Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network

TL;DR

This study introduces a deep learning-based method using a U-net architecture to automatically detect and segment soft tissue lesions in digital mammography, aiming to assist radiologists in breast cancer screening.

Contribution

It presents a novel deep learning approach that simultaneously detects and segments lesions in mammograms, validated on a large, multi-vendor dataset with high sensitivity.

Findings

Maximum image-level sensitivity of 0.94 with 7.93 FP per image.

Maximum exam-level sensitivity of 0.98 with 7.81 FP per image.

Method provides accurate candidate detection and lesion segmentation.

Abstract

Computer-aided detection or decision support systems aim to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. Commonly such methods proceed in two steps: selection of candidate regions for malignancy, and later classification as either malignant or not. In this study, we present a candidate detection method based on deep learning to automatically detect and additionally segment soft tissue lesions in DM. A database of DM exams (mostly bilateral and two views) was collected from our institutional archive. In total, 7196 DM exams (28294 DM images) acquired with systems from three different vendors (General Electric, Siemens, Hologic) were collected, of which 2883 contained malignant lesions verified with histopathology. Data was randomly split on an exam level into training (50\%), validation (10\%) and testing (40\%) of deep neural network with u-net architecture. The u-net classifies the image but also provides lesion segmentation. Free receiver operating characteristic (FROC) analysis was used to evaluate the model, on an image and on an exam level. On an image level, a maximum sensitivity of 0.94 at 7.93 false positives (FP) per image was achieved. Similarly, per exam a maximum sensitivity of 0.98 at 7.81 FP per image was achieved. In conclusion, the method could be used as a candidate selection model with high accuracy and with the additional information of lesion segmentation.