Advancing discriminative to representative: A self-supervised classification framework by integrating selective diffusion model learned features for uterine adenomyosis diagnosis in transvaginal ultrasound image

Jianning Chi, H. Zhang, Zelan Li, Xiuwei Ling, Jiahui Chen, Ying Huang
In: Biomedical Signal Processing and Control · 2026 · vol. 129 , pp. 111381 · doi:10.1016/j.bspc.2026.111381 · W7213012172
article OA: hybrid CC0
🔓 Open OA copy View on OpenAlex View at publisher
⚙ AI-generated summary by qwen3.7-flash, 2026-09-17 ⓘ

A self-supervised classification framework integrating selective diffusion model features with texture information significantly improves the accuracy, specificity, and sensitivity of uterine adenomyosis diagnosis in transvaginal ultrasound images using limited labeled data.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

Abstract

Deep learning based methods have attracted attention for uterine adenomyosis in transvaginal ultrasound (TVUS) images due to their powerful abilities of feature representation, yet are hindered by a lack of labeled data. Self-supervised learning methods show the potential for this problem since they can learn feature representation from abundant unlabeled data for downstream tasks. However, the differences in TVUS images are usually subtle and ambiguous, while existing self-supervised learning methods tend to disrupt discriminative information when using auxiliary tasks such as generating positive–negative image pairs and reconstructing masked images. To address these problems, in this paper, we propose a self-supervised classification framework that derives the representative feature from diffusion model learned features and complements it with detailed texture information of the image. Specifically in the pre-training stage, the U-Net is trained following the Denoising Diffusion Probabilistic Model (DDPM) so that most of the valuable discriminative information is preserved by the network features. In the classification stage, the cross-attention fusion (CAF) module is designed to integrate multiple selective features from the pre-trained U-Net, yielding a representative feature that contains more comprehensive discriminative information. Furthermore, the adaptive normalization (AN) module is designed to introduce detailed texture information from parallel convolutional neural network (CNN) into the representative feature, enhancing the ability to recognize subtle differences between TVUS images. The proposed method is evaluated on the self-collected TVUS dataset and compared with state-of-the-art deep learning models. Experimental results demonstrate that the proposed method significantly enhances the accuracy, specificity, and sensitivity of uterine adenomyosis diagnosis, indicating that the network is capable of achieving accurate and robust diagnosis of uterine adenomyosis with a limited labeled dataset, thereby advancing the clinical application of deep learning for adenomyosis diagnosis.

My notes (saved in your browser only)

Citation neighborhood

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. [ expand to 2 hops ] — adds papers reached through this work's immediate citers/citees. Heavier; up to 60 extra dots.

References (23)

Source provenance

openalex
last seen: 2026-09-27T06:00:52.009428+00:00
License: CC0 · commercial use OK