Deep learning-based automatic segmentation of images in cardiac radiography: A promising challenge

Automatic 3D left atrial strain extraction framework on cardiac computed tomography

BACKGROUND AND OBJECTIVE

Strain analysis provides insights into myocardial function and cardiac condition evaluation. However, the anatomical characteristics of left atrium (LA) inherently limit LA strain analysis when using echocardiography. Cardiac computed tomography (CT) with its superior spatial resolution, has become critical for in-depth evaluation of LA function. Recent studies have explored the feasibility of CT-derived strain; however, they relied on manually selected regions of interest (ROIs) and mainly focused on left ventricle (LV). This study aimed to propose a first-of-its-kind fully automatic deep learning (DL)-based framework for three-dimensional (3D) LA strain extraction on cardiac CT.

METHODS

A total of 111 patients undergoing ECG-gated contrast-enhanced CT for evaluating subclinical atrial fibrillation (AF) were enrolled in this study. We developed a 3D strain extraction framework on cardiac CT images, containing a 2.5D GN-U-Net network for LA segmentation, axis-oriented 3D view extraction, and LA strain measure. The segmentation accuracy was evaluated using Dice similarity coefficient (DSC). The model-extracted LA volumes and emptying fraction (EF) were compared with ground-truth measurements using intraclass correlation coefficient (ICC), correlation coefficient (r), and Bland-Altman plot (B-A). The automatically extracted LA strains were evaluated against the LA strains measured from 2D echocardiograms. We utilized this framework to gauge the effect of AF burden on LA strain, employing the atrial high rate episode (AHRE) burden as the measurement parameter.

RESULTS

The GN-U-Net LA segmentation network achieved a DSC score of 0.9603 on the test set. The framework-extracted LA estimates demonstrated excellent ICCs of 0.949 (95 % CI: 0.93-0.97) for minimal LA volume, 0.904 (95 % CI: 0.86-0.93) for maximal LA volume, and 0.902 (95 % CI: 0.86-0.93) for EF, compared with expert measurements. The framework-extracted LA strains demonstrated moderate agreement with the LA strains based on 2D echocardiography (ICCs >0.703). Patients with AHRE > 6 min had significantly lower global strain and LAEF, as extracted by the framework than those with AHRE ≤ 6 min.

CONCLUSION

The promising results highlighted the feasibility and clinical usefulness of automatically extracting 3D LA strain from CT images using a DL-based framework. This tool could provide a 3D-based alternative to echocardiography for assessing LA function.

Fully automatic system to detect and segment the proximal femur in pelvic radiographic images for Legg-Calvé-Perthes disease

This study aimed to develop a method using computer vision techniques to accurately detect and delineate the proximal femur in radiographs of Legg-Calvé-Perthes disease (LCPD) patients. Currently, evaluating femoral head deformity, a crucial predictor of LCPD outcomes, relies on unreliable categorical and qualitative classifications. To address this limitation, we employed the pretrained object detection model YOLOv5 to detect the proximal femur on over 2000 radiographs, including images of shoulders and chests, to enhance robustness and generalizability. Subsequently, we utilized the U-Net convolutional neural network architecture for image segmentation of the proximal femur in more than 800 manually annotated images of stage IV LCPD. The results demonstrate outstanding performance, with the object detection model achieving high accuracy (mean average precision of 0.99) and the segmentation model attaining an accuracy score of 91%, dice coefficient of 0.75, and binary IoU score of 0.85 on the held-out test set. The proposed fully automatic proximal femur detection and segmentation system offers a promising approach to accurately detect and delineate the proximal femoral bone contour in radiographic images, which is essential for further image analysis in LCPD patients. Clinical significance: This study highlights the potential of computer vision techniques for enhancing the reliability of Legg-Calvé-Perthes disease staging and outcome prediction.

Automatization of CT Annotation: Combining AI Efficiency with Expert Precision

The integration of artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) algorithms, marks a transformative progression in medical imaging diagnostics. This technical note elucidates a novel methodology for semantic segmentation of the vertebral column in CT scans, exemplified by a dataset of 250 patients from Riga East Clinical University Hospital. Our approach centers on the accurate identification and labeling of individual vertebrae, ranging from C1 to the sacrum-coccyx complex. Patient selection was meticulously conducted, ensuring demographic balance in age and sex, and excluding scans with significant vertebral abnormalities to reduce confounding variables. This strategic selection bolstered the representativeness of our sample, thereby enhancing the external validity of our findings. Our workflow streamlined the segmentation process by eliminating the need for volume stitching, aligning seamlessly with the methodology we present. By leveraging AI, we have introduced a semi-automated annotation system that enables initial data labeling even by individuals without medical expertise. This phase is complemented by thorough manual validation against established anatomical standards, significantly reducing the time traditionally required for segmentation. This dual approach not only conserves resources but also expedites project timelines. While this method significantly advances radiological data annotation, it is not devoid of challenges, such as the necessity for manual validation by anatomically skilled personnel and reliance on specialized GPU hardware. Nonetheless, our methodology represents a substantial leap forward in medical data semantic segmentation, highlighting the potential of AI-driven approaches to revolutionize clinical and research practices in radiology.

A novel collaborative learning model for mixed dentition and fillings segmentation in panoramic radiographs

INTRODUCTION

It is critical for dentists to identify and differentiate primary and permanent teeth, fillings, dental restorations and areas with pathological findings when reviewing dental radiographs to ensure that an accurate diagnosis is made and the optimal treatment can be planned. Unfortunately, dental radiographs are sometimes read incorrectly due to human error or low-quality images. While secondary or group review can help catch errors, many dentists work in practice alone and/or do not have time to review all of their patients' radiographs with another dentist. Artificial intelligence may facilitate the accurate interpretation of radiographs. To help support the review of panoramic radiographs, we developed a novel collaborative learning model that simultaneously identifies and differentiates primary and permanent teeth and detects fillings.

METHODS

We used publicly accessible dental panoramic radiographic images and images obtained from the University of Missouri-Kansas City, School of Dentistry to develop and optimize two high-performance classifiers: (1) a system for tooth segmentation that can differentiate primary and permanent teeth and (2) a system to detect dental fillings.

RESULTS

By utilizing these high-performance classifiers, we created models that can identify primary and permanent teeth (mean average precision [mAP] 95.32 % and performance [F-1] 92.50 %), as well as their associated dental fillings (mAP 91.53 % and F-1 91.00 %). We also designed a novel method for collaborative learning that utilizes these two classifiers to enhance recognition performance (mAP 94.09 % and F-1 93.41 %).

CONCLUSIONS

Our model improves upon the existing machine learning models to simultaneously identify and differentiate primary and permanent teeth, and to identify any associated fillings.

CLINICAL SIGNIFICANCE

Human error can lead to incorrect readings of panoramic radiographs. By developing artificial intelligence and machine learning methods to analyze panoramic radiographs, dentists can use this information to support their radiograph interpretations, help communicate the information to patients, and assist dental students learning to read radiographs.

Autonomous detection of myocarditis based on the fusion of improved quantum genetic algorithm and adaptive differential evolution optimization back propagation neural network

Myocarditis is cardiac damage caused by a viral infection. Its result often leads to a variety of arrhythmias. However, rapid and reliable identification of myocarditis has a great impact on early diagnosis, expedited treatment, and improved patient survival rates. Therefore, a novel strategy for the autonomous detection of myocarditis is suggested in this work. First, the improved quantum genetic algorithm (IQGA) is proposed to extract the optimal features of ECG beat and heart rate variability (HRV) from raw ECG signals. Second, the backpropagation neural network (BPNN) is optimized using the adaptive differential evolution (ADE) algorithm to classify various ECG signal types with high accuracy. This study examines analogies among five different ECG signal types: normal, abnormal, myocarditis, myocardial infarction (MI), and prior myocardial infarction (PMI). Additionally, the study uses binary and multiclass classification to group myocarditis with other cardiovascular disorders in order to assess how well the algorithm performs in categorization. The experimental results demonstrate that the combination of IQGA and ADE-BPNN can effectively increase the precision and accuracy of myocarditis autonomous diagnosis. In addition, HRV assesses the method's robustness, and the classification tool can detect viruses in myocarditis patients one week before symptoms worsen. The model can be utilized in intensive care units or wearable monitoring devices and has strong performance in the detection of myocarditis.

MERGE: A model for multi-input biomedical federated learning

Driven by the deep learning (DL) revolution, artificial intelligence (AI) has become a fundamental tool for many biomedical tasks, including analyzing and classifying diagnostic images. Imaging, however, is not the only source of information. Tabular data, such as personal and genomic data and blood test results, are routinely collected but rarely considered in DL pipelines. Nevertheless, DL requires large datasets that often must be pooled from different institutions, raising non-trivial privacy concerns. Federated learning (FL) is a cooperative learning paradigm that aims to address these issues by moving models instead of data across different institutions. Here, we present a federated multi-input architecture using images and tabular data as a methodology to enhance model performance while preserving data privacy. We evaluated it on two showcases: the prognosis of COVID-19 and patients' stratification in Alzheimer's disease, providing evidence of enhanced accuracy and F1 scores against single-input models and improved generalizability against non-federated models.

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Breast cancer is a common malignancy and early detection and treatment of it is crucial. Computer-aided diagnosis (CAD) based on deep learning has significantly advanced medical diagnostics, enhancing accuracy and efficiency in recent years. Despite the convenience, this technology also has certain limitations. When the morphological characteristics of the patient's pathological section are not evident or complex, certain small lesions or cells deep within the lesion cannot be recognized, and misdiagnosis is prone to occur. As a result, MDFF-Net, a CNN-based multidimensional feature fusion network, is proposed. The model consists of a one-dimensional feature extraction network, a two-dimensional feature extraction network, and a feature fusion classification network. The basic part of the two-dimensional feature extraction network is stacked by modules integrated with multi-scale channel shuffling networks and channel attention modules. Furthermore, inspired by natural language processing, this model integrates a one-dimensional feature extraction network to extract detailed information in the image to avoid misdiagnosis caused by insufficient information extraction such as cell morphological characteristics and differentiation degree. Finally, the extracted one-dimensional and two-dimensional features are fused in the feature fusion network and employed for the final classification. The effectiveness of MDFF-Net and classical classification models were evaluated on the BreakHis and the BACH datasets. According to experimental results, MDFF-Net achieves an accuracy of 98.86% on the BreakHis and 86.25% on the BACH dataset. Furthermore, to further assess the effectiveness of the model in other classification tasks, the colon cancer and the lung cancer datasets were employed for additional experiments, achieving a classification accuracy of 100% in both cases.

Fully Automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM

BACKGROUND AND OBJECTIVE

The sheer volume of data generated by population imaging studies is unparalleled by current capabilities to extract objective and quantitative cardiac phenotypes; subjective and time-consuming manual image analysis remains the gold standard. Automated image analytics to compute quantitative imaging biomarkers of cardiac function are desperately needed. Data volumes and their variability pose a challenge to most state-of-the-art methods for endo- and epicardial contours, which lack robustness when applied to very large datasets. Our aim is to develop an analysis pipeline for the automatic quantification of cardiac function from cine magnetic resonance imaging data.

METHOD

This work adopt 4,638 cardiac MRI cases coming from UK Biobank with ground truth available for left and RV contours. A hybrid and robust algorithm is proposed to improve the accuracy of automatic left and right ventricle segmentation by harnessing the localization accuracy of deep learning and the morphological accuracy of 3D-ASM (three-dimensional active shape models). The contributions of this paper are three-fold. First, a fully automatic method is proposed for left and right ventricle initialization and cardiac MRI segmentation by taking full advantage of spatiotemporal constraint. Second, a deeply supervised network is introduced to train and segment the heart. Third, the 3D-ASM image search procedure is improved by combining image intensity models with convolutional neural network (CNN) derived distance maps improving endo- and epicardial edge localization.

RESULTS

The proposed architecture outperformed the state of the art for cardiac MRI segmentation from UK Biobank. The statistics of RV landmarks detection errors for Triscuspid valve and RV apex are 4.17 mm and 5.58 mm separately. The overlap metric, mean contour distance, Hausdorff distance and cardiac functional parameters are calculated for the LV (Left Ventricle) and RV (Right Ventricle) contour segmentation. Bland-Altman analysis for clinical parameters shows that the results from our automated image analysis pipelines are in good agreement with results from expert manual analysis.

CONCLUSIONS

Our hybrid scheme combines deep learning and statistical shape modeling for automatic segmentation of the LV/RV from cardiac MRI datasets is effective and robust and can compute cardiac functional indexes from population imaging.

Inflating 2D convolution weights for efficient generation of 3D medical images

BACKGROUND AND OBJECTIVE

The generation of three-dimensional (3D) medical images has great application potential since it takes into account the 3D anatomical structure. Two problems prevent effective training of a 3D medical generative model: (1) 3D medical images are expensive to acquire and annotate, resulting in an insufficient number of training images, and (2) a large number of parameters are involved in 3D convolution.

METHODS

We propose a novel GAN model called 3D Split&Shuffle-GAN. To address the 3D data scarcity issue, we first pre-train a two-dimensional (2D) GAN model using abundant image slices and inflate the 2D convolution weights to improve the initialization of the 3D GAN. Novel 3D network architectures are proposed for both the generator and discriminator of the GAN model to significantly reduce the number of parameters while maintaining the quality of image generation. Several weight inflation strategies and parameter-efficient 3D architectures are investigated.

RESULTS

Experiments on both heart (Stanford AIMI Coronary Calcium) and brain (Alzheimer's Disease Neuroimaging Initiative) datasets show that our method leads to improved 3D image generation quality (14.7 improvements on Frchet inception distance) with significantly fewer parameters (only 48.5% of the baseline method).

CONCLUSIONS

We built a parameter-efficient 3D medical image generation model. Due to the efficiency and effectiveness, it has the potential to generate high-quality 3D brain and heart images for real use cases.

Multi-task contrastive learning for semi-supervised medical image segmentation with multi-scale uncertainty estimation

Objective. Automated medical image segmentation is vital for the prevention and treatment of disease. However, medical data commonly exhibit class imbalance in practical applications, which may lead to unclear boundaries of specific classes and make it difficult to effectively segment certain tail classes in the results of semi-supervised medical image segmentation.Approach. We propose a novel multi-task contrastive learning framework for semi-supervised medical image segmentation with multi-scale uncertainty estimation. Specifically, the framework includes a student-teacher model. We introduce global image-level contrastive learning in the encoder to address the class imbalance and local pixel-level contrastive learning in the decoder to achieve intra-class aggregation and inter-class separation. Furthermore, we propose a multi-scale uncertainty-aware consistency loss to reduce noise caused by pseudo-label bias.Main results. Experiments on three public datasets ACDC, LA and LiTs show that our method achieves higher segmentation performance compared with state-of-the-art semi-supervised segmentation methods.Significance. The multi-task contrastive learning in our method facilitates the negative impact of class imbalance and achieves better classification results. The multi-scale uncertainty estimation encourages consistent predictions for the same input under different perturbations, motivating the teacher model to generate high-quality pseudo-labels. Code is available athttps://github.com/msctransu/MCSSMU.git.

A novel Gateaux derivatives with efficient DCNN-Resunet method for segmenting multi-class brain tumor

In hospitals and pathology, observing the features and locations of brain tumors in Magnetic Resonance Images (MRI) is a crucial task for assisting medical professionals in both treatment and diagnosis. The multi-class information about the brain tumor is often obtained from the patient's MRI dataset. However, this information may vary in different shapes and sizes for various brain tumors, making it difficult to detect their locations in the brain. To resolve these issues, a novel customized Deep Convolution Neural Network (DCNN) based Residual-Unet (ResUnet) model with Transfer Learning (TL) is proposed for predicting the locations of the brain tumor in an MRI dataset. The DCNN model has been used to extract the features from input images and select the Region Of Interest (ROI) by using the TL technique for training it faster. Furthermore, the min-max normalizing approach is used to enhance the color intensity value for particular ROI boundary edges in the brain tumor images. Specifically, the boundary edges of the brain tumors have been detected by utilizing Gateaux Derivatives (GD) method to identify the multi-class brain tumors precisely. The proposed scheme has been validated on two datasets namely the brain tumor, and Figshare MRI datasets for detecting multi-class Brain Tumor Segmentation (BTS).The experimental results have been analyzed by evaluation metrics namely, accuracy (99.78, and 99.03), Jaccard Coefficient (93.04, and 94.95), Dice Factor Coefficient (DFC) (92.37, and 91.94), Mean Absolute Error (MAE) (0.0019, and 0.0013), and Mean Squared Error (MSE) (0.0085, and 0.0012) for proper validation. The proposed system outperforms the state-of-the-art segmentation models on the MRI brain tumor dataset.

An early prediction and classification of lung nodule diagnosis on CT images based on hybrid deep learning techniques

Detection of malignant lung nodules at an early stage may allow for clinical interventions that increase the survival rate of lung cancer patients. Using hybrid deep learning techniques to detect nodules will improve the sensitivity of lung cancer screening and the interpretation speed of lung scans. Accurate detection of lung nodes is an important step in computed tomography (CT) imaging to detect lung cancer. However, it is very difficult to identify strong nodes due to the diversity of lung nodes and the complexity of the surrounding environment. Here, we proposed lung nodule detection and classification with CT images based on hybrid deep learning (LNDC-HDL) techniques. First, we introduce a chaotic bird swarm optimization (CBSO) algorithm for lung nodule segmentation using statistical information. Second, we illustrate an improved Fish Bee (IFB) algorithm for feature extraction and selection. Third, we develop a hybrid classifier i.e. hybrid differential evolution-based neural network (HDE-NN) for tumor prediction and classification. Experimental results have shown that the use of computed tomography, which demonstrates the efficiency and importance of the HDE-NN specific structure for detecting lung nodes on CT scans, increases sensitivity and reduces the number of false positives. The proposed method shows that the benefits of HDE-NN node detection can be reaped by combining clinical practice.

Brain image segmentation of the corpus callosum by combining Bi-Directional Convolutional LSTM and U-Net using multi-slice CT and MRI

BACKGROUND AND OBJECTIVE

Traditional disease diagnosis is usually performed by experienced physicians, but misdiagnosis or missed diagnosis still exists. Exploring the relationship between changes in the corpus callosum and multiple brain infarcts requires extracting corpus callosum features from brain image data, which requires addressing three key issues. (1) automation, (2) completeness, and (3) accuracy. Residual learning can facilitate network training, Bi-Directional Convolutional LSTM (BDC-LSTM) can exploit interlayer spatial dependencies, and HDC can expand the receptive domain without losing resolution.

METHODS

In this paper, we propose a segmentation method by combining BDC-LSTM and U-Net to segment the corpus callosum from multiple angles of brain images based on computed tomography (CT) and magnetic resonance imaging (MRI) in which two types of sequence, namely T2-weighted imaging as well as the Fluid Attenuated Inversion Recovery (Flair), were utilized. The two-dimensional slice sequences are segmented in the cross-sectional plane, and the segmentation results are combined to obtain the final results. Encoding, BDC- LSTM, and decoding include convolutional neural networks. The coding part uses asymmetric convolutional layers of different sizes and dilated convolutions to get multi-slice information and extend the convolutional layers' perceptual field.

RESULTS

This paper uses BDC-LSTM between the encoding and decoding parts of the algorithm. On the image segmentation of the brain in multiple cerebral infarcts dataset, accuracy rates of 0.876, 0.881, 0.887, and 0.912 were attained for the intersection of union (IOU), dice similarity coefficient (DS), sensitivity (SE), and predictive positivity value (PPV). The experimental findings demonstrate that the algorithm outperforms its rivals in accuracy.

CONCLUSION

This paper obtained segmentation results for three images using three models, ConvLSTM, Pyramid-LSTM, and BDC-LSTM, and compared them to verify that BDC-LSTM is the best method to perform the segmentation task for faster and more accurate detection of 3D medical images. We improve the convolutional neural network segmentation method to obtain medical images with high segmentation accuracy by solving the over-segmentation problem.

Qureshi A, Li J, Mahmood T. On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

Temporal and periorbital depressions identified by 3D images are correlated with malnutrition phenotypes in cancer patients: A pilot study

Background

Prompt diagnosis of malnutrition and appropriate interventions can substantially improve the prognosis of patients with cancer; however, it is difficult to unify the tools for screening malnutrition risk. 3D imaging technology has been emerging as an approach to assisting in the diagnosis of diseases, and we designed this study to explore its application value in identifying the malnutrition phenotype and evaluating nutrition status.

Methods

Hospitalized patients treating with maintenance chemotherapy for advanced malignant tumor of digestive system were recruited from the Department of Oncology, whose NRS 2002 score > 3. Physical examination and body composition data of patients at risk for malnutrition were analyzed by physicians trained to complete a subjective global assessment. The facial depression index was recognized using the Antera 3D® system, temporal and periorbital depression indexes were acquired using the companion software Antera Pro. This software captures quantitative data of depression volume, affected area, and maximum depth of temporal and periorbital concave areas.

Results

A total of 53 inpatients with malnutrition-related indicators were included. The volume of temporal depression was significantly negatively correlated with upper arm circumference (r = −0.293, p = 0.033) and calf circumference (r = −0.285, p = 0.038). The volume and affected area of periorbital depression were significantly negatively correlated with fat mass index (r = −0.273, p = 0.048 and r = −0.304, p = 0.026, respectively) and percent body fat (r = −0.317, p = 0.021 and r = −0.364, p = 0.007, respectively). The volume and affected area of temporal depression in patients with muscle loss phenotype (low arm circumference/low calf circumference/low handgrip strength/low fat-free mass index) were significantly higher than those in patients without muscle loss. Moreover, patients with fat mass loss phenotype (low fat mass index) showed a significant increase in the volume and affected area of periorbital depression.

Conclusion

The facial temporal region, and periorbital depression indicators extracted by 3D image recognition technology were significantly associated with the phenotype of malnutrition-related muscle and fat loss and showed a trend of grade changes in the population of different subjective global assessment nutritional classifications.

Stroke risk prediction by color Doppler ultrasound of carotid artery-based deep learning using Inception V3 and VGG-16

Purpose

This study aims to automatically classify color Doppler images into two categories for stroke risk prediction based on the carotid plaque. The first category is high-risk carotid vulnerable plaque, and the second is stable carotid plaque.

Method

In this research study, we used a deep learning framework based on transfer learning to classify color Doppler images into two categories: one is high-risk carotid vulnerable plaque, and the other is stable carotid plaque. The data were collected from the Second Affiliated Hospital of Fujian Medical University, including stable and vulnerable cases. A total of 87 patients with risk factors for atherosclerosis in our hospital were selected. We used 230 color Doppler ultrasound images for each category and further divided those into the training set and test set in a ratio of 70 and 30%, respectively. We have implemented Inception V3 and VGG-16 pre-trained models for this classification task.

Results

Using the proposed framework, we implemented two transfer deep learning models: Inception V3 and VGG-16. We achieved the highest accuracy of 93.81% by using fine-tuned and adjusted hyperparameters according to our classification problem.

Conclusion

In this research, we classified color Doppler ultrasound images into high-risk carotid vulnerable and stable carotid plaques. We fine-tuned pre-trained deep learning models to classify color Doppler ultrasound images according to our dataset. Our suggested framework helps prevent incorrect diagnoses caused by low image quality and individual experience, among other factors.

Breast MRI Segmentation and Ki-67 High- and Low-Expression Prediction Algorithm Based on Deep Learning

Background and Objective. Breast cancer is a common malignant tumor that seriously threatens the health of women in my country and even around the world. The proliferation marker Ki-67 has been utilized to distinguish luminal B from luminal A tumors and is a reliable indicator of more aggressive breast cancer growth. If a reliable prediction method for breast cancer patients to avoid invasive damage can be found to predict Ki-67 before pathological examination, it will be very beneficial for doctors to formulate later treatment plans and provide more useful treatment options. Methodology. This paper proposes a tumor segmentation and prediction framework based on the combination of improved attention U-Net and SVM. The framework first improves on attention U-Net by introducing coefficients for learning multidimensional attention. Make the attention mechanism more aware of the main situation in the segmentation process. At the same time, the segmented breast MRI results and corresponding labels were input into the SVM classifier to accurately predict the expression of Ki-67. Results. The DSC, PPV, and sensitivity of our combined model are 0.94, 0.93, and 0.94, respectively, with better segmentation performance. And we compare with the segmentation frameworks of other papers and find that our combined model can make accurate segmentation of breast tumors. Conclusion. Our method can adapt to the variability of breast tumors and segment breast tumors accurately and efficiently. In the future, it can be widely used in clinical practice, so as to help the clinic better formulate a reasonable diagnosis and treatment plan for breast cancer patients.

Breast MRI Tumor Automatic Segmentation and Triple-Negative Breast Cancer Discrimination Algorithm Based on Deep Learning

Background

Breast cancer is a kind of cancer that starts in the epithelial tissue of the breast. Breast cancer has been on the rise in recent years, with a younger generation developing the disease. Magnetic resonance imaging (MRI) plays an important role in breast tumor detection and treatment planning in today's clinical practice. As manual segmentation grows more time-consuming and the observed topic becomes more diversified, automated segmentation becomes more appealing. Methodology. For MRI breast tumor segmentation, we propose a CNN-SVM network. The labels from the trained convolutional neural network are output using a support vector machine in this technique. During the testing phase, the convolutional neural network's labeled output, as well as the test grayscale picture, is passed to the SVM classifier for accurate segmentation.

Results

We tested on the collected breast tumor dataset and found that our proposed combined CNN-SVM network achieved 0.93, 0.95, and 0.92 on DSC coefficient, PPV, and sensitivity index, respectively. We also compare with the segmentation frameworks of other papers, and the comparison results prove that our CNN-SVM network performs better and can accurately segment breast tumors.

Conclusion

Our proposed CNN-SVM combined network achieves good segmentation results on the breast tumor dataset. The method can adapt to the differences in breast tumors and segment breast tumors accurately and efficiently. It is of great significance for identifying triple-negative breast cancer in the future.

A Heart Segmentation Algorithm Based on Dynamic Ultrasound

The heart is one of the most important organs of the human body. The role of the heart is to promote blood flow and provide sufficient blood flow to organs and tissues. The research on the heart has important theoretical and clinical significance. Because of the noninvasive and intuitive display of ultrasound image, it can dynamically obtain the heart state and has become the main means to detect the heart dynamics. We analyze the characteristics of cardiac ultrasound image from the medical point of view and signal processing. The heart movement is periodic and rhythmic. The image signal can be decomposed. Firstly, the image is decomposed into high- and low-frequency signals to highlight different dimensional information. Then, the attention model was introduced, focusing on the heart region. Finally, the multidimensional network carrying model was established to achieve cardiac segmentation. The experimental results show that the AOM of the algorithm proposed in this paper reaches 92%, which has a certain degree of advancement and can assist doctors to make accurate diagnosis.