ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy
Abstract Thyroid nodules are a common endocrine condition, and accurate differentiation between benign and malignant nodules is essential for making appropriate treatment decisions. Traditional ultrasound-based diagnoses often depend on the expertise of physicians, which introduces a risk of misdiag...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86819-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862121934356480 |
|---|---|
| author | Xiaoxue Wang Yupeng Niu Hongli Liu Fa Tian Qiang Zhang Yimeng Wang Yeju Wang Yijia Li |
| author_facet | Xiaoxue Wang Yupeng Niu Hongli Liu Fa Tian Qiang Zhang Yimeng Wang Yeju Wang Yijia Li |
| author_sort | Xiaoxue Wang |
| collection | DOAJ |
| description | Abstract Thyroid nodules are a common endocrine condition, and accurate differentiation between benign and malignant nodules is essential for making appropriate treatment decisions. Traditional ultrasound-based diagnoses often depend on the expertise of physicians, which introduces a risk of misdiagnosis. To address this challenge, this study proposes a novel deep learning model, ThyroNet-X4 Genesis, designed to automatically classify thyroid nodules as benign or malignant. Built on the ResNet architecture, the model enhances feature extraction by incorporating grouped convolutions and using larger convolution kernels, improving its ability to analyze thyroid ultrasound images. The model was trained and validated using publicly available thyroid ultrasound imaging datasets, and its generalization was further tested using an external validation dataset from HanZhong Central Hospital. The ThyroNet-X4 Genesis model achieved 85.55% and 71.70% accuracy on the internal training and validation sets, respectively, and 67.02% accuracy on the external validation set. These results surpass those of other mainstream models, highlighting its potential for clinical use in thyroid nodule classification. This work underscores the growing role of deep learning in thyroid nodule diagnosis and provides a foundation for future research in high-performance medical diagnostic models. |
| format | Article |
| id | doaj-art-13f89b8b9144490e880e21d0c53dbea7 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-13f89b8b9144490e880e21d0c53dbea72025-02-09T12:37:36ZengNature PortfolioScientific Reports2045-23222025-02-0115111210.1038/s41598-025-86819-wThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancyXiaoxue Wang0Yupeng Niu1Hongli Liu2Fa Tian3Qiang Zhang4Yimeng Wang5Yeju Wang6Yijia Li7HanZhong Central HospitalCollege of Information Engineering, Sichuan Agricultural UniversityHanZhong Central HospitalCollege of Information Engineering, Sichuan Agricultural UniversityHanZhong Central HospitalHanZhong Central HospitalHanZhong Central HospitalHanZhong Central HospitalAbstract Thyroid nodules are a common endocrine condition, and accurate differentiation between benign and malignant nodules is essential for making appropriate treatment decisions. Traditional ultrasound-based diagnoses often depend on the expertise of physicians, which introduces a risk of misdiagnosis. To address this challenge, this study proposes a novel deep learning model, ThyroNet-X4 Genesis, designed to automatically classify thyroid nodules as benign or malignant. Built on the ResNet architecture, the model enhances feature extraction by incorporating grouped convolutions and using larger convolution kernels, improving its ability to analyze thyroid ultrasound images. The model was trained and validated using publicly available thyroid ultrasound imaging datasets, and its generalization was further tested using an external validation dataset from HanZhong Central Hospital. The ThyroNet-X4 Genesis model achieved 85.55% and 71.70% accuracy on the internal training and validation sets, respectively, and 67.02% accuracy on the external validation set. These results surpass those of other mainstream models, highlighting its potential for clinical use in thyroid nodule classification. This work underscores the growing role of deep learning in thyroid nodule diagnosis and provides a foundation for future research in high-performance medical diagnostic models.https://doi.org/10.1038/s41598-025-86819-wThyroid nodulesDeep learningAuxiliary diagnosisExternal validationClinical interpretability |
| spellingShingle | Xiaoxue Wang Yupeng Niu Hongli Liu Fa Tian Qiang Zhang Yimeng Wang Yeju Wang Yijia Li ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy Scientific Reports Thyroid nodules Deep learning Auxiliary diagnosis External validation Clinical interpretability |
| title | ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy |
| title_full | ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy |
| title_fullStr | ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy |
| title_full_unstemmed | ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy |
| title_short | ThyroNet-X4 genesis: an advanced deep learning model for auxiliary diagnosis of thyroid nodules’ malignancy |
| title_sort | thyronet x4 genesis an advanced deep learning model for auxiliary diagnosis of thyroid nodules malignancy |
| topic | Thyroid nodules Deep learning Auxiliary diagnosis External validation Clinical interpretability |
| url | https://doi.org/10.1038/s41598-025-86819-w |
| work_keys_str_mv | AT xiaoxuewang thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT yupengniu thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT hongliliu thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT fatian thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT qiangzhang thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT yimengwang thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT yejuwang thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy AT yijiali thyronetx4genesisanadvanceddeeplearningmodelforauxiliarydiagnosisofthyroidnodulesmalignancy |