MedGemma 1.5 Technical Report

Andrew Sellergren; Chufan Gao; Fereshteh Mahvar; Timo Kohlberger; Fayaz Jamil; Madeleine Traverse; Alberto Tono; Bashir Sadjad

cs.AIApr 6, 2026

MedGemma 1.5 Technical Report

Authors: Andrew Sellergren, Chufan Gao, Fereshteh Mahvar, Timo Kohlberger, Fayaz Jamil, Madeleine Traverse, Alberto Tono, Bashir Sadjad, Lin Yang, Charles Lau, Liron Yatziv, Tiffany Chen, Bram Sterling, Kenneth Philbrick, Richa Tiwari, Yun Liu, Madhuram Jajoo, Chandrashekar Sankarapu, Swapnil Vispute, Harshad Purandare, Abhishek Bijay Mishra, Sam Schmidgall, Tao Tu, Anil Palepu, Chunjong Park, Tim Strother, Rahul Thapa, Yong Cheng, Preeti Singh, Kat Black, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Joelle Barral, Tris Warkentin, Shravya Shetty, Dale Webster, Sunny Virmani, David F. Steiner, Can Kirmizibayrak, Daniel Golden

Abstract

We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/medgemma.

Figures & tables

Figure 1: Overview of model capabilities within the MedGemma collection. The updated MedGemma 1.5 4B architecture now supports 3D radiology (CT/MRI volumes), pathology whole slide imaging (WSI), anatomical localization, and multi-timepoint analysis. The original MedGemma 27B model remains available for complex clinical knowledge and reasoning tasks and MedSigLIP remains available for medical image classification and retrieval tasks.

Figure 2: The left panel details accuracy on medical text Q&A tasks (MedQA and EHRQA), while the right panel highlights performance across diverse medical imaging capabilities. Notably, the "medical image interpretation" score represents an unweighted macro average of the model’s performance across 7 distinct imaging tasks including MIMIC-CXR (both RadGraph F1 and report generation macro F1), CheXpert (unweighted average across 5 conditions), CXR 14 (unweighted average across 3 conditions), Path MCQA, DermMCQA, and EyePACS. "Lab report extraction" is macro-averaged over results from EHR dataset 2, 3 and 4 as well as Mendeley Clinical Laboratory Test Reports (macro F1). All scores are reported as percentages. While the out-of-the-box performance is highly promising, the model is not meant to be deployed without the necessary clinical fine-tuning. Fine-tuning may improve results and adapt the framework for practical use.

Modality	Dataset	No. Train Examples	Training stages	Description
Radiology	CXR-IND1	605,732	PT, Distill, RL	Dataset of chest X-ray images and free text reports from a large hospital system based in India
	CT Dataset 1	282,963	PT, Distill, RL	Dataset of different axial CT studies across body parts (head, chest, abdomen) from a US-based radiology outpatient diagnostic center network.
	MRI Dataset 1	167,674	PT, Distill, RL	Dataset of different axial multi-parametric MRI studies across body parts (head, abdomen, knee) from a US-based radiology outpatient diagnostic center network.
	Chest ImaGenome ( Wu et al., 2021 )	39,968	RL	Dataset of chest X-ray with sequential images and bounding boxes from IBM Research.
Pathology Whole Slide Imaging	Internal WSI Histopathology	335,825	PT, RL	WSIs with paired final diagnosis text reports. WSIs were tiled into individual patches and aggregated for input as described in the Methods.
Dermatology	Dermatology Dataset 4	25,560	PT, Distill	Dermatology dataset featuring multiple images and longitudinal visits and records from Japan.

Table 1: Additional training data for MedGemma 4B 1.5 relative to MedGemma 1

Task	Dataset	Modality	No. Eval. Examples	OOD $\dagger$	Public *
Medical text QA	EHRNoteQA ( Kweon et al., 2024 )	Text	962	✓	✓
CXR temporal analysis	MS-CXR-T ( Bannur et al., 2023b )	Radiology longitudinal	1326	-	✓
3D CT classification	CT Dataset 1	Radiology CT (Volumes)	1229	-	-
3D CT classification	CT-RATE ( Hamamci et al., 2024 )	Radiology CT (Volumes)	1558	✓	✓
CXR Finding localization	Chest ImaGenome ( Wu et al., 2021 )	Radiology localization	10000	-	✓
Pathology WSI to text	WSI Histopath	Pathology WSIs	9614	-	-

Table 2: Additional evaluation datasets for MedGemma 1.5

Small Models				Large Models
Task	Metric	MedGemma 1 4B	MedGemma 1.5 4B	MedGemma 1 27B	Qwen3 VL 4B	Gemini 3 Flash	Gemini 3 Pro
Text evaluation
MedQA (4-op) ( Jin et al., 2021 )	Accuracy	64.4	69.1	85.3	76.8	94.3	95.1
MedMCQA ( Pal et al., 2022 )	Accuracy	55.7	59.8	70.2	63.7	85.2	86.1
PubMedQA ( Jin et al., 2019 )	Accuracy	73.4	67.6	77.2	74.8	80.8	82.2
MMLU Med ( Hendrycks et al., 2020 )	Accuracy	70.0	69.7	86.2	78.3	87.5	88.1

Table 3: MedGemma 1.5 performance for original MedGemma 1 evaluation tasks We bolded best performing small models and large models separately.

		Small Models						Large Models
Task	Metric	MedGemma 1 4B	MedGemma 1.5 4B	MedGemma 1 27B	Qwen3 VL 4B	Gemma 3 4B	Gemma 3 27B	Gemini 3.0 Flash	Gemini 3.0 Pro	External SOTA
Text Only
EHRNoteQA	Accuracy	79.4	80.4	90.7	90.6	78.0	90.3	93.9	95.0	95.15-97.16 (1)
Document Understanding
EHR Dataset 2	Macro F1	78	91	76	-	84	93	92	93	-
EHR Dataset 3	Macro F1	50	71	66	-	61	74	74	90	-

Table 4: New Evaluation Task Results

Figure 3: Overview of MedGemma 1.5 capabilities. The updated 4B architecture now supports 3D radiology (CT/MRI volumes).

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Task	Metric	MedGemma 1 4B	MedGemma 1.5 4B	Gemini 3.0 Flash
CT-RATE ∗ (3D CT)	Macro F1	23.5	26.9	8.5

Appendix

Table 5: CT Rate Results

Type	Benchmark	MedGemma 1 4B	MedGemma 1.5 4B	Gemma 3 4B §	MedGemma 1 27B	Gemma 3 27B §
Text-only	MMLU Pro	39.1	33.8	43.6	60.2	67.5

Appendix

Table 6: Accuracy results on general, non-medical benchmarks.

Task	Prompt Template / Suffix
MedQA	{{ question }}\nYou may write out your argument before stating your final, very short, definitive, and concise answer (no more than a few words or the letter corresponding to your answer choice if the question is multiple choice) X in the format "Final Answer: X":
PubMedQA
MedMCQA
MMLU
MedXpertQA (Text)
AfriMed

Appendix

Table 7: Updated Prompts (Version 1.5) for General Medical Text Evaluation Tasks

Task	Prompt Template
MIMIC-CXR	{{ image }} + {{ question }} You MUST end your responce with either "Final Answer: yes" or "Final Answer: no
CheXpert
CXR14

Appendix

Table 8: Updated Prompts (Version 1.5) for Multimodal Binarized MCQ Evaluation Tasks. These tasks involve binary classification (Yes/No) and use a strict format constraint in Version 1.5.

Task	Prompt Template
SlakeVQA	{{image }} + {{ question }} You may write out your argument before stating your final, very short, definitive, and concise answer X (no more than a few words or the letter corresponding to your answer choice if the question is multiple choice) in the format "Final Answer: X":
VQA-Rad	{{image }} + {{ question }} You may write out your argument before stating your final, very short, definitive, and concise answer X (no more than a few words or the letter corresponding to your answer choice if the question is multiple choice) in the format "Final Answer: X":
Pathology WSI	{{images }} + Provide a brief diagnostic text for the set of pathology patches extracted from a pathology slide. Consider the tissue type and procedure (below) when deciding what to include in the diagnostic text. {{ type_procedure }} {{ question }}
DermMCQA	{{image }} + {{ question }} You must choose the most likely diagnosis and respond with "The most likely diagnosis is:" followed by your choice letter.
EyePACS	{{image }} + Given this fundus image, determine the most likely diabetic retinopathy (DR) stage present, even if you are unsure: A: No DR B: mild DR C: moderate DR D: severe DR E: proliferative DR You must choose the most likely diagnosis and respond with "The most likely diagnosis is:" followed by your choice letter.

Appendix

Table 9: Updated Prompts (Version 1.5) for Visual Evaluation Tasks. These tasks cover general visual question answering and specific diagnostic classification.

Task

Prompt Template

EHRNoteQA

BEGIN_INSTRUCTIONS Given the following discharge note for a patient, answer the question by only picking one of the A, B, C, D, E options. Each discharge note starts with "DISCHARGE ?:", the question starts with "QUESTION:" and the choices with "CHOICE_?:" where ? is a single character. To answer, describe your thought process for each choice; finish your answer with "Final Answer: (?)" where ? is a single character indicating the correct choice. END_INSTRUCTIONS {discharge_note} QUESTION: {orig_question} the choices are: CHOICE_A: {choice_A} CHOICE_B: {choice_B} CHOICE_C: {choice_C} CHOICE_D: {choice_D} CHOICE_E: {choice_E} Describe your thought process for each choice and end your answer with "Final Answer: (?)" where ? is a single character indicating the correct answer. Use this exact format at the end "Final Answer: (?)".

Appendix

Table 10: Prompt (Version 1.5) for EHRNoteQA

Task	Prompt Template
EHR Dataset 2	You are a Clinical Data Extraction Specialist. Your job is to parse lab reports with high precision. From the given lab report, extract all lab tests into a JSON list. Each test object in the list must include: name, result, unit, range, panel, method, specimen, sample_collection_time (formatted as DD-MM-YYYY HH:MM:SS)
EHR Dataset 3
EHR Dataset 4
Mendeley Clinical Laboratory Test Reports

Appendix

Table 11: Prompt (Version 1.5) for Document Understanding PNG/PDF images to JSON

Task	Prompt Template
Chest ImaGenome (Localization)	{{image }} + Where is the {object}?

Appendix

Table 12: Prompt (Version 1.5) for Anatomy Localization Tasks

Task	Prompt Template
CT-US1	{{images }} + After looking at the indication and patient history "{HISTORY}"... Is there "{Label}" in the CT volume? You may write out your argument before stating your final answer "Final Answer: yes" or "Final Answer: no".
MRI-US1	{{images }} + ’After looking at the patient history "history_text", Is there {{label}} in the MRI volume? You may write out your argument before stating your final answer ""Final Answer: yes"" or ""Final Answer: no""
CT-RATE	{{images }} + You are an expert radiologist for chest CT. Looking at these CT slices, is there Emphysema? Answer with ’Final Answer: yes’ or ’Final Answer: no’

Appendix

Table 13: Prompt (Version 1.5) for 3D CT Volumetric Analysis

Medical Imaging Foundation Models

Medical imaging foundation models learn reusable representations for tasks across clinical images, modalities, and institutions.

See all 234 papers

Single-Pass Decision Scores Enable Rapid Classification with Adjustable Thresholds in Medical Multimodal Large Language Models
Oct 14, 2026Patrick Wienholt, Frederik Hauke, Christiane Kuhl +3Medical LLMs Multimodal Classification
Lab for Artificial Intelligence in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. +2
MultiMedVision: Multi-Modal Medical Vision Framework
May 9, 2026Frank Li, Bardia Khosravi, Mohammadreza Chavoshi +5Medical Imaging Foundation Models Vision Transformer
Emory University · Yale University
Medical thinking with multiple images
Apr 14, 2026Zonghai Yao, Benlu Wang, Yifan Zhang +8Medical VQA Multimodal Reasoning
Manning College of Information and Computer Sciences, UMass Amherst · Center for Healthcare Organization and Implementation Research, VA Bedford Health Care · Department of Computer Science, Yale University +2

Oct 14, 2026J/K move · Enter open · S save

Single-Pass Decision Scores Enable Rapid Classification with Adjustable Thresholds in Medical Multimodal Large Language Models

Patrick Wienholt, Frederik Hauke, Christiane Kuhl, Jakob Nikolas Kather+2

Lab for Artificial Intelligence in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. · Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany.+2

Medical LLMs Multimodal Classification Language Model Calibration Medical Image Classification

Open paper AskPDF arXiv

Multimodal large language models (MLLMs) answer binary clinical questions with a yes or no token, leaving the decision threshold implicit and fixed. We derive a continuous score from a single forward pass by renormalizing the probabilities of the yes and no tokens, allowing the threshold to be adapted to clinical needs without retraining. We evaluated this approach with MedGemma and Gemma-3 (4B and 27B) on six medical imaging datasets. The default threshold was frequently misaligned with the task: for identifying normal chest radiographs, MedGemma-27B labeled every image as abnormal, whereas a validation-selected threshold yielded a sensitivity of 0.945 and a specificity of 0.696. Normalization achieved the highest AUROC on four of six datasets (CheXpert: 0.819 vs. 0.777 for raw and 0.743 for text-elicited probabilities), and a single decision required 53-79 ms on one GPU. This simple post-hoc method turns medical MLLMs into fast classifiers with adjustable operating points. Code: https://github.com/TruhnLab/llm-threshold-calibration

Abstract

Medical Imaging Foundation Models

Explore similar work

Single-Pass Decision Scores Enable Rapid Classification with Adjustable Thresholds in Medical Multimodal Large Language Models

MultiMedVision: Multi-Modal Medical Vision Framework

Medical thinking with multiple images