http://diposit.ub.edu/dspace/bitstream/2445/176697/1/708326.pdf

Deep learning for mass detection in Full Field Digital Mammograms.

Transfer learning for medical images analyses: A survey

Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review

Cancer is a fatal disease caused due to the undesirable spread of cells. Breast carcinoma is the most invasive tumors and is the main reason for cancer deaths in females. Therefore, early diagnosis and prognosis have become necessary to increase survivability and reduce death rates in the long run. New artificial intelligence technologies are assisting radiologists in medical image scrutiny, thereby improving cancer patients’ status. This survey enrolls peer-reviewed, newly developed computer-aided diagnosis (CAD) systems implementing machine learning (ML) and deep learning (DL) techniques for diagnosing breast carcinoma, compares them with previously established methods, and provides technical details with the pros and cons for each model. We also discuss some open issues, research gaps, and future research directions for the advanced CAD models in medical image analysis. Over the past decade, machine learning and deep learning have emerged as a subfield of artificial intelligence (AI), whose healthcare industry applications have provided excellent results with reduced cost and improved efficiency. This survey analyzes different classifiers of machine learning and deep learning approaches for breast cancer diagnosis. Results from previous studies proved that deep learning outperforms conventional machine learning for diagnosing breast carcinoma when the dataset is broad. Research gaps from the recent studies depict that practical and scientific research is an urgent necessity for improving healthcare in the long run.

Survey on Machine Learning and Deep Learning Applications in Breast Cancer Diagnosis

Breast segmentation and mass detection in medical images are important for diagnosis and treatment follow-up. Automation of these challenging tasks can assist radiologists by reducing the high manual workload of breast cancer analysis. In this paper, deep convolutional neural networks (DCNN) were employed for breast segmentation and mass detection in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). First, the region of the breasts was segmented from the remaining body parts by building a fully convolutional neural network based on U-Net++. Using the method of deep learning to extract the target area can help to reduce the interference external to the breast. Second, a faster region with convolutional neural network (Faster RCNN) was used for mass detection on segmented breast images. The dataset of DCE-MRI used in this study was obtained from 75 patients, and a 5-fold cross validation method was adopted. The statistical analysis of breast region segmentation was carried out by computing the Dice similarity coefficient (DSC), Jaccard coefficient, and segmentation sensitivity. For validation of breast mass detection, the sensitivity with the number of false positives per case was computed and analyzed. The Dice and Jaccard coefficients and the segmentation sensitivity value for breast region segmentation were 0.951, 0.908, and 0.948, respectively, which were better than those of the original U-Net algorithm, and the average sensitivity for mass detection achieved 0.874 with 3.4 false positives per case.

/pdf/deep-convolutional-neural-networks-based-automatic-breast-2101ylj9kv.pdf

Deep Convolutional Neural Networks-Based Automatic Breast Segmentation and Mass Detection in DCE-MRI.

Computer-aided detection of mass in digital breast tomosynthesis using a faster region-based convolutional neural network

Human epidermal growth factor receptor-2 (HER2) plays an important role in treatment strategy and prognosis determination in breast cancers. However, breast cancers are characterized by considerable heterogeneity both between and within tumors, which is a key impediment to accurately determine HER2 status for radiomic analysis. To this end, tumor heterogeneity was evaluated by unsupervised decomposition method on breast magnetic resonance imaging (MRI), in which three tumor subregions were generated terms as Input, Fast and Slow. This tumor decomposition was performed by a convex analysis of mixtures (CAM) method, which was designed according to analysis of contrast-enhancement patterns. The study retrospectively investigated 181 patients who underwent dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) examination. Among them, 124 were HER2-negative and 57 were HER2-positive status. Imaging features of texture and histogram were computed in each subregion. Multivariate logistic regression classifiers were trained and validated with leave-one-out cross-validation (LOOCV) method. An area under a receiver operating characteristic curve (AUC) was calculated to assess performance of the classifier. The classifier based on features from Fast subregion obtained an AUC of 0.802 ± 0.067 and was significantly (P = 0.0113) outperformed the classifier based on features from the whole tumors. When the predicted values from the respective classifiers were fused by weighted average, the AUC significantly increased to 0.820 ± 0.063 (P = 0.0011). The results indicate that analysis of intratumor heterogeneity through decomposing method of DCE-MRI has the potential to serve as a marker for predicting HER2 status.

DCE-MRI based analysis of intratumor heterogeneity by decomposing method for prediction of HER2 status in breast cancer

Breast cancer, with its high heterogeneity, is the most common malignancies in women. In addition to the entire tumor itself, tumor microenvironment could also play a fundamental role on the occurrence and development of tumors. The aim of this study is to investigate the role of heterogeneity within a tumor and the surrounding stromal tissue in predicting the Ki-67 proliferation status of oestrogen receptor (ER)-positive breast cancer patients. To this end, we collected 62 patients imaged with preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for analysis. The tumor and the peritumoral stromal tissue were segmented into 8 shells with 5 mm width outside of tumor. The mean enhancement rate in the stromal shells showed a decreasing order if their distances to the tumor increase. Statistical and texture features were extracted from the tumor and the surrounding stromal bands, and multivariate logistic regression classifiers were trained and tested based on these features. An area under the receiver operating characteristic curve (AUC) were calculated to evaluate performance of the classifiers. Furthermore, the statistical model using features extracted from boundary shell next to the tumor produced AUC of 0.796±0.076, which is better than that using features from the other subregions. Furthermore, the prediction model using 7 features from the entire tumor produced an AUC value of 0.855±0.065. The classifier based on 9 selected features extracted from peritumoral stromal region showed an AUC value of 0.870±0.050. Finally, after fusion of the predictive model obtained from entire tumor and the peritumoral stromal regions, the classifier performance was significantly improved with AUC of 0.920. The results indicated that heterogeneity in tumor boundary and peritumoral stromal region could be valuable in predicting the indicator associated with prognosis.

Yuanzhe Li

Papers

Computer-aided detection of mass in digital breast tomosynthesis using a faster region-based convolutional neural network

DCE-MRI based analysis of intratumor heterogeneity by decomposing method for prediction of HER2 status in breast cancer

Analysis of DCE-MRI features in tumor and the surrounding stroma for prediction of Ki-67 proliferation status in breast cancer