Feature Pyramid Nonlocal Network With Transform Modal Ensemble Learning for Breast Tumor Segmentation in Ultrasound Images

Automated breast ultrasound image segmentation is essential in a computer-aided diagnosis (CAD) system for breast tumors. In this article, we present a feature pyramid nonlocal network (FPNN) with transform modal ensemble learning (TMEL) for accurate breast tumor segmentation in ultrasound images. Specifically, the FPNN fuses multilevel features under special consideration of long-range dependencies by combining the nonlocal module and feature pyramid network. Additionally, the TMEL is introduced to guide two iFPNNs to extract different tumor details. Two publicly available datasets, i.e., the Dataset-Cairo University and Dataset-Merge, were used for evaluation. The proposed FPNN-TMEL achieves a Dice score of 84.70% +/- 0.53%, Jaccard Index (Jac) of 78.10% +/- 0.48% and Hausdorff distance (HD) of 2.815 +/- 0.016 mm on the Dataset-Cairo University, and Dice of 87.00% +/- 0.41%, Jac of 79.16% +/- 0.56%, and HD of 2.781 +/- 0.035 mm on the Dataset-Merge. Qualitative and quantitative experiments show that our method outperforms other state-of-the-art methods for breast tumor segmentation in ultrasound images. Our code is available at https://github.com/pixixiaonaogou/FPNN-TMEL.

Automated summary

Automated breast ultrasound image segmentation is crucial for computer-aided diagnosis of breast tumors. The FPNN-TMEL method proposed in this article combines a feature pyramid nonlocal network and transform modal ensemble learning for accurate segmentation of breast tumors in ultrasound images. Evaluation on two datasets demonstrates superior performance in segmentation accuracy compared to other state-of-the-art methods.