Prediction of reader estimates of mammographic density using convolutional neural networks.
Georgia V. Ionescu,Martin Fergie,Michael Berks,Elaine F. Harkness,Johan Hulleman,Adam R. Brentnall,Jack Cuzick,D. Gareth Evans,Susan M. Astley +8 more
TLDR
This work has built convolutional neural networks (CNN) to predict density VAS scores from full-field digital mammograms and shows promising results for cancer risk prediction and is comparable with human performance.Abstract:
Mammographic density is an important risk factor for breast cancer. In recent research, percentage density assessed visually using visual analogue scales (VAS) showed stronger risk prediction than existing automated density measures, suggesting readers may recognize relevant image features not yet captured by hand-crafted algorithms. With deep learning, it may be possible to encapsulate this knowledge in an automatic method. We have built convolutional neural networks (CNN) to predict density VAS scores from full-field digital mammograms. The CNNs are trained using whole-image mammograms, each labeled with the average VAS score of two independent readers. Each CNN learns a mapping between mammographic appearance and VAS score so that at test time, they can predict VAS score for an unseen image. Networks were trained using 67,520 mammographic images from 16,968 women and for model selection we used a dataset of 73,128 images. Two case-control sets of contralateral mammograms of screen detected cancers and prior images of women with cancers detected subsequently, matched to controls on age, menopausal status, parity, HRT and BMI, were used for evaluating performance on breast cancer prediction. In the case-control sets, odd ratios of cancer in the highest versus lowest quintile of percentage density were 2.49 (95% CI: 1.59 to 3.96) for screen-detected cancers and 4.16 (2.53 to 6.82) for priors, with matched concordance indices of 0.587 (0.542 to 0.627) and 0.616 (0.578 to 0.655), respectively. There was no significant difference between reader VAS and predicted VAS for the prior test set (likelihood ratio chi square, p = 0.134). Our fully automated method shows promising results for cancer risk prediction and is comparable with human performance.read more
Citations
More filters
Journal ArticleDOI
Mammographic density and the risk and detection of breast cancer
TL;DR: The conclusion of the current study was that the frequency of screening might be dependent on breast density and in such cases diagnostic techniques such as “digital mammography, ultra sonography and magnetic resonance imaging” may prove to be better detection tools.
Mammographic density-a review on the current understanding of its association with breast cancer
Cecilia W. Huo,G. L. Chew,Kara L. Britt,Wendy V. Ingman,Henderson,J. L. Hopper,Erik W. Thompson +6 more
TL;DR: Significant inroads are being made into the understanding of MD, which may lead to benefits in clinical screening, assessment and treatment strategies, and the biological and genetic pathways that determine and perhaps modulate MD remain largely unresolved.
Journal ArticleDOI
Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review
TL;DR: Although the DL methods show promising improvements in breast cancer diagnosis, there are still issues of data scarcity and computational cost, which have been overcome to a significant extent by applying data augmentation and improved computational power of DL algorithms.
Journal ArticleDOI
Medical image analysis based on deep learning approach.
Muralikrishna Puttagunta,S. Ravi +1 more
TL;DR: Deep Learning Approach (DLA) has been widely used in medical imaging to detect the presence or absence of the disease as discussed by the authors, and most of the implementations concentrate on the X-ray images, computerized tomography, mammography images, and digital histopathology images.
Journal ArticleDOI
Automated and Clinical Breast Imaging Reporting and Data System Density Measures Predict Risk for Screen-Detected and Interval Cancers: A Case-Control Study.
Karla Kerlikowske,Christopher G. Scott,Amir Pasha Mahmoudzadeh,Lin Ma,Stacey J. Winham,Matthew R. Jensen,Fang Fang Wu,Serghei Malkov,V. Shane Pankratz,Steven R. Cummings,John A. Shepherd,Kathleen R. Brandt,Diana L. Miglioretti,Celine M. Vachon +13 more
TL;DR: If automated BI-RADS density measures, which are reportedly more reproducible than clinical measures on repeated examinations (16, 17), can accurately predict cancer detection, automated breast density assessment might be used more widely for breast cancer prevention strategies.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.