Representation learning for mammography mass lesion classification with convolutional neural networks

By John Arevalo, Fabio A. González, Raúl Ramos-Pollán, José Luís Oliveira, Miguel Ángel Guevara-López. Comput. Methods Programs Biomed., 2016

443 citations recorded by the source corpus.

BACKGROUND AND OBJECTIVE The automatic classification of breast imaging lesions is currently an unsolved problem. This paper describes an innovative representation learning framework for breast cancer diagnosis in mammography that integrates deep learning techniques to automatically learn discriminative features avoiding the design of specific hand-crafted image-based feature detectors. METHODS A new biopsy proven benchmarking dataset was built from 344 breast cancer patients' cases containing a total of 736 film mammography (mediolateral oblique and craniocaudal) views, representative of manually segmented lesions associated with masses: 426 benign lesions and 310 malignant lesions. The developed method comprises two main stages: (i) preprocessing to enhance image details and (ii) supervised training for learning both the features and the breast imaging lesions classifier. In contrast to previous works, we adopt a hybrid approach where convolutional neural networks are used to learn the representation in a supervised way instead of designing particular descriptors to explain the content of mammography images. RESULTS Experimental results using the developed benchmarking breast cancer dataset demonstrated that our method exhibits significant improved performance when compared to state-of-the-art image descriptors, such as histogram of oriented gradients (HOG) and histogram of the gradient divergence (HGD), increasing the performance from 0.787 to 0.822 in terms of the area under the ROC curve (AUC). Interestingly, this model also outperforms a set of hand-crafted features that take advantage of additional information from segmentation by the radiologist. Finally, the combination of both representations, learned and hand-crafted, resulted in the best descriptor for mass lesion classification, obtaining 0.826 in the AUC score. CONCLUSIONS A novel deep learning based framework to automatically address classification of breast mass lesions in mammography was developed.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Pathology and Forensic Medicine

View Paper: https://www.semanticscholar.org/paper/a4360f362168a6107e1014b7fc61bed32038fc70

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “In detecting masses in MMM from BCDR database, CNN with 2 convolution layers and 1 fully connected layer (CNN3) performed similar to other methods (CNN3:82%, HGD: 83%, HOG: 81%, DeCAF: 82%), and CNN with 1 convolution layer and 1 fully connected layer performed poorly (CNN2: 78%) [151].”
Deep Convolutional Neural Networks for breast cancer screening (2018, unknown): “Besides, Arevalo et al. [17] adopted a hybrid approach where they used a CNN to learn the representation of the mammog-28 raphy images in a supervised way, and then combined the obtained features with hand-crafted descriptors to classify mass lesions from the BCDR database.”
Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks. (2018, methodology): “…were used to train a three layer CNN. 48 Similarly, since then, various studies have investigated different handcrafted features to train CNNs. 4,46,47,61,62 These methods conceptually work in a similar way: combining multiple modules and jointly training all parameters to demonstrate the power…”
A review on deep learning in medical image analysis (2021, methodology): “The self-supervised learning system needs only unlabelled data to formulate a pretext learning assignment, such as predicting context or image rotation, for which a target objective can be calculated without supervision [52].”
High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks (2017, background): “Others have focused on training a deep neural network for classifying a small region of interest into one of a few categories, assuming an existing mass detection system (9, 30–32).”
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification (2018, methodology): “In other CAD systems, these manually detected masses are directly fed into CNN to generate the integrated high-level deep features [10,19,37].”