_version_ 1866916236470779904
author Yang, Lin
Xu, Shawn
Sellergren, Andrew
Kohlberger, Timo
Zhou, Yuchen
Ktena, Ira
Kiraly, Atilla
Ahmed, Faruk
Hormozdiari, Farhad
Jaroensri, Tiam
Wang, Eric
Wulczyn, Ellery
Jamil, Fayaz
Guidroz, Theo
Lau, Chuck
Qiao, Siyuan
Liu, Yun
Goel, Akshay
Park, Kendall
Agharwal, Arnav
George, Nick
Wang, Yang
Tanno, Ryutaro
Barrett, David G. T.
Weng, Wei-Hung
Mahdavi, S. Sara
Saab, Khaled
Tu, Tao
Kalidindi, Sreenivasa Raju
Etemadi, Mozziyar
Cuadros, Jorge
Sorensen, Gregory
Matias, Yossi
Chou, Katherine
Corrado, Greg
Barral, Joelle
Shetty, Shravya
Fleet, David
Eslami, S. M. Ali
Tse, Daniel
Prabhakara, Shruthi
McLean, Cory
Steiner, Dave
Pilgrim, Rory
Kelly, Christopher
Azizi, Shekoofeh
Golden, Daniel
author_facet Yang, Lin
Xu, Shawn
Sellergren, Andrew
Kohlberger, Timo
Zhou, Yuchen
Ktena, Ira
Kiraly, Atilla
Ahmed, Faruk
Hormozdiari, Farhad
Jaroensri, Tiam
Wang, Eric
Wulczyn, Ellery
Jamil, Fayaz
Guidroz, Theo
Lau, Chuck
Qiao, Siyuan
Liu, Yun
Goel, Akshay
Park, Kendall
Agharwal, Arnav
George, Nick
Wang, Yang
Tanno, Ryutaro
Barrett, David G. T.
Weng, Wei-Hung
Mahdavi, S. Sara
Saab, Khaled
Tu, Tao
Kalidindi, Sreenivasa Raju
Etemadi, Mozziyar
Cuadros, Jorge
Sorensen, Gregory
Matias, Yossi
Chou, Katherine
Corrado, Greg
Barral, Joelle
Shetty, Shravya
Fleet, David
Eslami, S. M. Ali
Tse, Daniel
Prabhakara, Shruthi
McLean, Cory
Steiner, Dave
Pilgrim, Rory
Kelly, Christopher
Azizi, Shekoofeh
Golden, Daniel
contents Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03162
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advancing Multimodal Medical Capabilities of Gemini
Yang, Lin
Xu, Shawn
Sellergren, Andrew
Kohlberger, Timo
Zhou, Yuchen
Ktena, Ira
Kiraly, Atilla
Ahmed, Faruk
Hormozdiari, Farhad
Jaroensri, Tiam
Wang, Eric
Wulczyn, Ellery
Jamil, Fayaz
Guidroz, Theo
Lau, Chuck
Qiao, Siyuan
Liu, Yun
Goel, Akshay
Park, Kendall
Agharwal, Arnav
George, Nick
Wang, Yang
Tanno, Ryutaro
Barrett, David G. T.
Weng, Wei-Hung
Mahdavi, S. Sara
Saab, Khaled
Tu, Tao
Kalidindi, Sreenivasa Raju
Etemadi, Mozziyar
Cuadros, Jorge
Sorensen, Gregory
Matias, Yossi
Chou, Katherine
Corrado, Greg
Barral, Joelle
Shetty, Shravya
Fleet, David
Eslami, S. M. Ali
Tse, Daniel
Prabhakara, Shruthi
McLean, Cory
Steiner, Dave
Pilgrim, Rory
Kelly, Christopher
Azizi, Shekoofeh
Golden, Daniel
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Many clinical tasks require an understanding of specialized data, such as medical images and genomics, which is not typically found in general-purpose large multimodal models. Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data. Med-Gemini-2D sets a new standard for AI-based chest X-ray (CXR) report generation based on expert evaluation, exceeding previous best results across two separate datasets by an absolute margin of 1% and 12%, where 57% and 96% of AI reports on normal cases, and 43% and 65% on abnormal cases, are evaluated as "equivalent or better" than the original radiologists' reports. We demonstrate the first ever large multimodal model-based report generation for 3D computed tomography (CT) volumes using Med-Gemini-3D, with 53% of AI reports considered clinically acceptable, although additional research is needed to meet expert radiologist reporting quality. Beyond report generation, Med-Gemini-2D surpasses the previous best performance in CXR visual question answering (VQA) and performs well in CXR classification and radiology VQA, exceeding SoTA or baselines on 17 of 20 tasks. In histopathology, ophthalmology, and dermatology image classification, Med-Gemini-2D surpasses baselines across 18 out of 20 tasks and approaches task-specific model performance. Beyond imaging, Med-Gemini-Polygenic outperforms the standard linear polygenic risk score-based approach for disease risk prediction and generalizes to genetically correlated diseases for which it has never been trained. Although further development and evaluation are necessary in the safety-critical medical domain, our results highlight the potential of Med-Gemini across a wide range of medical tasks.
title Advancing Multimodal Medical Capabilities of Gemini
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.03162