# Medical Image Classification on Mura s Source: [Medical Image Classification on Mura s]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:40.128Z Evaluation of Medical Image Classification performance using the Mura s dataset, typically measured using Accuracy. 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) | Mura s | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LoRKD | 79.57 | Not recorded | 68fa730d1e209131cea5a279 | | LoRKD | 78.33 | Not recorded | 68fa730d1e209131cea5a279 | | LoRKD | 77.8 | Not recorded | 68fa730d1e209131cea5a279 | | STL | 77.26 | Not recorded | 68fa730d1e209131cea5a279 | | MTL | 77.09 | Not recorded | 68fa730d1e209131cea5a279 | | MTL | 76.91 | Not recorded | 68fa730d1e209131cea5a279 | | Aligned-MTL | 76.91 | Not recorded | 68fa730d1e209131cea5a279 | | MTL-KD | 76.91 | Not recorded | 68fa730d1e209131cea5a279 | | MoCo-MTL | 76.91 | Not recorded | 68fa730d1e209131cea5a279 | | Aligned-MTL | 76.9 | Not recorded | 68fa730d1e209131cea5a279 | | Baseline | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | STL-KD | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | Baseline | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | Baseline | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | Aligned-MTL | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | KF | 76.73 | Not recorded | 68fa730d1e209131cea5a279 | | MTL-KD | 76.55 | Not recorded | 68fa730d1e209131cea5a279 | | Foundation | 76.38 | Not recorded | 68fa730d1e209131cea5a279 | | MTL | 76.19 | Not recorded | 68fa730d1e209131cea5a279 | | MTL-KD | 75.84 | Not recorded | 68fa730d1e209131cea5a279 | | MoCo-MTL | 75.49 | Not recorded | 68fa730d1e209131cea5a279 | | KF | 74.96 | Not recorded | 68fa730d1e209131cea5a279 | | MoCo-MTL | 74.95 | Not recorded | 68fa730d1e209131cea5a279 | | KF | 74.77 | Not recorded | 68fa730d1e209131cea5a279 | | Foundation | 71.76 | Not recorded | 68fa730d1e209131cea5a279 | | Foundation | 71.05 | Not recorded | 68fa730d1e209131cea5a279 | ### LoRKD Accuracy: 79.57. Result ID: 6992bd883a6c314849112609. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### LoRKD Accuracy: 78.33. Result ID: 6992bd883a6c314849112619. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### LoRKD Accuracy: 77.8. Result ID: 6992bd883a6c314849112611. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### STL Accuracy: 77.26. Result ID: 6992bd883a6c314849112602. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MTL Accuracy: 77.09. Result ID: 6992bd883a6c314849112614. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MTL Accuracy: 76.91. Result ID: 6992bd883a6c314849112603. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Aligned-MTL Accuracy: 76.91. Result ID: 6992bd883a6c314849112607. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MTL-KD Accuracy: 76.91. Result ID: 6992bd883a6c314849112615. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MoCo-MTL Accuracy: 76.91. Result ID: 6992bd883a6c314849112616. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Aligned-MTL Accuracy: 76.9. Result ID: 6992bd883a6c31484911260f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Baseline Accuracy: 76.73. Result ID: 6992bd883a6c314849112601. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### STL-KD Accuracy: 76.73. Result ID: 6992bd883a6c314849112604. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Baseline Accuracy: 76.73. Result ID: 6992bd883a6c31484911260b. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Baseline Accuracy: 76.73. Result ID: 6992bd883a6c314849112613. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Aligned-MTL Accuracy: 76.73. Result ID: 6992bd883a6c314849112617. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### KF Accuracy: 76.73. Result ID: 6992bd883a6c314849112618. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"1.60","Comp. Ratio":"6.81%"}. This record does not assert independent reproduction. ### MTL-KD Accuracy: 76.55. Result ID: 6992bd883a6c314849112605. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### Foundation Accuracy: 76.38. Result ID: 6992bd883a6c31484911260a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"23.51","Comp. Ratio":"/"}. This record does not assert independent reproduction. ### MTL Accuracy: 76.19. Result ID: 6992bd883a6c31484911260c. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MTL-KD Accuracy: 75.84. Result ID: 6992bd883a6c31484911260d. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### MoCo-MTL Accuracy: 75.49. Result ID: 6992bd883a6c314849112606. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### KF Accuracy: 74.96. Result ID: 6992bd883a6c314849112608. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"1.60","Comp. Ratio":"6.81%"}. This record does not assert independent reproduction. ### MoCo-MTL Accuracy: 74.95. Result ID: 6992bd883a6c31484911260e. [Reporting paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.25","Comp. Ratio":"5.32%"}. This record does not assert independent reproduction. ### KF Accuracy: 74.77. Result ID: 6992bd883a6c314849112610. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"MedMnist","Params(M)":"1.60","Comp. Ratio":"6.81%"}. This record does not assert independent reproduction. ### Foundation Accuracy: 71.76. Result ID: 6992bd883a6c314849112612. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Med-MT","Params(M)":"23.51","Comp. Ratio":"/"}. This record does not assert independent reproduction. ### Foundation Accuracy: 71.05. Result ID: 6992bd883a6c314849112600. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Radimagenet","Params(M)":"23.51","Comp. Ratio":"/"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.