Fully automatic computer-aided mass detection and segmentation via pseudo-color mammograms and Mask R-CNN

TL;DR

This paper introduces a fully automatic CAD system that uses pseudo-color mammograms and Mask R-CNN to detect and segment breast masses simultaneously, improving accuracy over existing methods.

Contribution

The study presents an integrated approach combining pseudo-color image transformation and Mask R-CNN for joint detection and segmentation of mammographic masses without manual intervention.

Findings

Achieved 0.90 true positive rate at 0.9 false positives per image.

Attained an average Dice similarity index of 0.88 for segmentation.

Outperformed state-of-the-art methods on the INbreast dataset.

Abstract

Mammographic mass detection and segmentation are usually performed as serial and separate tasks, with segmentation often only performed on manually confirmed true positive detections in previous studies. We propose a fully-integrated computer-aided detection (CAD) system for simultaneous mammographic mass detection and segmentation without user intervention. The proposed CAD only consists of a pseudo-color image generation and a mass detection-segmentation stage based on Mask R-CNN. Grayscale mammograms are transformed into pseudo-color images based on multi-scale morphological sifting where mass-like patterns are enhanced to improve the performance of Mask R-CNN. Transfer learning with the Mask R-CNN is then adopted to simultaneously detect and segment masses on the pseudo-color images. Evaluated on the public dataset INbreast, the method outperforms the state-of-the-art methods by achieving an average true positive rate of 0.90 at 0.9 false positive per image and an average Dice similarity index of 0.88 for mass segmentation.