An improved method for thyroid nodule ultrasound image segmentation based on U²‐Net

Abstract

To achieve accurate segmentation of thyroid nodule ultrasound images, obtain information on the physiological parameters of the lesion area and guide the clinical formulation of individualized treatment plan, an improved network based on the U2‐Net model is proposed in this paper. Thyroid images of 264 patients and 215 healthy volunteers at the First Hospital of Shanxi Medical University from February 2016 to June 2022 are studied, and the digital database thyroid image (DDTI) data set is proposed for data expansion. The experimental results show that the Dice coefficient on the test set was 80.58%, and the mean intersection over union was 81.21%. The improved U2‐Net model has the best segmentation accuracy compared with similar models, realizes the automatic segmentation of thyroid nodules, provides help for manual segmentation, and has good application prospects and clinical value.

BCUIS‐Net: A breast cancer ultrasound image segmentation network via boundary‐aware and shape feature fusion

“…In clinical practice, breast cancer diagnosis mainly includes X‐ray, breast ultrasound, and MRI 3,4 . Among these, ultrasound imaging is an indispensable tool for early detection of breast cancer because of its cost‐effectiveness, radiation‐free imaging procedure, and high sensitivity in dense breast tissue 5 . However, ultrasound scans are significantly influenced by individual patient variability and physician expertise.…”

“…3,4 Among these, ultrasound imaging is an indispensable tool for early detection of breast cancer because of its costeffectiveness, radiation-free imaging procedure, and high sensitivity in dense breast tissue. 5 However, ultrasound scans are significantly influenced by individual patient variability and physician expertise. In addition, the large volume of examinations places a heavy workload on the physician.…”