Track topics on Twitter Track topics that are important to you
We present a deep convolutional neural network for breast cancer screening exam classification, trained and evaluated on over 200,000 exams (over 1,000,000 images). Our network achieves an AUC of 0.895 in predicting the presence of cancer in the breast, when tested on the screening population. We attribute the high accuracy to a few technical advances. (i) Our network's novel two-stage architecture and training procedure, which allows us to use a high-capacity patch-level network to learn from pixel-level labels alongside a network learning from macroscopic breast-level labels. (ii) A custom ResNet-based network used as a building block of our model, whose balance of depth and width is optimized for high-resolution medical images. (iii) Pretraining the network on screening BI-RADS classification, a related task with more noisy labels. (iv) Combining multiple input views in an optimal way among a number of possible choices. To validate our model, we conducted a reader study with 14 readers, each reading 720 screening mammogram exams, and show that our model is as accurate as experienced radiologists when presented with the same data. We also show that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of our neural network, is more accurate than either of the two separately. To further understand our results, we conduct a thorough analysis of our network's performance on different subpopulations of the screening population, the model's design, training procedure, errors, and properties of its internal representations. Our best models are publicly available at https://github.com/nyukat/breastcancerclassifier.
This article was published in the following journal.
Name: IEEE transactions on medical imaging
The usefulness of 3D deep learning-based classification of breast cancer and malignancy localization from MRI has been reported. This work can potentially be very useful in the clinical domain and aid...
Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can ...
The authors evaluate whether supplemental training for radiologists improves their breast screening performance and how this is measured.
Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in diag...
Sensory neuroscience aims to build models that predict neural responses and perceptual behaviors, and that provide insight into the principles that give rise to them. For decades, artificial neural ne...
We aim to experiment and implement various deep learning architectures in order to achieve human-level accuracy in Computer-aided diagnosis (CAD) systems. In particular, we are interested ...
The study is about the role of cellular neural networks-genetic algorithm in the diagnosis of periprosthetic hip infections. A retrospective case series of septic and aseptic loosening of ...
Recently, artificial intelligence (AI) assisted image recognition has made remarkable breakthroughs in various medical fields with the developing of deep learning and conventional neural n...
This phase II trial studies how well deep inspiratory breath hold or prone breast radiation therapy works in reducing cardiac dose in patients with breast cancer or ductal carcinoma in sit...
The brain networks controlling movement are complex, involving multiple areas of the brain. Some neurological diseases, like Parkinson's disease, cause abnormalities in the brain networks....
Abnormal accumulation of lymph in the arm, shoulder and breast area associated with surgical or radiation breast cancer treatments (e.g., MASTECTOMY).
Metastatic breast cancer characterized by EDEMA and ERYTHEMA of the affected breast due to LYMPHATIC METASTASIS and eventual obstruction of LYMPHATIC VESSELS by the cancer cells.
A infiltrating (invasive) breast cancer, relatively uncommon, accounting for only 5%-10% of breast tumors in most series. It is often an area of ill-defined thickening in the breast, in contrast to the dominant lump characteristic of ductal carcinoma. It is typically composed of small cells in a linear arrangement with a tendency to grow around ducts and lobules. There is likelihood of axillary nodal involvement with metastasis to meningeal and serosal surfaces. (DeVita Jr et al., Cancer: Principles & Practice of Oncology, 3d ed, p1205)
A deoxycytidine derivative and fluorouracil PRODRUG that is used as an ANTINEOPLASTIC ANTIMETABOLITE in the treatment of COLON CANCER; BREAST CANCER and GASTRIC CANCER.
Carbohydrate antigen elevated in patients with tumors of the breast, ovary, lung, and prostate as well as other disorders. The mucin is expressed normally by most glandular epithelia but shows particularly increased expression in the breast at lactation and in malignancy. It is thus an established serum marker for breast cancer.
Bladder Cancer Brain Cancer Breast Cancer Cancer Cervical Cancer Colorectal Head & Neck Cancers Hodgkin Lymphoma Leukemia Lung Cancer Melanoma Myeloma Ovarian Cancer Pancreatic Cancer ...
Women's Health - key topics include breast cancer, pregnancy, menopause, stroke Follow and track Women's Health News on BioPortfolio: Women's Health News RSS Women'...
Cancer is not just one disease but many diseases. There are more than 100 different types of cancer. Most cancers are named for the organ or type of cell in which they start - for example, cancer that begins in the colon is called colon cancer; cancer th...