Cesarean Scar Defect Segmentation in Transvaginal Ultrasound Images: a Dataset and Benchmark

2026-05-26

AI Summary

This study addresses the clinical challenge of missed diagnoses of cesarean scar defect (CSD), which arises from its subtle and irregular morphology, limited image quality in transvaginal ultrasound (TVUS), and the absence of publicly available segmentation datasets. To bridge this gap, we present the first high-quality, benchmark TVUS dataset for CSD segmentation, comprising 1,111 images and 16 video sequences from 501 positive cases. All data were acquired under standardized protocols and annotated at the pixel level by experienced sonographers following established clinical guidelines. This rigorously curated dataset establishes a reproducible foundation for training and evaluating deep learning and other medical image analysis methods, with the potential to significantly improve diagnostic accuracy for CSD and thereby enhance clinical management and quality of life for women of reproductive age.

Abstract

Cesarean Scar Defect (CSD) is one of the most prevalent complications following cesarean delivery. Transvaginal ultrasonography is widely used for primary CSD screening. Accurate determination of CSD outline and dimensions is crucial for treatment. However, CSDs are frequently overlooked by sonographers due to small size and irregular morphology, suboptimal image quality, and limited clinical awareness in resource-constrained settings. Despite artificial intelligence advances in medical imaging, no public dataset exists for transvaginal ultrasound CSD segmentation. To address this gap, we present a comprehensive CSD dataset comprising 1,111 images and 16 videos, yielding 501 positive samples with confirmed CSD and precise pixel-level manual annotations. Annotations are performed following standardized clinical guidelines through collaboration between experienced sonographers and trained PhD students. This work provides high-quality benchmark resources for advancing medical image segmentation algorithms and promoting clinical innovation. Ultimately, improved CSD diagnosis and subsequent treatment strategies can enhance the quality of life in women of reproductive age, representing significant value for both medical research and clinical practice.

Problem

• Cesarean Scar Defect
• Transvaginal Ultrasound
• Image Segmentation
• Medical Imaging
• Dataset

Innovation

• Cesarean Scar Defect
• Transvaginal Ultrasound
• Medical Image Segmentation
• Pixel-level Annotation
• Public Dataset