57 results about "Breast lesion" patented technology

The invention discloses a breast cancer immunohistochemical index and typing prediction method and system. The prediction method comprises the following steps: acquiring a breast ultrasound image and a breast magnetic resonance image of a patient; performing preprocessing and quality control on the mammary gland ultrasonic image and the mammary gland magnetic resonance image; performing breast lesion area segmentation by adopting a deep learning model to obtain segmented lesion areas; based on the segmented lesion area, extracting multi-modal radiomics characteristics of the breast ultrasonic image and the breast magnetic resonance image; fusing the multi-modal radiomics characteristics of the breast ultrasound image and the breast magnetic resonance image, constructing a machine learning model, and performing immunohistochemical index prediction to obtain an immunohistochemical index prediction result; and performing breast cancer molecular typing analysis according to the immunohistochemical index prediction result. By fusing the multi-modal image information, the tumor features can be described more comprehensively, and the accuracy of biomarker prediction is improved.

The invention provides a mammary gland pathological cell image detection method and system based on an improved YOLOv7 model, and the method comprises the steps: S1, collecting mammary gland pathological section images, and generating a data set; s2, carrying out frame labeling on cells obtained in the data set; s3, segmenting the marked data set into a training set and a verification set; step S4, establishing a YOLOv7 network, and respectively adding an ASFF module and a CBAM module in three branches of the YOLOv7 network to obtain an improved YOLOv7 network; and S5, inputting the training set into the improved YOLOv7 network for training, and verifying to obtain the high-precision breast pathological section cell detection model. The improved model can effectively avoid a large semantic gap between non-adjacent levels of mammary gland cell characteristics, greatly enhance the detection capability of multi-scale cell targets such as tiny early cancer cells and large normal mammary gland tissue cells, and improve the recognition precision of early mammary gland lesion cells.

The invention discloses an ultrasonic image and deep learning combined breast lesion automatic identification method, and relates to the technical field of breast lesion identification, and the method comprises the following steps: obtaining an original two-dimensional ultrasonic image of a breast part; inputting the preprocessed ultrasonic image into a feature extraction neural network with a multi-scale attention mechanism; inputting the preprocessed image into a super-resolution reconstruction network for image detail enhancement to generate a super-resolution enhanced image; sample expansion is carried out on the training data based on a generative adversarial network containing a category label condition, and the generative adversarial network is used for generating a composite image corresponding to the lesion category, namely a condition generation image; and inputting the joint features into a subsequent classification sub-network to realize category discrimination and refined classification of the breast lesion, and outputting a breast lesion category prediction result. Training the classification sub-network by adopting a joint loss function; according to the method, the fine-grained classification problem in automatic breast lesion recognition is solved.

The invention provides a tumor real-time tracking and benign and malignant detection method based on a mammary gland ultrasonic video, and the method comprises the steps: collecting the mammary gland ultrasonic video in real time, and inputting the mammary gland ultrasonic video into an UltraNet basic detector to generate a detection result of each frame of ultrasonic image; calculating a similarity probability matrix Si, j to reflect the similarity between the ith target and the jth target; performing cascade matching on the target based on the similarity probability matrix Si, j to form a target track pipeline Ti; and carrying out confidence coefficient updating and bounding box position updating on the detection result in each target track pipeline Ti, and finally outputting a breast lesion detection result of each frame of ultrasonic image. The tumor real-time tracking and benign and malignant detection method based on the breast ultrasonic video has the advantages of high calculation efficiency, high precision and strong robustness, can assist a doctor in accurately positioning a focus and performing diagnosis, and is beneficial to early discovery of breast diseases.

The invention relates to a breast tumor lesion part ultrasonic image segmentation method based on an SAM-VMama model. The method comprises the steps of obtaining a breast ultrasonic image set and performing preprocessing; the method comprises the following steps: constructing an SAM-VMama model, wherein the SAM-VMama model comprises a first encoder, a second encoder, a prompt encoder and a mask decoder; obtaining a trained model; obtaining a preprocessed breast ultrasound image to be segmented; and obtaining a segmentation result of the breast lesion tumor. According to the method, the local features are extracted through the first extraction, the global features are extracted through the second encoder, the interactive prompt information processed by the prompt encoder is combined, and the precise segmentation mask is generated through the mask decoder; the method not only retains the flexibility of SAM interactive segmentation, but also improves the long-sequence data processing capability and calculation efficiency through a Mamba structure, effectively adapts to the characteristics of uneven gray scale, multiple artifacts and the like of the ultrasonic image, and achieves the balance of high precision and high efficiency.

The invention is applied to the technical field of medical image segmentation, and discloses a dual-encoder breast cancer medical image segmentation method based on spatial entropy enhancement, and the method takes a U-Net network of a dual-encoder structure as a trunk frame, and fuses the spatial entropy feature of an ultrasonic image and the feature of an original image, so as to improve the segmentation precision of a breast focus area. According to the double-encoder breast cancer medical image segmentation method based on spatial entropy enhancement, the edge feature expression capability is enhanced, and the statistical characteristics and uncertainty of boundary fuzzy regions such as lesion edges in an ultrasonic image are effectively captured and emphasized by calculating and utilizing entropy information of a local region of the image; therefore, the recognition and expression ability of the model to the focus boundary is improved, a dual-path network structure is constructed, depth texture features and entropy-based statistical features are extracted respectively, effective complementation and integration among different dimension features are realized through a designed information fusion module, and the limitation of insufficient single-mode feature extraction is overcome.

The invention discloses a focus intelligent detection and diagnosis system based on multi-modal medical image fusion, and relates to the technical field of medical image processing. A molybdenum target image, an ultrasonic image and a magnetic resonance image of the mammary gland of the patient are acquired through the data acquisition module; a data registration module is used for carrying out partition affine and local refinement registration on the multi-modal image by taking the molybdenum target image as a geometric anchor point and combining parameters such as compression force; extracting registered fusion feature data through a data fusion module; generating a candidate focus set by a focus detection module; finally, the risk assessment module calculates a comprehensive risk score through weighting, correction and consistency verification processes based on a plurality of interpretable feature indexes. And the output module generates a visual diagnosis result. According to the invention, intelligent detection and risk assessment of rechecking of breast lesions are realized, and the diagnosis accuracy and clinical reliability are effectively improved.

The invention belongs to the technical field of focus progress trend prediction, and provides a mammary gland focus progress trend prediction method based on multimode data fusion, and the method comprises the steps: analyzing the local correlation degree between each index and a clinical progress state label and the change acceleration degree of each index in a time window; obtaining the sensitivity degree of each index of each patient in each time window; analyzing the individual physique difference degree of each index according to the sensitivity degree, further analyzing the stage difference degree of each index in each time window, and determining the fluctuation degree of each index of each patient in each time window; based on the sensitivity degree and the fluctuation degree, the fusion weight of each index of each patient in each time window is obtained, fusion of multiple indexes is carried out, and breast focus progress trend prediction is achieved. The method can overcome the defect that a fixed weight index fusion method is insufficient in adaptability in the mammary gland lesion evolution process, and the prediction accuracy of the mammary gland lesion progress trend is improved.

The present invention provides a method and apparatus for segmenting breast ultrasound images. The method comprises: obtaining an ultrasound image of a subject's breast region, the ultrasound image containing a breast lesion; identifying the type of BI-RADS feature of the breast lesion based on the ultrasound image, the BI-RADS feature including at least one of shape feature, direction feature, edge feature, internal echo feature, rear echo feature, calcification feature, and blood flow feature; determining a target segmentation model corresponding to the type of BI-RADS feature from a plurality of segmentation models corresponding to each type of preset BI-RADS feature; and performing breast lesion segmentation on the ultrasound image using the target segmentation model to segment the breast lesion region from the ultrasound image. The characteristics of the breast lesion are fully considered during segmentation, and the accuracy of breast lesion region segmentation is improved by using the target segmentation model corresponding to the type of BI-RADS feature to segment the ultrasound image.

The present application relates to a kind of breast lesion three-dimensional reconstruction methods, comprising the following steps: step S1, breast region self-rough scanning is carried out, and the depth image of breast region is acquired, and the three-dimensional model of breast and spatial position are determined;Step S2, fine scanning is carried out to lesion, and AI algorithm is used to realize the segmentation extraction of lesion feature in ultrasonic image;Step S3, with time, ultrasonic rotation angle or ultrasonic moving distance as interval, the image and position information of lesion feature during fine scanning are sequentially recorded;Step S4, the three-dimensional reconstruction of lesion is realized by three-dimensional reconstruction algorithm based on lesion boundary point cloud feature;Step S5, according to the recorded center position of lesion feature, the three-dimensional spatial position of lesion is calculated by weighted average method;Step S6, by breast center coordinates and lesion center coordinates, the relative position relationship of both based on mechanical arm coordinates is determined, and breast lesion three-dimensional reconstruction method is realized.The method can help doctor to determine the shape, size and its position in breast of lesion.

This invention provides a method for classifying benign and malignant breast lesions, comprising the following steps: Step 1, obtaining N sample pairs; Step 2, constructing a benign and malignant breast lesion classification model; Step 3, training the benign and malignant breast lesion classification model; Step 4, obtaining the benign and malignant breast lesion classification results. This invention can effectively improve the segmentation accuracy of breast lesions in radiological images, providing more accurate and reliable benign and malignant classification results, and has potential clinical application value.

The invention discloses a breast lesion image semi-supervised segmentation method. The method belongs to the technical field of medical image processing and semi-supervised learning. The technical problem of improving the feature extraction capability of a semi-supervised segmentation network in a complex breast lesion segmentation scene under a small number of labeled samples and realizing accurate segmentation of a breast lesion is solved. A dual-scale image of a mammary gland image is generated, so that the network can learn features of mammary gland lesions from different scales, the ability of the network to extract features of mammary gland lesions with large size and form differences is improved, data perturbation is performed on the dual-scale image, and a generator performs mutual generation on segmentation confidence maps of a source image and a perturbation image. And the network stability is improved. Through cascade inverse residual coding feature fusion and decoding feature fusion, more potential features are mined by using existing features, the segmentation performance of the network is improved under a small number of labeled samples, and accurate segmentation of a breast lesion can be realized by inputting a breast image into a final segmentation network.

The invention discloses a multi-degree-of-freedom precise puncture locator for breast lesions, and relates to the technical field of medical instruments, the multi-degree-of-freedom precise puncture locator comprises a locating piece, a lower control part and an upper control part, after a lower pressing plate is loosened, a middle spring, a lower spring and a lower pressure spring are reset, so that an abutting head abuts against the locating piece, a middle abutting column abuts against a folding rod, and the upper control part is connected with the upper control part; the effect of simultaneously controlling the position of the lower control part in the positioning piece and the height and torsion degree of the folding rod in the vertical cylinder is achieved; the control button is rotated to enable the inclined push block to move, when the inclined push block is far away from the inclined plane block, the push frame is separated from the side frame, the side frame is pulled by the front tension spring to be close to the sliding rod, the front abutting rod loses the force of abutting against the pointer shaft, when the inclined push block is close to the inclined plane block, the push frame pushes the side frame, the side frame and the sliding rod jointly abut against the folding rod, and the front abutting rod abuts against the pointer shaft. And the effect of simultaneously controlling the telescopic and circumferential rotation positions of the upper control part on the folding rod and the rotation angle of the positioning ring on the front frame is achieved.

The application discloses a breast lesion image semi-supervised segmentation method, and belongs to the technical field of medical image processing and semi-supervised learning. The technical problem of improving the feature extraction capability of a semi-supervised segmentation network in a complex breast lesion segmentation scene and realizing accurate segmentation of a breast lesion is solved. A double-scale image of a breast image is generated, so that the network can learn the features of the breast lesion from different scales, and the feature extraction capability of the network for the breast lesion with a large size and shape difference is improved. Meanwhile, data disturbance is performed on the double-scale image, the segmentation confidence maps of the source image and the disturbed image are generated by the generator, and the stability of the network is improved. Through cascading inverse residual coding feature fusion and decoding feature fusion, more potential features are mined from existing features, the segmentation performance of the network is improved under a small amount of labeled samples, and accurate segmentation of the breast lesion can be realized by inputting the breast image into the final segmentation network.

The invention discloses an automatic prompting lightweight ultrasound image breast lesion segmentation method and system, and the method comprises the steps: obtaining breast lesion ultrasound image data, and carrying out the data preprocessing, and obtaining a preprocessed breast lesion ultrasound image; an encoder module, an automatic prompt module and a decoder module are introduced, and an ultrasonic image mammary gland lesion segmentation model is constructed; and based on the ultrasonic image mammary gland lesion segmentation model, performing segmentation processing on the preprocessed mammary gland lesion ultrasonic image to obtain a mammary gland lesion ultrasonic image segmentation result. Complex structures and weak boundaries can be captured more finely in a breast ultrasound image segmentation task, and the segmentation precision is improved. The lightweight ultrasonic image breast lesion segmentation method and system with the automatic prompting function can be widely applied to the technical field of ultrasonic image segmentation.

The invention discloses a system for multispectral transmission image breast lesion segmentation, and belongs to the technical field of medical image processing and optical imaging. The system comprises an image preprocessing subsystem and a semi-supervised segmentation network subsystem. The preprocessing subsystem adopts modulation and demodulation, frame accumulation and a scattering correction technology based on spatial pyramid matching, so that the signal-to-noise ratio and the contrast ratio of an image are remarkably improved; the segmentation network subsystem proposes a multi-head consistency semi-supervised network model, integrates a multi-head decomposition module and a cross supervision module, and effectively utilizes unlabeled data to carry out uncertainty modeling and consistency constraint. Under the condition that only 20% of labeled data is used, the segmentation Dice coefficient on the self-built mammary gland phantom data set reaches 91.47% and is obviously superior to that of an existing method, and a complete solution from image enhancement to intelligent segmentation is provided for early diagnosis of the breast cancer.

The invention discloses a multifunctional radiofrequency ablation system for treating breast lesions, which comprises a radiofrequency host, an ablation electrode, a pumping device and a controller, the radiofrequency host is electrically connected with the controller, both the ablation electrode and the pumping device are electrically connected with the radiofrequency host, and the pumping device is communicated with the ablation electrode; the ablation electrode comprises a needle rod assembly and a handle assembly, a first channel is formed in the needle rod assembly, a second channel communicated with the first channel is formed in the handle assembly, and a quick-release connecting piece communicated with the second channel is arranged outside the handle assembly. The device integrates the five functions of radiofrequency ablation, cyst fluid suction, sampling biopsy, smoke exhaust and flushing, cyst fluid suction, sampling biopsy, flushing operation and inner cyst wall ablation in the normal saline environment are achieved through the ablation electrode, instruments do not need to be replaced repeatedly in the ablation process, smoke generated in the ablation process can be exhausted, and the ablation efficiency is improved. And the operation efficiency and the ablation accuracy are effectively improved.

The present invention provides a method for segmenting breast lesions from ultrasound videos that integrates spatiotemporal information, relating to the field of image processing technology. The method extracts temporal information from ultrasound video sequences in parallel through interval sampling, and adds the extracted temporal information sequence to the original sequence, using this as input information for spatial information extraction. During the spatial information extraction process, the temporal dimension and the channel dimension are merged to streamline the data structure, further reducing computational complexity through window grouping. Furthermore, through attention learning with a moving window, more comprehensive information learning and feature extraction can be performed. This method achieves effective extraction of spatiotemporal information, has better performance, and significantly reduces computational complexity, cost, and time, enabling end-to-end segmentation of ultrasound videos.

The application discloses a breast CEM image lesion recognition system and equipment based on deep learning, and relates to the field of medical image processing. By acquiring a low-energy image and a subtraction image of an original CEM image and performing pretreatment, lesions in a breast region of the image are labeled, and two ResNet50 networks are used to extract preliminary extraction features of the low-energy image and the subtraction image respectively. Double-mode auxiliary feature fusion is performed to obtain a multi-scale pyramid feature layer. A detection head with an attention mechanism is connected after each pyramid feature layer to finally position and classify breast lesions. The application realizes rapid detection, positioning and classification of breast lesions based on a multi-modal CEM image based on a deep learning method, and improves breast lesion recognition efficiency and precision.

The invention discloses an eight-electrode human body impedance spectroscopy measuring device which is used for simply screening human body diseases in the early stage. Aiming at the problems of invasiveness, huge size, complicated operation and the like of the existing breast cancer detection equipment, the device provides a wearable non-invasive detection scheme. The system mainly comprises a main control chip STM32F103ZET6, an impedance measurement chip AD5933, an analog switch chip ADG5409 and eight disposable silver chloride measurement electrodes. The main control chip is communicated with the AD5933 through a pin simulation IIC, a DDS generator in the main control chip is configured to output sine excitation signals of 1 kHz to 100 kHz, and impedance real part and imaginary part data after internal DSP Fourier transformation are read; meanwhile, the main control chip controls the ADG5409 to divide the eight electrodes into four pairs, and multi-channel switching measurement is carried out. Measurement data is transmitted to an upper computer through a UART1 serial port so as to draw a single-channel or four-channel impedance spectrum. The human health condition is judged through the impedance spectrum change trend, the whole system is small in size, easy to carry about and high in measurement precision, and early discovery and high-frequency prevention screening of breast lesions are facilitated.

The invention discloses a breast lesion segmentation method and device for contrast-enhanced ultrasound contrast images, and the method achieves the feature interaction through constructing a double-branch coding-single-branch decoding network and introducing a cross-modal multi-branch deep convolution module, effectively inhibits the background false positive through combining with a channel energy scoring mechanism and a gland priori weighting mechanism, and achieves the segmentation of the breast lesion of the contrast-enhanced ultrasound contrast images. And the focusing capability and the cross-equipment generalization capability of the model to the gland region are improved. The method has the advantages of compact model and high calculation efficiency while ensuring high segmentation precision, and is suitable for clinical real-time diagnosis scenes.

This invention discloses a method for detecting breast lesions in breast ultrasound video by incorporating spatiotemporal contextual information. Addressing the shortcomings of existing methods such as insufficient spatial representation, weak temporal correlation modeling, and high computational cost, this invention constructs a detection network comprising a backbone network, a single-frame cross-scale feature fusion module, a detection head, a cross-batch feature aggregation module, and a multi-frame temporal feature fusion module. The video is divided into consecutive multi-frame temporal segments, and shallow and deep features are enhanced through frequency-domain aware cross-scale fusion to improve spatial representation. A candidate feature memory stores high-quality candidate features, and cross-batch feature aggregation absorbs historical temporal information with low computational overhead. The multi-frame temporal feature fusion module then adaptively weights classification and regression features to highlight key temporal clues. This invention effectively improves the accuracy of breast ultrasound video lesion detection and grading without significantly increasing computational cost, and possesses good real-time performance and clinical application value.

The application discloses a method and device for autonomous scanning of breast lesions by an ultrasonic robot. The method comprises: controlling a probe to scan a breast according to a preset scanning track, and acquiring an ultrasonic image in real time during the scanning; detecting a breast lesion based on the current ultrasonic image; if the breast lesion is detected, fitting the detected breast lesion contour to obtain a current lesion contour; if the area of the current lesion contour is not less than a preset area threshold, determining whether the current lesion contour already exists in a historical scanning record; if not, adjusting the current lesion contour to the center of the ultrasonic image by controlling the probe to move; determining the included angle between the breast curved surface and the probe according to the preset scanning track and the current position of the probe; and controlling the probe to perform lesion fine scanning on the current lesion contour according to the calculated included angle between the breast curved surface and the probe and a preset search range.

This invention provides a guide frame, method of use, and testing method for breast lesion biopsy, belonging to the field of medical auxiliary device technology. It includes a breast positioning support component and a movable guide component. The breast positioning support component is placed on the scanning bed and has a scale plate with grid markings for stable support of the breast and quantification of lesion coordinates and height. The movable guide component is slidably disposed on the side of the scanning bed and includes a lifting adjustment mechanism, an angle adjustment guide frame, and a puncture guide with guide grooves, enabling multi-degree-of-freedom precise adjustment and locking of the puncture path. This invention is made of magnetically compatible materials, eliminating artifact interference; it achieves millimeter-level precise positioning through three-dimensional quantification of coordinates, height, and angle; it can be used in conjunction with a physical breast model for preoperative simulation, significantly improving the success rate and safety of puncture. The structure is simple and the cost is low, making it suitable for large-scale clinical application.

The present invention falls within the field of medical imaging, specifically imaging aimed at identifying breast lesions, specifically, identifying potential breast cancer lesion masses or potential cancer lesion calcifications of the breast. The object of the present invention is a computational method for the improved identification of breast lesions that involves obtaining digital images of a breast section, with at least two digital images obtained by different imaging technologies, their segmentation and consequent correlations, to identify one or more cancer lesions. This allows for improved automation of the identification of breast lesions.

The invention discloses a mammary gland calcification focus dye positioning method and a dye positioning needle, and relates to the technical field of medical instruments.The dye positioning needle is used for being installed on a three-dimensional positioning arm of a molybdenum target host and comprises a needle cylinder, dye is contained in the needle cylinder, one end of the needle cylinder is provided with a liquid outlet end, and a piston is further arranged in the needle cylinder in a sliding mode; the piston is configured to drive the dye to be discharged from the liquid outlet end during sliding; the needle head comprises a base part and a needle tube, the base part is detachably mounted at the liquid outlet end of the needle cylinder, and the needle tube is used for guiding the dye discharged from the liquid outlet end to be injected into the breast so as to mark and position boundary dyeing of a breast focus. The dye positioning needle injects dye into the four boundaries of the innermost side, the outermost side, the uppermost end and the lowermost end of the mammary gland calcification focus under the guidance of the molybdenum target machine positioning system, and dye marking positioning is achieved. And meanwhile, dye mark positioning of the four boundaries is combined with center point positioning of the metal guide wire, so that crossed three-dimensional boundary positioning can be realized.

The application discloses a breast lesion segmentation method and device based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which comprises the following steps: after pre-processing the DCE-MRI image, the breast region is segmented first, and then the breast cancer lesion region is segmented based on the segmented breast region; when the breast cancer lesion region is segmented, a U-shaped network comprising two encoders and a decoder is adopted, the pre-processed contrast-enhanced late-phase image, the pre-processed contrast-enhanced early-phase image and the pre-processed breast prediction image are spliced respectively and input into an encoder for breast cancer lesion region segmentation to obtain a breast cancer prediction image, and an attention module is adopted between the two encoders to comprehensively process the contrast multi-period information. Compared with the prior art, the application can alleviate the class imbalance problem and exclude the interference of the regions outside the breast, and has high segmentation precision for the segmentation of the breast cancer lesion.

The invention discloses a breast focus recognition and positioning method, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the breast focus image recognition and detection of a target patient through a molybdenum target technology, carrying out the statistics of the position features of a main detection focus with fuzzy boundary, and if the target patient is detected as a fat-type breast tissue dominant region, carrying out the recognition and positioning of a breast focus. If not, marking the distribution position of the fat-type mammary gland tissue as a central position to obtain the central position characteristics of the auxiliary measurement tissue, marking the main measurement focus position characteristics and the central position characteristics of the auxiliary measurement tissue to obtain a plurality of marked lines, and setting the included angles formed among the marked lines to be the same, and according to the distance value of the marked line and the angle value formed between the main measurement focus position feature and the nipple, the position inclination degree of breast focus recognition continuous examination on the target patient is preset, breast focus continuous examination is carried out on the target patient through the high-frequency sound wave imaging technology, and a focus proofreading and positioning result is obtained. The focus identification and positioning accuracy can be improved.

The invention discloses an ABUS-based nodule elastography detection method, device and equipment and a medium, and the method comprises the following steps: controlling a probe in an ABUS to carry out flat scanning along the surface of a mammary gland, obtaining a cross section two-dimensional ultrasonic image, and generating a coronal plane image; detecting and identifying the position of a focus in the coronal plane image, and tracing a cross section image sequence containing the focus; detecting and segmenting the focus, and determining the specific position of the focus in the sequence; a probe in the ABUS is controlled to move to the section position corresponding to the maximum section of the focus, the probe in the ABUS is controlled to apply pressure to the surface of the tissue, so that the tissue deforms, the displacement change of the tissue under the pressure effect is recorded, and a strain elasticity image is generated; and evaluating the relative hardness of the lesion area according to the strain elasticity image. The method has the advantages that the ABUS is used for achieving elastography of breast nodules, the relative hardness of a focus area is evaluated, the method can be used for breast lesion screening, positioning and tracking return visit, and the performance and application of ABUS equipment are expanded.

The invention discloses a multi-mode mammary gland spectral imaging and morphological imaging method. The method comprises the following steps: respectively scanning mammary glands on two sides by using ultrasonic waves, and determining the lesion position and area of the mammary glands on the affected side; the method comprises the following steps of: sequentially transmitting three incident lights with different wavelengths and the same incident intensity to the mammary glands on the two sides according to a time sequence, and respectively acquiring transmission intensity two-dimensional release data of each single-wavelength incident light after the single-wavelength incident light penetrates through the mammary glands on the two sides by using a CCD (Charge Coupled Device); calculating an oxyhemoglobin saturation variable quantity delta Oxy and a hemoglobin concentration variable quantity delta ODBV between the bilateral breast tissues corresponding to each pixel, and generating a two-dimensional functional diagram of the oxyhemoglobin saturation variable quantity and a two-dimensional functional diagram of the hemoglobin concentration variable quantity by using a computer; the incident light with the three wavelengths is used for transmitting the mammary gland on the affected side at the same time, and a transmission original image obtained after the incident light penetrates through the mammary gland is collected; and inputting the transmission original image into an equal-gray-scale curve processing device, a blood vessel manifestation processing device and an edge sharpening processing device to obtain an equal-gray-scale curve graph, a blood vessel manifestation graph and an edge sharpening graph.