Shih-Cheng Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shih-Cheng Huang has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
Matthew P. Lungren
Microsoft Research, Redmond, USA
6 shared publications- Serena Yeung
Stanford University
6 shared publications - Matthew Lungren
Department of Radiology, Stanford School of Medicine, Microsoft Health & Life Sciences, Stanford, Calif
5 shared publications - Akshay S. Chaudhari
Department of Radiology Stanford University Stanford California USA
4 shared publications - Curtis P. Langlotz
Stanford University
3 shared publications - Imon Banerjee
Department of Radiology, Mayo Clinic, Phoenix, USA
3 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 1 April 2025
- Published by Springer Nature in Nature Communications
- Vol. 16  (1) , 1-15
A clinically accessible small multimodal radiology model and evaluation metric for chest X-ray findings
Large foundation models show promise in biomedicine but face challenges in clinical use due to performance gaps, accessibility, cost, and lack of scalable evaluation. Here we show that open-source small multimodal models can bridge these gaps in radiology by generating free-text findings from chest X-ray images. Our data-centric approach leverages 697K curated radiology image-text pairs to train a specialized, domain-adapted chest X-ray encoder. We integrate this encoder with pre-trained language models via a lightweight adapter that aligns image and text modalities. To enable robust, clinically relevant evaluation, we develop and validate CheXprompt, a GPT-4-based metric for assessing factual accuracy aligned with radiologists’ evaluations. Benchmarked with CheXprompt and other standard factuality metrics, LLaVA-Rad (7B) achieves state-of-the-art performance, outperforming much larger models like GPT-4V and Med-PaLM M (84B). While not immediately ready for real-time clinical deployment, LLaVA-Rad is a scalable, privacy-preserving and cost-effective step towards clinically adaptable multimodal AI for radiology.
- 1 April 2025
- Published by Springer Nature in Nature Communications
- Vol. 16  (1) , 1-15
Top Cited PapersOpen AccessA clinically accessible small multimodal radiology model and evaluation metric for chest X-ray findings
Large foundation models show promise in biomedicine but face challenges in clinical use due to performance gaps, accessibility, cost, and lack of scalable evaluation. Here we show that open-source small multimodal models can bridge these gaps in radiology by generating free-text findings from chest X-ray images. Our data-centric approach leverages 697K curated radiology image-text pairs to train a specialized, domain-adapted chest X-ray encoder. We integrate this encoder with pre-trained language models via a lightweight adapter that aligns image and text modalities. To enable robust, clinically relevant evaluation, we develop and validate CheXprompt, a GPT-4-based metric for assessing factual accuracy aligned with radiologists’ evaluations. Benchmarked with CheXprompt and other standard factuality metrics, LLaVA-Rad (7B) achieves state-of-the-art performance, outperforming much larger models like GPT-4V and Med-PaLM M (84B). While not immediately ready for real-time clinical deployment, LLaVA-Rad is a scalable, privacy-preserving and cost-effective step towards clinically adaptable multimodal AI for radiology.
- Open Access
Multimodal Foundation Models for Medical Imaging - A Systematic Review and Implementation Guidelines
Advancements in artificial intelligence (AI) offer promising solutions for enhancing clinical workflows and patient care, potentially revolutionizing healthcare delivery. However, the traditional paradigm of AI integration in healthcare is limited by models that rely on single input modalities during training and require extensive labeled data, failing to capture the multimodal nature of medical practice. Multimodal foundation models, particularly Large Vision Language Models (VLMs), have the potential to overcome these limitations by processing diverse data types and learning from large-scale unlabeled datasets or natural pairs of different modalities, thereby significantly contributing to the development of more robust and versatile AI systems in healthcare. In this review, we establish a unified terminology for multimodal foundation models for medical imaging applications and provide a systematic analysis of papers published between 2012 and 2024. In total, we screened 1,144 papers from medical and AI domains and extracted data from 97 included studies. Our comprehensive effort aggregates the collective knowledge of prior work, evaluates the current state of multimodal AI in healthcare, and delineates both prevailing limitations and potential growth areas. We provide implementation guidelines and actionable recommendations for various stakeholders, including model developers, clinicians, policymakers, and dataset curators.
Open AccessMultimodal Foundation Models for Medical Imaging - A Systematic Review and Implementation Guidelines
Advancements in artificial intelligence (AI) offer promising solutions for enhancing clinical workflows and patient care, potentially revolutionizing healthcare delivery. However, the traditional paradigm of AI integration in healthcare is limited by models that rely on single input modalities during training and require extensive labeled data, failing to capture the multimodal nature of medical practice. Multimodal foundation models, particularly Large Vision Language Models (VLMs), have the potential to overcome these limitations by processing diverse data types and learning from large-scale unlabeled datasets or natural pairs of different modalities, thereby significantly contributing to the development of more robust and versatile AI systems in healthcare. In this review, we establish a unified terminology for multimodal foundation models for medical imaging applications and provide a systematic analysis of papers published between 2012 and 2024. In total, we screened 1,144 papers from medical and AI domains and extracted data from 97 included studies. Our comprehensive effort aggregates the collective knowledge of prior work, evaluates the current state of multimodal AI in healthcare, and delineates both prevailing limitations and potential growth areas. We provide implementation guidelines and actionable recommendations for various stakeholders, including model developers, clinicians, policymakers, and dataset curators.
- Open Access
INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
Synthesizing information from multiple data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of patients at risk for pulmonary embolism (PE), along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, radiology report impression sections, and structured electronic health record (EHR) data (i.e. demographics, diagnoses, procedures, vitals, and medications). Using INSPECT, we develop and release a benchmark for evaluating several baseline modeling approaches on a variety of important PE related tasks. We evaluate image-only, EHR-only, and multimodal fusion models. Trained models and the de-identified dataset are made available for non-commercial use under a data use agreement. To the best of our knowledge, INSPECT is the largest multimodal dataset integrating 3D medical imaging and EHR for reproducible methods evaluation and research.
Open AccessINSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
Synthesizing information from multiple data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of patients at risk for pulmonary embolism (PE), along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, radiology report impression sections, and structured electronic health record (EHR) data (i.e. demographics, diagnoses, procedures, vitals, and medications). Using INSPECT, we develop and release a benchmark for evaluating several baseline modeling approaches on a variety of important PE related tasks. We evaluate image-only, EHR-only, and multimodal fusion models. Trained models and the de-identified dataset are made available for non-commercial use under a data use agreement. To the best of our knowledge, INSPECT is the largest multimodal dataset integrating 3D medical imaging and EHR for reproducible methods evaluation and research.
- Top Cited PapersOpen Access
- 26 April 2023
- Published by Springer Nature in npj Digital Medicine
- Vol. 6  (1) , 1-16
Self-supervised learning for medical image classification: a systematic review and implementation guidelines
Advancements in deep learning and computer vision provide promising solutions for medical image analysis, potentially improving healthcare and patient outcomes. However, the prevailing paradigm of training deep learning models requires large quantities of labeled training data, which is both time-consuming and cost-prohibitive to curate for medical images. Self-supervised learning has the potential to make significant contributions to the development of robust medical imaging models through its ability to learn useful insights from copious medical datasets without labels. In this review, we provide consistent descriptions of different self-supervised learning strategies and compose a systematic review of papers published between 2012 and 2022 on PubMed, Scopus, and ArXiv that applied self-supervised learning to medical imaging classification. We screened a total of 412 relevant studies and included 79 papers for data extraction and analysis. With this comprehensive effort, we synthesize the collective knowledge of prior work and provide implementation guidelines for future researchers interested in applying self-supervised learning to their development of medical imaging classification models.
- 26 April 2023
- Published by Springer Nature in npj Digital Medicine
- Vol. 6  (1) , 1-16
Top Cited PapersOpen AccessSelf-supervised learning for medical image classification: a systematic review and implementation guidelines
Advancements in deep learning and computer vision provide promising solutions for medical image analysis, potentially improving healthcare and patient outcomes. However, the prevailing paradigm of training deep learning models requires large quantities of labeled training data, which is both time-consuming and cost-prohibitive to curate for medical images. Self-supervised learning has the potential to make significant contributions to the development of robust medical imaging models through its ability to learn useful insights from copious medical datasets without labels. In this review, we provide consistent descriptions of different self-supervised learning strategies and compose a systematic review of papers published between 2012 and 2022 on PubMed, Scopus, and ArXiv that applied self-supervised learning to medical imaging classification. We screened a total of 412 relevant studies and included 79 papers for data extraction and analysis. With this comprehensive effort, we synthesize the collective knowledge of prior work and provide implementation guidelines for future researchers interested in applying self-supervised learning to their development of medical imaging classification models.
- Open Access
Video Pretraining Advances 3D Deep Learning on Chest CT Tasks
Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practitioners to rely on pretrained 2D models to featurize slices. However, these 2D models have been surpassed by 3D models on 3D computer vision benchmarks since they do not natively leverage cross-sectional or temporal information. In this study, we explore whether natural video pretraining for 3D models can enable higher performance on smaller datasets for 3D medical tasks. We demonstrate video pretraining improves the average performance of seven 3D models on two chest CT datasets, regardless of finetuning dataset size, and that video pretraining allows 3D models to outperform 2D baselines. Lastly, we observe that pretraining on the large-scale out-of-domain Kinetics dataset improves performance more than pretraining on a typically-sized in-domain CT dataset. Our results show consistent benefits of video pretraining across a wide array of architectures, tasks, and training dataset sizes, supporting a shift from small-scale in-domain pretraining to large-scale out-of-domain pretraining for 3D medical tasks. Our code is available at: https://github.com/rajpurkarlab/chest-ct-pretraining
Open AccessVideo Pretraining Advances 3D Deep Learning on Chest CT Tasks
Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practitioners to rely on pretrained 2D models to featurize slices. However, these 2D models have been surpassed by 3D models on 3D computer vision benchmarks since they do not natively leverage cross-sectional or temporal information. In this study, we explore whether natural video pretraining for 3D models can enable higher performance on smaller datasets for 3D medical tasks. We demonstrate video pretraining improves the average performance of seven 3D models on two chest CT datasets, regardless of finetuning dataset size, and that video pretraining allows 3D models to outperform 2D baselines. Lastly, we observe that pretraining on the large-scale out-of-domain Kinetics dataset improves performance more than pretraining on a typically-sized in-domain CT dataset. Our results show consistent benefits of video pretraining across a wide array of architectures, tasks, and training dataset sizes, supporting a shift from small-scale in-domain pretraining to large-scale out-of-domain pretraining for 3D medical tasks. Our code is available at: https://github.com/rajpurkarlab/chest-ct-pretraining
- Open Access
Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation
Given the prevalence of 3D medical imaging technologies such as MRI and CT that are widely used in diagnosing and treating diverse diseases, 3D segmentation is one of the fundamental tasks of medical image analysis. Recently, Transformer-based models have started to achieve state-of-the-art performances across many vision tasks, through pre-training on large-scale natural image benchmark datasets. While works on medical image analysis have also begun to explore Transformer-based models, there is currently no optimal strategy to effectively leverage pre-trained Transformers, primarily due to the difference in dimensionality between 2D natural images and 3D medical images. Existing solutions either split 3D images into 2D slices and predict each slice independently, thereby losing crucial depth-wise information, or modify the Transformer architecture to support 3D inputs without leveraging pre-trained weights. In this work, we use a simple yet effective weight inflation strategy to adapt pre-trained Transformers from 2D to 3D, retaining the benefit of both transfer learning and depth information. We further investigate the effectiveness of transfer from different pre-training sources and objectives. Our approach achieves state-of-the-art performances across a broad range of 3D medical image datasets, and can become a standard strategy easily utilized by all work on Transformer-based models for 3D medical images, to maximize performance.
Open AccessAdapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation
Given the prevalence of 3D medical imaging technologies such as MRI and CT that are widely used in diagnosing and treating diverse diseases, 3D segmentation is one of the fundamental tasks of medical image analysis. Recently, Transformer-based models have started to achieve state-of-the-art performances across many vision tasks, through pre-training on large-scale natural image benchmark datasets. While works on medical image analysis have also begun to explore Transformer-based models, there is currently no optimal strategy to effectively leverage pre-trained Transformers, primarily due to the difference in dimensionality between 2D natural images and 3D medical images. Existing solutions either split 3D images into 2D slices and predict each slice independently, thereby losing crucial depth-wise information, or modify the Transformer architecture to support 3D inputs without leveraging pre-trained weights. In this work, we use a simple yet effective weight inflation strategy to adapt pre-trained Transformers from 2D to 3D, retaining the benefit of both transfer learning and depth information. We further investigate the effectiveness of transfer from different pre-training sources and objectives. Our approach achieves state-of-the-art performances across a broad range of 3D medical image datasets, and can become a standard strategy easily utilized by all work on Transformer-based models for 3D medical images, to maximize performance.
- Open Access
Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
The collection and curation of large-scale medical datasets from multiple institutions is essential for training accurate deep learning models, but privacy concerns often hinder data sharing. Federated learning (FL) is a promising solution that enables privacy-preserving collaborative learning among different institutions, but it generally suffers from performance deterioration due to heterogeneous data distributions and a lack of quality labeled data. In this paper, we present a robust and label-efficient self-supervised FL framework for medical image analysis. Our method introduces a novel Transformer-based self-supervised pre-training paradigm that pre-trains models directly on decentralized target task datasets using masked image modeling, to facilitate more robust representation learning on heterogeneous data and effective knowledge transfer to downstream models. Extensive empirical results on simulated and real-world medical imaging non-IID federated datasets show that masked image modeling with Transformers significantly improves the robustness of models against various degrees of data heterogeneity. Notably, under severe data heterogeneity, our method, without relying on any additional pre-training data, achieves an improvement of 5.06%, 1.53% and 4.58% in test accuracy on retinal, dermatology and chest X-ray classification compared to the supervised baseline with ImageNet pre-training. In addition, we show that our federated self-supervised pre-training methods yield models that generalize better to out-of-distribution data and perform more effectively when fine-tuning with limited labeled data, compared to existing FL algorithms. The code is available at https://github.com/rui-yan/SSL-FL.
Open AccessLabel-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
The collection and curation of large-scale medical datasets from multiple institutions is essential for training accurate deep learning models, but privacy concerns often hinder data sharing. Federated learning (FL) is a promising solution that enables privacy-preserving collaborative learning among different institutions, but it generally suffers from performance deterioration due to heterogeneous data distributions and a lack of quality labeled data. In this paper, we present a robust and label-efficient self-supervised FL framework for medical image analysis. Our method introduces a novel Transformer-based self-supervised pre-training paradigm that pre-trains models directly on decentralized target task datasets using masked image modeling, to facilitate more robust representation learning on heterogeneous data and effective knowledge transfer to downstream models. Extensive empirical results on simulated and real-world medical imaging non-IID federated datasets show that masked image modeling with Transformers significantly improves the robustness of models against various degrees of data heterogeneity. Notably, under severe data heterogeneity, our method, without relying on any additional pre-training data, achieves an improvement of 5.06%, 1.53% and 4.58% in test accuracy on retinal, dermatology and chest X-ray classification compared to the supervised baseline with ImageNet pre-training. In addition, we show that our federated self-supervised pre-training methods yield models that generalize better to out-of-distribution data and perform more effectively when fine-tuning with limited labeled data, compared to existing FL algorithms. The code is available at https://github.com/rui-yan/SSL-FL.
- Open Access
- 18 November 2022
- Published by Springer Nature in Nature Communications
- Vol. 13  (1) , 1-6
Developing medical imaging AI for emerging infectious diseases
Advances in artificial intelligence (AI) and computer vision hold great promise for assisting medical staff, optimizing healthcare workflow, and improving patient outcomes. The COVID-19 pandemic, which caused unprecedented stress on healthcare systems around the world, presented what seems to be a perfect opportunity for AI to demonstrate its usefulness. However, of the several hundred medical imaging AI models developed for COVID-19, very few were fit for deployment in real-world settings, and some were potentially harmful. This review aims to examine the strengths and weaknesses of prior studies and provide recommendations for different stages of building useful AI models for medical imaging, among them: needfinding, dataset curation, model development and evaluation, and post-deployment considerations. In addition, this review summarizes the lessons learned to inform the scientific community about ways to create useful medical imaging AI in a future pandemic. Very few of the COVID-19 ML models were fit for deployment in real-world settings. In this Comment, Huang et al. discuss the main steps required to develop clinically useful models in the context of an emerging infectious disease.
- 18 November 2022
- Published by Springer Nature in Nature Communications
- Vol. 13  (1) , 1-6
Open AccessDeveloping medical imaging AI for emerging infectious diseases
Advances in artificial intelligence (AI) and computer vision hold great promise for assisting medical staff, optimizing healthcare workflow, and improving patient outcomes. The COVID-19 pandemic, which caused unprecedented stress on healthcare systems around the world, presented what seems to be a perfect opportunity for AI to demonstrate its usefulness. However, of the several hundred medical imaging AI models developed for COVID-19, very few were fit for deployment in real-world settings, and some were potentially harmful. This review aims to examine the strengths and weaknesses of prior studies and provide recommendations for different stages of building useful AI models for medical imaging, among them: needfinding, dataset curation, model development and evaluation, and post-deployment considerations. In addition, this review summarizes the lessons learned to inform the scientific community about ways to create useful medical imaging AI in a future pandemic. Very few of the COVID-19 ML models were fit for deployment in real-world settings. In this Comment, Huang et al. discuss the main steps required to develop clinically useful models in the context of an emerging infectious disease.
- Open Access
Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning
Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. Second, to reduce the training effort and enhance the generalizability to the unseen task, we apply multi-task learning to make the model learn to generalize to new tasks better. The experiment results show that our proposed method can successfully control several state-of-the-art (SOTA) dialogue models without accessing their parameters. Furthermore, the model demonstrates the strong ability to quickly adapt to an unseen task in fewer steps than the baseline model.
Open AccessLearning to Generate Prompts for Dialogue Generation through Reinforcement Learning
Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. Second, to reduce the training effort and enhance the generalizability to the unseen task, we apply multi-task learning to make the model learn to generalize to new tasks better. The experiment results show that our proposed method can successfully control several state-of-the-art (SOTA) dialogue models without accessing their parameters. Furthermore, the model demonstrates the strong ability to quickly adapt to an unseen task in fewer steps than the baseline model.
- Open Access
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (6) , 2570-2581
Automatic Lung Nodule Segmentation and Intra-Nodular Heterogeneity Image Generation
Automatic segmentation of lung nodules on computed tomography (CT) images is challenging owing to the variability of morphology, location, and intensity. In addition, few segmentation methods can capture intra-nodular heterogeneity to assist lung nodule diagnosis. In this study, we propose an end-to-end architecture to perform fully automated segmentation of multiple types of lung nodules and generate intra-nodular heterogeneity images for clinical use. To this end, a hybrid loss is considered by introducing a Faster R-CNN model based on generalized intersection over union loss in generative adversarial network. The Lung Image Database Consortium image collection dataset, comprising 2,635 lung nodules, was combined with 3,200 lung nodules from five hospitals for this study. Compared with manual segmentation by radiologists, the proposed model obtained an average dice coefficient (DC) of 82.05% on the test dataset. Compared with U-net , NoduleNet , nnU-net , and other three models, the proposed method achieved comparable performance on lung nodule segmentation and generated more vivid and valid intra-nodular heterogeneity images, which are beneficial in radiological diagnosis. In an external test of 91 patients from another hospital, the proposed model achieved an average DC of 81.61%. The proposed method effectively addresses the challenges of inevitable human interaction and additional pre-processing procedures in the existing solutions for lung nodule segmentation. In addition, the results show that the intra-nodular heterogeneity images generated by the proposed model are suitable to facilitate lung nodule diagnosis in radiology.
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (6) , 2570-2581
Open AccessAutomatic Lung Nodule Segmentation and Intra-Nodular Heterogeneity Image Generation
Automatic segmentation of lung nodules on computed tomography (CT) images is challenging owing to the variability of morphology, location, and intensity. In addition, few segmentation methods can capture intra-nodular heterogeneity to assist lung nodule diagnosis. In this study, we propose an end-to-end architecture to perform fully automated segmentation of multiple types of lung nodules and generate intra-nodular heterogeneity images for clinical use. To this end, a hybrid loss is considered by introducing a Faster R-CNN model based on generalized intersection over union loss in generative adversarial network. The Lung Image Database Consortium image collection dataset, comprising 2,635 lung nodules, was combined with 3,200 lung nodules from five hospitals for this study. Compared with manual segmentation by radiologists, the proposed model obtained an average dice coefficient (DC) of 82.05% on the test dataset. Compared with U-net , NoduleNet , nnU-net , and other three models, the proposed method achieved comparable performance on lung nodule segmentation and generated more vivid and valid intra-nodular heterogeneity images, which are beneficial in radiological diagnosis. In an external test of 91 patients from another hospital, the proposed model achieved an average DC of 81.61%. The proposed method effectively addresses the challenges of inevitable human interaction and additional pre-processing procedures in the existing solutions for lung nodule segmentation. In addition, the results show that the intra-nodular heterogeneity images generated by the proposed model are suitable to facilitate lung nodule diagnosis in radiology.