arXiv subjects

Hongying Feng

Publications and source records attributed to Hongying Feng.

16 recordsLinked to original sources

arXiv2026

Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision Support

In recent years, the advances of large language models and autonomous agents have revolutionized the healthcare field, facilitating diagnosis and improving treatment results. However, most existing AI systems rely on pre-trained knowledge and predefined pipelines, which struggle to learn dynamically from the interactive chat session history that contains patient outcomes and past failures. To address this limitation, we propose VIBEMed, a multi-agent framework with a built-in self-evolution mechanism and architecture-level safety sandbox for robust clinical decision support. The system integrates three specialized agents, including a Clinical Diagnostic Agent (CDA) for hypothesis generation, a Therapeutic Execution Agent (TEA) for treatment planning, and a Clinical Evolution Manager Agent (CEMA) that distills longitudinal clinical feedback into reusable knowledge, transforming multimodal patient information into personalized medical decisions. Through self-evolution mechanism, the framework enables iterative updates across memory, model behavior, and decision strategies, allowing the system to improve over time. Experimental results show that VIBEMed demonstrates superior performance through its evolving mechanism in complex clinical cases, particularly in tasks that require integrated decision-making and longitudinal planning. The framework also supports reliable end-to-end decisions in challenging scenarios such as oncology treatment planning, highlighting its feasibility in real-world clinical contexts. Overall, VIBEMed provides a practical path beyond static AI systems toward adaptive, experience-driven clinical decision support, demonstrating the value of combining multi-agent collaboration with continuous evolution for advancing precision medicine.

cs.AI↗

arXiv2025

AI in Proton Therapy Treatment Planning: A Review

Purpose: Proton therapy provides superior dose conformity compared to photon therapy, but its treatment planning is challenged by sensitivity to anatomical changes, setup/range uncertainties, and computational complexity. This review evaluates the role of artificial intelligence (AI) in improving proton therapy treatment planning. Materials and methods: Recent studies on AI applications in image reconstruction, image registration, dose calculation, plan optimization, and quality assessment were reviewed and summarized by application domain and validation strategy. Results: AI has shown promise in automating contouring, enhancing imaging for dose calculation, predicting dose distributions, and accelerating robust optimization. These methods reduce manual workload, improve efficiency, and support more personalized planning and adaptive planning. Limitations include data scarcity, model generalizability, and clinical integration. Conclusion: AI is emerging as a key enabler of efficient, consistent, and patient-specific proton therapy treatment planning. Addressing challenges in validation and implementation will be essential for its translation into routine clinical practice.

physics.med-ph↗

arXiv2025

Diffusion Transformer-based Universal Dose Denoising for Pencil Beam Scanning Proton Therapy

Purpose: Intensity-modulated proton therapy (IMPT) offers precise tumor coverage while sparing organs at risk (OARs) in head and neck (H&N) cancer. However, its sensitivity to anatomical changes requires frequent adaptation through online adaptive radiation therapy (oART), which depends on fast, accurate dose calculation via Monte Carlo (MC) simulations. Reducing particle count accelerates MC but degrades accuracy. To address this, denoising low-statistics MC dose maps is proposed to enable fast, high-quality dose generation. Methods: We developed a diffusion transformer-based denoising framework. IMPT plans and 3D CT images from 80 H&N patients were used to generate noisy and high-statistics dose maps using MCsquare (1 min and 10 min per plan, respectively). Data were standardized into uniform chunks with zero-padding, normalized, and transformed into quasi-Gaussian distributions. Testing was done on 10 H&N, 10 lung, 10 breast, and 10 prostate cancer cases, preprocessed identically. The model was trained with noisy dose maps and CT images as input and high-statistics dose maps as ground truth, using a combined loss of mean square error (MSE), residual loss, and regional MAE (focusing on top/bottom 10% dose voxels). Performance was assessed via MAE, 3D Gamma passing rate, and DVH indices. Results: The model achieved MAEs of 0.195 (H&N), 0.120 (lung), 0.172 (breast), and 0.376 Gy[RBE] (prostate). 3D Gamma passing rates exceeded 92% (3%/2mm) across all sites. DVH indices for clinical target volumes (CTVs) and OARs closely matched the ground truth. Conclusion: A diffusion transformer-based denoising framework was developed and, though trained only on H&N data, generalizes well across multiple disease sites.

physics.med-ph↗

arXiv2025

Critical review of patient outcome study in head and neck cancer radiotherapy

Rapid technological advances in radiation therapy have significantly improved dose delivery and tumor control for head and neck cancers. However, treatment-related toxicities caused by high-dose exposure to critical structures remain a significant clinical challenge, underscoring the need for accurate prediction of clinical outcomes-encompassing both tumor control and adverse events (AEs). This review critically evaluates the evolution of data-driven approaches in predicting patient outcomes in head and neck cancer patients treated with radiation therapy, from traditional dose-volume constraints to cutting-edge artificial intelligence (AI) and causal inference framework. The integration of linear energy transfer in patient outcomes study, which has uncovered critical mechanisms behind unexpected toxicity, was also introduced for proton therapy. Three transformative methodological advances are reviewed: radiomics, AI-based algorithms, and causal inference frameworks. While radiomics has enabled quantitative characterization of medical images, AI models have demonstrated superior capability than traditional models. However, the field faces significant challenges in translating statistical correlations from real-world data into interventional clinical insights. We highlight that how causal inference methods can bridge this gap by providing a rigorous framework for identifying treatment effects. Looking ahead, we envision that combining these complementary approaches, especially the interventional prediction models, will enable more personalized treatment strategies, ultimately improving both tumor control and quality of life for head and neck cancer patients treated with radiation therapy.

physics.med-ph↗

arXiv2024

Enabling Clinical Use of Linear Energy Transfer in Proton Therapy for Head and Neck Cancer -- A Review of Implications for Treatment Planning and Adverse Events Study

Proton therapy offers significant advantages due to its unique physical and biological properties, particularly the Bragg peak, enabling precise dose delivery to tumors while sparing healthy tissues. However, the clinical implementation is challenged by the oversimplification of the relative biological effectiveness (RBE) as a fixed value of 1.1, which does not account for the complex interplay between dose, linear energy transfer (LET), and biological endpoints. Lack of heterogeneity control or the understanding of the complex interplay may result in unexpected adverse events and suboptimal patient outcomes. On the other hand, expanding our knowledge of variable tumor RBE and LET optimization may provide a better management strategy for radioresistant tumors. This review examines recent advancements in LET calculation methods, including analytical models and Monte Carlo simulations. The integration of LET into plan evaluation is assessed to enhance plan quality control. LET-guided robust optimization demonstrates promise in minimizing high-LET exposure to organs at risk, thereby reducing the risk of adverse events. Dosimetric seed spot analysis is discussed to show its importance in revealing the true LET-related effect upon the adverse event initialization by finding the lesion origins and eliminating the confounding factors from the biological processes. Dose-LET volume histograms (DLVH) are discussed as effective tools for correlating physical dose and LET with clinical outcomes, enabling the derivation of clinically relevant dose-LET volume constraints without reliance on uncertain RBE models. Based on DLVH, the dose-LET volume constraints (DLVC)-guided robust optimization is introduced to upgrade conventional dose-volume constraints-based robust optimization, which optimizes the joint distribution of dose and LET simultaneously.

physics.med-ph↗

arXiv2024

Robust Optimization for Spot Scanning Proton Therapy based on Dose-Linear Energy Transfer (LET) Volume Constraints

Purpose: Historically, spot scanning proton therapy (SSPT) treatment planning utilizes dose volume constraints and linear-energy-transfer (LET) volume constraints separately to balance tumor control and organs-at-risk (OARs) protection. We propose a novel dose-LET volume constraint (DLVC)-based robust optimization (DLVCRO) method for SSPT in treating prostate cancer to obtain a desirable joint dose and LET distribution to minimize adverse events (AEs). Methods: DLVCRO treats DLVC as soft constraints controlling the joint distribution of dose and LET. Ten prostate cancer patients were included with rectum and bladder as OARs. DLVCRO was compared with the conventional robust optimization (RO) method using the worst-case analysis method. Besides the dose-volume histogram (DVH) indices, the analogous LETVH and extra-biological-dose (xBD)-volume histogram indices were also used. The Wilcoxon signed rank test was used to measure statistical significance. Results: In nominal scenario, DLVCRO significantly improved dose, LET and xBD distributions to protect OARs (rectum: V70Gy: 3.07\% vs. 2.90\%, p = .0063, RO vs. DLVCRO; $\text{LET}_{\max}$ (keV/um): 11.53 vs. 9.44, p = .0101; $\text{xBD}_{\max}$ (Gy$\cdot$keV/um): 420.55 vs. 398.79, p = .0086; bladder: V65Gy: 4.82\% vs. 4.61\%, p = .0032; $\text{LET}_{\max}$ 8.97 vs. 7.51, p = .0047; $\text{xBD}_{\max}$ 490.11 vs. 476.71, p = .0641). The physical dose distributions in targets are comparable (D2%: 98.57\% vs. 98.39\%; p = .0805; CTV D2% - D98%: 7.10\% vs. 7.75\%, p = .4624). In the worst-case scenario, DLVCRO robustly enhanced OAR while maintaining the similar plan robustness in target dose coverage and homogeneity. Conclusion: DLVCRO upgrades 2D DVH-based to 3D DLVH-based treatment planning to adjust dose/LET distributions simultaneously and robustly. DLVCRO is potentially a powerful tool to improve patient outcomes in SSPT.

physics.med-ph↗

arXiv2024

Fast Monte Carlo Dose Calculation in Proton Therapy

This article examines the critical role of fast Monte Carlo dose calculations in advancing proton therapy techniques, particularly in the context of increasing treatment customization and precision. As adaptive radiotherapy and other patient-specific approaches evolve, the need for accurate and precise dose calculations, essential for techniques like proton-based stereotactic radiosurgery, becomes more prominent. These calculations, however, are time-intensive, with the treatment planning/optimization process constrained by the achievable speed of dose computations. Thus, enhancing the speed of Monte Carlo methods is vital, as it not only facilitates the implementation of novel treatment modalities but also improves the optimality of treatment plans. Today, the state-of-the-art in Monte Carlo dose calculation speeds is 106 - 107 protons per second. This review highlights the latest advancements in fast Monte Carlo dose calculations that have led to such speeds, including emerging artificial intelligence-based techniques, and discusses their application in both current and emerging proton therapy strategies.

physics.med-ph↗

arXiv2024

Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images

In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging(OBI) unavailable. But tumor visibility is constrained due to the projection of patient's anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT(CBCT), the field of view(FOV) of CBCT is limited with unnecessarily high imaging dose, thus unfavorable for pediatric patients. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position. Here, we propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images as the solo input and can synthesize accurate, full-size 3D CT in real time(within milliseconds). We demonstrate the feasibility of the proposed approach on 10 patients with head and neck (H&N) cancer using image quality(MAE: <45HU), dosimetrical accuracy(Gamma passing rate (2%/2mm/10%)>97%) and patient position uncertainty(shift error: <0.4mm). The proposed framework can generate accurate 3D CT faithfully mirroring real-time patient position, thus significantly improving patient setup accuracy, keeping imaging dose minimum, and maintaining treatment veracity.

eess.SP↗

arXiv2024

Proton Pencil-Beam Scanning Stereotactic Body Radiation Therapy and Hypofractionated Radiation Therapy for Thoracic Malignancies: Patterns of Practice Survey and Recommendations for Future Development from NRG Oncology and PTCOG

Stereotactic body radiation therapy (SBRT) and hypofractionation using pencil-beam scanning (PBS) proton therapy (PBSPT) is an attractive option for thoracic malignancies. Combining the advantages of target coverage conformity and critical organ sparing from both PBSPT and SBRT, this new delivery technique has great potential to improve the therapeutic ratio, particularly for tumors near critical organs. Safe and effective implementation of PBSPT SBRT/hypofractionation to treat thoracic malignancies is more challenging than the conventionally-fractionated PBSPT due to concerns of amplified uncertainties at the larger dose per fraction. NRG Oncology and Particle Therapy Cooperative Group (PTCOG) Thoracic Subcommittee surveyed US proton centers to identify practice patterns of thoracic PBSPT SBRT/hypofractionation. From these patterns, we present recommendations for future technical development of proton SBRT/hypofractionation for thoracic treatment. Amongst other points, the recommendations highlight the need for volumetric image guidance and multiple CT-based robust optimization and robustness tools to minimize further the impact of uncertainties associated with respiratory motion. Advances in direct motion analysis techniques are urgently needed to supplement current motion management techniques.

physics.med-ph↗

arXiv2024

The Radiation Oncology NLP Database

We present the Radiation Oncology NLP Database (ROND), the first dedicated Natural Language Processing (NLP) dataset for radiation oncology, an important medical specialty that has received limited attention from the NLP community in the past. With the advent of Artificial General Intelligence (AGI), there is an increasing need for specialized datasets and benchmarks to facilitate research and development. ROND is specifically designed to address this gap in the domain of radiation oncology, a field that offers many opportunities for NLP exploration. It encompasses various NLP tasks including Logic Reasoning, Text Classification, Named Entity Recognition (NER), Question Answering (QA), Text Summarization, and Patient-Clinician Conversations, each with a distinct focus on radiation oncology concepts and application cases. In addition, we have developed an instruction-tuning dataset consisting of over 20k instruction pairs (based on ROND) and trained a large language model, CancerChat. This serves to demonstrate the potential of instruction-tuning large language models within a highly-specialized medical domain. The evaluation results in this study could serve as baseline results for future research. ROND aims to stimulate advancements in radiation oncology and clinical NLP by offering a platform for testing and improving algorithms and models in a domain-specific context. The ROND dataset is a joint effort of multiple U.S. health institutions. The data is available at https://github.com/zl-liu/Radiation-Oncology-NLP-Database.

cs.CL↗

arXiv2023

Noisy probing dose facilitated dose prediction for pencil beam scanning proton therapy: physics enhances generalizability

Purpose: Prior AI-based dose prediction studies in photon and proton therapy often neglect underlying physics, limiting their generalizability to handle outlier clinical cases, especially for pencil beam scanning proton therapy (PBSPT). Our aim is to design a physics-aware and generalizable AI-based PBSPT dose prediction method that has the underlying physics considered to achieve high generalizability to properly handle the outlier clinical cases. Methods and Materials: This study analyzed PBSPT plans of 103 prostate and 78 lung cancer patients from our institution,with each case comprising CT images, structure sets, and plan doses from our Monte-Carlo dose engine (serving as the ground truth). Three methods were evaluated in the ablation study: the ROI-based method, the beam mask and sliding window method, and the noisy probing dose method. Twelve cases with uncommon beam angles or prescription doses tested the methods' generalizability to rare treatment planning scenarios. Performance evaluation used DVH indices, 3D Gamma passing rates (3%/2mm/10%), and dice coefficients for dose agreement. Results: The noisy probing dose method showed improved agreement of DVH indices, 3D Gamma passing rates, and dice coefficients compared to the conventional methods for the testing cases. The noisy probing dose method showed better generalizability in the 6 outlier cases than the ROI-based and beam mask-based methods with 3D Gamma passing rates (for prostate cancer, targets: 89.32%$\pm$1.45% vs. 93.48%$\pm$1.51% vs. 96.79%$\pm$0.83%, OARs: 85.87%$\pm$1.73% vs. 91.15%$\pm$1.13% vs. 94.29%$\pm$1.01%). The dose predictions were completed within 0.3 seconds. Conclusions: We've devised a novel noisy probing dose method for PBSPT dose prediction in prostate and lung cancer patients. With more physics included, it enhances the generalizability of dose prediction in handling outlier clinical cases.

physics.med-ph↗

arXiv2023

Artificial Intelligence-Facilitated Online Adaptive Proton Therapy Using Pencil Beam Scanning Proton Therapy

We propose an oAPT workflow that incorporates all these functionalities and validate its clinical implementation feasibility with prostate patients. AI-based auto-segmentation tool AccuContourTM (Manteia, Xiamen, China) was seamlessly integrated into oAPT. Initial spot arrangement tool on the vCT for re-optimization was implemented using raytracing. An LET-based biological effect evaluation tool was developed to assess the overlap region of high dose and high LET in selected OARs. Eleven prostate cancer patients were retrospectively selected to verify the efficacy and efficiency of the proposed oAPT workflow. The time cost of each component in the workflow was recorded for analysis. The verification plan showed significant degradation of the CTV coverage and rectum and bladder sparing due to the interfractional anatomical changes. Re-optimization on the vCT resulted in great improvement of the plan quality. No overlap regions of high dose and high LET distributions were observed in bladder or rectum in re-plans. 3D Gamma analyses in PSQA confirmed the accuracy of the re-plan doses before delivery (Gamma passing rate = 99.57%), and after delivery (98.59%). The robustness of the re-plans passed all clinical requirements. The average time for the complete execution of the workflow was 9.12minutes, excluding manual intervention time. The AI-facilitated oAPT workflow was demonstrated to be both efficient and effective by generating a re-plan that significantly improved the plan quality in prostate cancer treated with PBSPT.

physics.med-ph↗

arXiv2023

Benchmarking a foundation LLM on its ability to re-label structure names in accordance with the AAPM TG-263 report

Purpose: To introduce the concept of using large language models (LLMs) to re-label structure names in accordance with the American Association of Physicists in Medicine (AAPM) Task Group (TG)-263 standard, and to establish a benchmark for future studies to reference. Methods and Materials: The Generative Pre-trained Transformer (GPT)-4 application programming interface (API) was implemented as a Digital Imaging and Communications in Medicine (DICOM) storage server, which upon receiving a structure set DICOM file, prompts GPT-4 to re-label the structure names of both target volumes and normal tissues according to the AAPM TG-263. Three disease sites, prostate, head and neck, and thorax were selected for evaluation. For each disease site category, 150 patients were randomly selected for manually tuning the instructions prompt (in batches of 50) and 50 patients were randomly selected for evaluation. Structure names that were considered were those that were most likely to be relevant for studies utilizing structure contours for many patients. Results: The overall re-labeling accuracy of both target volumes and normal tissues for prostate, head and neck, and thorax cases was 96.0%, 98.5%, and 96.9% respectively. Re-labeling of target volumes was less accurate on average except for prostate - 100%, 93.1%, and 91.1% respectively. Conclusions: Given the accuracy of GPT-4 in re-labeling structure names of both target volumes and normal tissues as presented in this work, LLMs are poised to be the preferred method for standardizing structure names in radiation oncology, especially considering the rapid advancements in LLM capabilities that are likely to continue.

physics.med-ph↗

arXiv2023

Modelling small block aperture in an in-house developed GPU-accelerated Monte Carlo-based dose engine for pencil beam scanning proton therapy

Purpose: To enhance an in-house graphic-processing-unit (GPU) accelerated virtual particle (VP)-based Monte Carlo (MC) proton dose engine (VPMC) to model aperture blocks in both dose calculation and optimization for pencil beam scanning proton therapy (PBSPT)-based stereotactic radiosurgery (SRS). Methods and Materials: A block aperture module was integrated into VPMC. VPMC was validated by an opensource code, MCsquare, in eight water phantom simulations with 3cm thick brass apertures: four were with aperture openings of 1, 2, 3, and 4cm without a range shifter, while the other four were with same aperture opening configurations with a range shifter of 45mm water equivalent thickness. VPMC was benchmarked with MCsquare and RayStation MC for 10 patients with small targets (average volume 8.4 cc). Finally, 3 patients were selected for robust optimization with aperture blocks using VPMC. Results: In the water phantoms, 3D gamma passing rate (2%/2mm/10%) between VPMC and MCsquare were 99.71$\pm$0.23%. In the patient geometries, 3D gamma passing rates (3%/2mm/10%) between VPMC/MCsquare and RayStation MC were 97.79$\pm$2.21%/97.78$\pm$1.97%, respectively. The calculation time was greatly decreased from 112.45$\pm$114.08 seconds (MCsquare) to 8.20$\pm$6.42 seconds (VPMC), both having statistical uncertainties of about 0.5%. The robustly optimized plans met all the dose-volume-constraints (DVCs) for the targets and OARs per our institutional protocols. The mean calculation time for 13 influence matrices in robust optimization by VPMC was 41.6 seconds. Conclusion: VPMC has been successfully enhanced to model aperture blocks in dose calculation and optimization for the PBSPT-based SRS.

physics.med-ph↗

arXiv2023

Segment Anything Model (SAM) for Radiation Oncology

In this study, we evaluate the performance of the Segment Anything Model (SAM) in clinical radiotherapy. Our results indicate that SAM's 'segment anything' mode can achieve clinically acceptable segmentation results in most organs-at-risk (OARs) with Dice scores higher than 0.7. SAM's 'box prompt' mode further improves the Dice scores by 0.1 to 0.5. Considering the size of the organ and the clarity of its boundary, SAM displays better performance for large organs with clear boundaries but performs worse for smaller organs with unclear boundaries. Given that SAM, a model pre-trained purely on natural images, can handle the delineation of OARs from medical images with clinically acceptable accuracy, these results highlight SAM's robust generalization capabilities with consistent accuracy in automatic segmentation for radiotherapy. In other words, SAM can achieve delineation of different OARs at different sites using a generic automatic segmentation model. SAM's generalization capabilities across different disease sites suggest that it is technically feasible to develop a generic model for automatic segmentation in radiotherapy.

eess.IV↗

arXiv2023

Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer

Purpose: In some proton therapy facilities, patient alignment relies on two 2D orthogonal kV images, taken at fixed, oblique angles, as no 3D on-the-bed imaging is available. The visibility of the tumor in kV images is limited since the patient's 3D anatomy is projected onto a 2D plane, especially when the tumor is behind high-density structures such as bones. This can lead to large patient setup errors. A solution is to reconstruct the 3D CT image from the kV images obtained at the treatment isocenter in the treatment position. Methods: An asymmetric autoencoder-like network built with vision-transformer blocks was developed. The data was collected from 1 head and neck patient: 2 orthogonal kV images (1024x1024 voxels), 1 3D CT with padding (512x512x512) acquired from the in-room CT-on-rails before kVs were taken and 2 digitally-reconstructed-radiograph (DRR) images (512x512) based on the CT. We resampled kV images every 8 voxels and DRR and CT every 4 voxels, thus formed a dataset consisting of 262,144 samples, in which the images have a dimension of 128 for each direction. In training, both kV and DRR images were utilized, and the encoder was encouraged to learn the jointed feature map from both kV and DRR images. In testing, only independent kV images were used. The full-size synthetic CT (sCT) was achieved by concatenating the sCTs generated by the model according to their spatial information. The image quality of the synthetic CT (sCT) was evaluated using mean absolute error (MAE) and per-voxel-absolute-CT-number-difference volume histogram (CDVH). Results: The model achieved a speed of 2.1s and a MAE of <40HU. The CDVH showed that <5% of the voxels had a per-voxel-absolute-CT-number-difference larger than 185 HU. Conclusion: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.

cs.CV↗