, wherein the method comprises the following steps: processing the fluorescence image according to a two-dimensional texture mapping algorithm to realize digital reconstruction of each point on the fluorescence image; and calculating the processed fluorescence image according to a self-adaptive negative feedback algorithm and a pseudo color reconstruction algorithm, and determining an overexposed area and an underexposed area.
Further, analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolutional neural network model, and determining the excitation light dose required by each point of the fluorescence image, wherein the method comprises the following steps: and increasing the excitation light dose corresponding to the underexposed area on the fluorescence image according to the preset convolution neural network model, and reducing the excitation light dose corresponding to the overexposed area on the fluorescence image to obtain the excitation light dose required by each point of the fluorescence image.
A second aspect of an embodiment of the present invention provides a photodynamic therapy system, including: the system comprises a light source, an acquisition device, a modulation device and a microprocessor, wherein the light source irradiates on a photosensitizer of a tissue to be treated to generate a fluorescence image; the acquisition device acquires the fluorescence image and inputs the fluorescence image to the microprocessor; the microprocessor comprises a calculation module and an analysis module, wherein the calculation module is used for calculating the fluorescence image according to a fluorescence image processing algorithm and determining an overexposed area and an underexposed area of the fluorescence image; the analysis module is used for analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolution neural network model and determining the required excitation light dose of each point of the fluorescence image; the modulation device modulates the light beam output by the light source according to the exciting light dosage required by each point of the fluorescence image to generate the treatment light intensity for treatment.
Further, the calculation module includes: the image processing module is used for processing the fluorescence image according to a two-dimensional texture mapping algorithm to realize digital reconstruction of each point on the fluorescence image; and the exposure determining module is used for calculating the processed fluorescence image according to a self-adaptive negative feedback algorithm and a pseudo color reconstruction algorithm and determining an overexposed area and an underexposed area of the fluorescence image.
Further, the analysis module includes: and the parameter adjusting module is used for increasing the excitation light dose corresponding to the underexposed area on the fluorescence image according to the preset convolution neural network model, reducing the excitation light dose corresponding to the overexposed area on the fluorescence image and obtaining the excitation light dose required by each point of the fluorescence image.
Further, the modulation device comprises a spatial light modulator.
Further, the photodynamic therapy system further comprises: an endoscope unit for acquiring imaging information of a tissue to be treated.
A third aspect of embodiments of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform a method of photodynamic therapy system based therapy as described in any one of the first and second aspects of embodiments of the present invention.
A fourth aspect of an embodiment of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for photodynamic therapy system-based therapy according to any one of the first aspect and the first aspect of the embodiments of the present invention.
The technical scheme provided by the invention has the following effects:
the photodynamic therapy system provided by the embodiment of the invention integrates the fluorescence imaging system and the irradiation system into a set of light path system, and further expands the clinical application range of the system by integrating the endoscope system, so that the system can be applied to body surface photodynamic therapy and can also be applied to in-vivo treatment areas which can be achieved by means of the endoscope. The light beam emitted by the light source is irradiated on the photosensitizer through the modulation device to generate a fluorescence image, the fluorescence image is input into the microprocessor after being collected by the collection device to obtain the distribution area of the photosensitizer and the concentration information contained in each area, the required irradiation parameters are obtained through calculation by utilizing the information, the obtained parameters are input into the modulation device, the modulation device is utilized to distribute the power density of the irradiation area of the light source and each irradiation point, so that different areas of the photosensitizer receive corresponding irradiation doses, and the precise regulation and control of the photodynamic therapy process are realized through imaging guidance.
The photodynamic therapy system provided by the embodiment of the invention trains the convolutional neural network model in advance, when determining the light dose required by each point of the fluorescence image, the fluorescence image marked with the overexposed area and the underexposed area can be input into the preset convolutional neural network model, and the excitation light dose required by each point when obtaining the optimal fluorescence imaging result can be rapidly determined through machine learning training of the preset convolutional neural network model. Compared with the mode that in the prior art, the light source output light intensity is changed continuously according to the fluorescence image of each exposure by directly adopting a negative feedback algorithm, and multiple exposures are needed, the photodynamic therapy system adopts the mode that the preset convolution neural network model accurately determines the light dose required by each point of the fluorescence image, so that the exposure times can be greatly reduced, and the optimal imaging can be realized by using the minimum exposure times. And the fluorescence bleaching caused by excessive exposure times of the photosensitizer is reduced.
The photodynamic therapy system provided by the embodiment of the invention can firstly adopt exciting light with uniform light intensity to irradiate a region to be treated containing the photosensitizer to generate a fluorescence image, receive the fluorescence image acquired by the acquisition device through the microprocessor, determine relatively accurate light dose required by each region of the photosensitizer through a fluorescence image processing algorithm and a preset convolutional neural network module, irradiate the photosensitizer with the light dose to perform secondary exposure, basically meet the required requirements, and can determine the required light dose through the microprocessor and modulate the light source to output light beams again even if part of the photosensitizer needs to be irradiated again, so that the required light intensity requirement of each region of a focus is met. Therefore, the photodynamic therapy system provided by the embodiment of the invention can obtain the optimal imaging quality by only three short-time exposures at most, and realizes the optimal imaging by using the least number of exposures.
According to the treatment method based on the photodynamic treatment system, the fluorescence image generated by irradiating the light beam on the photosensitizer is obtained, the fluorescence image processing algorithm and the preset convolutional neural network module are used for determining the accurate exciting light dose required by each region of the photosensitizer, the photosensitizer is irradiated by the exciting light dose for re-exposure, the required requirements can be basically met, even if part of the photosensitizer needs to be irradiated again, the required light dose determined by the re-collected fluorescence image through the microprocessor can be used for re-modulating the light source to output the exciting light beam, and therefore the light intensity requirement required by each region of a focus is met. Therefore, the treatment method based on the photodynamic treatment system provided by the embodiment of the invention can obtain the optimal imaging quality by only three short-time exposures at most, and realizes the optimal imaging by using the least number of exposures.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a block diagram of a photodynamic therapy system in accordance with an embodiment of the invention;
FIG. 2 is a flow chart of a method of treatment based on a photodynamic therapy system in accordance with an embodiment of the invention;
FIG. 3 is a schematic structural diagram of a computer-readable storage medium provided according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a photodynamic therapy system, as shown in fig. 1, the photodynamic therapy system includes: the system comprises a light source 1, an acquisition device 2, a modulation device 3 and a microprocessor 4, wherein the light source 1 irradiates a photosensitizer 5 of a tissue to be treated to generate a fluorescence image; the acquisition device 2 acquires a fluorescence image and inputs the fluorescence image to the microprocessor 4; the microprocessor 4 comprises a calculation module and an analysis module, wherein the calculation module is used for calculating the fluorescence image according to a fluorescence image processing algorithm and determining an overexposed area and an underexposed area of the fluorescence image; the analysis module is used for analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolution neural network model and determining the required excitation light dose of each point of the fluorescence image; the modulation device 3 modulates the light beam output by the light source 1 according to the dose of the exciting light required by each point of the fluorescence image to generate the therapeutic light intensity for treatment. Wherein the excitation light dose required for each spot determined may be a dose such that the photosensitizer exerts the optimal therapeutic effect.
In one embodiment, the light source 1 may be a laser, a xenon lamp, a mercury lamp, or an LED, and the light source 1 is not limited in the present invention as long as the photosensitizer is excited to generate photosensitization. As for the selection of the modulation Device 3, different types of Spatial light modulation devices can be selected according to the size and optical characteristics of the tissue to be treated, such as a Spatial Light Modulator (SLM) that modulates the light field with liquid crystal molecules or a Digital Micromirror Device (DMD) that modulates the light field with an aluminum mirror array. The acquisition means 2 may be an ICCD for acquiring the fluorescence image. The photodynamic therapy system may further comprise an endoscope unit, which may be arranged in the imaging part of the system for acquiring imaging information of the tissue to be treated.
In an embodiment, the preset convolutional neural network model may be obtained through pre-training, specifically, a large number of fluorescence images of the photosensitizer are obtained first, where the fluorescence images include three types of sample sets, and the three types of sample sets respectively include an underexposed area, an overexposed area, an appropriate exposed area, and the light intensities of exposures adopted by the three areas. Inputting the three sample sets with the corresponding exposure labels into a convolutional neural network for training, and finally obtaining the required preset convolutional neural network model.
The photodynamic therapy system provided by the embodiment of the invention integrates the fluorescence imaging system and the irradiation system into a set of light path system, and further expands the clinical application range of the system by integrating the endoscope system, so that the system can be applied to body surface photodynamic therapy and can also be applied to in-vivo treatment areas which can be achieved by means of the endoscope. The light beam emitted by the light source is irradiated on the photosensitizer through the modulation device to generate a fluorescence image, the fluorescence image is input into the microprocessor after being collected by the collection device to obtain the distribution area of the photosensitizer and the concentration information contained in each area, the required irradiation parameters are obtained through calculation by utilizing the information, the obtained parameters are input into the modulation device, the modulation device is utilized to distribute the power density of the irradiation area of the light source and each irradiation point, so that different areas of the photosensitizer receive corresponding irradiation doses, and the precise regulation and control of the photodynamic therapy process are realized through imaging guidance.
The photodynamic therapy system provided by the embodiment of the invention trains the convolutional neural network model in advance, when determining the light dose required by each point of the fluorescence image, the fluorescence image marked with the overexposed area and the underexposed area can be input into the preset convolutional neural network model, and the light dose required by each point of the fluorescence image can be determined through the output of the preset convolutional neural network model. Compared with the mode that the light source output light intensity is changed continuously according to the fluorescence image of each exposure by directly adopting a negative feedback algorithm in the prior art and multiple exposures are needed, the photodynamic therapy system adopts the mode that the preset convolution neural network model accurately determines the light dose needed by each point of the fluorescence image, so that the exposure times can be greatly reduced, and the optimal imaging effect can be obtained by using the minimum exposure times. Reduce the fluorescence bleaching of the photosensitizer caused by excessive exposure times.
In one embodiment, photodynamic therapy software can be arranged in the microprocessor, the software is started and then enters a fluorescence image acquisition interface, a required camera is selected, the position of an imaging area is adjusted according to the size of light beam radiation output by the light source after clicking is started, the area boundary after spatial light modulation is ensured to be aligned with a reference frame set by the software, and accurate positioning of subsequent treatment is facilitated. Imaging is performed in the area outlined by the reference frame. Then, in a program setting interface, determining a port connected with a computer, setting stray signal parameters required to be filtered, setting image processing parameters, setting the sensitivity of a filter, setting an image saving path and setting the minimum pixel of a search point. After configuration is completed, the software main interface is returned, and the imaging button is pressed to trigger the light source and acquire the fluorescence image of the photosensitizer. At this time, the light beam emitted from the light source may be a uniform light beam. After the light dose required by each point of the fluorescence image is determined, a gray scale image can be generated by integrating data and is led into the spatial light modulator as an input parameter, and finally, the illumination parameter is modulated by the spatial light modulator, so that the distribution of the treatment light intensity is controlled, the light intensity requirement required by each region of a focus is met, and the purpose of imaging, guiding, accurately adjusting and controlling the light treatment is achieved.
In an embodiment, during the irradiation process of the light source, the irradiation area of the light source may be constantly locked by using an image tracking technique, and the irradiation area is dynamically adjusted according to the change of the imaging of the irradiation area, so as to ensure the accuracy of each position of the irradiation point. It is ensured that no shift of the pre-irradiation area and the actual irradiation area is caused by a slight change of the irradiation target itself during the irradiation. Enhancing the operability in practical clinical application.
In an embodiment, the acquired fluorescence image may be processed by the image processing module to realize digital reconstruction of each point on the fluorescence image. Specifically, since the image collected by the collecting device is vertically inverted compared with the image displayed on the modulating device, in order to make the points on the two correspond to each other, the fluorescence image collected by the collecting device can be adjusted according to a two-dimensional texture mapping algorithm to make the fluorescence image correspond to the image displayed on the modulating device, so as to obtain the processed fluorescence image. For the processed fluorescence image, an exposure determination module may be used to determine an overexposed region and an underexposed region of the fluorescence image, and specifically, the adjusted fluorescence image may be calculated according to the detected fluorescence signal intensity through an adaptive negative feedback algorithm and a pseudo color reconstruction algorithm to determine a gray value of each point on the fluorescence image, and the overexposed region and the underexposed region of the fluorescence image are determined according to the gray value, for example, a gray value greater than 240 is determined as the overexposed region, a gray value less than 10 is determined as the underexposed region, and different regions may also be determined according to gray values of other values. Wherein the acquired fluorescence image may be an image with a grey value below 255.
The self-adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm are image processing algorithms commonly used in the existing photodynamic therapy system, and through the two algorithms, overexposed and underexposed areas can be calculated according to the fluorescence signal intensity of the fluorescence image. Because the fluorescence image is generated by irradiating the photosensitizer with the uniform light beam, overexposure occurs at a place with high fluorescent dye concentration, and underexposure occurs at a place with low fluorescent dye concentration, namely, the gray value of an overexposed area is larger, and the gray value of an underexposed area is smaller.
In an embodiment, a preset convolutional neural network model may be used to determine the light doses required in two regions, specifically, because the preset convolutional neural network model is obtained by training three types of sample sets, a fluorescence image including an overexposed region and an underexposed region is input into the preset convolutional neural network model, in an analysis process of the model on the image, it may be first determined whether to need to be re-exposed, when re-exposure is needed, the light dose corresponding to the underexposed region on the fluorescence image may be increased, the light dose corresponding to the overexposed region on the fluorescence image may be reduced, specifically, the light power at the time of re-exposure is reduced for a region whose gray value is higher than a median (128), and the light power at the time of re-exposure is enhanced for a region whose gray value is lower than the median, thereby determining the light dose required for each point of the fluorescence image.
The photodynamic therapy system provided by the embodiment of the invention can firstly adopt uniform illumination to irradiate the photosensitizer to generate a fluorescence image, the fluorescence image acquired by the acquisition device is received by the microprocessor, the accurate light dose required by each region of the photosensitizer can be determined by a fluorescence image processing algorithm and a preset convolution neural network module, the photosensitizer is irradiated by adopting the light dose to be exposed again, the required requirements can be basically met, even if part of the photosensitizer needs to be irradiated again, the light dose required by the reacquired fluorescence image determined by the microprocessor can be used for modulating the light source output light beam again, and the light intensity required by each region of a focus is met. Therefore, the photodynamic therapy system provided by the embodiment of the invention can obtain the optimal imaging quality by only three short-time exposures at most, and realizes the optimal imaging by using the least number of exposures.
The embodiment of the present invention further provides a treatment method based on a photodynamic treatment system, as shown in fig. 2, the treatment method includes the following steps:
step S101: acquiring a fluorescence image generated when the photosensitizer on the tissue to be treated is irradiated; in particular, when a light source is illuminated on the photosensitizer, a fluorescence image is generated, which can be acquired by the acquisition device ICCD. Wherein the acquired fluorescence image may be an image with a grey value below 255.
Step S102: calculating the fluorescence image according to a fluorescence image processing algorithm, and determining an overexposed area and an underexposed area of the fluorescence image; specifically, for the acquired fluorescence image, the fluorescence image may be calculated according to the detected fluorescence signal intensity through an adaptive negative feedback algorithm and a pseudo color reconstruction algorithm to determine the gray value of each point on the fluorescence image, and the overexposed region and the underexposed region of the fluorescence image are determined according to the gray value, for example, the gray value is greater than 240 and is determined as the overexposed region, the gray value is less than 10 and is determined as the underexposed region, and different regions may also be determined according to the gray values of other values.
The self-adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm are image processing algorithms commonly used in the existing photodynamic therapy system, and the overexposed area and the underexposed area can be calculated according to the fluorescence signal intensity of the fluorescence image through the two algorithms. Because the fluorescence image is generated by irradiating the photosensitizer with the uniform light beam, overexposure can occur at a place with high fluorescent dye concentration, and underexposure can occur at a place with low fluorescent dye concentration, namely, the gray value of an overexposed area is larger, and the gray value of an underexposed area is smaller.
In an embodiment, before the calculation by the adaptive negative feedback algorithm and the pseudo color reconstruction algorithm, the acquired fluorescence image may be adjusted, and specifically, since the image acquired by the acquisition device is inverted up and down, the fluorescence image acquired by the acquisition device may be processed according to the two-dimensional texture mapping algorithm so as to correspond to each point of the image on the subsequent device, thereby obtaining the processed fluorescence image.
Step S103: and analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolutional neural network model, and determining the required excitation light dose of each point of the fluorescence image.
In an embodiment, the preset convolutional neural network model may be obtained through pre-training, specifically, a large number of fluorescence images of the photosensitizer are obtained first, where the fluorescence images include three types of sample sets, and the three types of sample sets include underexposed regions, overexposed regions, and suitable exposure regions, and the light intensities of the exposures adopted by the three regions. Inputting the three sample sets with the corresponding exposure labels into a convolutional neural network for training, and finally obtaining the required preset convolutional neural network model.
In an embodiment, the light dose required in two regions may be determined by using a preset convolutional neural network model, specifically, the preset convolutional neural network model is obtained by training three types of sample sets, so that a fluorescence image including an overexposed region and an underexposed region is input into the preset convolutional neural network model, in an analysis process of the image by the model, it is first determined whether to need to be exposed again, when the image needs to be exposed again, the light dose corresponding to the underexposed region on the fluorescence image is increased, the light dose corresponding to the overexposed region on the fluorescence image is reduced, specifically, the light power during the re-exposure may be reduced for a region with a gray value higher than a median value (128), and the light power during the re-exposure is enhanced for a region with a gray value lower than the median value, so as to obtain the light dose required for each point of the fluorescence image.
Step S104: and generating treatment light intensity according to the excitation light dose required by each point of the fluorescence image for treatment. Specifically, after the excitation light dose required by each point of the fluorescence image is determined, a gray scale image can be generated by integrating data, the gray scale image is led into a modulation device such as a spatial light modulator to serve as an input parameter, and finally, the illumination parameter is modulated by the spatial light modulator, so that the distribution of the treatment light intensity is controlled, the light intensity requirement required by each region of a focus is met, and the purpose of accurately regulating and controlling the light treatment by imaging guidance is achieved.
According to the treatment method based on the photodynamic therapy system, the fluorescence image generated by irradiating the light beam on the photosensitizer is obtained, the accurate light dose required by each area of the photosensitizer is determined by the fluorescence image processing algorithm and the preset convolution neural network module, the photosensitizer is irradiated by the light dose for exposure again, the required requirement can be basically met, even if part of the photosensitizer needs to be irradiated again, the required light dose determined by the fluorescence image acquired again can be used for modulating the light source to output the light beam again through the microprocessor, and therefore the light intensity requirement required by each area of a focus is met. Therefore, the treatment method based on the photodynamic treatment system provided by the embodiment of the invention can obtain the optimal imaging quality by only three short-time exposures at most, and realizes the optimal imaging by using the least number of exposures.
The treatment method based on the photodynamic treatment system provided by the embodiment of the invention trains the convolutional neural network model in advance, when the light dose required by each point of the fluorescence image is determined, the fluorescence image marked with the overexposed area and the underexposed area can be input into the preset convolutional neural network model, and the light dose required by each point of the fluorescence image can be determined through the output of the preset convolutional neural network model. Compared with the mode that in the prior art, the output light intensity of the light source is changed continuously according to the fluorescence image of each exposure by directly adopting a negative feedback algorithm, and multiple exposures are needed, the treatment method based on the photodynamic therapy system adopts the mode that the preset convolution neural network model accurately determines the light dose required by each point of the fluorescence image, so that the exposure times can be greatly reduced, and the optimal imaging can be realized by using the minimum exposure times. Reduce the fluorescence bleaching of the photosensitizer caused by excessive exposure times.
The functional description of the treatment method based on the photodynamic therapy system provided by the embodiment of the invention refers to the description of the photodynamic therapy system in the above embodiment in detail.
An embodiment of the present invention further provides a storage medium, as shown in fig. 3, on which a computer program 601 is stored, and the instructions, when executed by a processor, implement the steps of the photodynamic therapy system-based therapy method in the above-described embodiment. The storage medium is also stored with audio and video stream data, characteristic frame data, an interactive request signaling, encrypted data, preset data size and the like. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
An embodiment of the present invention further provides an electronic device, as shown in fig. 4, the electronic device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected through a bus or in another manner, and fig. 4 takes the connection through the bus as an example.
The processor 51 may be a Central Processing Unit (CPU). The Processor 51 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the corresponding program instructions/modules in the embodiments of the present invention. The processor 51 executes various functional applications and data processing of the processor by executing non-transitory software programs, instructions and modules stored in the memory 52, namely, implements the photodynamic therapy system-based therapy method in the above method embodiments.
The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 51, and the like. Further, the memory 52 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and these remote memories may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 52 and when executed by the processor 51 perform a method of photodynamic therapy system based therapy as in the embodiment of fig. 2.
The details of the electronic device may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 2, and are not described herein again.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (8)
1. A method of operation based on a photodynamic therapy system, comprising:
acquiring a fluorescence image generated when the photosensitizer is irradiated;
calculating the fluorescence image according to a fluorescence image processing algorithm, and determining an overexposed area and an underexposed area of the fluorescence image;
analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolutional neural network model, and determining the required excitation light dose of each point of the fluorescence image;
generating light intensity required by each point according to the exciting light dose required by each point of the fluorescence image;
analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolution neural network model, and determining the excitation light dosage required by each point of the fluorescence image, wherein the method comprises the following steps:
and increasing the excitation light dose corresponding to the underexposed area on the fluorescence image according to the preset convolution neural network model, and reducing the excitation light dose corresponding to the overexposed area on the fluorescence image to obtain the excitation light dose required by each point of the fluorescence image.
2. The method of claim 1, wherein computing the fluorescence image according to a fluorescence image processing algorithm to determine overexposed and underexposed regions of the fluorescence image comprises:
processing the fluorescence image according to a two-dimensional texture mapping algorithm to realize digital reconstruction of each point on the fluorescence image;
and calculating the processed fluorescence image according to a self-adaptive negative feedback algorithm and a pseudo color reconstruction algorithm, and determining an overexposed area and an underexposed area.
3. A photodynamic therapy system, comprising: a light source, a collecting device, a modulating device and a microprocessor,
the light source irradiates on the photosensitizer to generate a fluorescence image;
the acquisition device acquires the fluorescence image and inputs the fluorescence image to the microprocessor;
the microprocessor comprises a calculation module and an analysis module,
the calculation module is used for calculating the fluorescence image according to a fluorescence image processing algorithm and determining an overexposed area and an underexposed area of the fluorescence image;
the analysis module is used for analyzing the overexposed area and the underexposed area of the fluorescence image according to a preset convolution neural network model and determining the required excitation light dose of each point of the fluorescence image;
the modulation device modulates the light beam output by the light source according to the exciting light dose required by each point of the fluorescent image to generate the light intensity required by each point;
the analysis module includes:
and the parameter adjusting module is used for increasing the excitation light dose corresponding to the underexposed area on the fluorescence image according to the preset convolution neural network model, reducing the excitation light dose corresponding to the overexposed area on the fluorescence image and obtaining the excitation light dose required by each point of the fluorescence image.
4. The photodynamic therapy system according to claim 3, wherein the calculation module comprises:
the image processing module is used for processing the fluorescence image according to a two-dimensional texture mapping algorithm to realize digital reconstruction of each point on the fluorescence image;
and the exposure determining module is used for calculating the processed fluorescence image according to a self-adaptive negative feedback algorithm and a pseudo color reconstruction algorithm and determining an overexposed area and an underexposed area of the fluorescence image.
5. Photodynamic therapy system according to claim 3, characterized in that the modulating means comprises a spatial light modulator.
6. The photodynamic therapy system according to claim 3, further comprising: an endoscope unit for acquiring imaging information of a tissue to be treated.
7. A computer-readable storage medium storing computer instructions for causing a computer to perform the method of operation of a photodynamic therapy system as claimed in claim 1 or 2.
8. An electronic device, comprising: a memory and a processor, the memory and the processor being communicatively coupled to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method of operating the photodynamic therapy system according to claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893496.5A CN111991704B (en) | 2020-08-28 | 2020-08-28 | Operation method based on photodynamic therapy system and photodynamic therapy system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010893496.5A CN111991704B (en) | 2020-08-28 | 2020-08-28 | Operation method based on photodynamic therapy system and photodynamic therapy system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111991704A CN111991704A (en) | 2020-11-27 |
| CN111991704B true CN111991704B (en) | 2022-12-09 |
Family
ID=73465754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010893496.5A Active CN111991704B (en) | 2020-08-28 | 2020-08-28 | Operation method based on photodynamic therapy system and photodynamic therapy system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111991704B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113376931B (en) * | 2021-06-10 | 2022-11-04 | 复旦大学 | Fluorescence area light intensity supplementary lighting method, device and system for parathyroid gland detection |
| US20230038534A1 (en) * | 2021-08-03 | 2023-02-09 | Modulight, Inc. | Theranostic laser system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6128525A (en) * | 1997-07-29 | 2000-10-03 | Zeng; Haishan | Apparatus and method to monitor photodynamic therapy (PDT) |
| CN1769834A (en) * | 2004-10-21 | 2006-05-10 | 株式会社米姿托约 | Smear-limit based system and method for controlling vision systems for consistently accurate and high-speed inspection |
| CN108956564A (en) * | 2018-06-21 | 2018-12-07 | 深圳市优迈医学科技有限公司 | photosensitizer concentration detection device, system and method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103933671A (en) * | 2014-04-22 | 2014-07-23 | 天津大学 | Precision photodynamic therapy system |
| US20170224205A1 (en) * | 2016-02-04 | 2017-08-10 | Wright State University | Light endoscope system for imaging, light delivery, and therapy response monitoring |
| CN107582085B (en) * | 2017-09-14 | 2021-02-05 | 广州七喜医疗设备有限公司 | Intelligent digital X-ray exposure control device and method |
| CN107977969B (en) * | 2017-12-11 | 2020-07-21 | 北京数字精准医疗科技有限公司 | Endoscope fluorescence image segmentation method, device and storage medium |
| WO2020047536A1 (en) * | 2018-08-31 | 2020-03-05 | Board Of Regents, University Of Texas System | Deep learning based dosed prediction for treatment planning and quality assurance in radiation therapy |
| CN109730704B (en) * | 2018-12-29 | 2022-11-01 | 上海联影智能医疗科技有限公司 | Method and system for controlling exposure of medical diagnosis and treatment equipment |
| CN110478625B (en) * | 2019-08-21 | 2020-12-08 | 中国科学院苏州生物医学工程技术研究所 | Precise photodynamic treatment system based on hyperspectral and fluorescence imaging guidance |
| CN111182232A (en) * | 2019-12-31 | 2020-05-19 | 浙江华诺康科技有限公司 | Exposure parameter adjusting method, device, equipment and computer readable storage medium |
| CN111568451A (en) * | 2020-05-22 | 2020-08-25 | 上海联影医疗科技有限公司 | Exposure dose adjusting method and system |
-
2020
- 2020-08-28 CN CN202010893496.5A patent/CN111991704B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6128525A (en) * | 1997-07-29 | 2000-10-03 | Zeng; Haishan | Apparatus and method to monitor photodynamic therapy (PDT) |
| CN1769834A (en) * | 2004-10-21 | 2006-05-10 | 株式会社米姿托约 | Smear-limit based system and method for controlling vision systems for consistently accurate and high-speed inspection |
| CN108956564A (en) * | 2018-06-21 | 2018-12-07 | 深圳市优迈医学科技有限公司 | photosensitizer concentration detection device, system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111991704A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111991704B (en) | Operation method based on photodynamic therapy system and photodynamic therapy system | |
| Reutsky-Gefen et al. | Holographic optogenetic stimulation of patterned neuronal activity for vision restoration | |
| WO2022041102A1 (en) | Therapy method based on photodynamic therapy system, and photodynamic therapy system | |
| EP1166723A3 (en) | Laser treatment apparatus | |
| CN1433287A (en) | Optical feedback system for vision correction | |
| JP2009279169A5 (en) | ||
| Alexander et al. | Color Cherenkov imaging of clinical radiation therapy | |
| KR20180085250A (en) | Uv targeted phototherapy of photo responsive apparatus and method using 3d scanning technology | |
| US20130053699A1 (en) | Apparatus and method for performing photodynamic diagnosis and photodynamic therapy | |
| JPWO2017073286A1 (en) | Endoscope system | |
| CN110681070B (en) | Photodynamic therapy light source capable of being regulated and controlled in personalized mode and regulation and control method | |
| CN104740786A (en) | Precise blood vessel photodynamic-therapy device | |
| CN115153397A (en) | Imaging method for endoscopic camera system and endoscopic camera system | |
| CN204709655U (en) | A kind of precisely blood vessel photodynamic treatment device | |
| CN108697814A (en) | Equipment for process and control dosage to the colour former dosage in cornea tissue | |
| WO2016035450A1 (en) | Imaging device | |
| US20200264187A1 (en) | Living body observation method and living body observation device | |
| KR20110057828A (en) | Apparatus for treatment skin using light and method thereof | |
| JP2011104103A (en) | Energy subtraction image photographing apparatus | |
| KR101984849B1 (en) | Imaging device for multi-exposure laser speckle image and calibration method thereof | |
| US20230066464A1 (en) | Device for acquiring functional image of tissue and method for generating same | |
| CN115998246A (en) | Control method, device, equipment, medium and program product for imaging system | |
| CN106963341A (en) | A kind of near-infrared fluorescent X-ray bimodulus small animal imaging equipment | |
| CN114028727A (en) | Intelligent photon therapeutic apparatus and control method | |
| KR101959394B1 (en) | Imaging device for multi-exposure laser speckle image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230105 Address after: B106, Languang Science and Technology Building, No. 27, Gaoxin North 6th Road, Songpingshan Community, Xili Street, Nanshan District, Shenzhen, Guangdong 518000 Patentee after: Shenzhen Optical Health Technology Co.,Ltd. Address before: 518000 No. 3688 Nanhai Road, Shenzhen, Guangdong, Nanshan District Patentee before: SHENZHEN University |
|
| TR01 | Transfer of patent right |