An integrated diffusion-weighted imaging processing and interpretation platform for MR-guided radiotherapy

Yunxiang Li; Yan Dai; Yen-Peng Liao; Jie Deng; Jill B De Vis; You Zhang

physics.med-phAug 20, 2026

An integrated diffusion-weighted imaging processing and interpretation platform for MR-guided radiotherapy

Authors: Yunxiang Li, Yan Dai, Yen-Peng Liao, Jie Deng, Jill B De Vis, You Zhang

Organizations: Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA · Department of Radiation Oncology, University of California San Francisco, San Francisco, California, USA

Abstract

Background: Magnetic resonance imaging-guided linear accelerators (MR-Linacs) allow diffusion-weighted imaging (DWI) to be acquired at every treatment fraction, but converting these low-signal-to-noise-ratio acquisitions into clinical decisions requires both reliable quantitative processing and an interpretation that reconciles a scattered and often contradictory literature. Purpose: To describe and evaluate an integrated, web-based platform that carries raw MR-Linac DWI to a structured, literature-grounded clinical interpretation, and to assess its retrieval-augmented generation (RAG) interpretation module by independent expert rating. Methods: The platform couples a deep-learning processing pipeline, comprising distortion correction, denoising, and intravoxel incoherent motion (IVIM)/apparent diffusion coefficient (ADC) fitting, with longitudinal region-of-interest analysis and a RAG interpretation agent. The agent reasons over a two-layer knowledge base of curated publications (a structured catalog index plus line-indexed full text), delegates arithmetic to deterministic tools, and is designed to trace each statement to a source document, section, and line range. One medical physicist and one physician independently rated the agent's reports for nine longitudinal glioblastoma cases on a 1-5 scale across three metrics: clinical-reasoning soundness, literature-citation quality, and overall clinical utility. Results: Across 54 ratings, the pooled mean was 4.65 +/- 0.80, with 93% of ratings >= 4; metric means were 4.6 (reasoning), 4.5 (citation), and 4.8 (utility), and raters agreed within one point on 85% of paired ratings. Conclusions: A single platform can integrate MR-Linac DWI post-processing with traceable, expert-evaluated clinical interpretation, while highlighting the safeguards needed to verify LLM-generated reasoning in radiation oncology.

Figures & tables

Component	Version	Role in the platform
Python	3.10	Implementation language
Flask / Flask-SocketIO	2.3 / 5.5	Web server and real-time progress streaming
PyTorch	2.6 (CUDA 12.6)	Deep-learning models (distortion, denoising, fitting)
pydicom	3.0.1	DICOM reading and metadata extraction
nibabel	5.3.2	NIfTI input/output
SimpleITK	2.4.1	Reorientation, resampling, geometry

Table 1: Principal software components of the platform and their roles. Versions reflect the validated deployment configuration.

Figure 1: End-to-end architecture and data flow of the platform. Raw MR-Linac DICOM data are organized and converted to NIfTI (with $b$ -value separation for DWI and mask extraction for segmentations), processed through a deep-learning pipeline into IVIM/ADC parameter maps, analyzed longitudinally over regions of interest, and finally interpreted by a retrieval-augmented generation (RAG) agent that is designed to trace evidence-supported statements to line-indexed source literature passages. Processed maps can be exported back to DICOM.

Figure 2: The DWI/IVIM processing pipeline. Raw multi- $b$ -value MR-Linac DWI, acquired at each treatment fraction, is processed through six steps; quantitative fitting is performed at native DWI resolution (steps 2–5) and only the final maps are resampled to anatomical resolution before inter-fractional registration (step 6).

Figure 3: The web platform interface, with a brain GBM case shown. (a) The ADC & IVIM processing pipeline, with the DICOM data browser (patient/date/series, left) and the numbered processing steps (right). (b) The analysis tool, showing per-fraction parameter-map overlays on the anatomical image and the corresponding ROI intensity histograms. (c) Longitudinal trend statistics (mean, median, interquartile range, percentiles, skewness, and kurtosis) computed within a fixed ROI across treatment fractions.

Figure 4: The retrieval-augmented interpretation agent. Longitudinal IVIM/ADC trajectories, together with the conventional imaging context, are ingested (stage 1) and characterized (stage 2). Catalog-guided retrieval then shortlists tumor-type- and parameter-matched publications from the two-layer knowledge base and fetches only the anchored passages (stage 3). The LLM integrates the evidence and resolves multi-parameter discordance (stage 4), and a structured report is produced in which evidence-supported statements are traced back to a source document, section, and line range (stage 5).

Figure 5: The clinical-interpretation interface. (a) The one-click AI clinical-interpretation view, where the user selects the target ROIs (e.g., GTV/CTV/PTV imported from RT-STRUCT) and launches an analysis. Prior analysis sessions are retained for review. (b) The retrieval knowledge base (“literature library”), which lists each indexed publication with its tumor types and reported parameters and accepts new papers by PDF upload.

Attribute	Categories (examples)	Coverage
Tumor type	Glioblastoma / glioma / brain metastases	predominant
	Pancreatic adenocarcinoma; head and neck; prostate	secondary
Parameters	ADC	28 papers
	IVIM ( $f_{p}$ , $D_{t}$ , $D_{p}$ )	13 papers
Setting	MR-Linac / MR-guided radiotherapy; chemoradiation
Evidence	Original studies, systematic reviews/meta-analyses, position statements	mixed

Table 2: Composition of the retrieval knowledge base (28 publications). Counts of tumor types and reported parameters exceed 28 because individual papers may span multiple categories.

Figure 6: A representative longitudinal GBM case. (a) GTV-mean trajectories of ADC,

D_{t}

D_{p}

, and

f_{p}

across five longitudinal time points, showing an early diffusivity rise followed by a late decline with preserved/rising perfusion fraction. (b) Excerpt of the agent’s report, in which the interpretation is anchored to specific lines of matched source literature. This case received the maximum rating on all three dimensions from both reviewers.

Figure 7: Independent expert ratings of agent-generated reports by metric and rater (mean

\pm

SD; 1–5 Likert). The dashed line marks the “good” scale anchor (4).Overall clinical utility received the highest and most consistent ratings from both reviewers. The physician’s ratings showed greater variability, driven by a few atypical cases (reasoning scores of 2, 3, and 3 in three cases and one citation score of 1), whereas the physicist assigned a reasoning of 5 to all cases.

Dimension	Physicist	Physician	Pooled
	( $n=9$ )	( $n=9$ )	( $n=18$ )
Clinical-reasoning soundness	$5.00\pm 0.00$	$4.22\pm 1.20$	$4.61\pm 0.92$
Literature-citation quality	$4.56\pm 0.53$	$4.44\pm 1.33$	$4.50\pm 0.99$
Overall clinical utility	$4.78\pm 0.44$	$4.89\pm 0.33$	$4.83\pm 0.38$
Overall	$4.78\pm 0.42$	$4.52\pm 1.05$	$4.65\pm 0.80$

Table 3: Expert evaluation of agent-generated reports on nine longitudinal GBM cases. Values are mean

\pm

standard deviation on a 1–5 Likert scale (higher is better). The pooled column combines both raters (

n=18

per metric).

Diffusion MRI

Diffusion MRI measures water motion in tissue to characterize brain microstructure, white-matter pathways, and disease.

See all 51 papers

Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning
Mar 12, 2026Robin Peretzke, Marlin Hanstein, Maximilian Fischer +15Multimodal Classification Classification
Deutsches Krebsforschungszentrum (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Medical Faculty, Heidelberg University, Heidelberg, Germany · Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany +8
Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment
Mar 23, 2026Mohamed Sobhi Jabal, Jikai Zhang, Dominic LaBella +6Brain Tumor Classification Multi-Agent Systems
Department of Radiology, Duke University Medical Center, Durham, NC · Department of Electrical and Computer Engineering, Duke University, Durham, NC · Duke Center for Artificial Intelligence in Radiology, Duke University Medical Center, Durham, NC +5
Reading the Mask: Descriptor-Grounded BI-RADS Rationale Generation for Breast MRI Segmentation
Oct 21, 2026Hrishikesh Singh, Aarti Sharma, Divyanshu Kumar +1Explainable Medical Image Analysis
Department of Applied Mathematics and Scientific Computing, Indian Institute of Technology Roorkee, Roorkee, India · Indian Institute of Technology Madras, Chennai, India · Also with Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Roorkee.

Mar 12, 2026J/K move · Enter open · S save

Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning

Robin Peretzke, Marlin Hanstein, Maximilian Fischer, Lars Badhi Wessel+14

Deutsches Krebsforschungszentrum (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Medical Faculty, Heidelberg University, Heidelberg, Germany · Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany+8

Multimodal Classification Classification Brain Tumor Classification

Open paper AskPDF arXiv

The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology.

Abstract

Diffusion MRI

Explore similar work

Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning

Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment

Reading the Mask: Descriptor-Grounded BI-RADS Rationale Generation for Breast MRI Segmentation