Research on precise segmentation model of thyroid nodules based on deep learning
- 1School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, Anhui, China
- 2College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China
Abstract
Thyroid nodules are a prevalent condition in clinical practice, typically identified via ultrasound imaging with visual assessment by physicians. However, the ambiguous features of malignant nodules, their proximity to surrounding tissues, image noise, and unclear boundaries can lead to variability in diagnostic outcomes among different practitioners. In this study, we initially employed nine established models to segment ultrasound images from two publicly available datasets, TN3K and DDTI. Evaluation metrics including IoU, F1-score, accuracy (Acc), specificity (Spec), and precision (Pre) were utilized to assess the segmentation performance of these models. The experimental results indicate that, given the current data scale, the overall segmentation performance of each model is relatively low. Analysis suggests this is primarily due to the limited number of samples in the medical imaging dataset. During training, the model struggles to fully learn the discriminative features of the lesion area. Particularly during the encoder’s down-sampling stage, the feature expression ability is constrained, affecting the model’s ability to accurately recognize lesion locations. To address this, we enhanced the classic model by incorporating the Residual Network ResNet34, constructing a new thyroid nodule segmentation model. The improved model demonstrated enhanced segmentation performance, with most IoU values on the TN3K dataset exceeding 0.8. However, models trained on the DDTI dataset rarely achieved high performance. Further analysis attributes this performance disparity to differences in the number of training samples. To further enhance model performance, we initialized the improved model with pre-trained ResNet34 weights from the ImageNet dataset, resulting in significant performance improvements. Notably, Res34-PAN performed best across both datasets. On the DDTI dataset, the model achieved an IoU of 0.8778, an F1-score of 0.9349, an accuracy of 0.9872, a specificity of 0.9928, and a precision of 0.9342. To further validate the model design’s rationale, we conducted a systematic ablation experiment. We selected commonly used network structures for encoders and used them as the encoders for nine segmentation models, comparing performance with and without the ImageNet pre-trained weights. The results further confirmed the effectiveness of the proposed method in the thyroid nodule segmentation task.
Related
- Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
- Real-Time AI-Based ACR TI-RADS Classification of Thyroid Nodules on the Ultrasound Console: A Prospective Agreement Study in a Region with Historical Iodine Deficiency
- Hashimoto Thyroiditis Modifies the Association Between Nuclear Atypia and Malignancy in Bethesda III Thyroid Nodules
- Incremental Diagnostic Value of Cell-Block-Based Targeted BRAF and RAS Testing in TBSRTC Category III–IV Thyroid Nodules: A Single-Center Retrospective Study
- BRAFV600E-Informed TI-RADS Reclassification of Biopsy Eligibility in Thyroid Nodules: A Retrospective Oracle Decision–Simulation Study
BibTeX
@article{zhang2026research,
title = {{Research on precise segmentation model of thyroid nodules based on deep learning}},
author = {Qingpeng Zhang and Qinqin Xiao and Jiacheng Wu and Guangming Shao},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0358892},
url = {https://doi.org/10.1371/journal.pone.0358892},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Research on precise segmentation model of thyroid nodules based on deep learning
AU - Qingpeng Zhang
AU - Qinqin Xiao
AU - Jiacheng Wu
AU - Guangming Shao
PY - 2026
DA - 2026/10/08
JO - PLOS One
DO - 10.1371/journal.pone.0358892
UR - https://doi.org/10.1371/journal.pone.0358892
AB - Thyroid nodules are a prevalent condition in clinical practice, typically identified via ultrasound imaging with visual assessment by physicians. However, the ambiguous features of malignant nodules, their proximity to surrounding tissues, image noise, and unclear boundaries can lead to variability in diagnostic outcomes among different practitioners. In this study, we initially employed nine established models to segment ultrasound images from two publicly available datasets, TN3K and DDTI. Evaluation metrics including IoU, F1-score, accuracy (Acc), specificity (Spec), and precision (Pre) were utilized to assess the segmentation performance of these models. The experimental results indicate that, given the current data scale, the overall segmentation performance of each model is relatively low. Analysis suggests this is primarily due to the limited number of samples in the medical imaging dataset. During training, the model struggles to fully learn the discriminative features of the lesion area. Particularly during the encoder’s down-sampling stage, the feature expression ability is constrained, affecting the model’s ability to accurately recognize lesion locations. To address this, we enhanced the classic model by incorporating the Residual Network ResNet34, constructing a new thyroid nodule segmentation model. The improved model demonstrated enhanced segmentation performance, with most IoU values on the TN3K dataset exceeding 0.8. However, models trained on the DDTI dataset rarely achieved high performance. Further analysis attributes this performance disparity to differences in the number of training samples. To further enhance model performance, we initialized the improved model with pre-trained ResNet34 weights from the ImageNet dataset, resulting in significant performance improvements. Notably, Res34-PAN performed best across both datasets. On the DDTI dataset, the model achieved an IoU of 0.8778, an F1-score of 0.9349, an accuracy of 0.9872, a specificity of 0.9928, and a precision of 0.9342. To further validate the model design’s rationale, we conducted a systematic ablation experiment. We selected commonly used network structures for encoders and used them as the encoders for nine segmentation models, comparing performance with and without the ImageNet pre-trained weights. The results further confirmed the effectiveness of the proposed method in the thyroid nodule segmentation task.
SN - 1932-6203
ER -