Elamur Research⌕
☰
home / papers / 2025 / MedGemma Technical Report

MedGemma Technical Report

Paper · 2025 · Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri et al.

Summary

General-purpose multimodal models often lack dependable medical knowledge. Building medical AI is also hard because health data is heterogeneous, tasks vary widely, and privacy constraints limit how much labelled data is available. The authors from Google Research and Google DeepMind address this with MedGemma, an open family of medical foundation models built on Gemma 3. It has a 4B variant that accepts images and text and a 27B variant tuned for text. Training proceeded in stages:

  • They first adapted the SigLIP vision encoder on tens of millions of medical image–text pairs while still replaying general web data.
  • They then continued multimodal pretraining.
  • Finally, they post-trained the models with distillation from a larger instruction-tuned teacher and with reinforcement learning.

The resulting models clearly outperform comparably sized generative models and get close to task-specific systems, while keeping Gemma 3's general skills. Fine-tuning on narrow subdomains improves results further. A standalone encoder, MedSigLIP, is released alongside the models. Because everything is openly available, developers can adapt these models for radiology, pathology, dermatology, ophthalmology and clinical-text applications.

Key points

  • Out-of-distribution gains over base Gemma 3:
    • 2.6–10% on medical multimodal QA
    • 15.5–18.1% on chest X-ray finding classification
    • 10.8% on agentic evaluation (AgentClinic)
  • Encoder adaptation data: over 33M pairs, of which roughly 32.6M are histopathology patches and about 635k come from other modalities. Medical data was mixed in at 2% weight. In decoder pretraining, medical data was mixed in at 10% weight.
  • Text post-training data: responses and logits sampled from the teacher on MedQA, MedMCQA, PubMedQA, MedExpQA, AfriMed-QA, HealthSearchQA and LiveQA, plus about 200,000 synthetic questions. PathVQA and MedVQA were dropped over data-quality concerns.
  • Fine-tuning results: errors in EHR information retrieval fell by about half, and pneumothorax and histopathology patch classification reached the level of specialized state-of-the-art methods.
  • MedSigLIP: a 400M-parameter encoder released at 448×448 resolution (MedGemma itself uses 896×896). It matches or beats specialized medical image encoders, including in zero-shot classification and retrieval.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksComputer Vision and Pattern Recognition · 3,486 worksMedicine · 275 worksHealth Informatics · 214 works

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 811 works

Cite

Cite as Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cian Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, Lu Yang, Kejia Chen, Per Bjornsson, Shashir Reddy, Ryan Brush, Kenneth Philbrick, Mercy Asiedu, Ines Mezerreg, Howard Hu, Howard Yang, Richa Tiwari, Sunny Jansen, Preeti Singh, Yun Liu, Shekoofeh Azizi, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Rame, Morgane Riviere, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Elena Buchatskaya, Jean-Baptiste Alayrac, Dmitry Lepikhin, Vlad Feinberg, Sebastian Borgeaud, Alek Andreev, Cassidy Hardin, Robert Dadashi, Leonard Hussenot, Armand Joulin, Olivier Bachem, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Clement Farabet, Joelle Barral, Tris Warkentin, Jonathon Shlens, David Fleet, Victor Cotruta, Omar Sanseviero, Gus Martins, Phoebe Kirk, Anand Rao, Shravya Shetty, David F. Steiner, Can Kirmizibayrak, Rory Pilgrim, Daniel Golden and Lin Yang. 2025. MedGemma Technical Report. arXiv:2507.05201.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2507.05201 · arXiv 2507.05201

@misc{sellergren2025medgemma,
  title = {{MedGemma Technical Report}},
  author = {Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cian Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, Lu Yang, Kejia Chen, Per Bjornsson, Shashir Reddy, Ryan Brush, Kenneth Philbrick, Mercy Asiedu, Ines Mezerreg, Howard Hu, Howard Yang, Richa Tiwari, Sunny Jansen, Preeti Singh, Yun Liu, Shekoofeh Azizi, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Rame, Morgane Riviere, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Elena Buchatskaya, Jean-Baptiste Alayrac, Dmitry Lepikhin, Vlad Feinberg, Sebastian Borgeaud, Alek Andreev, Cassidy Hardin, Robert Dadashi, Leonard Hussenot, Armand Joulin, Olivier Bachem, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Clement Farabet, Joelle Barral, Tris Warkentin, Jonathon Shlens, David Fleet, Victor Cotruta, Omar Sanseviero, Gus Martins, Phoebe Kirk, Anand Rao, Shravya Shetty, David F. Steiner, Can Kirmizibayrak, Rory Pilgrim, Daniel Golden and Lin Yang},
  year = {2025},
  doi = {10.48550/arxiv.2507.05201},
  eprint = {2507.05201},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2507.05201}
}

References

82 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Asma Ben Abacha, Eugene Agichtein, Yuval Pinter, and Dina Demner-Fushman. Overview of the medical question answering task at trec 2017 liveqa. In TREC, pages 1–12, 2017. find
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  3. Ahmed Alaa, Thomas Hartvigsen, Niloufar Golchini, Shiladitya Dutta, Frances Dean, Inioluwa Deborah Raji, and Travis Zack. Medical large language model benchmarks should prioritize construct validity. arXiv preprint arXiv:2503.10694, 2025. — [arXiv:2503.10694](https://arxiv.org/abs/2503.10694) find
  4. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems, 35:23716–23736, 2022.
  5. Iñigo Alonso, Maite Oronoz, and Rodrigo Agerri. Medexpqa: Multilingual benchmarking of large language models for medical question answering. Artificial intelligence in medicine, 155:102938, 2024. find
  6. Malaikannan Sankarasubbu Ankit Pal. Openbiollms: Advancing open-source large language models for healthcare and life sciences. https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B , 2024. ↗
  7. Shruthi Bannur, Kenza Bouzid, Daniel C Castro, Anton Schwaighofer, Anja Thieme, Sam Bond-Taylor, Maximilian Ilse, Fernando Pérez-García, Valentina Salvatelli, Harshita Sharma, et al. Maira-2: Grounded radiology report generation. arXiv preprint arXiv:2406.04449, 2024. — [arXiv:2406.04449](https://arxiv.org/abs/2406.04449) find
  8. Suhana Bedi, Hejie Cui, Miguel Fuentes, Alyssa Unell, Michael Wornow, Juan M Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, et al. Medhelm: Holistic evaluation of large language models for medical tasks. arXiv preprint arXiv:2505.23802, 2025. find
  9. Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, and Geoffrey Hinton. Big self-supervised models are strong semi-supervised learners, 2020a. URL https://arxiv.org/abs/ 2006.10029 . ↗
  10. Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. PaLi: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794, 2022.
  11. Zhihong Chen, Yan Song, Tsung-Hui Chang, and Xiang Wan. Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056, 2020b.
  12. Jorge Cuadros and George Bresnick. Eyepacs: an adaptable telemedicine system for diabetic retinopathy screening. Journal of diabetes science and technology, 3(3):509–516, 2009. find
  13. Tianjie Dai, Ruipeng Zhang, Feng Hong, Jiangchao Yao, Ya Zhang, and Yanfeng Wang. Unichest: Conquer-and-divide pre-training for multi-source chest x-ray classification, 2024. URL https://arxiv.org/abs/2312.11038 . — [arXiv:2312.11038](https://arxiv.org/abs/2312.11038) ↗
  14. DeepSeek-AI. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025. URL https://arxiv.org/abs/2501.12948 . ↗
  15. Aaron Defazio, Francis Bach, and Simon Lacoste-Julien. Saga: A fast incremental gradient method with support for non-strongly convex composite objectives. Advances in neural information processing systems, 27, 2014. find
  16. Nicolas Deperrois, Hidetoshi Matsuo, Samuel Ruipérez-Campillo, Moritz Vandenhirtz, Sonia Laguna, Alain Ryser, Koji Fujimoto, Mizuho Nishio, Thomas M Sutter, Julia E Vogt, et al. Radvlm: A multitask conversational vision-language model for radiology. arXiv preprint arXiv:2502.03333, 2025. — [arXiv:2502.03333](https://arxiv.org/abs/2502.03333) find
  17. Mark Endo, Rayan Krishnan, Viswesh Krishna, Andrew Y Ng, and Pranav Rajpurkar. Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model. In Machine Learning for Health, pages 209–219. PMLR, 2021. find
  18. Endurance Evbayekha, Abiodun Benjamin Idowu, and Shane LaRue. Sacubitril/valsartan vs ace inhibitors or arbs: A systematic review and meta-analysis of randomized trials. JACC: Advances, 4 (3):101598, 2025. find
  19. Scott L. Fleming, Alejandro Lozano, William J. Haberkorn, Jenelle A. Jindal, Eduardo Reis, Rahul Thapa, Louis Blankemeier, Julian Z. Genkins, Ethan Steinberg, Ashwin Nayak, Birju Patel, Chia-Chun Chiang, Alison Callahan, Zepeng Huo, Sergios Gatidis, Scott Adams, Oluseyi Fayanju, Shreya J. Shah, Thom… find
  20. Gemma-Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, et al. Gemma 3 technical report. arXiv preprint arXiv:2503.19786, 2025. find
  21. Ary L Goldberger, Luis AN Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. circulation, 101… find
  22. Tianyu Han, Lisa C Adams, Jens-Michalis Papaioannou, Paul Grundmann, Tom Oberhauser, Alexander Löser, Daniel Truhn, and Keno K Bressem. Medalpaca–an open-source collection of medical conversational ai models and training data. arXiv preprint arXiv:2304.08247, 2023.
  23. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300, 2020.
  24. Stephanie L Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C Castro, Mercy Ranjit, Anton Schwaighofer, Fernando Pérez-García, Valentina Salvatelli, Shaury Srivastav, Anja Thieme, et al. Maira-1: A specialised large multimodal model for radiology report generation. arXiv preprint arXiv:2311.13668, 2023… — [arXiv:2311.13668](https://arxiv.org/abs/2311.13668) find
  25. IQVIA. Introducing iqvia medical reasoning (med-r1 8b): Best-in-class medical reasoning llm. Web Page, April 2025. URL https://www.iqvia.com/blogs/2025/04/ introducing-iqvia-medical-reasoning-med-r1-8b . Accessed 2025-06-11. ↗
  26. Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, et al. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on artificia… find
  27. Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, et al. Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463, 2021. — [arXiv:2106.14463](https://arxiv.org/abs/2106.14463) find
  28. Ronnachai Jaroensri, Ellery Wulczyn, Narayan Hegde, Trissia Brown, Isabelle Flament-Auvigne, Fraser Tan, Yuannan Cai, Kunal Nagpal, Emad A Rakha, David J Dabbs, et al. Deep learning models for histologic grading of breast cancer and association with disease prognosis. NPJ breast cancer, 8(1): 113, 2… find
  29. Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. What disease does this patient have? a large-scale open domain question answering dataset from medical exams. Applied Sciences, 11(14):6421, 2021.
  30. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. Pubmedqa: A dataset for biomedical research question answering. arXiv preprint arXiv:1909.06146, 2019.
  31. John Snow Labs. Jsl-medllama-3-8b-v2.0. https://huggingface.co/johnsnowlabs/ JSL-MedLlama-3-8B-v2.0 , 2024. Accessed 2025-06-11. ↗
  32. A Johnson, T Pollard, R Mark, S Berkowitz, and S Horng. MIMIC-CXR database (version 2.0. 0). PhysioNet, 2019a. find
  33. Alistair Johnson, Matthew Lungren, Yifan Peng, Zhiyong Lu, Roger Mark, Seth Berkowitz, and Steven Horng. Mimic-cxr-jpg - chest radiographs with structured labels, November 2019b. URL https://doi.org/10.13026/8360-t248 . — [doi:10.13026/8360-t248](https://doi.org/10.13026/8360-t248) ↗
  34. Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, 6(1):317, 2019c. find
  35. Alistair EW Johnson, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J Pollard, Sicheng Hao, Benjamin Moody, Brian Gow, et al. Mimic-iv, a freely accessible electronic health record dataset. Scientific data, 10(1):1, 2023.
  36. J. N. Kather, N. Halama, and A. Marx. 100,000 histological images of human colorectal cancer and healthy tissue, 2018. URL https://doi.org/10.5281/zenodo.1214456 . [Data set]. — [doi:10.5281/zenodo.1214456](https://doi.org/10.5281/zenodo.1214456) ↗
  37. Atilla P Kiraly, Sebastien Baur, Kenneth Philbrick, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Nick George, Fayaz Jamil, Jing Tang, et al. Health ai developer foundations. arXiv preprint arXiv:2411.15128, 2024. — [arXiv:2411.15128](https://arxiv.org/abs/2411.15128) find
  38. Sunjun Kweon, Jiyoun Kim, Heeyoung Kwak, Dongchul Cha, Hangyul Yoon, Kwang Hyun Kim, Jeewon Yang, Seunghyun Won, and Edward Choi. Ehrnoteqa: An llm benchmark for real-world clinical practice using discharge summaries. PhysioNet, version 1.0.1, June 2024. URL https://doi.org/10.13026/acga-ht95 . — [doi:10.13026/acga-ht95](https://doi.org/10.13026/acga-ht95) ↗
  39. Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, and Richard Dufour. Biomistral: A collection of open-source pretrained large language models for medical domains. arXiv preprint arXiv:2402.10373, 2024.
  40. Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. A dataset of clinically generated visual questions and answers about radiology images. Scientific data, 5(1):1–10, 2018. find
  41. Gyubok Lee, Sunjun Kweon, Seongsu Bae, and Edward Choi. Overview of the EHRSQL 2024 shared task on reliable text-to-SQL modeling on electronic health records. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 644–654. Association for Computational Linguistics, June 2024.… find
  42. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems, 36:28541–28564, 2023.
  43. Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, and Xiao-Ming Wu. Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pages 1650–1654. find
  44. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744, 2023.
  45. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. Advances in neural information processing systems, 36, 2024.
  46. Yuan Liu, Ayush Jain, Clara Eng, David H Way, Kang Lee, Peggy Bui, Kimberly Kanada, Guilherme de Oliveira Marinho, Jessica Gallegos, Sara Gabriele, et al. A deep learning system for differential diagnosis of skin diseases. Nature medicine, 26(6):900–908, 2020. find
  47. Faisal Mahmood. A benchmarking crisis in biomedical machine learning. Nature Medicine, 31(4): 1060–1060, 2025. find
  48. Anna Majkowska, Sid Mittal, David F Steiner, Joshua J Reicher, Scott Mayer McKinney, Gavin E Duggan, Krish Eswaran, Po-Hsuan Cameron Chen, Yun Liu, Sreenivasa Raju Kalidindi, et al. Chest radiograph interpretation with deep learning models: assessment with radiologist-adjudicated reference standards… find
  49. Yasuhide Miura, Yuhao Zhang, Emily Bao Tsai, Curtis P Langlotz, and Dan Jurafsky. Improving factual completeness and consistency of image-to-text radiology report generation. arXiv preprint arXiv:2010.10042, 2020. find
  50. Kunal Nagpal, Davis Foote, Yun Liu, Po-Hsuan Cameron Chen, Ellery Wulczyn, Fraser Tan, Niels Olson, Jenny L Smith, Arash Mohtashamian, James H Wren, et al. Development and validation of a deep learning algorithm for improving gleason scoring of prostate cancer. NPJ digital medicine, 2 (1):48, 2019. find
  51. Kunal Nagpal, Davis Foote, Fraser Tan, Yun Liu, Po-Hsuan Cameron Chen, David F Steiner, Naren Manoj, Niels Olson, Jenny L Smith, Arash Mohtashamian, et al. Development and validation of a deep learning algorithm for gleason grading of prostate cancer from biopsy specimens. JAMA oncology, 6(9):1372–1… find
  52. Aaron Nicolson, Jason Dowling, and Bevan Koopman. Improving chest x-ray report generation by leveraging warm starting. Artificial intelligence in medicine, 144:102633, 2023. find
  53. Tobi Olatunji, Charles Nimo, Abraham Owodunni, Tassallah Abdullahi, Emmanuel Ayodele, Mardhiyah Sanni, Chinemelu Aka, Folafunmi Omofoye, Foutse Yuehgoh, Timothy Faniran, et al. Afrimed-qa: A pan-african, multi-specialty, medical question-answering benchmark dataset. arXiv preprint arXiv:2411.15640,…
  54. OpenAI. GPT-4V(ision) Technical Work and Authors. Technical report, OpenAI, 2023. URL https://cdn.openai.com/contributions/gpt-4v.pdf . ↗
  55. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Conference on health, inference, and learning, pages 248–260. PMLR, 2022. — MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering
  56. Anusri Pampari, Preethi Raghavan, Jennifer Liang, and Jian Peng. emrQA: A large corpus for question answering on electronic medical records. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2357–2368. Association for Computational Linguistics, october-…
  57. Preethi Raghavan, Jennifer J Liang, Diwakar Mahajan, Rachita Chandra, and Peter Szolovits. emrK-BQA: A clinical knowledge-base question answering dataset. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 64–73. Association for Computational Linguistics, june 2021. doi: 10… find
  58. Khaled Saab, Tao Tu, Wei-Hung Weng, Ryutaro Tanno, David Stutz, Ellery Wulczyn, Fan Zhang, Tim Strother, Chunjong Park, Elahe Vedadi, et al. Capabilities of gemini models in medicine. arXiv preprint arXiv:2404.18416, 2024.
  59. Apaar Sadhwani, Huang-Wei Chang, Ali Behrooz, Trissia Brown, Isabelle Auvigne-Flament, Hardik Patel, Robert Findlater, Vanessa Velez, Fraser Tan, Kamilla Tekiela, et al. Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology… find
  60. Samuel Schmidgall, Rojin Ziaei, Carl Harris, Eduardo Reis, Jeffrey Jopling, and Michael Moor. Agentclinic: a multimodal agent benchmark to evaluate ai in simulated clinical environments. arXiv preprint arXiv:2405.07960, 2024. — [arXiv:2405.07960](https://arxiv.org/abs/2405.07960) find
  61. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. Large language models encode clinical knowledge. Nature, 620(7972):172–180, 2023a.
  62. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. Large language models encode clinical knowledge. Nature, 620(7972):172–180, 2023b.
  63. Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, Stephen Pfohl, Heather Cole-Lewis, Darlene Neal, et al. Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617, 2023c.
  64. Andreas Steiner, André Susano Pinto, Michael Tschannen, Daniel Keysers, Xiao Wang, Yonatan Bitton, Alexey Gritsenko, Matthias Minderer, Anthony Sherbondy, Shangbang Long, et al. Paligemma 2: A family of versatile vlms for transfer. arXiv preprint arXiv:2412.03555, 2024. — [arXiv:2412.03555](https://arxiv.org/abs/2412.03555) find
  65. Ryutaro Tanno, David Barrett, Andrew Sellergren, Sumedh Ghaisas, Sumanth Dathathri, Abigail See, Johannes Welbl, Karan Singhal, Shekoofeh Azizi, Tao Tu, et al. Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation. arXiv preprint arXiv:23… — [arXiv:2311.18260](https://arxiv.org/abs/2311.18260) find
  66. Augustin Toma, Patrick R Lawler, Jimmy Ba, Rahul G Krishnan, Barry B Rubin, and Bo Wang. Clinical camel: An open-source expert-level medical language model with dialogue-based knowledge encoding. arXiv preprint arXiv:2305.12031, 2023. find
  67. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  68. Tao Tu, Shekoofeh Azizi, Danny Driess, Mike Schaekermann, Mohamed Amin, Pi-Chuan Chang, Andrew Carroll, Charles Lau, Ryutaro Tanno, Ira Ktena, et al. Towards generalist biomedical AI. NEJM AI, 1(3):AIoa2300138, 2024. find
  69. Eugene Vorontsov, Alican Bozkurt, Adam Casson, George Shaikovski, Michal Zelechowski, Siqi Liu, Kristen Severson, Eric Zimmermann, James Hall, Neil Tenenholtz, et al. Virchow: A million-slide digital pathology foundation model. arXiv preprint arXiv:2309.07778, 2023. — [arXiv:2309.07778](https://arxiv.org/abs/2309.07778) find
  70. Jason Walonoski, Mark Kramer, Joseph Nichols, Andre Quina, Chris Moesel, Dylan Hall, Carlton Duffett, Kudakwashe Dube, Thomas Gallagher, and Scott McLachlan. Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record. Journa… — [doi:10.1093/jamia/ocx079](https://doi.org/10.1093/jamia/ocx079) find
  71. Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, and Ronald M Summers. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE conference on computer vision and patte… find
  72. Joy Wu, Nkechinyere Agu, Ismini Lourentzou, Arjun Sharma, Joseph Paguio, Jasper Seth Yao, Edward Christopher Dee, William Mitchell, Satyananda Kashyap, Andrea Giovannini, et al. Chest imagenome dataset. Physio Net, 2021. find
  73. Yunfei Xie, Ce Zhou, Lang Gao, Juncheng Wu, Xianhang Li, Hong-Yu Zhou, Sheng Liu, Lei Xing, James Zou, Cihang Xie, et al. Medtrinity-25m: A large-scale multimodal dataset with multigranular annotations for medicine. arXiv preprint arXiv:2408.02900, 2024. — [arXiv:2408.02900](https://arxiv.org/abs/2408.02900) find
  74. Shawn Xu, Lin Yang, Christopher Kelly, Marcin Sieniek, Timo Kohlberger, Martin Ma, Wei-Hung Weng, Attila Kiraly, Sahar Kazemzadeh, Zakkai Melamed, et al. ELIXR: Towards a general purpose x-ray artificial intelligence system through alignment of large language models and radiology vision encoders. ar… — [arXiv:2308.01317](https://arxiv.org/abs/2308.01317) find
  75. An Yan, Zexue He, Xing Lu, Jiang Du, Eric Chang, Amilcare Gentili, Julian McAuley, and Chun-nan Hsu. Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4009–4015, 2021. find
  76. Lin Yang, Shawn Xu, Andrew Sellergren, Timo Kohlberger, Yuchen Zhou, Ira Ktena, Atilla Kiraly, Faruk Ahmed, Farhad Hormozdiari, Tiam Jaroensri, et al. Advancing multimodal medical capabilities of gemini. arXiv preprint arXiv:2405.03162, 2024. — [arXiv:2405.03162](https://arxiv.org/abs/2405.03162) find
  77. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–2380,…
  78. Anna Zawacki, Carol Wu, George Shih, Julia Elliott, Mikhail Fomitchev, Mohannad Hussain, ParasLakhani, Phil Culliton, and Shunxing Bao. Siim-acr pneumothorax segmentation. https://kaggle.com/competitions/siim-acr-pneumothorax-segmentation , 2019. Kaggle. ↗
  79. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid loss for language image pre-training. In Proceedings of the IEEE/CVF international conference on computer vision, pages 11975–11986, 2023.
  80. Kai Zhang, Jun Yu, Eashan Adhikarla, Rong Zhou, Zhiling Yan, Yixin Liu, Zhengliang Liu, Lifang He, Brian Davison, Xiang Li, et al. Biomedgpt: A unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks. arXiv e-prints, pages arXiv–2305, 2023. find
  81. Hong-Yu Zhou, Subathra Adithan, Julián Nicolás Acosta, Eric J. Topol, and Pranav Rajpurkar. A generalist learner for multifaceted medical image interpretation, 2024. URL https://arxiv.org/abs/2405.07988 . — [arXiv:2405.07988](https://arxiv.org/abs/2405.07988) ↗
  82. Yuxin Zuo, Shang Qu, Yifei Li, Zhangren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, and Bowen Zhou. Medxpertqa: benchmarking expert-level medical reasoning and understanding. In ICML’25: Proceedings of the 42nd International Conference on Machine Learning, pages 80961–80990, 2025.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sellergren-2025-medgemma-technical-report/