From task-specific AI to multimodal foundation models in PET/CT: a readiness framework for clinical translation.
- 1Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
- 2Department of Thoracic/Head and Neck Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
- 3Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
Abstract
Artificial intelligence in PET/CT is evolving from narrowly optimized systems toward reusable pretrained representations and multimodal models. PET/CT is a demanding test case because clinically meaningful interpretation must preserve quantitative molecular information while integrating anatomic CT, acquisition metadata, longitudinal examinations, and free-text imaging reports. This focused narrative review synthesizes literature reported from January 2021 through July 2026, spanning PET reconstruction and enhancement, attenuation correction, segmentation, outcome modeling, pretrained representations, vision-language systems, and agentic workflows. We distinguish task-specific models, reusable pretrained representations, promptable models, vision-language systems, generalist foundation-model candidates, and agentic systems according to demonstrated capabilities, while separately considering evaluation benchmarks. Task-specific deep learning has demonstrated promising technical performance in low-count imaging and whole-body tumor analysis, but most evidence remains retrospective and restricted by radiotracer, disease, scanner, institution, or endpoint. Emerging PET-native studies demonstrate label-efficient segmentation, image-text grounding, report generation, and modular tool orchestration; however, they do not yet establish broad cross-tracer generalization or prospective clinical benefit. We therefore propose MOSAIC-PET, an author-developed heuristic six-domain evaluation framework for PET/CT foundation models encompassing Molecular fidelity, Organ and anatomic grounding, Semantic faithfulness, Adaptability, Integration and clinical impact, and Continuous governance. MOSAIC-PET has not undergone Delphi consensus or formal validation and is intended to organize PET-specific evidence requirements rather than function as a validated clinical-readiness tool. The near-term translational priority is the development of modular, auditable systems in which validated quantitative tools and evidence-linked language outputs remain under specialist oversight, with progression from external testing to silent evaluation, assisted-use studies, clinical-impact assessment, and continuous lifecycle monitoring.
Related
- Foundation first: a health-system readiness framework for responsible AI adoption in Somalia.
- Enhancing Evidence Translation Through Structured Clinical Reasoning: A Mixed-Methods Controlled Feasibility Study of Peer Visibility and Readiness Mechanisms in Applied Learning
- Clinical translation of artificial intelligence in musculoskeletal care: a systematic review of current applications, evidence gaps, and implementation readiness
- Benchmark Readiness of Open-access Musculoskeletal Radiograph Datasets for Foundation Model Segmentation: A Systematic Audit
- Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning
BibTeX
@article{muneer2026from,
title = {{From task-specific AI to multimodal foundation models in PET/CT: a readiness framework for clinical translation.}},
author = {Amgad Muneer and Maliazurina B Saad and Hui Xu and Jia Wu},
journal = {Frontiers in nuclear medicine},
year = {2026},
month = oct,
doi = {10.3389/fnume.2026.1956567},
url = {https://europepmc.org/article/MED/42923220},
note = {CC BY},
}
RIS
TY - JOUR
TI - From task-specific AI to multimodal foundation models in PET/CT: a readiness framework for clinical translation.
AU - Amgad Muneer
AU - Maliazurina B Saad
AU - Hui Xu
AU - Jia Wu
PY - 2026
DA - 2026/10/08
JO - Frontiers in nuclear medicine
DO - 10.3389/fnume.2026.1956567
UR - https://europepmc.org/article/MED/42923220
AB - Artificial intelligence in PET/CT is evolving from narrowly optimized systems toward reusable pretrained representations and multimodal models. PET/CT is a demanding test case because clinically meaningful interpretation must preserve quantitative molecular information while integrating anatomic CT, acquisition metadata, longitudinal examinations, and free-text imaging reports. This focused narrative review synthesizes literature reported from January 2021 through July 2026, spanning PET reconstruction and enhancement, attenuation correction, segmentation, outcome modeling, pretrained representations, vision-language systems, and agentic workflows. We distinguish task-specific models, reusable pretrained representations, promptable models, vision-language systems, generalist foundation-model candidates, and agentic systems according to demonstrated capabilities, while separately considering evaluation benchmarks. Task-specific deep learning has demonstrated promising technical performance in low-count imaging and whole-body tumor analysis, but most evidence remains retrospective and restricted by radiotracer, disease, scanner, institution, or endpoint. Emerging PET-native studies demonstrate label-efficient segmentation, image-text grounding, report generation, and modular tool orchestration; however, they do not yet establish broad cross-tracer generalization or prospective clinical benefit. We therefore propose MOSAIC-PET, an author-developed heuristic six-domain evaluation framework for PET/CT foundation models encompassing Molecular fidelity, Organ and anatomic grounding, Semantic faithfulness, Adaptability, Integration and clinical impact, and Continuous governance. MOSAIC-PET has not undergone Delphi consensus or formal validation and is intended to organize PET-specific evidence requirements rather than function as a validated clinical-readiness tool. The near-term translational priority is the development of modular, auditable systems in which validated quantitative tools and evidence-linked language outputs remain under specialist oversight, with progression from external testing to silent evaluation, assisted-use studies, clinical-impact assessment, and continuous lifecycle monitoring.
SN - 2673-8880
ER -