Using convolutional neural networks for the classification of breast cancer images
Eric Bonnet
备注：
13 pages, 4 figures, 4 tables; corrected typos; added an additional breast carcinoma image dataset; added a total of twelve CNN models tested. Additional testing for transfer learning and complexity of the models
An important part of breast cancer staging is the assessment of the sentinel axillary node for early signs of tumor spreading. However, this assessment by pathologists is not always easy and retrospective surveys often requalify the status of a high proportion of sentinel nodes. Convolutional Neural Networks (CNNs) are a class of deep learning algorithms that have shown excellent performances in the most challenging visual classification tasks, with numerous applications in medical imaging. In this study I compare twelve different CNNs and different hardware acceleration devices for the detection of breast cancer from microscopic images of breast cancer tissue. Convolutional models are trained and tested on two public datasets. The first one is composed of more than 300,000 images of sentinel lymph node tissue from breast cancer patients, while the second one has more than 220,000 images from inductive breast carcinoma tissue, one of the most common forms of breast cancer. Four different hardware acceleration cards were used, with an off-the-shelf deep learning framework. The impact of transfer learning and hyperparameters fine-tuning are tested. Hardware acceleration device performance can improve training time by a factor of five to twelve, depending on the model used. On the other hand, increasing convolutional depth will augment the training time by a factor of four to six times, depending on the acceleration device used. Increasing the depth and the complexity of the model generally improves performance, but the relationship is not linear and also depends on the architecture of the model. The performance of transfer learning is always worse compared to a complete retraining of the model. Fine-tuning the hyperparameters of the model improves the results, with the best model showing a performance comparable to state-of-the-art models.
University of Kentucky（肯塔基大学）；Miami University（迈阿密大学）
Breast cancer is the malignant tumor that causes the highest number of cancer deaths in females. Digital mammograms (DM or 2D mammogram) and digital breast tomosynthesis (DBT or 3D mammogram) are the two types of mammography imagery that are used in clinical practice for breast cancer detection and diagnosis. Radiologists usually read both imaging modalities in combination; however, existing computer-aided diagnosis tools are designed using only one imaging modality. Inspired by clinical practice, we propose an innovative convolutional neural network (CNN) architecture for breast cancer classi…
Cancer is one of the most dangerous diseases to humans, and yet no permanent cure has been developed for it. Breast cancer is one of the most common cancer types. According to the National Breast Cancer foundation, in 2020 alone, more than 276,000 new cases of invasive breast cancer and more than 48,000 non-invasive cases were diagnosed in the US. To put these figures in perspective, 64% of these cases are diagnosed early in the disease's cycle, giving patients a 99% chance of survival. Artificial intelligence and machine learning have been used effectively in detection and treatment of severa…
Characterization of breast parenchyma on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging task owing to the complexity of underlying tissue structures. Current quantitative approaches, including radiomics and deep learning models, do not explicitly capture the complex and subtle parenchymal structures, such as fibroglandular tissue. In this paper, we propose a novel method to direct a neural network's attention to a dedicated set of voxels surrounding biologically relevant tissue structures. By extracting multi-dimensional topological structures with high salienc…
Experts' cognition-driven safe noisy labels learning for precise segmentation of residual tumor in breast cancer
Institute of Clinical Pathology, West China Hospital, Sichuan University（四川大学华西医院临床病理研究所）；Zhongjiu Flash Medical Technology Co., Ltd.（中久闪医科技有限公司）；McGill University（麦吉尔大学）
In order to investigate the breast cancer prediction problem on the aging population with the grades of DCIS, we conduct a tree augmented naive Bayesian network experiment trained and tested on a large clinical dataset including consecutive diagnostic mammography examinations, consequent biopsy outcomes and related cancer registry records in the population of women across all ages. The aggregated results of our ten-fold cross validation method recommend a biopsy threshold higher than 2% for the aging population.
tBregs are a newly discovered subcategory of B regulatory cells, which are generated by breast cancer, resulting in the increase of Tregs and therefore in the death of NK cells. In this study, we use a mathematical and computational approach to investigate the complex interactions between the aforementioned cells as well as CD8$^+$ T cells, CD4$^+$ T cells and B cells. Furthermore, we use data fitting to prove that the functional response regarding the lysis of breast cancer cells by NK cells has a ratio-dependent form. Additionally, we include in our model the concentration of rituximab - a m…
University of Toronto（多伦多大学）；National Cancer Research Centre（国家癌症研究中心）；Institute for Oncology and Radiology（肿瘤与放射学研究所）
Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this paper, we propose a practical and self-interpretable invasive cancer diagnosis solution. With minimum annotation information, the proposed method mines contrast patterns between normal and malignant images in unsupervised manner and generates a probability map of abnormalities to verify its reasoning. Particularly, a fully convolutional autoencoder is used to learn the dominant structural patter…
Driver event discovery is a crucial demand for breast cancer diagnosis and therapy. Especially, discovering subtype-specificity of drivers can prompt the personalized biomarker discovery and precision treatment of cancer patients. still, most of the existing computational driver discovery studies mainly exploit the information from DNA aberrations and gene interactions. Notably, cancer driver events would occur due to not only DNA aberrations but also RNA alternations, but integrating multi-type aberrations from both DNA and RNA is still a challenging task for breast cancer drivers. On the one…
Lovely Professional University（洛弗利专业大学）；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Maharaja Agrasen Institute of Technology（马哈拉贾·阿格拉森技术学院）；University of Economics Ho Chi Minh City（胡志明市经济大学）
Breast cancer is a common cancer for women. Early detection of breast cancer can considerably increase the survival rate of women. This paper mainly focuses on transfer learning process to detect breast cancer. Modified VGG (MVGG), residual network, mobile network is proposed and implemented in this paper. DDSM dataset is used in this paper. Experimental results show that our proposed hybrid transfers learning model (Fusion of MVGG16 and ImageNet) provides an accuracy of 88.3% where the number of epoch is 15. On the other hand, only modified VGG 16 architecture (MVGG 16) provides an accuracy 8…
Marshall University（马歇尔大学）；Troy University（特洛伊大学）；Virginia State University（弗吉尼亚州立大学）
Detecting cancer manually in whole slide images requires significant time and effort on the laborious process. Recent advances in whole slide image analysis have stimulated the growth and development of machine learning-based approaches that improve the efficiency and effectiveness in the diagnosis of cancer diseases. In this paper, we propose an unsupervised learning approach for detecting cancer in breast invasive carcinoma (BRCA) whole slide images. The proposed method is fully automated and does not require human involvement during the unsupervised learning procedure. We demonstrate the ef…
Cancer has become one of the most widespread diseases in the world. Specifically, breast cancer is diagnosed more often than any other type of cancer. However, breast cancer patients and their individual tumors are often unique. Identifying the underlying genetic phenotype can lead to precision (personalized) medicine. Tailoring medical treatment strategies to best fit the needs of individual patients can dramatically improve their health. Such an approach requires sufficient knowledge of the patients and the diseases, which is currently unavailable to practitioners. This study focuses on brea…
Breast cancer is the most common type of cancer observed in women. Communication with the tumor microenvironment allows invading breast cancer cells, such as triple negative breast cancer cells, to adapt to specific substrates. The substrate topography modulates the cellular behavior, among other factors. A number of different materials and micro/nanofabrication techniques have been employed to develop substrates for cell culturing. Silicon-based substrates present a lot of advantages as they are amenable to a wide range of processing techniques and they permit rigorous control over the surfac…
University of Delhi（德里大学）；All India Institute of Medical Sciences（全印医学科学学院）；Hans Raj College（汉斯拉吉学院）
Breast cancer has long been a prominent cause of mortality among women. Diagnosis, therapy, and prognosis are now possible, thanks to the availability of RNA sequencing tools capable of recording gene expression data. Molecular subtyping being closely related to devising clinical strategy and prognosis, this paper focuses on the use of gene expression data for the classification of breast cancer into four subtypes, namely, Basal, Her2, LumA, and LumB. In stage 1, we suggested a deep learning-based model that uses an autoencoder to reduce dimensionality. The size of the feature set is reduced f…
Due to the heavy burden on medical institutes and computer-aided image diagnostics (CAD) have been gaining importance in diagnostic medicine to aid the medical staff to attain better service for the patients. Breast cancer is a fatal disease that can be treated successfully if it is detected early. Quantum neural network (QNN) has been introduced by many researchers around the world and presented recently by research corporations such as Microsoft, Google, and IBM. In this paper, we are trying to answer the question of: whether can the QNN be an effective method for mass-scale early breast can…
