# Thyroid nodule classification on Hospital Ultrasound dataset (test) Source: [Thyroid nodule classification on Hospital Ultrasound dataset (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:03.359Z Evaluation of model performance for thyroid nodule classification using the test split of the Hospital Ultrasound dataset, reporting Accuracy, F1-score, and AUROC. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Thyroid nodule classification | | Dataset (including any stated split) | Hospital Ultrasound dataset (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [AUROC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Deblurring MAE \[Gaussian\] | 90.19 | Not recorded | 68fa700a1e209131cea48c7d | | Deblurring MAE \[SRAD\] | 90.07 | Not recorded | 68fa700a1e209131cea48c7d | | MAE | 89.45 | Not recorded | 68fa700a1e209131cea48c7d | | Zhou et al. | 88.15 | Not recorded | 68fa700a1e209131cea48c7d | | ConvNext | 87.76 | Not recorded | 68fa700a1e209131cea48c7d | | Wang et al. | 87.44 | Not recorded | 68fa700a1e209131cea48c7d | | Swin Transformer | 87.43 | Not recorded | 68fa700a1e209131cea48c7d | | MAE | 87.25 | Not recorded | 68fa700a1e209131cea48c7d | | MoCo v3 | 87.08 | Not recorded | 68fa700a1e209131cea48c7d | | MoCo v3 | 86.96 | Not recorded | 68fa700a1e209131cea48c7d | | ViT | 86.38 | Not recorded | 68fa700a1e209131cea48c7d | | SimCLR | 86.21 | Not recorded | 68fa700a1e209131cea48c7d | | ResNet | 86.06 | Not recorded | 68fa700a1e209131cea48c7d | | ViT | 80.6 | Not recorded | 68fa700a1e209131cea48c7d | | Denoising MAE | 80.38 | Not recorded | 68fa700a1e209131cea48c7d | ### Deblurring MAE \[Gaussian\] Accuracy: 90.19. Result ID: 699117e33a6c31484905a0c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"Ultrasound","Blurring Operation":"Gaussian (sigma=1.1)"}. This record does not assert independent reproduction. ### Deblurring MAE \[SRAD\] Accuracy: 90.07. Result ID: 699117e33a6c31484905a0c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"Ultrasound","Blurring Operation":"SRAD (N=40, t=0.1)"}. This record does not assert independent reproduction. ### MAE Accuracy: 89.45. Result ID: 699117e33a6c31484905a0bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"Ultrasound"}. This record does not assert independent reproduction. ### Zhou et al. Accuracy: 88.15. Result ID: 699117e33a6c31484905a0b8. [Reporting paper]() Recorded evaluation configuration: {"Training Strategy":"Supervised"}. This record does not assert independent reproduction. ### ConvNext Accuracy: 87.76. Result ID: 699117e33a6c31484905a0b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ConvNeXt-L","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### Wang et al. Accuracy: 87.44. Result ID: 699117e33a6c31484905a0b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Strategy":"Supervised"}. This record does not assert independent reproduction. ### Swin Transformer Accuracy: 87.43. Result ID: 699117e33a6c31484905a0b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"Swin-L","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### MAE Accuracy: 87.25. Result ID: 699117e33a6c31484905a0be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### MoCo v3 Accuracy: 87.08. Result ID: 699117e33a6c31484905a0bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ResNet-50","Pretraining":"Ultrasound"}. This record does not assert independent reproduction. ### MoCo v3 Accuracy: 86.96. Result ID: 699117e33a6c31484905a0bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ResNet-50","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### ViT Accuracy: 86.38. Result ID: 699117e33a6c31484905a0ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### SimCLR Accuracy: 86.21. Result ID: 699117e33a6c31484905a0bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ResNet-50","Pretraining":"ImageNet"}. This record does not assert independent reproduction. ### ResNet Accuracy: 86.06. Result ID: 699117e33a6c31484905a0b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ResNet-101","Pretraining":"Supervised"}. This record does not assert independent reproduction. ### ViT Accuracy: 80.6. Result ID: 699117e33a6c31484905a0b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"Supervised"}. This record does not assert independent reproduction. ### Denoising MAE Accuracy: 80.38. Result ID: 699117e33a6c31484905a0c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"ViT-B","Pretraining":"Ultrasound"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.