Medical Image Analysis Applications Research Articles

Dense Convolutional Network and Its Application in Medical Image Analysis

Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis. In this paper, DenseNet is summarized from the following aspects. First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image segmentation, and object detection. The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet.

MEDAS: an open-source platform as a service to help break the walls between medicine and informatics.

In the past decade, deep learning (DL) has achieved unprecedented success in numerous fields, such as computer vision and healthcare. Particularly, DL is experiencing an increasing development in advanced medical image analysis applications in terms of segmentation, classification, detection, and other tasks. On the one hand, tremendous needs that leverage DL’s power for medical image analysis arise from the research community of a medical, clinical, and informatics background to share their knowledge, skills, and experience jointly. On the other hand, barriers between disciplines are on the road for them, often hampering a full and efficient collaboration. To this end, we propose our novel open-source platform, i.e., MEDAS–the MEDical open-source platform As Service. To the best of our knowledge, MEDAS is the first open-source platform providing collaborative and interactive services for researchers from a medical background using DL-related toolkits easily and for scientists or engineers from informatics modeling faster. Based on tools and utilities from the idea of RINV (Rapid Implementation aNd Verification), our proposed platform implements tools in pre-processing, post-processing, augmentation, visualization, and other phases needed in medical image analysis. Five tasks, concerning lung, liver, brain, chest, and pathology, are validated and demonstrated to be efficiently realizable by using MEDAS. MEDAS is available at http://medas.bnc.org.cn/.

Progressive attention module for segmentation of volumetric medical images.

Medical image segmentation is critical for many medical image analysis applications. 3D convolutional neural networks (CNNs) have been widely adopted in the segmentation of volumetric medical images. The recent development of channelwise and spatialwise attentions achieves the state-of-the-art feature representation performance. However, these attention strategies have not explicitly modeled interdependencies among slices in 3D medical volumes. In this work, we propose a novel attention module called progressive attention module (PAM) to explicitly model the slicewise importance for 3D medical image analysis. The proposed method is composed of three parts: Slice Attention (SA) block, Key-Slice-Selection (KSS) block, and Channel Attention (CA) block. First, the SA is a novel attention block to explore the correlation among slices for 3D medical image segmentation. SA is designed to explicitly reweight the importance of each slice in the 3D medical image scan. Second, the KSS block, cooperating with the SA block, is designed to adaptively emphasize the critical slice features while suppressing the irrelevant slice features, which helps the model focus on the slices with rich structural and contextual information. Finally, the CA block receives the output of KSS as input for further feature recalibration. Our proposed PAM organically combines SA, KSS, and CA, progressively highlights the key slices containing rich information for the relevant tasks while suppressing those irrelevantslices. To demonstrate the effectiveness of PAM, we embed it into 3D CNNs architectures and evaluate the segmentation performance on three public challenging data sets: BraTS 2018 data set, MALC data set, and HVSMR data set. We achieve 80.34%, 88.98%, and 84.43% of the Dice similarity coefficient on these three data sets, respectively. Experimental results show that the proposed PAM not only boosts the segmentation accuracy of the standard 3D CNNs methods consistently, but also outperforms the other attention mechanisms with slight extracosts. We propose a new PAM to identify the most informative slices and recalibrate channelwise feature responses for volumetric medical image segmentation. The proposed method is evaluated on three public data sets, and the results show improvements over other methods. This proposed technique can effectively assist physicians in many medical image analysis. It is also anticipated to be generalizable and transferable to assist physicians in a wider range of medical imaging applications to produce greater value and impact tohealth.

Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism

Computational intelligence has been widely used in medical information processing. The deep learning methods, especially, have many successful applications in medical image analysis. In this paper, we proposed an end-to-end medical lesion segmentation framework based on convolutional neural networks with a dual attention mechanism, which integrates both fully and weakly supervised segmentation. The weakly supervised segmentation module achieves accurate lesion segmentation by using bounding-box labels of lesion areas, which solves the problem of the high cost of pixel-level labels with lesions in the medical images. In addition, a dual attention mechanism is introduced to enhance the network’s ability for visual feature learning. The dual attention mechanism (channel and spatial attention) can help the network pay attention to feature extraction from important regions. Compared with the current mainstream method of weakly supervised segmentation using pseudo labels, it can greatly reduce the gaps between ground-truth labels and pseudo labels. The final experimental results show that our proposed framework achieved more competitive performances on oral lesion dataset, and our framework further extended to dermatological lesion segmentation.

Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds.

Shape reconstruction from sparse point clouds/images is a challenging and relevant task required for a variety of applications in computer vision and medical image analysis (e.g. surgical navigation, cardiac motion analysis, augmented/virtual reality systems). A subset of such methods, viz. 3D shape reconstruction from 2D contours, is especially relevant for computer-aided diagnosis and intervention applications involving meshes derived from multiple 2D image slices, views or projections. We propose a deep learning architecture, coined Mesh Reconstruction Network (MR-Net), which tackles this problem. MR-Net enables accurate 3D mesh reconstruction in real-time despite missing data and with sparse annotations. Using 3D cardiac shape reconstruction from 2D contours defined on short-axis cardiac magnetic resonance image slices as an exemplar, we demonstrate that our approach consistently outperforms state-of-the-art techniques for shape reconstruction from unstructured point clouds. Our approach can reconstruct 3D cardiac meshes to within 2.5-mm point-to-point error, concerning the ground-truth data (the original image spatial resolution is ∼1.8×1.8×10mm3). We further evaluate the robustness of the proposed approach to incomplete data, and contours estimated using an automatic segmentation algorithm. MR-Net is generic and could reconstruct shapes of other organs, making it compelling as a tool for various applications in medical image analysis.

Decomposition of Longitudinal Deformations via Beltrami Descriptors

We present a mathematical model to decompose a longitudinal deformation into normal and abnormal components. The goal is to detect and extract subtle abnormal deformation from periodic motions in a video sequence. It has important applications in medical image analysis. To achieve this goal, we consider a representation of the longitudinal deformation, called the Beltrami descriptor, based on quasiconformal theories. The Beltrami descriptor is a complex-valued matrix. Each longitudinal deformation is associated to a Beltrami descriptor and vice versa. To decompose the longitudinal deformation, we propose to carry out the low rank and sparse decomposition of the Beltrami descriptor. The low rank component corresponds to the periodic motions, whereas the sparse part corresponds to the abnormal motions of a longitudinal deformation. Experiments have been carried out on both synthetic and real video sequences. Results demonstrate the efficacy of our proposed model to decompose a longitudinal deformation into regular and irregular components.

What is new in computer vision and artificial intelligence in medical image analysis applications.

Computer vision and artificial intelligence applications in medicine are becoming increasingly important day by day, especially in the field of image technology. In this paper we cover different artificial intelligence advances that tackle some of the most important worldwide medical problems such as cardiology, cancer, dermatology, neurodegenerative disorders, respiratory problems, and gastroenterology. We show how both areas have resulted in a large variety of methods that range from enhancement, detection, segmentation and characterizations of anatomical structures and lesions to complete systems that automatically identify and classify several diseases in order to aid clinical diagnosis and treatment. Different imaging modalities such as computer tomography, magnetic resonance, radiography, ultrasound, dermoscopy and microscopy offer multiple opportunities to build automatic systems that help medical diagnosis, taking advantage of their own physical nature. However, these imaging modalities also impose important limitations to the design of automatic image analysis systems for diagnosis aid due to their inherent characteristics such as signal to noise ratio, contrast and resolutions in time, space and wavelength. Finally, we discuss future trends and challenges that computer vision and artificial intelligence must face in the coming years in order to build systems that are able to solve more complex problems that assist medical diagnosis.

Dynamic-weighting hierarchical segmentation network for medical images

Automatic medical image segmentation plays a crucial role in many medical image analysis applications, such as disease diagnosis and prognosis. Despite the extensive progress of existing deep learning based models for medical image segmentation, they focus on extracting accurate features by designing novel network structures and solely utilize fully connected (FC) layer for pixel-level classification. Considering the insufficient capability of FC layer to encode the extracted diverse feature representations, we propose a Hierarchical Segmentation (HieraSeg) Network for medical image segmentation and devise a Hierarchical Fully Connected (HFC) layer. Specifically, it consists of three classifiers and decouples each category into several subcategories by introducing multiple weight vectors to denote the diverse characteristics in each category. A subcategory-level and a category-level learning schemes are then designed to explicitly enforce the discrepant subcategories and automatically capture the most representative characteristics. Hence, the HFC layer can fit the variant characteristics so as to derive an accurate decision boundary. To enhance the robustness of HieraSeg Network with the variability of lesions, we further propose a Dynamic-Weighting HieraSeg (DW-HieraSeg) Network, which introduces an Image-level Weight Net (IWN) and a Pixel-level Weight Net (PWN) to learn data-driven curriculum. Through progressively incorporating informative images and pixels in an easy-to-hard manner, DW-HieraSeg Network is able to eliminate local optimums and accelerate the training process. Additionally, a class balanced loss is proposed to constrain the PWN for preventing the overfitting problem in minority category. Comprehensive experiments on three benchmark datasets, EndoScene, ISIC and Decathlon, show our newly proposed HieraSeg and DW-HieraSeg Networks achieve state-of-the-art performance, which clearly demonstrates the effectiveness of the proposed approaches for medical image segmentation.

Evaluation of deep learning-based artificial intelligence techniques for breast cancer detection on mammograms: Results from a retrospective study using a BreastScreen Victoria dataset.

IntroductionThis study aims to evaluate deep learning (DL)‐based artificial intelligence (AI) techniques for detecting the presence of breast cancer on a digital mammogram image.MethodsWe evaluated several DL‐based AI techniques that employ different approaches and backbone DL models and tested the effect on performance of using different data‐processing strategies on a set of digital mammographic images with annotations of pathologically proven breast cancer.ResultsOur evaluation uses the area under curve (AUC) and accuracy (ACC) for performance measurement. The best evaluation result, based on 349 test cases (930 test images), was an AUC of 0.8979 [95% confidence interval (CI) 0.873, 0.923] and ACC of 0.8178 [95% CI 0.785, 0.850]. This was achieved by an AI technique that utilises a certain family of DL models, namely ResNet, as its backbone, combines the global features extracted from the whole mammogram and the local features extracted from the automatically detected cancer and non‐cancer local regions in the whole image, and leverages background cropping and text removal, contrast adjustment and more training data.ConclusionDL‐based AI techniques have shown promising results in retrospective studies for many medical image analysis applications. Our study demonstrates a significant opportunity to boost the performance of such techniques applied to breast cancer detection by exploring different types of approaches, backbone DL models and data‐processing strategies. The promising results we have obtained suggest further development of AI reading services could transform breast cancer screening in the future.

Methodology for comprehensive cell-level analysis of wound healing experiments using deep learning in MATLAB

BackgroundEndothelial healing after deployment of cardiovascular devices is particularly important in the context of clinical outcome. It is therefore of great interest to develop tools for a precise prediction of endothelial growth after injury in the process of implant deployment. For experimental investigation of re-endothelialization in vitro cell migration assays are routinely used. However, semi-automatic analyses of live cell images are often based on gray value distributions and are as such limited by image quality and user dependence. The rise of deep learning algorithms offers promising opportunities for application in medical image analysis. Here, we present an intelligent cell detection (iCD) approach for comprehensive assay analysis to obtain essential characteristics on cell and population scale.ResultsIn an in vitro wound healing assay, we compared conventional analysis methods with our iCD approach. Therefore we determined cell density and cell velocity on cell scale and the movement of the cell layer as well as the gap closure between two cell monolayers on population scale. Our data demonstrate that cell density analysis based on deep learning algorithms is superior to an adaptive threshold method regarding robustness against image distortion. In addition, results on cell scale obtained with iCD are in agreement with manually velocity detection, while conventional methods, such as Cell Image Velocimetry (CIV), underestimate cell velocity by a factor of 0.5. Further, we found that iCD analysis of the monolayer movement gave results just as well as manual freehand detection, while conventional methods again shows more frayed leading edge detection compared to manual detection. Analysis of monolayer edge protrusion by ICD also produced results, which are close to manual estimation with an relative error of 11.7%. In comparison, the conventional Canny method gave a relative error of 76.4%.ConclusionThe results of our experiments indicate that deep learning algorithms such as our iCD have the ability to outperform conventional methods in the field of wound healing analysis. The combined analysis on cell and population scale using iCD is very well suited for timesaving and high quality wound healing analysis enabling the research community to gain detailed understanding of endothelial movement.

Deep learning in structural and functional lung image analysis.

The recent resurgence of deep learning (DL) has dramatically influenced the medical imaging field. Medical image analysis applications have been at the forefront of DL research efforts applied to multiple diseases and organs, including those of the lungs. The aims of this review are twofold: (i) to briefly overview DL theory as it relates to lung image analysis; (ii) to systematically review the DL research literature relating to the lung image analysis applications of segmentation, reconstruction, registration and synthesis. The review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. 479 studies were initially identified from the literature search with 82 studies meeting the eligibility criteria. Segmentation was the most common lung image analysis DL application (65.9% of papers reviewed). DL has shown impressive results when applied to segmentation of the whole lung and other pulmonary structures. DL has also shown great potential for applications in image registration, reconstruction and synthesis. However, the majority of published studies have been limited to structural lung imaging with only 12.9% of reviewed studies employing functional lung imaging modalities, thus highlighting significant opportunities for further research in this field. Although the field of DL in lung image analysis is rapidly expanding, concerns over inconsistent validation and evaluation strategies, intersite generalisability, transparency of methodological detail and interpretability need to be addressed before widespread adoption in clinical lung imaging workflow.

Modeling and Enhancing Low-Quality Retinal Fundus Images.

Retinal fundus images are widely used for the clinical screening and diagnosis of eye diseases. However, fundus images captured by operators with various levels of experience have a large variation in quality. Low-quality fundus images increase uncertainty in clinical observation and lead to the risk of misdiagnosis. However, due to the special optical beam of fundus imaging and structure of the retina, natural image enhancement methods cannot be utilized directly to address this. In this article, we first analyze the ophthalmoscope imaging system and simulate a reliable degradation of major inferior-quality factors, including uneven illumination, image blurring, and artifacts. Then, based on the degradation model, a clinically oriented fundus enhancement network (cofe-Net) is proposed to suppress global degradation factors, while simultaneously preserving anatomical retinal structures and pathological characteristics for clinical observation and analysis. Experiments on both synthetic and real images demonstrate that our algorithm effectively corrects low-quality fundus images without losing retinal details. Moreover, we also show that the fundus correction method can benefit medical image analysis applications, e.g., retinal vessel segmentation and optic disc/cup detection.

Active Cell Appearance Model Induced Generative Adversarial Networks for Annotation-Efficient Cell Segmentation and Identification on Adaptive Optics Retinal Images.

Data annotation is a fundamental precursor for establishing large training sets to effectively apply deep learning methods to medical image analysis. For cell segmentation, obtaining high quality annotations is an expensive process that usually requires manual grading by experts. This work introduces an approach to efficiently generate annotated images, called "A-GANs", created by combining an active cell appearance model (ACAM) with conditional generative adversarial networks (C-GANs). ACAM is a statistical model that captures a realistic range of cell characteristics and is used to ensure that the image statistics of generated cells are guided by real data. C-GANs utilize cell contours generated by ACAM to produce cells that match input contours. By pairing ACAM-generated contours with A-GANs-based generated images, high quality annotated images can be efficiently generated. Experimental results on adaptive optics (AO) retinal images showed that A-GANs robustly synthesize realistic, artificial images whose cell distributions are exquisitely specified by ACAM. The cell segmentation performance using as few as 64 manually-annotated real AO images combined with 248 artificially-generated images from A-GANs was similar to the case of using 248 manually-annotated real images alone (Dice coefficients of 88% for both). Finally, application to rare diseases in which images exhibit never-seen characteristics demonstrated improvements in cell segmentation without the need for incorporating manual annotations from these new retinal images. Overall, A-GANs introduce a methodology for generating high quality annotated data that statistically captures the characteristics of any desired dataset and can be used to more efficiently train deep-learning-based medical image analysis applications.

An Efficient Memristor-Based Circuit Implementation of Squeeze-and-Excitation Fully Convolutional Neural Networks.

Recently, there has been a surge of interest in applying memristors to hardware implementations of deep neural networks due to various desirable properties of the memristor, such as nonvolativity, multivalue, and nanosize. Most existing neural network circuit designs, however, are based on generic frameworks that are not optimized for memristors. Furthermore, to the best of our knowledge, there are no existing efficient memristor-based implementations of complex neural network operators, such as deconvolutions and squeeze-and-excitation (SE) blocks, which are critical for achieving high accuracy in common medical image analysis applications, such as semantic segmentation. This article proposes convolution-kernel first (CKF), an efficient scheme for designing memristor-based fully convolutional neural networks (FCNs). Compared with existing neural network circuits, CKF enables effective parameter pruning, which significantly reduces circuit power consumption. Furthermore, CKF includes the novel, memristor-optimized implementations of deconvolution layers and SE blocks. Simulation results on real medical image segmentation tasks confirm that CKF obtains up to 56.2% reduction in terms of computations and 33.62-W reduction in terms of power consumption in the circuit after weight pruning while retaining high accuracy on the test set. Moreover, the pruning results can be applied directly to existing circuits without any modification for the corresponding system.

Adaptive Mesh Refinement in Deformable Image Registration: A Posteriori Error Estimates for Primal and Mixed Formulations

Deformable image registration (DIR) is a popular technique for the alignment of digital images, with highly relevant applications in medical image analysis. However, the numerical solution of DIR p...

Medical Image Analysis Using AM-FM Models and Methods.

Medical image analysis methods require the use of effective representations for differentiating between lesions, diseased regions, and normal structure. Amplitude Modulation-Frequency Modulation (AM-FM) models provide effective representations through physically meaningful descriptors of complex non-stationary structures that can differentiate between the different lesions and normal structure. Based on AM-FM models, medical images are decomposed into AM-FM components where the instantaneous frequency provides a descriptor of local texture, the instantaneous amplitude captures slowly-varying brightness variations, while the instantaneous phase provides for a powerful descriptor of location, generalizing the traditionally important role of phase in the Fourier Analysis of images. Over the years, AM-FM representations have been used in a wide variety of medical image analysis applications based on a vastly reduced number of features that can be easily learned by simple classifiers. The paper provides an overview of AM-FM models and methods, followed by applications in medical image analysis. We also provide a summary of emerging trends and future directions.

Advances in Deep Learning-Based Medical Image Analysis

Importance. With the booming growth of artificial intelligence (AI), especially the recent advancements of deep learning, utilizing advanced deep learning-based methods for medical image analysis has become an active research area both in medical industry and academia. This paper reviewed the recent progress of deep learning research in medical image analysis and clinical applications. It also discussed the existing problems in the field and provided possible solutions and future directions.Highlights. This paper reviewed the advancement of convolutional neural network-based techniques in clinical applications. More specifically, state-of-the-art clinical applications include four major human body systems: the nervous system, the cardiovascular system, the digestive system, and the skeletal system. Overall, according to the best available evidence, deep learning models performed well in medical image analysis, but what cannot be ignored are the algorithms derived from small-scale medical datasets impeding the clinical applicability. Future direction could include federated learning, benchmark dataset collection, and utilizing domain subject knowledge as priors.Conclusion. Recent advanced deep learning technologies have achieved great success in medical image analysis with high accuracy, efficiency, stability, and scalability. Technological advancements that can alleviate the high demands on high-quality large-scale datasets could be one of the future developments in this area.

A Review of Deep Learning on Medical Image Analysis

Compared with common deep learning methods (e.g., convolutional neural networks), transfer learning is characterized by simplicity, efficiency and its low training cost, breaking the curse of small datasets. Medical image analysis plays an indispensable role in both scientific research and clinical diagnosis. Common medical image acquisition methods include Computer Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound (US), X-Ray, etc. Although these medical imaging methods can be applied for non-invasive qualitative and quantitative analysis of patients—compared with image datasets in other computer vision fields such like faces—medical images, especially its labeling, is still scarce and insufficient. Therefore, more and more researchers adopted transfer learning for medical image processing. In this study, after reviewing one hundred representative papers from IEEE, Elsevier, Google Scholar, Web of Science and various sources published from 2000 to 2020, a comprehensive review is presented, including (i) structure of CNN, (ii) background knowledge of transfer learning, (iii) different types of strategies performing transfer learning, (iv) application of transfer learning in various sub-fields of medical image analysis, and (v) discussion on the future prospect of transfer learning in the field of medical image analysis. Through this review paper, beginners could receive an overall and systematic knowledge of transfer learning application in medical image analysis. And policymaker of related realm will benefit from the summary of the trend of transfer learning in medical imaging field and may be encouraged to make policy positive to the future development of transfer learning in the field of medical image analysis.

Combinatorial Double Auction Based Meta-scheduler for Medical Image Analysis Application in Grid Environment

Background: Medical image analysis application has complex resource requirement. Scheduling Medical image analysis application is the complex task to the grid resources. It is necessary to develop a new model to improve the breast cancer screening process. Proposed novel Meta scheduler algorithm allocate the image analyse applications to the local schedulers and local scheduler submit the job to the grid node which analyses the medical image and generates the result sent back to Meta scheduler. Meta schedulers are distinct from the local scheduler. Meta scheduler and local scheduler have the aim at resource allocation and management. Objective: The main objective of the CDAM meta-scheduler is to maximize the number of jobs accepted. Methods: In the beginning, the user sends jobs with the deadline to the global grid resource broker. Resource providers sent information about the available resources connected in the network at a fixed interval of time to the global grid resource broker, the information such as valuation of the resource and number of an available free resource. CDAM requests the global grid resource broker for available resources details and user jobs. After receiving the information from the global grid resource broker, it matches the job with the resources. CDAM sends jobs to the local scheduler and local scheduler schedule the job to the local grid site. Local grid site executes the jobs and sends the result back to the CDAM. Success full completion of the job status and resource status are updated into the auction history database. CDAM collect the result from all local grid site and return to the grid users. Results: The CDAM was simulated using grid simulator. Number of jobs increases then the percentage of the jobs accepted also decrease due to the scarcity of resources. CDAM is providing 2% to 5% better result than Fair share Meta scheduling algorithm. CDAM algorithm bid density value is generated based on the user requirement and user history and ask value is generated from the resource details. Users who, having the most significant deadline are generated the highest bid value, grid resource which is having the fastest processor are generated lowest ask value. The highest bid is assigned to the lowest Ask it means that the user who is having the most significant deadline is assigned to the grid resource which is having the fastest processor. The deadline represents a time by which the user requires the result. The user can define the deadline by which the results are needed, and the CDAM will try to find the fastest resource available in order to meet the user-defined deadline. If the scheduler detects that the tasks cannot be completed before the deadline, then the scheduler abandons the current resource, tries to select the next fastest resource and tries until the completion of application meets the deadline. CDAM is providing 25% better result than grid way Meta scheduler this is because grid way Meta scheduler allocate jobs to the resource based on the first come first served policy. Conclusion: The proposed CDAM model was validated through simulation and was evaluated based on jobs accepted. The experimental results clearly show that the CDAM model maximizes the number of jobs accepted than conventional Meta scheduler. We conclude that a CDAM is highly effective meta-scheduler systems and can be used for an extraordinary situation where jobs have a combinatorial requirement.

Aggregated Deep Global Feature Representation for Breast Cancer Histopathology Image Classification

Convolutional neural networks (CNNs), successfully used in a great number of medical image analysis applications, have also achieved the state-of-the-art performance in breast cancer histopathology image (BCHI) classification problem recently. However, due to the large varieties among within-class images and insufficient data volume, it is still a challenge to obtain more competitive results by using deep CNN models alone. In this paper, we aim to explore the combination of CNN models with a milestone feature representation method in visual tasks, i.e., vector of locally aggregated descriptors (VLAD), for the BCHI classification, and further propose a novel aggregated deep global feature representation (ADGFR) for this problem. ADGFR adopts the deep features that are extracted from the fully connected layer to form an individual descriptor vector, and augments input images to generate different descriptors for achieving the final aggregated descriptor vector. The individual descriptor vector can effectively keep the global features of benign and malignant image, whose discriminability is further reinforced by the aggregate operation, leading to the more discriminant capability of ADGFR for BCHI. Extensive experiments on the public Break His dataset illuminate that our ADGFR can achieve the optimal classification accuracies of 95.05% at image level and 95.50% at patient level, respectively.