The application value of deep learning-based nomograms in benign–malignant discrimination of TI-RADS category 4 thyroid nodules

Zhang, Xinru; Jia, Cheng; Sun, Meng; Ma, Zhe

doi:10.1038/s41598-024-58668-6

Cited by 2 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liang [13] developed a deep learning model speci cally for classifying thyroid and breast nodules. Zhang [14] utilized the YOLOv3 model to discriminate between benign and malignant thyroid nodules in TIRADS category 4, signi cantly impacting subsequent treatment decisions and patient outcomes. Moussa [15] used the ImageNet-pretrained ResNet50 for transfer learning, achieving promising diagnostic results in their own ultrasound image dataset.…”

Section: Introductionmentioning

confidence: 99%

ThyroNet-X4 Genesis: An Advanced Deep Learning Model for Auxiliary Diagnosis of Thyroid Nodules' Malignancy

Wang,

Niu,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

Thyroid nodules are common endocrine disorders, and the discrimination between benign and malignant nodules is crucial for treatment decisions. Traditional ultrasound diagnosis relies on the experience of physicians, which may pose risks of misdiagnosis. In this study, we propose a novel deep learning model, ThyroNet-X4 Genesis, for the automatic classification of thyroid nodules' malignancy. This model is based on the ResNet module, which optimizes computational efficiency and enhances feature extraction capabilities by introducing grouped convolution and increasing the convolution kernel size, thus extracting features and classifying nodules in ultrasound images. We obtained data from publicly available medical imaging databases for internal training and validation and used ultrasound images collected from HanZhong Central Hospital as an external validation set to evaluate the model's generalization ability and practical application value.ThyroNet-X4 Genesis achieved training and validation accuracies of 85.55% and 71.70%, respectively, on the internal validation set, with a testing accuracy of 67.02% on the external validation set, outperforming other mainstream comparative models, indicating its good performance in actual clinical applications. The development of this model showcases the potential of deep learning in thyroid imaging analysis, providing valuable references for future development of high-performance medical diagnostic models.

show abstract

Section: Introductionmentioning

confidence: 99%

ThyroNet-X4 Genesis: An Advanced Deep Learning Model for Auxiliary Diagnosis of Thyroid Nodules' Malignancy

Wang,

Niu,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Predictive Value of the Nomogram Model Based on Multimodal Ultrasound Features for Benign and Malignant Thyroid Nodules of C-TIRADS Category 4

Wu,

Shu,

Tian

et al. 2024

Ultrason Imaging

View full text Add to dashboard Cite

To explore the predictive value of the nomogram model based on multimodal ultrasound features for benign and malignant thyroid nodules of C-TIRADS category 4. A retrospective analysis was conducted on the general conditions and ultrasound features of patients who underwent thyroid ultrasound examination and fine needle aspiration biopsy (FNA) or thyroidectomy at the Affiliated Hospital of Zunyi Medical University from April 2020 to April 2023. Predictive signs for benign and malignant nodules of thyroid C-TIRADS category 4 were screened through LASSO regression and multivariate logistic regression analysis to construct a nomogram prediction model. The predictive efficiency and accuracy of the model were assessed through ROC curves and calibration curves. Seven independent risk factors in the predictive model for benign and malignant thyroid nodules of C-TIRADS category 4 were growth pattern, morphology, microcalcifications, SR, arterial phase enhancement intensity, initial perfusion time, and PE [%]. Based on these features, the area under the curve (AUC) of the constructed prediction model was 0.971 (p ＜ .001, 95% CI: 0.952–0.989), with a prediction accuracy of 93.1%. Internal validation showed that the nomogram calibration curve was consistent with reality, and the decision curve analysis indicated that the model has high clinical application value. The nomogram prediction model constructed based on the multimodal ultrasound features of thyroid nodules of C-TIRADS category 4 has high clinical application value.

show abstract

The application value of deep learning-based nomograms in benign–malignant discrimination of TI-RADS category 4 thyroid nodules

Cited by 2 publications

References 21 publications

ThyroNet-X4 Genesis: An Advanced Deep Learning Model for Auxiliary Diagnosis of Thyroid Nodules' Malignancy

ThyroNet-X4 Genesis: An Advanced Deep Learning Model for Auxiliary Diagnosis of Thyroid Nodules' Malignancy

Predictive Value of the Nomogram Model Based on Multimodal Ultrasound Features for Benign and Malignant Thyroid Nodules of C-TIRADS Category 4

Contact Info

Product

Resources

About