Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2601.00685

Human-like AI-based Auto-Field-in-Field Whole-Brain Radiotherapy Treatment Planning With Conversation Large Language Model Feedback

Adnan Jafar·An Qin·Gavin Atkins·Xiaoyu Hu·Yin Gao·Xun Jia
View original source ↗Read source document ↗Export metadata ↓

Abstract

Whole-brain radiotherapy (WBRT) is a common treatment due to its simplicity and effectiveness. While automated Field-in-Field (Auto-FiF) functions assist WBRT planning in modern treatment planning systems, it still requires manual approaches for optimal plan generation including patient-specific hyperparameters definition and plan refinement based on quality feedback. This study introduces an automated WBRT planning pipeline that integrates a deep learning (DL) Hyperparameter Prediction model for patient-specific parameter generation and a large-language model (LLM)-based conversational interface for interactive plan refinement. The Hyperparameter Prediction module was trained on 55 WBRT cases using geometric features of clinical target volume (CTV) and organs at risk (OARs) to determine optimal Auto-FiF settings in RayStation treatment planning system. Plans were generated under predicted hyperparameters. For cases in which the generated plan was suboptimal, quality feedback via voice input was captured by a Conversation module, transcribed using Whisper, and interpreted by GPT-4o to adjust planning settings. Plan quality was evaluated in 15 independent cases using clinical metrics and expert review, and model explainability was supported through analysis of feature importance. Fourteen of 15 DL-generated plans were clinically acceptable. Normalized to identical CTV D95% as the clinical plans, the DL-generated and clinical plans showed no statistically significant differences in doses to the eyes, lenses, or CTV dose metrics D1% and D99%. The DL-based planning required under 1 minute of computation and achieved total workflow execution in approximately 7 minutes with a single mouse click, compared to 15 minutes for manual planning. In cases requiring adjustment, the Conversational module successfully improved dose conformity and hotspot reduction.

Explore related subjects

physics.med-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Adnan Jafar, An Qin, Gavin Atkins, Xiaoyu Hu, Yin Gao, Xun Jia. 2026-01-02. Human-like AI-based Auto-Field-in-Field Whole-Brain Radiotherapy Treatment Planning With Conversation Large Language Model Feedback. https://arxiv.org/abs/2601.00685

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Voxel-Matching NORDIC: Non-local patch formation by time-series similarity increases tSNR in high-resolution BOLD fMRI

Submillimeter functional magnetic resonance imaging (fMRI) based on blood-oxygenation-level-dependent (BOLD) signal enables the study of brain function at the submillimeter level, uncovering insights into fine-scale organisations like cortical layers and columns. However, its inherently low contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) often limit its reliability and applicability. Noise Reduction with Distribution Corrected Principal Components Analysis (NORDIC PCA) is a locally low-rank denoising algorithm that reduces thermal noise levels in BOLD fMRI in a local patch manner. However, local patches often contain a mixture of signals from multiple tissues that negatively affects the low-rank structure of the patches, which limits the denoising capabilities of the algorithm. We propose an alternative approach for patch formation by gathering similar non-local voxels, dubbed voxel-matching (VM) NORDIC. The results on submillimeter-resolution BOLD fMRI data indicate that VM-NORDIC effectively promotes the low rank of the patches by boosting signal redundancy, allowing for more efficient noise attenuation. Moreover, the method barely affects spatial smoothness due to the non-local voxel selection based on time-series similarity. In particular, VM-NORDIC outperforms standard NORDIC with default local patching (Standard-NORDIC) in terms of temporal SNR (tSNR) (~9-90% larger than Standard-NORDIC; ~23-250% larger than the original) and spatial smoothness estimates (~20% of the smoothness induced by Standard-NORDIC). These improvements are fundamental to improving the validity and precision of fMRI studies at submillimeter resolutions.

physics.med-ph↗
arXiv2026

Computed Tomography Reconstruction Algorithm Using Markov Random Field Model

X-ray computed tomography (CT) reveals the materials' internal structures non-destructively from a tilt series of projected images. Filtered back projection (FBP) is a widely-adopted reconstruction algorithm in CT owing to its small computational cost. Under low-dose or sparse-view conditions, however, FBP often amplifies noise, severely degrading the reconstructed images. In this study, we evaluated the performance of a Bayesian CT reconstruction algorithm based on the Markov random field model under such adverse conditions. Through simulations, we demonstrated that the proposed algorithm shows higher reconstruction performance than FBP under both low-dose and sparse-view conditions. The hyperparameters are estimated by minimizing the Bayesian free energy, enabling adaptive reconstruction that reflects the noise characteristics of the observed projection data. These results suggest that the proposed algorithm can broaden the applicability of CT to dose-sensitive applications and time-constrained measurements, where only limited observed projection data are available.

physics.med-ph↗
arXiv2026

Charge Collection Efficiency in Air-Vented Plane-Parallel Ionisation Chambers at Ultra-High Dose Rates: A Self-Consistent Garfield++ Monte Carlo Model Including Space-Charge Effects and Ion Recombination

Ultra-high dose rate (UHDR) irradiation used in FLASH radiotherapy can lead to significant reductions in charge collection efficiency (CCE) in plane-parallel ionisation chambers (PPICs) due to enhanced ion recombination, while the high charge densities involved can also induce strong space-charge-induced electric-field distortions. To investigate these coupled effects, we extended the Garfield++ Monte Carlo particle-transport framework by implementing ion--ion recombination and self-consistent space-charge electric field calculations. The developed Monte Carlo model couples particle transport, electron attachment, recombination processes, and dynamic electric-field distortions. The implementation was validated against analytical and numerical models from the literature. Excellent agreement was obtained for the free electron fraction (FEF), CCE, induced current, and electric field evolution under UHDR conditions. The simulations show that space charge can locally increase the electric field by more than a factor of four or reduce it to nearly zero in some regions of the chamber. The results further suggest that the reduction of the CCE under UHDR conditions is mainly driven by the decrease of the FEF caused by electric-field-dependent electron attachment. This finding indicates that the complex problem of recombination under UHDR conditions may be largely governed by the evolution of the FEF, opening promising perspectives for the development of improved analytical models and real-time correction methods for ionisation chamber dosimetry under UHDR irradiation conditions. This work provides a flexible and self-consistent Monte Carlo framework for investigating recombination phenomena and improving dosimetry models for FLASH radiotherapy.

physics.med-ph↗