FBN: Weakly Supervised Thyroid Nodule Segmentation Optimized by Online Foreground and Background

Ruiguo Yu; Shaoqi Yan; Jie Gao; Mankun Zhao; Xuzhou Fu; Yang Yan; Ming Li; Xuewei Li

doi:10.1016/j.ultrasmedbio.2023.04.009

FBN: Weakly Supervised Thyroid Nodule Segmentation Optimized by Online Foreground and Background

Ultrasound Med Biol. 2023 Sep;49(9):1940-1950. doi: 10.1016/j.ultrasmedbio.2023.04.009. Epub 2023 Jun 11.

Authors

Ruiguo Yu¹, Shaoqi Yan¹, Jie Gao¹, Mankun Zhao¹, Xuzhou Fu¹, Yang Yan², Ming Li², Xuewei Li³

Affiliations

¹ College of Intelligence and Computing, Tianjin University, Tianjin, China; Tianjin Key Laboratory of Advanced Networking, Tianjin University, Tianjin, China; Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China.
² Tianjin Medical University General Hospital, Tianjin Medical University, Tianjin, China.
³ College of Intelligence and Computing, Tianjin University, Tianjin, China; Tianjin Key Laboratory of Advanced Networking, Tianjin University, Tianjin, China; Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin, China. Electronic address: lixuewei@tju.edu.cn.

PMID: 37308370
DOI: 10.1016/j.ultrasmedbio.2023.04.009

Abstract

Objective: The main objective of the work described here was to train a semantic segmentation model using classification data for thyroid nodule ultrasound images to reduce the pressure of obtaining pixel-level labeled data sets. Furthermore, we improved the segmentation performance of the model by mining the image information to narrow the gap between weakly supervised semantic segmentation (WSSS) and fully supervised semantic segmentation.

Methods: Most WSSS methods use a class activation map (CAM) to generate segmentation results. However, the lack of supervision information makes it difficult for a CAM to highlight the object region completely. Therefore, we here propose a novel foreground and background pair (FB-Pair) representation method, which consists of high- and low-response regions highlighted by the original CAM-generated online in the original image. During training, the original CAM is revised using the CAM generated by the FB-Pair. In addition, we design a self-supervised learning pretext task based on FB-Pair, which requires the model to predict whether the pixels in FB-Pair are from the original image during training. After this task, the model will accurately distinguish between different categories of objects.

Results: Experiments on the thyroid nodule ultrasound image (TUI) data set revealed that our proposed method outperformed existing methods, with a 5.7% improvement in the mean intersection-over-union (mIoU) performance of segmentation compared with the second-best method and a reduction to 2.9% in the difference between the performance of benign and malignant nodules.

Conclusion: Our method trains a well-performing segmentation model on ultrasound images of thyroid nodules using only classification data. In addition, we determined that CAM can take full advantage of the information in the images to highlight the target regions more accurately and thus improve the segmentation performance.

Keywords: Segmentation; Thyroid Nodule; Ultrasound; Weakly supervised.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Humans
Image Processing, Computer-Assisted
Thyroid Nodule* / diagnostic imaging