# Medical Interaction Segmentation on MR-MedSeg (val) Source: [Medical Interaction Segmentation on MR-MedSeg (val)]() Collection index: [llms.txt]() Data updated: 2026-03-11T06:44:08.716Z Evaluation of Medical Interaction Segmentation performance on the validation split of the MR-MedSeg dataset, reporting metrics such as Dice, gIoU, and cIoU. 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 Interaction Segmentation | | Dataset (including any stated split) | MR-MedSeg (val) | | Metric | Dice | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Dice](): Higher is better; unit: PERCENT. - [gIoU](): Higher is better; unit: PERCENT. - [cIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | Dice | Result date | Report paper | | --- | --- | --- | --- | | MedSAM | 77.7 | Not recorded | 691bfdf46750be83fe5ceb61 | | IMIS-Net | 77 | Not recorded | 691bfdf46750be83fe5ceb61 | | MediRound + JCM | 58.4 | Not recorded | 691bfdf46750be83fe5ceb61 | | MediRound | 55.8 | Not recorded | 691bfdf46750be83fe5ceb61 | | MediRound + READ | 53.9 | Not recorded | 691bfdf46750be83fe5ceb61 | | Human-Thinking + MediSee | 43 | Not recorded | 691bfdf46750be83fe5ceb61 | | Qwen3-VL + MediSee | 42.7 | Not recorded | 691bfdf46750be83fe5ceb61 | | SegLLM-13B | 38.9 | Not recorded | 691bfdf46750be83fe5ceb61 | | GPT-4o + MediSee | 36.8 | Not recorded | 691bfdf46750be83fe5ceb61 | | SegLLM-7B | 36.3 | Not recorded | 691bfdf46750be83fe5ceb61 | | Human-Thinking + MedPLIB | 33.7 | Not recorded | 691bfdf46750be83fe5ceb61 | | Gemini-2.5-Pro + MediSee | 33.5 | Not recorded | 691bfdf46750be83fe5ceb61 | | Human-Thinking + IMIS-Net | 30.5 | Not recorded | 691bfdf46750be83fe5ceb61 | | Gemini-2.5-Pro + IMIS-Net | 26.9 | Not recorded | 691bfdf46750be83fe5ceb61 | | Qwen3-VL + IMIS-Net | 26.6 | Not recorded | 691bfdf46750be83fe5ceb61 | | Human-Thinking + BiomedParse | 21.1 | Not recorded | 691bfdf46750be83fe5ceb61 | | GPT-4o + IMIS-Net | 19.3 | Not recorded | 691bfdf46750be83fe5ceb61 | ### MedSAM Dice: 77.7. Result ID: 69b10f216dbb7075b95acf1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input":"bbox input"}. This record does not assert independent reproduction. ### IMIS-Net Dice: 77. Result ID: 69b10f216dbb7075b95acf20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input":"bbox input"}. This record does not assert independent reproduction. ### MediRound + JCM Dice: 58.4. Result ID: 69b10f216dbb7075b95acf37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"true"}. This record does not assert independent reproduction. ### MediRound Dice: 55.8. Result ID: 69b10f216dbb7075b95acf36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"true"}. This record does not assert independent reproduction. ### MediRound + READ Dice: 53.9. Result ID: 69b10f216dbb7075b95acf35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"true"}. This record does not assert independent reproduction. ### Human-Thinking + MediSee Dice: 43. Result ID: 69b10f216dbb7075b95acf2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Qwen3-VL + MediSee Dice: 42.7. Result ID: 69b10f216dbb7075b95acf32. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### SegLLM-13B Dice: 38.9. Result ID: 69b10f216dbb7075b95acf34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"true"}. This record does not assert independent reproduction. ### GPT-4o + MediSee Dice: 36.8. Result ID: 69b10f216dbb7075b95acf30. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### SegLLM-7B Dice: 36.3. Result ID: 69b10f216dbb7075b95acf33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"true"}. This record does not assert independent reproduction. ### Human-Thinking + MedPLIB Dice: 33.7. Result ID: 69b10f216dbb7075b95acf2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro + MediSee Dice: 33.5. Result ID: 69b10f216dbb7075b95acf31. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Human-Thinking + IMIS-Net Dice: 30.5. Result ID: 69b10f216dbb7075b95acf2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro + IMIS-Net Dice: 26.9. Result ID: 69b10f216dbb7075b95acf2e. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Qwen3-VL + IMIS-Net Dice: 26.6. Result ID: 69b10f216dbb7075b95acf2f. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### Human-Thinking + BiomedParse Dice: 21.1. Result ID: 69b10f216dbb7075b95acf29. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. ### GPT-4o + IMIS-Net Dice: 19.3. Result ID: 69b10f216dbb7075b95acf2d. [Reporting paper]() Recorded evaluation configuration: {"Independent Model (T)":"false"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.