Mass Segmentation Research Articles

Irkutsk architectural appearance changes in the 1960s-2010s

The article highlights the changes in the architectural appearance of Irkutsk during the post-Stalin times. The development of the historical city in the Soviet period proceeded in accordance with the needs of the Soviet system: industrial facilities and mass segment housing were built; residential neighborhoods with a set of social and domestic facilities were created. Sometimes there was a successful weaving of the new forms into the established ones. In some cases, innovations destroyed the historical view of the environment. The contribution of architects and statesmen to the development of the city has been considered. In the conditions of a market economy, multidirectional trends have been indicated. Thus, on the one hand, the integrity and originality of the city centre is spoiled and distorted through the infill development. On the other hand, the demand for creating a comfortable city environment is reflected in interesting forms of the cityscape: new squares, monuments, fountains, and other objects appear. The city symbols are being updated, an attempt to brand Irkutsk has been made. The regeneration of the city environment leads to the introduction of 130 Kvartal quarter, which is a successful attempt to create a new public space. There are also other attempts to make the architectural appearance of the city more modern and its image – memorable.

A new data augmentation method based on local image warping for medical image segmentation.

The segmentation accuracy of medical images was improved by increasing the number of training samples using a local image warping technique. The performance of the proposed method was evaluated in the segmentation of breast masses, prostate and brain tumors, and lung nodules. We propose a simple data augmentation method which is called stochastic evolution (SE). Specifically, the idea of SE stems from our thinking about the deterioration of the diseased tissue and the healing process. In order to simulate this natural process, we implement it according to the local distortion algorithm in image warping. In other words, the irregular deterioration and healing processes of the diseased tissue is simulated according to the direction of the local distortion, thereby producing a natural sample that is indistinguishable by humans. The proposed method is evaluated on four segmentation tasks of breast masses, prostate, brain tumors, and lung nodules. Comparing the experimental results of four segmentation methods based on the UNet segmentation architecture without adding any expanded data during training, the accuracy and the Hausdorff distance obtained in our approach remain almost the same as other methods. However, the dice similarity coefficient (DSC) and sensitivity (SEN) have both improved to some extent. Among them, DSC is increased by 5.2%, 2.8%, 1.0%, and 3.2%, respectively; SEN is increased by 6.9%, 4.3%, 1.2%, and 4.5%, respectively. Experimental results show that the proposed SE data augmentation method could improve the segmentation accuracy of breast masses, prostate, brain tumors, and lung nodules. The method also shows the robustness with different image datasets and imaging modalities.

딥러닝을 이용한 유방조영술의 종양 분할

딥러닝을 이용한 유방조영술의 종양 분할

Breast cancer: One-stage automated detection, segmentation, and classification of digital mammograms using UNet model based-semantic segmentation

Breast cancer is one of the most common cancers in women. It is known as asymptomatic cancer that presents no noticeable symptoms in its early stage. Thus, regular mammography screening helps detect breast cancer early before it spreads to nearby normal tissues or to other organs. Hence, an automated system for early detection of breast cancer in mammograms will assist radiologists in their diagnosis. The rapid advance of deep learning models has considerably arisen much interest in their application to medical imaging problems, particularly for breast cancer diagnosis. In this paper, we propose an end-to-end UNet model for the detection, segmentation, and classification of breast masses in one-stage. The proposed model is evaluated in terms of its performance in segmenting and classifying breast masses using the publicly available datasets, DDSM and INbreast. The mass segmentation and classification evaluation results give an intersection over union (IOU) score of 90.50% and an area under the curve of 99.88% for both DDSM and INbreast datasets. The proposed model scores a dice coefficient of 99.20% and 99.56% and a weighted F1-score of 99.19% and 99.65% for the DDSM and INbreast datasets, respectively. The results show that the proposed model outperforms the existing methodologies.

Applying a Random Projection Algorithm to Optimize Machine Learning Model for Breast Lesion Classification.

Since computer-aided diagnosis (CAD) schemes of medical images usually computes large number of image features, which creates a challenge of how to identify a small and optimal feature vector to build robust machine learning models, the objective of this study is to investigate feasibility of applying a random projection algorithm (RPA) to build an optimal feature vector from the initially CAD-generated large feature pool and improve performance of machine learning model. We assemble a retrospective dataset involving 1,487 cases of mammograms in which 644 cases have confirmed malignant mass lesions and 843 have benign lesions. A CAD scheme is first applied to segment mass regions and initially compute 181 features. Then, support vector machine (SVM) models embedded with several feature dimensionality reduction methods are built to predict likelihood of lesions being malignant. All SVM models are trained and tested using a leave-one-case-out cross-validation method. SVM generates a likelihood score of each segmented mass region depicting on one-view mammogram. By fusion of two scores of the same mass depicting on two-view mammograms, a case-based likelihood score is also evaluated. Comparing with the principle component analyses, nonnegative matrix factorization, and Chi-squared methods, SVM embedded with RPA yielded a significantly higher case-based lesion classification performance with the area under ROC curve of 0.84 ± 0.01 (p<0.02). The study demonstrates that RPA is a promising method to generate optimal feature vectors and improve SVM performance. This study presents a new method to develop CAD schemes with significantly higher and robust performance.

Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network.

To develop a 3D U-Net-based deep learning model for automated segmentation of kidney and renal mass, and detection of renal mass in corticomedullary phase of computed tomography urography (CTU). Data on 882 kidneys obtained from CTU data of 441 patients with renal mass were used to learn and evaluate the deep learning model. The CTU data of 35 patients with small renal tumors (diameter ≤ 1.5 cm) were used for additional testing. The ground truth data for the kidney, renal tumor, and cyst were manually annotated on corticomedullary phase images of CTU. The proposed segmentation model for kidney and renal mass was constructed based on a 3D U-Net. The segmentation accuracy was evaluated through the Dice similarity coefficient (DSC). The volume of the maximum 3D volume of interest of renal tumor and cyst in the predicted segmentation by the model was used as an identification indicator, while the detection performance of the model was evaluated by the area under the receiver operation characteristic curve. The proposed model showed a high accuracy in segmentation of kidney and renal tumor, with average DSC of 0.973 and 0.844, respectively. It performed moderately in the renal cyst segmentation, with an average DSC of 0.536 in the test set. Also, this model showed good performance in detecting renal tumor and cyst. The proposed automated segmentation and detection model based on 3D U-Net shows promising results for the segmentation of kidney and renal tumor, and the detection of renal tumor and cyst. • The segmentation model based on 3D U-Net showed high accuracy in segmentation of kidney and renal neoplasm, and good detection performance of renal neoplasm and cyst in corticomedullary phase of CTU. • The segmentation model based on 3D U-Net is a fully automated aided diagnostic tool that could be used to reduce the workload of radiologists and improve the accuracy of diagnosis. • The segmentation model based on 3D U-Net would be helpful to provide quantitative information for diagnosis, treatment, surgical planning, etc.

SAP-cGAN: Adversarial learning for breast mass segmentation in digital mammogram based on superpixel average pooling.

Breast mass segmentation is a prerequisite step in the use of computer-aided tools designed for breast cancer diagnosis and treatment planning. However, mass segmentation remains challenging due to the low contrast, irregular shapes, and fuzzy boundaries of masses. In this work, we propose a mammography mass segmentation model for improving segmentation performance. We propose a mammography mass segmentation model called SAP-cGAN, which is based on an improved conditional generative adversarial network (cGAN). We introduce a superpixel average pooling layer into the cGAN decoder, which utilizes superpixels as a pooling layout to improve boundary segmentation. In addition, we adopt a multiscale input strategy to enable the network to learn scale-invariant features with increased robustness. The performance of the model is evaluated with two public datasets: CBIS-DDSM and INbreast. Moreover, ablation analysis is conducted to evaluate further the individual contribution of each block to the performance of the network. Dice and Jaccard scores of 93.37% and 87.57%, respectively, are obtained for the CBIS-DDSM dataset. The Dice and Jaccard scores for the INbreast dataset are 91.54% and 84.40%, respectively. These results indicate that our proposed model outperforms current state-of-the-art breast mass segmentation methods. The superpixel average pooling layer and multiscale input strategy has improved the Dice and Jaccard scores of the original cGAN by 7.8% and 12.79%, respectively. Adversarial learning with the addition of a superpixel average pooling layer and multiscale input strategy can encourage the Generator network to generate masks with increased realism and improve breast mass segmentation performance through the minimax game between the Generator network and Discriminator network.

Integrating segmentation information into CNN for breast cancer diagnosis of mammographic masses

Background and ObjectivesSegmentation of mammographic lesions has been proven to be a valuable source of information, as it can assist in both extracting shape-related features and providing accurate localization of the lesion. In this work, a methodology is proposed for integrating mammographic mass segmentation information into a convolutional neural network (CNN), aiming to improve the diagnosis of breast cancer in mammograms. MethodsThe proposed methodology involves modification of each convolutional layer of a CNN, so that information of not only the input image but also the corresponding segmentation map is considered. Furthermore, a new loss function is introduced, which adds an extra term to the standard cross-entropy, aiming to steer the attention of the network to the mass region, penalizing strong feature activations based on their location. The segmentation maps are acquired either from the provided ground-truth or from an automatic segmentation stage. ResultsPerformance evaluation in diagnosis is conducted on two mammographic mass datasets, namely DDSM-400 and CBIS-DDSM, with differences in quality of the corresponding ground-truth segmentation maps. The proposed method achieves diagnosis performance of 0.898 and 0.862 in terms AUC when using ground-truth segmentation maps and a maximum of 0.880 and 0.860 when a U-Net-based automatic segmentation stage is employed, for DDSM-400 and CBIS-DDSM, respectively. ConclusionsThe experimental results demonstrate that integrating segmentation information into a CNN leads to improved performance in breast cancer diagnosis of mammographic masses.

Mechanical possessions of jute/sisal natural fiber mixture amalgams

Over the last epochs, the use of conventional fibre as a way to strengthen polyamide has dramatically improved. Current research efforts to make use of conventional fibre jute /sisal have been developed. The goal of this paper is to explain how a new mixture of traditional fibre amalgams was invented and characterized. Strengthens the jute/sisal fibres with polyester mastic in the matrix employing a hand-designed method. Traditional fibres are obtained through manual collection and testing. Mixed amalgam was completed using jute/sisal fibres 0/50, 10/40, 25/25, 40/10, 50/0 mass segment ratios the maximum fibre mass segment was a fixed 0.5 mass segment. The flexural possessions and tensile possessions are calculated using mixture amalgam specimens. The results show that the application of jute fibre to sisal /polyester amalgams has better mechanical possessions by up to 50% of the mass segment.

ПОТРЕБИТЕЛЬСКОЕ ПОВЕДЕНИЕ НА АРТ-РЫНКЕ. ОСОБЕННОСТИ ФОРМИРОВАНИЯ И ПРОБЛЕМЫ ИССЛЕДОВАНИЯ

In the article the segmentation of the art market is presented according to various criteria: by mass audience, by periods of creation of works of art, by price categories. The necessity of a typology of the audience in the mass segment is substantiated. The practice of audience typology is considered. It is shown that the different nature of needs for goods and services, on the one hand, and for art objects, on the other, makes it necessary to adapt the classical economic methodology for the analysis of the art market and diagnosis of consumer behavior.

Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms

Breast cancer causes approximately 684,996 deaths worldwide, making it the leading cause of female cancer mortality. However, these figures can be reduced with early diagnosis through mammographic imaging, allowing for the timely and effective treatment of this disease. To establish the best tools for contributing to the automatic diagnosis of breast cancer, different deep learning (DL) architectures were compared in terms of breast lesion segmentation, lesion type classification, and degree of suspicion of malignancy tests. The tasks were completed with state-of-the-art architectures and backbones. Initially, during segmentation, the base UNet, Visual Geometry Group 19 (VGG19), InceptionResNetV2, EfficientNet, MobileNetv2, ResNet, ResNeXt, MultiResUNet, linkNet-VGG19, DenseNet, SEResNet and SeResNeXt architectures were compared, where “Res” denotes a residual network. In addition, training was performed with 5 of the most advanced loss functions and validated by the Dice coefficient, sensitivity, and specificity. The proposed models achieved Dice values above 90%, with the EfficientNet architecture achieving 94.75% and 99% accuracy on the two tasks. Subsequently, classification was addressed with the ResNet50V2, VGG19, InceptionResNetV2, DenseNet121, InceptionV3, Xception and EfficientNetB7 networks. The proposed models achieved 96.97% and 97.73% accuracy through the VGG19 and ResNet50V2 networks on the lesion classification and degree of suspicion tasks, respectively. All three tasks were addressed with open-access databases, including the Digital Database for Screening Mammography (DDSM), the Mammographic Image Analysis Society (MIAS) database, and INbreast.

Body composition of women with and without dynapenia defined by different cut-off points

ABSTRACT Objective To compare body composition of postmenopausal women with and without dynapenia, defined by different cut-off points. Methods Body composition was assessed by electrical bioimpedance and the nutritional status by the body mass index. Dynapenia was diagnosed according to handgrip strength, using the following cut-off points: handgrip strength &lt;16kgf and &lt;20 kgf. Results A total of 171 women (50 to 92 years of age) participated in the investigation. The mean age of non-dynapenic and dynapenic women (handgrip strength &lt;20kgf) was 69.4±8.2 and 74.5±8.2 years, respectively. The mean age of women with dynapenia (handgrip strength &lt;16kgf) was 75.0±10.1 years and non-dynapenic women, 71.1±8.2 years. It was found that dynapenic women, with handgrip strength &lt;20 and &lt;16kgf, had an average of 2.38 and 2.47kg less muscle mass respectively, when compared to non-dynapenic women (p&lt;0.05). However, there was no difference in muscle mass between the different dynapenic groups. Non-dynapenic women (handgrip strength ≥20kgf) had more total (3.55kg) and central fat (1.47kg) (p&lt;0.05). Conclusion Dynapenic women, diagnosed considering both cutoff points, had less total and segmental muscle mass compared to non-dynapenic women. In addition, dynapenic women with handgrip strength &lt;20kgf had lower total and trunk adiposity.

Active contours for overlapping cervical cell segmentation

The nuclei and cytoplasm segmentation of cervical cells is a well studied problem. However, the current segmentation algorithms are not robust to clinical practice due to the high computational cost or because they cannot accurately segment cells with high overlapping. In this paper, we propose a method that is capable of segmenting both cytoplasm and nucleus of each individual cell in a clump of overlapping cells. The proposed method consists of three steps: 1) cellular mass segmentation; 2) nucleus segmentation; 3) cytoplasm identification based on an active contour method. We carried out experiments on both synthetic and real cell images. The performance evaluation of the proposed method showed that it was less sensitive to the increase in the number of cells per image and the overlapping ratio against two other existing algorithms. It has also achieved a promising low processing time and, hence, it has the potential to support expert systems for cervical cell recognition.

Unsupervised Method to Localize Masses in Mammograms

Breast cancer is one of the most common and prevalent type of cancer that mainly affects the women population. chances of effective treatment increases with early diagnosis. Mammography is considered one of the effective and proven techniques for early diagnosis of breast cancer. Tissues around masses look identical in mammogram, which makes automatic detection process a very challenging task. They are indistinguishable from the surrounding parenchyma. In this paper, we present an efficient and automated approach to segment masses in mammograms. The proposed method uses hierarchical clustering to isolate the salient area, and then features are extracted to reject false detection. We applied our method on two popular publicly available datasets (mini-MIAS and DDSM). A total of 56 images from mini-mias database, and 76 images from DDSM were randomly selected. Results are explained in-terms of ROC (Receiver Operating Characteristics) curves and compared with the other techniques. Experimental results demonstrate the efficiency and advantages of the proposed system in automatic mass identification in mammograms.

Uncertainty Aware Temporal-Ensembling Model for Semi-Supervised ABUS Mass Segmentation.

Accurate breast mass segmentation of automated breast ultrasound (ABUS) images plays a crucial role in 3D breast reconstruction which can assist radiologists in surgery planning. Although the convolutional neural network has great potential for breast mass segmentation due to the remarkable progress of deep learning, the lack of annotated data limits the performance of deep CNNs. In this article, we present an uncertainty aware temporal ensembling (UATE) model for semi-supervised ABUS mass segmentation. Specifically, a temporal ensembling segmentation (TEs) model is designed to segment breast mass using a few labeled images and a large number of unlabeled images. Considering the network output contains correct predictions and unreliable predictions, equally treating each prediction in pseudo label update and loss calculation may degrade the network performance. To alleviate this problem, the uncertainty map is estimated for each image. Then an adaptive ensembling momentum map and an uncertainty aware unsupervised loss are designed and integrated with TEs model. The effectiveness of the proposed UATE model is mainly verified on an ABUS dataset of 107 patients with 170 volumes, including 13382 2D labeled slices. The Jaccard index (JI), Dice similarity coefficient (DSC), pixel-wise accuracy (AC) and Hausdorff distance (HD) of the proposed method on testing set are 63.65%, 74.25%, 99.21% and 3.81mm respectively. Experimental results demonstrate that our semi-supervised method outperforms the fully supervised method, and get a promising result compared with existing semi-supervised methods.

Taxation of personal income in the context of issues of social fairness

The subject. The leading position of the personal income tax in most countries is due to a number of circumstances. First, it is a personal tax, the object of which is the income actually received by the payer, and not the estimated average income that could be received in specific economic conditions. Second, income tax allows to maximize the implementation of the basic principles of taxation - universality and uniformity. In recent decades, national regimes of personal income taxation regimes have been actively developed both in foreign countries and in Russia. Purpose of the study. The article shows the results of analysis of the framework of personal income taxation in the Russian Federation in the context of the principle of the social fairness. Dealing with selected provisions of the national legislation of European countries and Russia the article shows that elements of progressive taxation can be applied only in particular aspects. The proposals of taxation of rich taxpayers are also brought into light. Methodology. The research was carried out with the application of the formally legal interpretation of legal acts as well as the comparative analysis of Russian and European legal literature. Structural and systemic methods are also the basis of the research, The main results. After studying the European experience of personal income taxation the authors come to the conclusion that some of the ideas described can be transferred to the Russian tax legislation, but this should be done with caution. It is not necessary to introduce a progressive tax system in its pure form in the Russian Federation, but it is worth considering options for switching to a dualistic system. The authors believe that the elements of borrowing foreign experience should be aimed rather at a fair distribution of benefits, for example, through rules that fix tax benefits. Conclusions. The following proposals can be formulated to improve the legal regulation of personal income taxation in the Russian Federation: the distinction between taxation of taxpayers with ultra-high incomes and those with minimal incomes should be based not on the income criterion, but on the expenditure criterion; to establish a non-taxable minimum in the amount of the minimum wage, which will ensure tax fairness for taxpayers with lower-average incomes; to review the criteria of taxation of luxury vehicles, raising the border separating the mass and premium segments of the Russian car market by at least two times - up to 6 million rubles. The best solution would be to abolish the vehicle tax and impose an increased excise tax on fuel and lubricants for personal transport.

Convolutional neural network for automated mass segmentation in mammography

BackgroundAutomatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed end-to-end convolutional neural network (CNN) based model extracts contextual information by combining low-level and high-level features. We trained the proposed model using huge publicly available databases, (CBIS-DDSM, BCDR-01, and INbreast), and a private database from the University of Connecticut Health Center (UCHC).ResultsWe compared the performance of the proposed model with those of the state-of-the-art DL models including the fully convolutional network (FCN), SegNet, Dilated-Net, original U-Net, and Faster R-CNN models and the conventional region growing (RG) method. The proposed Vanilla U-Net model outperforms the Faster R-CNN model significantly in terms of the runtime and the Intersection over Union metric (IOU). Training with digitized film-based and fully digitized MG images, the proposed Vanilla U-Net model achieves a mean test accuracy of 92.6%. The proposed model achieves a mean Dice coefficient index (DI) of 0.951 and a mean IOU of 0.909 that show how close the output segments are to the corresponding lesions in the ground truth maps. Data augmentation has been very effective in our experiments resulting in an increase in the mean DI and the mean IOU from 0.922 to 0.951 and 0.856 to 0.909, respectively.ConclusionsThe proposed Vanilla U-Net based model can be used for precise segmentation of masses in MG images. This is because the segmentation process incorporates more multi-scale spatial context, and captures more local and global context to predict a precise pixel-wise segmentation map of an input full MG image. These detected maps can help radiologists in differentiating benign and malignant lesions depend on the lesion shapes. We show that using transfer learning, introducing augmentation, and modifying the architecture of the original model results in better performance in terms of the mean accuracy, the mean DI, and the mean IOU in detecting mass lesion compared to the other DL and the conventional models.

PSIX-7 Grazing toxic endophyte-infected tall fescue does not influence pancreatic or small intestinal digestive enzyme activities in beef steers

Abstract The objective of this experiment was to determine the influence of toxic endophyte-infected tall fescue exposure on pancreatic and small intestinal digestive enzyme activities in steers. Twelve fescue-naive beef steers [693 ± 42.7 kg of body weight (BW)] were stratified by BW and randomly assigned within BW ranks to graze non-toxic endophyte-infected tall fescue (NTE, n = 6; 0.01 ± 0.009 mg ergovaline + ergovalinine/kg) or toxic endophyte-infected tall fescue (TE, n = 6; 0.50 ± 0.048 mg ergovaline + ergovalinine/kg) pastures for 84 d. After the grazing period, steers were weighed and then slaughtered in three groups for tissue collection. A 1-m segment of the small intestine was collected 5-m distal to the pyloric sphincter. Subsamples of the small intestinal mucosa and pancreas were collected, homogenized in saline, and assayed for protein concentration. Pancreatic and small intestinal digestive enzyme activities were assayed. Data were analyzed using the GLM procedure of SAS as a randomized complete block design for effects of treatment and slaughter group (blocking factor). Steers grazing NTE pastures had a greater (P &amp;lt; 0.001) average daily gain (0.282 vs -0.631 kg/d) and final BW at slaughter (739 vs 620 kg) than steers grazing TE pastures. Small intestinal segment mass and mucosal density (P ≥ 0.16) were not influenced by treatment. Grazing TE pasture did not influence (P ≥ 0.21) pancreatic or small intestinal protein concentrations. Pancreatic α-amylase and trypsin activity per gram pancreas (P ≥ 0.21) or per gram pancreatic protein (P ≥ 0.30) were not influenced by fescue treatment. Small intestinal glucoamylase, isomaltase, and maltase activities did not differ between steers grazing NTE or TE pastures when expressed per gram of intestinal tissue (P ≥ 0.47) or per gram of intestinal protein (P ≥ 0.60). These data indicate that decreased gains observed in cattle consuming TE are not a result of decreased pancreatic or small intestinal digestive enzyme activities.

Crossover-Net: Leveraging vertical-horizontal crossover relation for robust medical image segmentation

Accurate boundary segmentation in medical images is significant yet challenging due to large variation of shape, size and appearance within intra- and inter- samples. In this paper, we present a novel deep model termed as Crossover-Net for robust segmentation in medical images. The proposed model is inspired by an interesting observation – the features learned from horizontal and vertical directions can provide informative and complement contextual information to enhance discriminative ability between different tissues. Specifically, we first originally propose a cross-shaped patch, namely crossover-patch which consists of a pair of (orthogonal and overlapping) vertical and horizontal patches. Then, we develop our Crossover-Net to learn the vertical and horizontal crossover relation according to the proposed crossover-patches. To train our model end-to-end, we design a novel loss function to (1) impose the consistency on overlapping region of vertical and horizontal patches and (2) preserve the diversity on their non-overlapping regions. We have extensively evaluated our method on CT kidney tumor, MR cardiac, and X-ray breast mass segmentation tasks, showing promising results compared with the current state-of-the-art methods. The code is available at https://github.com/Qianyu1226/Crossover-Net.

Mass Detection and Segmentation in Digital Breast Tomosynthesis Using 3D-Mask Region-Based Convolutional Neural Network: A Comparative Analysis.

Digital breast tomosynthesis (DBT) is an emerging breast cancer screening and diagnostic modality that uses quasi-three-dimensional breast images to provide detailed assessments of the dense tissue within the breast. In this study, a framework of a 3D-Mask region-based convolutional neural network (3D-Mask RCNN) computer-aided diagnosis (CAD) system was developed for mass detection and segmentation with a comparative analysis of performance on patient subgroups with different clinicopathological characteristics. To this end, 364 samples of DBT data were used and separated into a training dataset (n = 201) and a testing dataset (n = 163). The detection and segmentation results were evaluated on the testing set and on subgroups of patients with different characteristics, including different age ranges, lesion sizes, histological types, lesion shapes and breast densities. The results of our 3D-Mask RCNN framework were compared with those of the 2D-Mask RCNN and Faster RCNN methods. For lesion-based mass detection, the sensitivity of 3D-Mask RCNN-based CAD was 90% with 0.8 false positives (FPs) per lesion, whereas the sensitivity of the 2D-Mask RCNN- and Faster RCNN-based CAD was 90% at 1.3 and 2.37 FPs/lesion, respectively. For breast-based mass detection, the 3D-Mask RCNN generated a sensitivity of 90% at 0.83 FPs/breast, and this framework is better than the 2D-Mask RCNN and Faster RCNN, which generated a sensitivity of 90% with 1.24 and 2.38 FPs/breast, respectively. Additionally, the 3D-Mask RCNN achieved significantly (p < 0.05) better performance than the 2D methods on subgroups of samples with characteristics of ages ranged from 40 to 49 years, malignant tumors, spiculate and irregular masses and dense breast, respectively. Lesion segmentation using the 3D-Mask RCNN achieved an average precision (AP) of 0.934 and a false negative rate (FNR) of 0.053, which are better than those achieved by the 2D methods. The results suggest that the 3D-Mask RCNN CAD framework has advantages over 2D-based mass detection on both the whole data and subgroups with different characteristics.