WO2022041102A1 - 一种基于光动力治疗系统的治疗方法及光动力治疗系统 - Google Patents

一种基于光动力治疗系统的治疗方法及光动力治疗系统 Download PDF

Info

Publication number
WO2022041102A1
WO2022041102A1 PCT/CN2020/112029 CN2020112029W WO2022041102A1 WO 2022041102 A1 WO2022041102 A1 WO 2022041102A1 CN 2020112029 W CN2020112029 W CN 2020112029W WO 2022041102 A1 WO2022041102 A1 WO 2022041102A1
Authority
WO
WIPO (PCT)
Prior art keywords
fluorescent image
area
photodynamic therapy
therapy system
image
Prior art date
Application number
PCT/CN2020/112029
Other languages
English (en)
French (fr)
Inventor
屈军乐
许皓
黄燕霞
泰梅石
Original Assignee
深圳大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳大学 filed Critical 深圳大学
Priority to PCT/CN2020/112029 priority Critical patent/WO2022041102A1/zh
Publication of WO2022041102A1 publication Critical patent/WO2022041102A1/zh

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
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N5/00—Radiation therapy
    • A61N5/06—Radiation therapy using light
    • 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

Definitions

  • the invention relates to the technical field of photodynamic diagnosis and treatment equipment, in particular to a photodynamic therapy system-based treatment method and a photodynamic therapy system.
  • Photodynamic therapy requires the use of light to excite a photosensitizer, and the photosensitization effect produced by the photosensitizer can kill the diseased tissue. Since the light itself is controllable in the intensity, time and area of irradiation, and the photosensitizer has little effect on the non-irradiated area, photodynamic therapy has become an ideal precise treatment method. At the same time, photosensitizers can also be used for fluorescence imaging. Therefore, using photosensitizer distribution and other information obtained by photosensitizer fluorescence imaging to guide photodynamic irradiation to achieve precise photodynamic therapy is a very promising technology for clinical application.
  • the embodiments of the present invention provide a treatment method and a photodynamic therapy system based on a photodynamic therapy system, so as to solve the problem of using multiple exposures and stacking when using a photodynamic therapy system for treatment in the prior art, which often causes problems.
  • the photosensitive agent is bleached and the ideal imaging effect cannot be obtained.
  • a first aspect of the embodiments of the present invention provides a treatment method based on a photodynamic therapy system, the treatment method includes: acquiring a fluorescent image generated when a photosensitizer on a tissue to be treated is irradiated; Calculate to determine the overexposed area and underexposed area of the fluorescent image; analyze the overexposed area and the underexposed area of the fluorescent image according to the preset convolutional neural network model, and determine the excitation light dose required for each point of the fluorescent image; The required excitation light dose at each point of the image generates the treatment light intensity for treatment.
  • calculating the fluorescent image according to a fluorescent image processing algorithm, and determining the overexposed area and the underexposed area of the fluorescent image includes: processing the fluorescent image according to a two-dimensional texture mapping algorithm, so as to realize on-the-fly on the fluorescent image. Digital reconstruction is performed on each point; the processed fluorescent image is calculated according to the adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm, and the overexposed area and the underexposed area are determined.
  • analyzing the overexposed area and the underexposed area of the fluorescent image according to the preset convolutional neural network model, and determining the excitation light dose required for each point of the fluorescent image including: increasing the amount of light on the fluorescent image according to the preset convolutional neural network model.
  • the excitation light dose corresponding to the underexposed area is reduced, and the excitation light dose corresponding to the overexposed area on the fluorescent image is reduced to obtain the excitation light dose required for each point of the fluorescent image.
  • a second aspect of the embodiments of the present invention provides a photodynamic therapy system, which includes: a light source, a collection device, a modulation device, and a microprocessor, the light source irradiates the photosensitizer of the tissue to be treated to generate a fluorescent image; the collection The device collects the fluorescence image and inputs it to the microprocessor; the microprocessor includes a calculation module and an analysis module, and the calculation module is used to calculate the fluorescence image according to a fluorescence image processing algorithm, and determine the performance of the fluorescence image.
  • the analysis module is used to analyze the overexposed area and the underexposed area of the fluorescent image according to the preset convolutional neural network model, and determine the excitation light dose required for each point of the fluorescent image;
  • the modulation The device modulates the output beam of the light source according to the excitation light dose required for each point of the fluorescent image to generate a treatment light intensity for treatment.
  • the calculation module includes: an image processing module for processing the fluorescent image according to a two-dimensional texture mapping algorithm to realize digital reconstruction of each point on the fluorescent image; an exposure determination module for The adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm are used to calculate the processed fluorescence image, and determine the overexposed area and the underexposed area of the fluorescence image.
  • the analysis module includes: a parameter adjustment module, configured to increase the excitation light dose corresponding to the underexposed area on the fluorescent image according to the preset convolutional neural network model, and reduce the excitation light dose corresponding to the overexposed area on the fluorescent image, to obtain: The excitation light dose required for each point of the fluorescence image.
  • a parameter adjustment module configured to increase the excitation light dose corresponding to the underexposed area on the fluorescent image according to the preset convolutional neural network model, and reduce the excitation light dose corresponding to the overexposed area on the fluorescent image, to obtain: The excitation light dose required for each point of the fluorescence image.
  • the modulation device includes a spatial light modulator.
  • the photodynamic therapy system further includes: an endoscope unit, where the endoscope unit is used to acquire imaging information of the tissue to be treated.
  • a third aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the first and first aspects of the embodiments of the present invention.
  • the treatment method based on a photodynamic therapy system according to any one of the aspects.
  • a fourth aspect of the embodiments of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor are connected in communication with each other, the memory stores computer instructions, and the processor executes the computer instructions, so as to execute the treatment method based on the photodynamic therapy system according to any one of the first aspect and the first aspect of the embodiments of the present invention.
  • the photodynamic therapy system integrates the fluorescence imaging system and the irradiation system into a set of optical path system, and further expands the clinical application scope of the system by integrating the endoscope system, so that it can be applied to body surface photodynamics
  • the treatment can also be applied to the treatment areas in the body that can be reached with the aid of an endoscope.
  • the light beam emitted by the light source is irradiated on the photosensitizer by the modulation device to generate a fluorescent image, which is collected by the acquisition device and then input to the microprocessor to obtain the information on the distribution area of the photosensitizer and the concentration contained in each area, and then use the information to calculate and obtain Irradiate the required parameters, input the obtained parameters into the modulation device, and use the modulation device to distribute the irradiation area of the light source and the power density of each irradiation point, so that different areas of the photosensitizer receive the corresponding light dose, so as to achieve light alignment through imaging guidance. Precise control of the dynamic therapy process.
  • a convolutional neural network model is pre-trained, and when determining the light dose required for each point of the fluorescent image, the fluorescent image marked with the over-exposed area and the under-exposed area can be input into the pre-exposed area.
  • the excitation light dose required for each point to obtain optimal fluorescence imaging results can be quickly determined by machine learning training of the preset convolutional neural network model.
  • the photodynamic therapy system uses a preset convolutional neural network model to accurately determine each fluorescence image.
  • the light dose required for the spot can be greatly reduced by the number of exposures, and the optimal imaging can be achieved with the minimum number of exposures. Reduces fluorescence bleaching of photosensitizers due to excessive exposure.
  • an excitation light with uniform light intensity can be used to irradiate the area to be treated containing the photosensitizer to generate a fluorescent image
  • the fluorescent image collected by the acquisition device is received by the microprocessor, and the fluorescent image can be processed by the fluorescent image.
  • the algorithm and the preset convolutional neural network module determine the more accurate light dose required for each area of the photosensitizer. Using this light dose to irradiate the photosensitizer for re-exposure can basically meet the required requirements.
  • the photodynamic therapy system provided by the embodiment of the present invention only needs three short-time exposures at most to obtain optimal imaging quality, and realizes optimal imaging with a minimum number of exposures.
  • the fluorescence image generated by the light beam irradiated on the photosensitizer is obtained, and the fluorescence image processing algorithm and the preset convolutional neural network module are used to determine the required ratio of each area of the photosensitizer.
  • Accurate excitation light dose, using this excitation light dose to irradiate the photosensitizer for re-exposure can basically meet the required requirements.
  • the fluorescence image collected again can be used to determine the required light dose through the microprocessor
  • the light source is modulated again to output the excitation beam, so as to achieve the required light intensity in each area of the lesion. Therefore, in the treatment method based on the photodynamic therapy system provided by the embodiments of the present invention, the optimal imaging quality can be obtained by only three short-time exposures at most, and the optimal imaging can be achieved with the minimum number of exposures.
  • FIG. 1 is a structural block diagram of a photodynamic therapy system according to an embodiment of the present invention.
  • FIG. 2 is a flowchart of a treatment method based on a photodynamic therapy system according to an embodiment of the present 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 provided according to an embodiment of the present invention.
  • the photodynamic therapy system includes: a light source 1 , a collection device 2 , a modulation device 3 and a microprocessor 4 .
  • the fluorescence image is generated on the agent 5; the collection device 2 collects the fluorescence image and inputs it to the microprocessor 4; the microprocessor 4 includes a calculation module and an analysis module, and the calculation module is used to calculate the fluorescence image according to the fluorescence image processing algorithm, and determine the Overexposed area and underexposed area; the analysis module is used to analyze the overexposed area and underexposed area of the fluorescent image according to the preset convolutional neural network model, and determine the excitation light dose required for each point of the fluorescent image; the modulation device 3 is based on The excitation light dose required for each point of the fluorescent image modulates the output beam of the light source 1 to generate a treatment light intensity for treatment.
  • the excitation light dose required for each determined point may be the dose that enables the
  • the light source 1 can be selected from a laser, a xenon lamp, a mercury lamp or an LED.
  • the present invention does not limit the selection of the light source 1, as long as the photosensitizer can be excited to produce photosensitivity.
  • different types of spatial light modulation devices can be selected according to the size and optical properties of the tissue to be treated, such as a spatial light modulator (SLM) that uses liquid crystal molecules to modulate the light field or an aluminum Digital Micro mirror Device (DMD), etc.
  • the acquisition device 2 can select an ICCD for acquiring fluorescence images.
  • the photodynamic therapy system may further include an endoscope unit, and the endoscope unit may be arranged in the imaging part of the system for acquiring imaging information of the tissue to be treated.
  • the preset convolutional neural network model can be obtained through pre-training. Specifically, a large number of fluorescent images of photosensitizers are obtained first, and the fluorescent images include three types of sample sets, and the three types of sample sets respectively include underexposure. The area, the overexposed area and the exposure suitable area and the three areas correspond to the light intensity of the exposure used. The three types of sample sets with corresponding exposure labels are input into the convolutional neural network for training, and finally the required preset convolutional neural network model is obtained.
  • the photodynamic therapy system integrates the fluorescence imaging system and the irradiation system into a set of optical path system, and further expands the clinical application scope of the system by integrating the endoscope system, so that it can be applied to body surface photodynamics
  • the treatment can also be applied to the treatment areas in the body that can be reached with the aid of an endoscope.
  • the light beam emitted by the light source is irradiated on the photosensitizer by the modulation device to generate a fluorescent image, which is collected by the acquisition device and then input to the microprocessor to obtain the information on the distribution area of the photosensitizer and the concentration contained in each area, and then use the information to calculate and obtain Irradiate the required parameters, input the obtained parameters into the modulation device, and use the modulation device to distribute the irradiation area of the light source and the power density of each irradiation point, so that different areas of the photosensitizer receive the corresponding light dose, so as to achieve light alignment through imaging guidance. Precise control of the dynamic therapy process.
  • a convolutional neural network model is pre-trained, and when determining the light dose required for each point of the fluorescent image, the fluorescent image marked with the over-exposed area and the under-exposed area can be input into the pre-exposed area.
  • the light dose required for each point of the fluorescent image can be determined through the output of the preset convolutional neural network model.
  • the photodynamic therapy system uses a preset convolutional neural network model to accurately determine each fluorescence image.
  • the light dose required by the spot can greatly reduce the number of exposures, and achieve the optimal imaging effect with the least number of exposures. Reduces fluorescence bleaching of photosensitizers due to excessive exposure.
  • the photodynamic therapy software can be set in the microprocessor. After starting the software, it enters the fluorescence image acquisition interface, first select the required camera, click start, and adjust the position of the imaging area according to the size of the output beam radiation of the light source to ensure that the The region boundary after spatial light modulation is aligned with the reference frame set by the software, which facilitates the precise positioning of subsequent treatments. Image the area outlined by the reference frame. Then, in the program setting interface, determine the port connected to the computer, set the stray signal parameters to be filtered, set the image processing parameters, set the sensitivity of the filter, set the image saving path, and set the minimum pixel of the search point. .
  • the light beam emitted by the light source may be a uniform light beam.
  • a grayscale image can be generated by integrating the data, imported into the spatial light modulator as input parameters, and finally the illumination parameters are modulated by the spatial light modulator to control the treatment light.
  • the strong distribution meets the light intensity requirements of each area of the lesion, and achieves the purpose of imaging-guided precise regulation of light therapy.
  • image tracking technology can also be used to lock the irradiation area of the light source at all times, and dynamically adjust the irradiation area according to changes in the imaging of the irradiation area to ensure the accuracy of each position of the irradiation point. Make sure that there is no deviation between the pre-irradiation area and the actual irradiation area due to small changes in the irradiation target itself during the irradiation process. Enhance operability in practical clinical applications.
  • the acquired fluorescence image may be processed by an image processing module first, so as to realize digital reconstruction of each point on the fluorescence image.
  • the fluorescence image collected by the collection device can be adjusted according to the two-dimensional texture mapping algorithm. Make it correspond to the image displayed on the modulation device, so as to obtain the processed fluorescence image.
  • an exposure determination module can be used to determine its overexposed area and underexposed area.
  • an adaptive negative feedback algorithm and a pseudo-color reconstruction algorithm can be used to adjust the adjusted fluorescence image according to the intensity of the detected fluorescence signal. Calculation is performed to determine the gray value of each point on the fluorescent image, and the overexposed area and the underexposed area of the fluorescent image are determined by the size of the gray value. For underexposed areas, etc., different areas can also be determined according to the grayscale values of other numerical values. Wherein, the acquired fluorescence image may be an image with a grayscale value lower than 255.
  • the adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm are both commonly used image processing algorithms in the existing photodynamic therapy system.
  • the overexposed and underexposed areas can be calculated according to the fluorescence signal intensity of the fluorescence image. . Since the fluorescent image at this time is generated by irradiating the photosensitizer with a uniform beam, overexposure will occur in places with high fluorescent dye concentration, and underexposure will occur in places with low fluorescent dye concentration, that is, the gray value of the overexposed area is large. Underexposed areas have smaller grayscale values.
  • a preset convolutional neural network model can be used to determine the required light dose in the two regions. Specifically, since the preset convolutional neural network model is obtained by training with three types of sample sets, therefore, Input the fluorescent image containing the overexposed area and the underexposed area into the preset convolutional neural network model. During the model's analysis of the image, it will first determine whether re-exposure is required. When re-exposure is required, the underexposure on the fluorescent image will be increased.
  • the light dose corresponding to the area reduce the light dose corresponding to the overexposed area on the fluorescent image, specifically for the area with gray value higher than the median value (128), reduce the light power during re-exposure, for the area with gray value lower than the median value Increase the light power during re-exposure to determine the required light dose at each point of the fluorescent image.
  • a fluorescent image can be generated by irradiating the photosensitizer with uniform light, and the fluorescent image collected by the acquisition device can be received by the microprocessor, and the fluorescent image processing algorithm and the preset convolutional neural network can be used to generate the fluorescent image.
  • the module determines the more accurate light dose required for each area of the photosensitizer. Using this light dose to irradiate the photosensitizer for re-exposure can basically meet the required requirements.
  • the photodynamic therapy system provided by the embodiment of the present invention only needs three short-time exposures at most to obtain optimal imaging quality, and realizes optimal imaging with a minimum number of exposures.
  • An embodiment of the present invention also provides a treatment method based on a photodynamic therapy system, as shown in FIG. 2 , the treatment method includes the following steps:
  • Step S101 Acquire a fluorescent image generated when the photosensitizer on the tissue to be treated is irradiated; specifically, a fluorescent image will be generated when a light source is irradiated on the photosensitizer, and the fluorescent image can be collected by the collection device ICCD.
  • the acquired fluorescence image may be an image with a grayscale value lower than 255.
  • Step S102 Calculate the fluorescence image according to the fluorescence image processing algorithm, and determine the overexposed area and the underexposed area of the fluorescence image; Calculate the fluorescence signal intensity of the fluorescence image, determine the gray value of each point on the fluorescence image, and determine the overexposed area and underexposed area of the fluorescent image by the size of the gray value. , a gray value less than 10 is determined as an underexposed area, etc., and different areas can also be determined according to the gray value of other numerical values.
  • the adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm are both commonly used image processing algorithms in the existing photodynamic therapy system.
  • the overexposed and underexposed areas can be calculated according to the fluorescence signal intensity of the fluorescence image. . Since the fluorescent image at this time is generated by irradiating the photosensitizer with a uniform beam, overexposure will occur in places with high fluorescent dye concentration, and underexposure will occur in places with low fluorescent dye concentration, that is, the gray value of the overexposed area is large. Underexposed areas have smaller grayscale values.
  • the collected fluorescence image can be adjusted before the calculation is performed by the adaptive negative feedback algorithm and the pseudo-color reconstruction algorithm.
  • the mapping algorithm processes the fluorescence image collected by the acquisition device so that it corresponds to each point of the image on the subsequent device, thereby obtaining the processed fluorescence image.
  • Step S103 Analyze the overexposed area and the underexposed area of the fluorescent image according to the preset convolutional neural network model, and determine the excitation light dose required for each point of the fluorescent image.
  • the preset convolutional neural network model can be obtained through pre-training. Specifically, a large number of fluorescence images of photosensitizers are first acquired, and the fluorescence images include three types of sample sets, and the three types of sample sets include exposure. The underexposed area, the overexposed area, the properly exposed area and the three areas correspond to the light intensity of the exposure used. The three types of sample sets with corresponding exposure labels are input into the convolutional neural network for training, and finally the required preset convolutional neural network model is obtained.
  • a preset convolutional neural network model can be used to determine the required light dose in the two regions. Specifically, since the preset convolutional neural network model is obtained by training with three types of sample sets, therefore, Input the fluorescent image containing the overexposed area and the underexposed area into the preset convolutional neural network model. During the model's analysis of the image, it will first determine whether re-exposure is required. When re-exposure is required, the underexposure on the fluorescent image will be increased. The light dose corresponding to the area, reduce the light dose corresponding to the overexposed area on the fluorescent image.
  • the light power during re-exposure is enhanced to obtain the required light dose for each point of the fluorescent image.
  • Step S104 generating treatment light intensity according to the excitation light dose required for each point of the fluorescence image to perform treatment. Specifically, after the excitation light dose required for each point of the fluorescent image is determined, a grayscale image can be generated by integrating the data, imported into a modulation device such as a spatial light modulator as an input parameter, and finally the illumination parameters are adjusted by the spatial light modulator. Modulation is performed to control the distribution of the treatment light intensity, meet the light intensity requirements of each area of the lesion, and achieve the purpose of imaging-guided precise regulation of light therapy.
  • the fluorescence image generated by the light beam irradiated on the photosensitizer is obtained, and the fluorescence image processing algorithm and the preset convolutional neural network module are used to determine the required ratio of each area of the photosensitizer.
  • Accurate light dose, using this light dose to irradiate the photosensitizer for re-exposure can basically meet the required requirements. Even if some photosensitizers need to be irradiated again, the re-collected fluorescence image can be re-modulated by the microprocessor to determine the required light dose.
  • the light source outputs light beams, so as to meet the light intensity requirements required by each area of the lesion. Therefore, in the treatment method based on the photodynamic therapy system provided by the embodiments of the present invention, the optimal imaging quality can be obtained by only three short-time exposures at most, and the optimal imaging can be achieved with the minimum number of exposures.
  • the convolutional neural network model is pre-trained, and when determining the light dose required for each point of the fluorescence image, the fluorescence in the overexposed area and the underexposed area can be marked.
  • the image is input into the preset convolutional neural network model, and the light dose required for each point of the fluorescent image can be determined through the output of the preset convolutional neural network model.
  • the treatment method based on the photodynamic therapy system adopts a preset convolutional neural network model to be accurate. Determining the light dose required for each point of a fluorescent image can significantly reduce the number of exposures, enabling optimal imaging with a minimum number of exposures. Reduces fluorescence bleaching of photosensitizers due to excessive exposure.
  • 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 when the instruction is executed by the processor, implements the steps of the treatment method based on the photodynamic therapy system in the foregoing embodiment.
  • the storage medium also stores audio and video stream data, feature frame data, interaction 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 (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or solid-state hard disk (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard) Disk Drive, abbreviation: HDD) or solid-state drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.
  • An embodiment of the present invention also provides an electronic device.
  • 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 other ways. Take bus connection as an example.
  • the processor 51 may be a central processing unit (Central Processing Unit, CPU).
  • the processor 51 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), application specific integrated circuits (Application Specific Integrated Circuits, ASICs), Field-Programmable Gate Arrays (Field-Programmable Gate Arrays, FPGAs) or Other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above types of chips.
  • DSPs Digital Signal Processors
  • ASICs Application Specific Integrated Circuits
  • FPGAs Field-Programmable Gate Arrays
  • Other programmable logic devices discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above types of chips.
  • the memory 52 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as 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 running the non-transitory software programs, instructions and modules stored in the memory 52, that is, to realize the treatment method based on the photodynamic therapy system 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 and an application program required by at least one function; the storage data area may store data created by the processor 51 and the like. Additionally, 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, memory 52 may optionally include memory located remotely from processor 51 , which may be connected to processor 51 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the one or more modules are stored in the memory 52, and when executed by the processor 51, perform the treatment method based on the photodynamic therapy system in the embodiment shown in FIG. 2 .

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Radiation-Therapy Devices (AREA)

Abstract

一种基于光动力治疗系统的操作方法及光动力治疗系统，该方法包括：获取待治疗组织上光敏剂被照射时生成的荧光图像(S101)；根据荧光图像处理算法对荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域(S102)；根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量(S103)；根据荧光图像各点所需的激发光剂量生成治疗光强(S104)。将标记了过曝区域和曝光不足区域的荧光图像输入到预设卷积神经网络模型中，由预设卷积神经网络模型的输出即可确定获得最佳荧光图像时各点所需的激发光参数。实现了用最少的曝光次数来获得最优成像。减少了光敏剂因曝光次数过多引起的荧光漂白。

Description

一种基于光动力治疗系统的治疗方法及光动力治疗系统 技术领域
本发明涉及光动力诊疗设备技术领域，具体涉及一种基于光动力治疗系统的治疗方法及光动力治疗系统。
背景技术
光动力治疗需要利用光来激发光敏剂，通过光敏剂产生的光敏化效应来实现对病变组织的杀伤。由于光本身在照射的强度、时间和区域上可控，加之光敏剂对非照射区域的影响小，使得光动力治疗成为一种理想的精准治疗方法。同时，光敏剂又可以用于荧光成像，因此利用光敏剂荧光成像所获得的光敏剂分布等信息来引导光动力照射，实现精准的光动力治疗是一项非常具有临床应用前景的技术。
目前，在利用光敏剂进行的荧光成像中，由于光敏剂分布的区域不同以及各生物组织自身性质的不同，当使用照射功率均一的光源进行光敏剂荧光成像时，往往会出现一些区域曝光过度，而另外一些区域曝光不足，极大的降低了成像信息的获取。而采用多次曝光叠加的方式，往往会造成光敏剂荧光的漂白，无法获得理想的成像效果。因此，如何能根据光敏剂浓度分布区域的不同，实时调整各区域内光源照射功率，利用最少的曝光次数来获得最优的成像效果，在光动力疗法的临床诊疗一体化上具有重要意义。
发明内容
有鉴于此，本发明实施例提供了一种基于光动力治疗系统的治疗方法及光动力治疗系统，以解决现有技术中采用光动力治疗系统进行治疗时采用多次曝 光叠加的方式，往往会造成光敏剂荧光的漂白，无法获得理想的成像效果的问题。
本发明提出的技术方案如下：
本发明实施例第一方面提供一种基于光动力治疗系统的治疗方法，该治疗方法包括：获取待治疗组织上光敏剂被照射时生成的荧光图像；根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量；根据荧光图像各点所需的激发光剂量生成治疗光强进行治疗。
进一步地，根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域，包括：根据二维纹理映射算法对所述荧光图像进行处理，实现所述荧光图像上各点进行数字重构；根据自适应负反馈算法和伪彩色重建算法对所述处理后的荧光图像进行计算，确定过曝区域和曝光不足区域。
进一步地，根据预设卷积神经网络模型对荧光图像过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量，包括：根据预设卷积神经网络模型增加荧光图像上曝光不足区域对应的激发光剂量，减少荧光图像上过曝区域对应的激发光剂量，得到荧光图像各点所需的激发光剂量。
本发明实施例第二方面提供一种光动力治疗系统，该系统包括：光源、采集装置、调制装置及微处理器，所述光源照射在待治疗组织的光敏剂上生成荧光图像；所述采集装置采集所述荧光图像输入至所述微处理器；所述微处理器包括计算模块和分析模块，所述计算模块用于根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；所述分析模块用于根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析， 确定荧光图像各点所需的激发光剂量；所述调制装置根据所述荧光图像各点所需的激发光剂量对光源输出光束进行调制生成治疗光强进行治疗。
进一步地，所述计算模块包括：图像处理模块，用于根据二维纹理映射算法对所述荧光图像进行处理，实现所述荧光图像上各点进行数字重构；曝光确定模块，用于根据自适应负反馈算法和伪彩色重建算法对所述处理后的荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域。
进一步地，所述分析模块包括：参数调整模块，用于根据预设卷积神经网络模型增加荧光图像上曝光不足区域对应的激发光剂量，减少荧光图像上过曝区域对应的激发光剂量，得到荧光图像各点所需的激发光剂量。
进一步地，所述调制装置包括空间光调制器。
进一步地，该光动力治疗系统还包括：内窥镜单元，所述内窥镜单元用于获取待治疗组织的成像信息。
本发明实施例第三方面提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使所述计算机执行如本发明实施例第一方面及第一方面任一项所述的基于光动力治疗系统的治疗方法。
本发明实施例第四方面提供一种电子设备，包括：存储器和处理器，所述存储器和所述处理器之间互相通信连接，所述存储器存储有计算机指令，所述处理器通过执行所述计算机指令，从而执行如本发明实施例第一方面及第一方面任一项所述的基于光动力治疗系统的治疗方法。
本发明提供的技术方案，具有如下效果：
本发明实施例提供的光动力治疗系统将荧光成像系统和照射系统整合到一 套光路系统中，并通过整合内窥镜系统进一步拓展系统的临床应用范围，使其即能应用于体表光动力治疗，也能应用于借助内窥镜所能达到的体内治疗区域。其中，光源发出的光束通过调制装置照射在光敏剂上生成荧光图像，并由采集装置采集后输入到微处理器获得光敏剂分布的区域以及各区域所含浓度的信息，再利用这些信息计算获得照射所需参数，将所获得参数输入调制装置，利用调制装置对光源的照射区域和各照射点的功率密度进行分配，使得光敏剂不同区域接收到相应的光照剂量，从而通过成像引导实现对光动力治疗过程的精准调控。
本发明实施例提供的光动力治疗系统，预先训练了卷积神经网络模型，在确定荧光图像各点所需的光剂量时，可以将标记了过曝区域和曝光不足区域的荧光图像输入到预设卷积神经网络模型中，通过对该预设卷积神经网络模型的机器学习训练即可快速确定获得最优荧光成像结果时各点所需的激发光剂量。相比现有技术中直接采用负反馈算法不断根据每次曝光的荧光图像改变光源输出光强，需要多次曝光的方式，该光动力治疗系统采用预设卷积神经网络模型精准确定荧光图像各点所需的光剂量的方式可以大幅减少曝光次数，实现了用最少的曝光次数来实现最优成像。减少光敏剂因曝光次数过多引起的荧光漂白。
本发明实施例提供的光动力治疗系统，可以先采用光强均匀的激发光照射含光敏剂的待治疗区域生成荧光图像，通过微处理器接收采集装置采集的该荧光图像，可以由荧光图像处理算法以及预设卷积神经网络模块确定光敏剂各区域所需的较为准确的光剂量，采用该光剂量照射光敏剂再次曝光，可以基本达到所需要求，即使有部分光敏剂需要再次照射，可以将再次采集的荧光图像通过微处理器确定所需的光剂量并再次调制光源输出光束，从而达到病灶各区域所需的光强要求。由此，本发明实施例提供的光动力治疗系统，最多仅需三次短时曝光即可获得最优的成像质量，实现了用最少的曝光次数来实现最优成像。
本发明实施例提供的基于光动力治疗系统的治疗方法，通过获取光束照射 在光敏剂上生成的荧光图像，由荧光图像处理算法以及预设卷积神经网络模块确定光敏剂各区域所需的较为准确的激发光剂量，采用该激发光剂量照射光敏剂再次曝光，可以基本达到所需要求，即使有部分光敏剂需要再次照射，可以将再次采集的荧光图像通过微处理器确定所需的光剂量再次调制光源输出激发光束，从而达到病灶各区域所需的光强要求。由此，本发明实施例提供的基于光动力治疗系统的治疗方法，最多仅需三次短时曝光即可获得最优的成像质量，实现了用最少的曝光次数来实现最优成像。
附图说明
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是根据本发明实施例的光动力治疗系统的结构框图；
图2是根据本发明实施例的基于光动力治疗系统的治疗方法的流程图；
图3是根据本发明实施例提供的计算机可读存储介质的结构示意图；
图4是根据本发明实施例提供的电子设备的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实 施例，都属于本发明保护的范围。
本发明实施例提供一种光动力治疗系统，如图1所示，该光动力治疗系统包括：光源1、采集装置2、调制装置3及微处理器4，光源1照射在待治疗组织的光敏剂5上生成荧光图像；采集装置2采集荧光图像输入至微处理器4；微处理器4包括计算模块和分析模块，计算模块用于根据荧光图像处理算法对荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；分析模块用于根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量；调制装置3根据荧光图像各点所需的激发光剂量对光源1输出光束进行调制生成治疗光强进行治疗。其中，确定的各点所需的激发光剂量可以是使得光敏剂发挥最佳治疗效果的剂量。
在一实施例中，光源1可以选择激光、氙灯、汞灯或LED等光源，本发明对光源1的选择不做限定，只要能激发光敏剂产生光敏作用即可。对于调制装置3的选择，可以根据待治疗组织的大小和光学特性选定不同种类的空间光调制设备，例如利用液晶分子调控光场的空间光调制器(Spatial light modulator,SLM)或利用铝制反射镜面阵列调控光场的数字微镜器件(Digital Micro mirror Device,DMD)等。采集装置2可以选择ICCD，用于采集荧光图像。该光动力治疗系统还可以包括内窥镜单元，内窥镜单元可以设置在系统的成像部分，用于获取待治疗组织的成像信息。
在一实施例中，对于预设卷积神经网络模型可以通过预先训练得到，具体地，首先获取大量的光敏剂的荧光图像，荧光图像中包括三类样本集，三类样本集分别包括曝光不足区域、过曝区域和曝光合适区域以及三个区域对应采用的曝光的光强。将三类带有相应曝光标签的样本集输入到卷积神经网络中进行训练，最终得到所需的预设卷积神经网络模型。
本发明实施例提供的光动力治疗系统将荧光成像系统和照射系统整合到一 套光路系统中，并通过整合内窥镜系统进一步拓展系统的临床应用范围，使其即能应用于体表光动力治疗，也能应用于借助内窥镜所能达到的体内治疗区域。其中，光源发出的光束通过调制装置照射在光敏剂上生成荧光图像，并由采集装置采集后输入到微处理器获得光敏剂分布的区域以及各区域所含浓度的信息，再利用这些信息计算获得照射所需参数，将所获得参数输入调制装置，利用调制装置对光源的照射区域和各照射点的功率密度进行分配，使得光敏剂不同区域接收到相应的光照剂量，从而通过成像引导实现对光动力治疗过程的精准调控。
本发明实施例提供的光动力治疗系统，预先训练了卷积神经网络模型，在确定荧光图像各点所需的光剂量时，可以将标记了过曝区域和曝光不足区域的荧光图像输入到预设卷积神经网络模型中，通过该预设卷积神经网络模型的输出即可确定荧光图像各点所需的光剂量。相比现有技术中直接采用负反馈算法不断根据每次曝光的荧光图像改变光源输出光强，需要多次曝光的方式，该光动力治疗系统采用预设卷积神经网络模型精准确定荧光图像各点所需的光剂量的方式可以大幅减少曝光次数，实现了用最少的曝光次数来获得最优成像效果。减少光敏剂因曝光次数过多引起的荧光漂白。
在一实施例中，可以在微处理器中设置光动力治疗软件，启动软件后进入荧光图像采集界面，先选择所需相机，点击开始，根据光源输出光束辐射的尺寸调整成像区域的位置，保证经空间光调制后的区域边界与软件设定的参考框对齐，便于后续治疗的精确定位。按参考框所勾勒的区域进行成像。随后，在程序设置界面，确定与电脑连接的端口，设定所需过滤的杂散信号参数，设定图像处理参数，设定滤波器的灵敏度，设定图像保存路径，设置搜索点的最小像素。完成配置后，回到软件主界面，按下成像按钮可触发光源并采集光敏剂的荧光图像。此时，光源发出的光束可以是均匀的光束。之后确定荧光图像各点所需的光剂量之后，可以通过对数据整合生成灰度图，导入到空间光调制器 中作为输入参数，最后通过空间光调制器对光照参数进行调制，从而控制治疗光强的分布，满足病灶各区域所需的光强要求，达到成像引导精准调控光治疗的目的。
在一实施例中，在光源的照射过程中，还可以利用图像追踪技术，时刻锁定光源的照射区域，根据照射区域成像的变化动态调整照射区域，确保照射点各位置的精准。确保不会因照射过程中照射目标本身的微小变化，导致预照射区域和实际照射区域的偏移。增强实际临床应用中的可操作性。
在一实施例中，对于采集的荧光图像可以先由图像处理模块进行处理，实现荧光图像上各点进行数字重构。具体地，由于采集装置采集的图像相比调制装置上显示的图像发生了上下反转，为了使两者上的各点对应，可以根据二维纹理映射算法对采集装置采集的荧光图像进行调整，使其和调制装置上显示图像对应，从而得到处理后的荧光图像。对于处理后的荧光图像，可以采用曝光确定模块确定其过曝区域和曝光不足区域，具体地，可以通过自适应负反馈算法和伪彩色重建算法，根据探测的荧光信号强度对调整后的荧光图像进行计算，确定荧光图像上各点的灰度值，由灰度值的大小确定荧光图像的过曝区域和曝光不足区域，例如灰度值大于240确定为过曝区域、灰度值小于10确定为曝光不足区域等，也可以根据其他数值的灰度值确定不同区域。其中，采集的荧光图像可以是灰度值低于255的图像。
其中，自适应负反馈算法和伪彩色重建算法均为现有的光动力治疗系统中常用的图像处理算法，通过这两个算法，可以根据荧光图像的荧光信号强度计算出过曝和曝光不足区域。由于此时的荧光图像是均匀光束照射光敏剂生成的，在荧光染料浓度高的地方会出现过曝，在荧光染料浓度少的地方会出现曝光不足，即过曝区域的灰度值较大，曝光不足区域的灰度值较小。
在一实施例中，可以采用预设卷积神经网络模型确定两个区域中所需的光 剂量，具体地，由于预设卷积神经网络模型是采用三类样本集进行训练得到的，因此，将包含过曝区域和曝光不足区域的荧光图像输入预设卷积神经网络模型中，在模型对图像的分析过程中，会首先判断是否需要再次曝光，当需要再次曝光会增加荧光图像上曝光不足区域对应的光剂量，减少荧光图像上过曝区域对应的光剂量，具体对于灰度值高于中值(128)的区域减少再次曝光时的光照功率，对于灰度值低于中值的区域增强再次曝光时的光照功率，从而确定荧光图像各点所需的光剂量。
本发明实施例提供的光动力治疗系统，可以先采用均匀的光照照射光敏剂生成荧光图像，通过微处理器接收采集装置采集的该荧光图像，可以由荧光图像处理算法以及预设卷积神经网络模块确定光敏剂各区域所需的较为准确的光剂量，采用该光剂量照射光敏剂再次曝光，可以基本达到所需要求，即使有部分光敏剂需要再次照射，可以将再次采集的荧光图像通过微处理器确定所需的光剂量再次调制光源输出光束，从而达到病灶各区域所需的光强要求。由此，本发明实施例提供的光动力治疗系统，最多仅需三次短时曝光即可获得最优的成像质量，实现了用最少的曝光次数来实现最优成像。
本发明实施例还提供一种基于光动力治疗系统的治疗方法，如图2所示，该治疗方法包括如下步骤：
步骤S101：获取待治疗组织上光敏剂被照射时生成的荧光图像；具体地，当光源照射在光敏剂上会产生荧光图像，可以由采集装置ICCD采集该荧光图像。其中，采集的荧光图像可以是灰度值低于255的图像。
步骤S102：根据荧光图像处理算法对荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；具体地，对于采集的荧光图像，可以通过自适应负反馈算法和伪彩色重建算法，根据探测的荧光信号强度对荧光图像进行计算，确定荧光图像上各点的灰度值，由灰度值的大小确定荧光图像的过曝区域和曝 光不足区域，例如灰度值大于240确定为过曝区域、灰度值小于10确定为曝光不足区域等，也可以根据其他数值的灰度值确定不同区域。
其中，自适应负反馈算法和伪彩色重建算法均为现有的光动力治疗系统中常用的图像处理算法，通过这两个算法，可以根据荧光图像的荧光信号强度计算出过曝和曝光不足区域。由于此时的荧光图像是均匀光束照射光敏剂生成的，在荧光染料浓度高的地方会出现过曝，在荧光染料浓度少的地方会出现曝光不足，即过曝区域的灰度值较大，曝光不足区域的灰度值较小。
在一实施例中，在通过自适应负反馈算法和伪彩色重建算法计算之前，可以对于采集的荧光图像进行调整，具体地，由于采集装置采集的图像发生了上下反转，可以根据二维纹理映射算法对采集装置采集的荧光图像进行处理，使其和后续装置上图像各点对应，从而得到处理后的荧光图像。
步骤S103：根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量。
在一实施例中，对于预设卷积神经网络模型可以通过预先训练得到，具体地，首先获取大量的光敏剂的荧光图像，荧光图像中包括三类样本集，三类样本集分部包括曝光不足区域、过曝区域和曝光合适区域以及三个区域对应采用的曝光的光强。将三类带有相应曝光标签的样本集输入到卷积神经网络中进行训练，最终得到所需的预设卷积神经网络模型。
在一实施例中，可以采用预设卷积神经网络模型确定两个区域中所需的光剂量，具体地，由于预设卷积神经网络模型是采用三类样本集进行训练得到的，因此，将包含过曝区域和曝光不足区域的荧光图像输入预设卷积神经网络模型中，在模型对图像的分析过程中，会首先判断是否需要再次曝光，当需要再次曝光会增加荧光图像上曝光不足区域对应的光剂量，减少荧光图像上过曝区域对应的光剂量，具体可以对于灰度值高于中值(128)的区域减少再次曝光时的光 照功率，对于灰度值低于中值的区域增强再次曝光时的光照功率，得到荧光图像各点所需的光剂量。
步骤S104：根据荧光图像各点所需的激发光剂量生成治疗光强进行治疗。具体地，在确定荧光图像各点所需的激发光剂量之后，可以通过对数据整合生成灰度图，导入到调制装置如空间光调制器中作为输入参数，最后通过空间光调制器对光照参数进行调制，从而控制治疗光强的分布，满足病灶各区域所需的光强要求，达到成像引导精准调控光治疗的目的。
本发明实施例提供的基于光动力治疗系统的治疗方法，通过获取光束照射在光敏剂上生成的荧光图像，由荧光图像处理算法以及预设卷积神经网络模块确定光敏剂各区域所需的较为准确的光剂量，采用该光剂量照射光敏剂再次曝光，可以基本达到所需要求，即使有部分光敏剂需要再次照射，可以将再次采集的荧光图像通过微处理器确定所需的光剂量再次调制光源输出光束，从而达到病灶各区域所需的光强要求。由此，本发明实施例提供的基于光动力治疗系统的治疗方法，最多仅需三次短时曝光即可获得最优的成像质量，实现了用最少的曝光次数来实现最优成像。
本发明实施例提供的基于光动力治疗系统的治疗方法，预先训练了卷积神经网络模型，在确定荧光图像各点所需的光剂量时，可以将标记了过曝区域和曝光不足区域的荧光图像输入到预设卷积神经网络模型中，通过该预设卷积神经网络模型的输出即可确定荧光图像各点所需的光剂量。相比现有技术中直接采用负反馈算法不断根据每次曝光的荧光图像改变光源输出光强，需要多次曝光的方式，该基于光动力治疗系统的治疗方法采用预设卷积神经网络模型精准确定荧光图像各点所需的光剂量的方式可以大幅减少曝光次数，实现了用最少的曝光次数来实现最优成像。减少光敏剂因曝光次数过多引起的荧光漂白。
本发明实施例提供的基于光动力治疗系统的治疗方法的功能描述详细参见 上述实施例中光动力治疗系统的描述。
本发明实施例还提供一种存储介质，如图3所示，其上存储有计算机程序601，该指令被处理器执行时实现上述实施例中基于光动力治疗系统的治疗方法的步骤。该存储介质上还存储有音视频流数据，特征帧数据、交互请求信令、加密数据以及预设数据大小等。其中，存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)、随机存储记忆体(Random Access Memory，RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive，缩写：HDD)或固态硬盘(Solid-State Drive，SSD)等；所述存储介质还可以包括上述种类的存储器的组合。
本领域技术人员可以理解，实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)、随机存储记忆体(Random Access Memory，RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive，缩写：HDD)或固态硬盘(Solid-State Drive，SSD)等；所述存储介质还可以包括上述种类的存储器的组合。
本发明实施例还提供了一种电子设备，如图4所示，该电子设备可以包括处理器51和存储器52，其中处理器51和存储器52可以通过总线或者其他方式连接，图4中以通过总线连接为例。
处理器51可以为中央处理器(Central Processing Unit，CPU)。处理器51还可以为其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等芯片，或者上述各类 芯片的组合。
存储器52作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块，如本发明实施例中的对应的程序指令/模块。处理器51通过运行存储在存储器52中的非暂态软件程序、指令以及模块，从而执行处理器的各种功能应用以及数据处理，即实现上述方法实施例中的基于光动力治疗系统的治疗方法。
存储器52可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储处理器51所创建的数据等。此外，存储器52可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器52可选包括相对于处理器51远程设置的存储器，这些远程存储器可以通过网络连接至处理器51。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器52中，当被所述处理器51执行时，执行如图2所示实施例中的基于光动力治疗系统的治疗方法。
上述电子设备具体细节可以对应参阅图2所示的实施例中对应的相关描述和效果进行理解，此处不再赘述。
虽然结合附图描述了本发明的实施例，但是本领域技术人员可以在不脱离本发明的精神和范围的情况下做出各种修改和变型，这样的修改和变型均落入由所附权利要求所限定的范围之内。

Claims (10)

  1. 一种基于光动力治疗系统的治疗方法，其特征在于，包括：
    获取待治疗组织上光敏剂被照射时生成的荧光图像；
    根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；
    根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量；
    根据荧光图像各点所需的激发光剂量生成治疗光强进行治疗。
  2. 根据权利要求1所述的基于光动力治疗系统的治疗方法，其特征在于，根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域，包括：
    根据二维纹理映射算法对所述荧光图像进行处理，实现所述荧光图像上各点进行数字重构；
    根据自适应负反馈算法和伪彩色重建算法对所述处理后的荧光图像进行计算，确定过曝区域和曝光不足区域。
  3. 根据权利要求1所述的基于光动力治疗系统的治疗方法，其特征在于，根据预设卷积神经网络模型对荧光图像过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量，包括：
    根据预设卷积神经网络模型增加荧光图像上曝光不足区域对应的激发光剂量，减少荧光图像上过曝区域对应的激发光剂量，得到荧光图像各点所需的激发光剂量。
  4. 一种光动力治疗系统，其特征在于，包括：光源、采集装置、调制装置及微处理器，
    所述光源照射在待治疗组织的光敏剂上生成荧光图像；
    所述采集装置采集所述荧光图像输入至所述微处理器；
    所述微处理器包括计算模块和分析模块，
    所述计算模块用于根据荧光图像处理算法对所述荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域；
    所述分析模块用于根据预设卷积神经网络模型对荧光图像的过曝区域和曝光不足区域进行分析，确定荧光图像各点所需的激发光剂量；
    所述调制装置根据所述荧光图像各点所需的激发光剂量对光源输出光束进行调制生成治疗光强进行治疗。
  5. 根据权利要求4所述的光动力治疗系统，其特征在于，所述计算模块包括：
    图像处理模块，用于根据二维纹理映射算法对所述荧光图像进行处理，实现所述荧光图像上各点进行数字重构；
    曝光确定模块，用于根据自适应负反馈算法和伪彩色重建算法对所述处理后的荧光图像进行计算，确定荧光图像的过曝区域和曝光不足区域。
  6. 根据权利要求4所述的光动力治疗系统，其特征在于，所述分析模块包括：
    参数调整模块，用于根据预设卷积神经网络模型增加荧光图像上曝光不足区域对应的激发光剂量，减少荧光图像上过曝区域对应的激发光剂量，得到荧 光图像各点所需的激发光剂量。
  7. 根据权利要求4所述的光动力治疗系统，其特征在于，所述调制装置包括空间光调制器。
  8. 根据权利要求4所述的光动力治疗系统，其特征在于，还包括：内窥镜单元，所述内窥镜单元用于获取待治疗组织的成像信息。
  9. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使所述计算机执行如权利要求1-3任一项所述的基于光动力治疗系统的治疗方法。
  10. 一种电子设备，其特征在于，包括：存储器和处理器，所述存储器和所述处理器之间互相通信连接，所述存储器存储有计算机指令，所述处理器通过执行所述计算机指令，从而执行如权利要求1-4任一项所述的基于光动力治疗系统的治疗方法。
PCT/CN2020/112029 2020-08-28 2020-08-28 一种基于光动力治疗系统的治疗方法及光动力治疗系统 WO2022041102A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/112029 WO2022041102A1 (zh) 2020-08-28 2020-08-28 一种基于光动力治疗系统的治疗方法及光动力治疗系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/112029 WO2022041102A1 (zh) 2020-08-28 2020-08-28 一种基于光动力治疗系统的治疗方法及光动力治疗系统

Publications (1)

Publication Number Publication Date
WO2022041102A1 true WO2022041102A1 (zh) 2022-03-03

Family

ID=80352445

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/112029 WO2022041102A1 (zh) 2020-08-28 2020-08-28 一种基于光动力治疗系统的治疗方法及光动力治疗系统

Country Status (1)

Country Link
WO (1) WO2022041102A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115999069A (zh) * 2022-12-08 2023-04-25 北京师范大学珠海校区 经颅光刺激的参数确定方法、装置、设备及存储介质
WO2024062118A1 (en) * 2022-09-23 2024-03-28 Jerker Widengren Method and apparatus for monitoring of photodynamic-therapy precursor states for enhanced therapeutic efficiency

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030153825A1 (en) * 2002-02-12 2003-08-14 Science & Engineering Associates, Inc. Cancer detection and adaptive dose optimization treatment system
JP2012115406A (ja) * 2010-11-30 2012-06-21 Fujifilm Corp 内視鏡装置
CN102791329A (zh) * 2010-03-15 2012-11-21 索尼公司 评价装置和评价方法
WO2016151888A1 (ja) * 2015-03-26 2016-09-29 オリンパス株式会社 画像処理装置
US20170224205A1 (en) * 2016-02-04 2017-08-10 Wright State University Light endoscope system for imaging, light delivery, and therapy response monitoring
CN108956564A (zh) * 2018-06-21 2018-12-07 深圳市优迈医学科技有限公司 光敏剂浓度检测装置、系统以及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030153825A1 (en) * 2002-02-12 2003-08-14 Science & Engineering Associates, Inc. Cancer detection and adaptive dose optimization treatment system
CN102791329A (zh) * 2010-03-15 2012-11-21 索尼公司 评价装置和评价方法
JP2012115406A (ja) * 2010-11-30 2012-06-21 Fujifilm Corp 内視鏡装置
WO2016151888A1 (ja) * 2015-03-26 2016-09-29 オリンパス株式会社 画像処理装置
US20170224205A1 (en) * 2016-02-04 2017-08-10 Wright State University Light endoscope system for imaging, light delivery, and therapy response monitoring
CN108956564A (zh) * 2018-06-21 2018-12-07 深圳市优迈医学科技有限公司 光敏剂浓度检测装置、系统以及方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024062118A1 (en) * 2022-09-23 2024-03-28 Jerker Widengren Method and apparatus for monitoring of photodynamic-therapy precursor states for enhanced therapeutic efficiency
CN115999069A (zh) * 2022-12-08 2023-04-25 北京师范大学珠海校区 经颅光刺激的参数确定方法、装置、设备及存储介质
CN115999069B (zh) * 2022-12-08 2024-01-05 北京师范大学珠海校区 经颅光刺激的参数确定装置和设备

Similar Documents

Publication Publication Date Title
WO2022041102A1 (zh) 一种基于光动力治疗系统的治疗方法及光动力治疗系统
CN111991704B (zh) 一种基于光动力治疗系统的操作方法及光动力治疗系统
CN107205845A (zh) 用于眼的交联治疗的系统和方法
EP1166723A3 (en) Laser treatment apparatus
CN1433287A (zh) 用于视力矫正的光学反馈系统
KR101950362B1 (ko) 3차원 스캐닝 기술 및 피드백을 이용한 광 감응성 피부질환 자외선 표적 광선 치료 장치 및 방법
WO2018132563A1 (en) Systems and methods for determining cross-linking distribution in a cornea and/or structural characteristics of a cornea
JP2023528678A (ja) パーソナルケアデバイスのための皮膚接触を判定するためのシステム及び方法
JP2009279169A5 (zh)
Alexander et al. Color Cherenkov imaging of clinical radiation therapy
CN110681070B (zh) 一种可个性化调控的光动力治疗光源及调控方法
JP2596221B2 (ja) 医療用レーザ装置および診断・治療装置
US11612518B2 (en) Process for dosing a chromophoric agent in a corneal tissue and apparatus for controlling the dosing
JP2011104103A (ja) エネルギサブトラクション画像撮影装置
JP2024063237A (ja) 眼の治療中の眼球追跡のためのシステム及び方法
KR101984849B1 (ko) 다중-노출 레이저 스펙클 영상 수집 장치 및 이의 보정 방법
KR102351785B1 (ko) 조직의 기능적 영상 획득 장치 및 이의 생성 방법
US20090042238A1 (en) Method of evaluating cell function, system for evaluating cell function, fluorescent microscope system, phototherapy method and phototherapy system
CN106963341A (zh) 一种近红外荧光‑x射线双模小动物成像设备
CN207477489U (zh) 一种近红外荧光-x射线双模小动物成像设备
EP4410363A1 (en) Patterned optical simulation device and method
JP2603390B2 (ja) 細胞情報解析装置
TWI775229B (zh) 美膚檢測系統及其方法
CN113821970B (zh) 一种epid灰度-注量标定方法、介质和设备
Bongartz et al. Living human face measurements using pulsed holography

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20950772

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06/06/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20950772

Country of ref document: EP

Kind code of ref document: A1