Breast mass detection in digital mammography based on anchor-free architecture

TL;DR

This paper introduces BMassDNet, an anchor-free, one-stage detection network for breast masses in mammography, utilizing advanced normalization, augmentation, and transfer learning to improve detection accuracy and robustness.

Contribution

The paper presents a novel anchor-free detection architecture with specialized normalization, augmentation, and transfer learning techniques for improved breast mass detection.

Findings

Achieved 93% recall on INbreast dataset

Attained 94.3% recall on DDSM dataset

Reduced false positives compared to previous methods

Abstract

Background and Objective: Accurate detection of breast masses in mammography images is critical to diagnose early breast cancer, which can greatly improve the patients survival rate. However, it is still a big challenge due to the heterogeneity of breast masses and the complexity of their surrounding environment.Methods: To address these problems, we propose a one-stage object detection architecture, called Breast Mass Detection Network (BMassDNet), based on anchor-free and feature pyramid which makes the detection of breast masses of different sizes well adapted. We introduce a truncation normalization method and combine it with adaptive histogram equalization to enhance the contrast between the breast mass and the surrounding environment. Meanwhile, to solve the overfitting problem caused by small data size, we propose a natural deformation data augmentation method and mend the train data dynamic updating method based on the data complexity to effectively utilize the limited data. Finally, we use transfer learning to assist the training process and to improve the robustness of the model ulteriorly.Results: On the INbreast dataset, each image has an average of 0.495 false positives whilst the recall rate is 0.930; On the DDSM dataset, when each image has 0.599 false positives, the recall rate reaches 0.943.Conclusions: The experimental results on datasets INbreast and DDSM show that the proposed BMassDNet can obtain competitive detection performance over the current top ranked methods.