# Medical Image Classification on PAD-UFES 20 (OA, AUC) Source: [Medical Image Classification on PAD-UFES 20 (OA, AUC)]() Collection index: [llms.txt]() Data updated: 2026-05-22T09:26:43.662Z Evaluation of Medical Image Classification performance on the PAD-UFES-20 dataset, specifically reporting Overall Accuracy (OA) and Area Under the Curve (AUC). 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 | Medical image classification | | Dataset (including any stated split) | PAD-UFES 20 | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Overall Accuracy](): Higher is better; unit: PERCENT. - [AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MKG-CARE | 62.3 | Not recorded | 6a0fe33bf984739ed6739f93 | | KEM | 62 | Not recorded | 6a0fe33bf984739ed6739f93 | | Gemini-3-pro | 61.1 | Not recorded | 6a0fe33bf984739ed6739f93 | | Swin-Transformer | 59.7 | Not recorded | 6a0fe33bf984739ed6739f93 | | Qwen3.5-plus | 59.1 | Not recorded | 6a0fe33bf984739ed6739f93 | | MedMamba | 58.8 | Not recorded | 6a0fe33bf984739ed6739f93 | | GPT-5.1 | 57.7 | Not recorded | 6a0fe33bf984739ed6739f93 | | HuatuoGPT-Vision-34B | 54.9 | Not recorded | 6a0fe33bf984739ed6739f93 | | medgemma-1.5-4b-it | 53.5 | Not recorded | 6a0fe33bf984739ed6739f93 | | VMamba | 52.3 | Not recorded | 6a0fe33bf984739ed6739f93 | | EfficientNetV2 | 51.7 | Not recorded | 6a0fe33bf984739ed6739f93 | | ConvNeXt | 49.4 | Not recorded | 6a0fe33bf984739ed6739f93 | | Health-GPT-XL32 | 39.2 | Not recorded | 6a0fe33bf984739ed6739f93 | ### MKG-CARE Overall Accuracy: 62.3. Result ID: 6a101f5ffbc373592c096831. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Ours"}. This record does not assert independent reproduction. ### KEM Overall Accuracy: 62. Result ID: 6a101f5ffbc373592c096830. [Reporting paper]() Recorded evaluation configuration: {"Category":"Knowledge-enhanced","Year":"2025"}. This record does not assert independent reproduction. ### Gemini-3-pro Overall Accuracy: 61.1. Result ID: 6a101f5ffbc373592c09682e. [Reporting paper]() Recorded evaluation configuration: {"Category":"General LVLM","Year":"2025"}. This record does not assert independent reproduction. ### Swin-Transformer Overall Accuracy: 59.7. Result ID: 6a101f5ffbc373592c096825. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision-based","Year":"2021"}. This record does not assert independent reproduction. ### Qwen3.5-plus Overall Accuracy: 59.1. Result ID: 6a101f5ffbc373592c09682f. [Reporting paper]() Recorded evaluation configuration: {"Category":"General LVLM","Year":"2026"}. This record does not assert independent reproduction. ### MedMamba Overall Accuracy: 58.8. Result ID: 6a101f5ffbc373592c096829. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Vision-based","Year":"2024"}. This record does not assert independent reproduction. ### GPT-5.1 Overall Accuracy: 57.7. Result ID: 6a101f5ffbc373592c09682d. [Reporting paper]() Recorded evaluation configuration: {"Category":"General LVLM","Year":"2025"}. This record does not assert independent reproduction. ### HuatuoGPT-Vision-34B Overall Accuracy: 54.9. Result ID: 6a101f5ffbc373592c09682b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Med-LVLM","Year":"2024"}. This record does not assert independent reproduction. ### medgemma-1.5-4b-it Overall Accuracy: 53.5. Result ID: 6a101f5ffbc373592c09682c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Med-LVLM","Year":"2026"}. This record does not assert independent reproduction. ### VMamba Overall Accuracy: 52.3. Result ID: 6a101f5ffbc373592c096828. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision-based","Year":"2024"}. This record does not assert independent reproduction. ### EfficientNetV2 Overall Accuracy: 51.7. Result ID: 6a101f5ffbc373592c096826. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision-based","Year":"2021"}. This record does not assert independent reproduction. ### ConvNeXt Overall Accuracy: 49.4. Result ID: 6a101f5ffbc373592c096827. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Vision-based","Year":"2022"}. This record does not assert independent reproduction. ### Health-GPT-XL32 Overall Accuracy: 39.2. Result ID: 6a101f5ffbc373592c09682a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Med-LVLM","Year":"2024"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.