Automatic Breast Cancer Lesion Detection and Classification in Mammograms Using Faster R-CNN Deep Learning Network

This paper studies various existing Computer Aided Diagnostics System (CAD) for Mammography and proposes a CAD system for breast cancer lesion with an advanced object detection architecture and validates with an experimental dataset. Mammography is an important tool in the early detection of breast cancers which makes the patient to realize the changes much earlier than they are able to feel the changes in their breasts. CAD system uses digital mammography images and searches for abnormality present in breast such as well-defined or circumscribed mass, calcification, architectural distortion and asymmetry. Feature extraction by Machine learning methods require domain knowledge which is challenging and time-consuming process. Whereas deep learning methods adaptively extract the features by learning from the expert annotated input data. Deep learning methods like convolutional neural networks (CNN) have been a tremendous success in various imaging tasks like image detection, recognition and classification. This paper proposes a CAD system for automatic detection and classification of breast cancer lesion in mammograms based on Faster R-CNN, an advanced, successful object detection framework having region proposal generation and classifier layers. The system generated a mAP (mean Average Precision) value of 0.857 for the testing set, which is the combined performance accuracy of both classification and object detection.

Aims: Automatic detection and classification of Breast Cancer lesion in mammograms using Faster R-CNN deep learning network.

Methods and Materials: This paper proposes a CAD system for detection and classification of breast cancer lesion in mammograms based on Faster R-CNN, an advanced, successful object detection framework having region proposal generation and classifier layers. The proposed CAD system uses mini-MIAS database (mini-Mammographic Image Analysis Society) with 115 images to train the model. The original MIAS database has 330 digitised mammographic images at 50 micron resolution, which has been reduced to 200 micron resolution with Portable Gray Map (PGM) format file of 1024 x 1024 pixels.

Conclusions: This paper considered mini-MIAS database as the database which requires minimal data pre-processing steps with a limited hardware. The enhancement to this CAD system is planning to use CBIS-DDSM database, which is a part of the original DDSM (Digital Database for Screening Mammography) database with annotations by a trained mammographer. The CBIS-DDSM database includes the mammographic images which have been decompressed and converted into DICOM format.