Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation

Thyroid nodules are detected in up to 65% of the general population, and their early identification is clinically significant for formulating personalized treatment plans. Precise segmentation of nodules in ultrasound images is essential for assessing their morphological and pathological characteris...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiheng Zhang, Lin Li, Cheng Zhao, Peng Ren, Ran Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11121866/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736784887414784
author Zhiheng Zhang
Lin Li
Cheng Zhao
Peng Ren
Ran Zhang
author_facet Zhiheng Zhang
Lin Li
Cheng Zhao
Peng Ren
Ran Zhang
author_sort Zhiheng Zhang
collection DOAJ
description Thyroid nodules are detected in up to 65% of the general population, and their early identification is clinically significant for formulating personalized treatment plans. Precise segmentation of nodules in ultrasound images is essential for assessing their morphological and pathological characteristics. In current clinical practice, the annotation of nodule regions primarily relies on manual operations performed by physicians. This process is not only time-consuming but also labor-intensive. Furthermore, due to variations in physicians’ professional experience, the annotation results are difficult to ensure consistency and reliability. This study proposes an asymmetric encoder-decoder segmentation architecture based on Convolutional Neural Networks (CNN) and attention mechanisms for automatically and precisely segmenting thyroid nodules in ultrasound images. The framework introduces an Efficient Convolutional Block (ECB) to extract high-level semantic features, constructs a Convolutional Modulation Module (CMM) to enhance feature representation, and incorporates a Spatial Semantic Enhancement Module (SSEM) to optimize detail reconstruction. Experimental results on a public thyroid nodule ultrasound dataset demonstrate that the proposed method significantly outperforms existing models’ overall segmentation performance, achieving a Dice Similarity Coefficient (DSC) of 0.8332 and an Intersection over Union (IOU) of 0.7473 on the test set. Ablation studies and visual analysis further confirm the effectiveness and interpretability of each module.
format Article
id doaj-art-da3118599408445ea2baa669387c92fb
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-da3118599408445ea2baa669387c92fb2025-08-20T03:07:10ZengIEEEIEEE Access2169-35362025-01-011314190814191910.1109/ACCESS.2025.359746011121866Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule SegmentationZhiheng Zhang0Lin Li1Cheng Zhao2Peng Ren3https://orcid.org/0000-0001-7883-1873Ran Zhang4https://orcid.org/0000-0001-8628-3803School of Stomatology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaThyroid nodules are detected in up to 65% of the general population, and their early identification is clinically significant for formulating personalized treatment plans. Precise segmentation of nodules in ultrasound images is essential for assessing their morphological and pathological characteristics. In current clinical practice, the annotation of nodule regions primarily relies on manual operations performed by physicians. This process is not only time-consuming but also labor-intensive. Furthermore, due to variations in physicians’ professional experience, the annotation results are difficult to ensure consistency and reliability. This study proposes an asymmetric encoder-decoder segmentation architecture based on Convolutional Neural Networks (CNN) and attention mechanisms for automatically and precisely segmenting thyroid nodules in ultrasound images. The framework introduces an Efficient Convolutional Block (ECB) to extract high-level semantic features, constructs a Convolutional Modulation Module (CMM) to enhance feature representation, and incorporates a Spatial Semantic Enhancement Module (SSEM) to optimize detail reconstruction. Experimental results on a public thyroid nodule ultrasound dataset demonstrate that the proposed method significantly outperforms existing models’ overall segmentation performance, achieving a Dice Similarity Coefficient (DSC) of 0.8332 and an Intersection over Union (IOU) of 0.7473 on the test set. Ablation studies and visual analysis further confirm the effectiveness and interpretability of each module.https://ieeexplore.ieee.org/document/11121866/Attention mechanismconvolutional neural networkdeep learningmedical image computingthyroid nodule segmentation
spellingShingle Zhiheng Zhang
Lin Li
Cheng Zhao
Peng Ren
Ran Zhang
Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
IEEE Access
Attention mechanism
convolutional neural network
deep learning
medical image computing
thyroid nodule segmentation
title Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
title_full Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
title_fullStr Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
title_full_unstemmed Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
title_short Asymmetric Network Based on CNN and Attention Mechanisms for Thyroid Nodule Segmentation
title_sort asymmetric network based on cnn and attention mechanisms for thyroid nodule segmentation
topic Attention mechanism
convolutional neural network
deep learning
medical image computing
thyroid nodule segmentation
url https://ieeexplore.ieee.org/document/11121866/
work_keys_str_mv AT zhihengzhang asymmetricnetworkbasedoncnnandattentionmechanismsforthyroidnodulesegmentation
AT linli asymmetricnetworkbasedoncnnandattentionmechanismsforthyroidnodulesegmentation
AT chengzhao asymmetricnetworkbasedoncnnandattentionmechanismsforthyroidnodulesegmentation
AT pengren asymmetricnetworkbasedoncnnandattentionmechanismsforthyroidnodulesegmentation
AT ranzhang asymmetricnetworkbasedoncnnandattentionmechanismsforthyroidnodulesegmentation