End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding

TL;DR

This paper introduces RO-LMM, a large multimodal model for radiation oncology that performs multiple clinical tasks with high robustness and consistency, utilizing novel fine-tuning and segmentation techniques.

Contribution

The paper presents RO-LMM, a comprehensive multimodal model for radiation oncology, and introduces CEFTune and CESEG methods to improve task robustness and consistency.

Findings

RO-LMM achieves promising multi-task clinical performance.

CEFTune enhances robustness to noisy inputs.

Multi-centre validation confirms generalization capabilities.

Abstract

Recent advances in AI foundation models have significant potential for lightening the clinical workload by mimicking the comprehensive and multi-faceted approaches used by medical professionals. In the field of radiation oncology, the integration of multiple modalities holds great importance, so the opportunity of foundational model is abundant. Inspired by this, here we present RO-LMM, a multi-purpose, comprehensive large multimodal model (LMM) tailored for the field of radiation oncology. This model effectively manages a series of tasks within the clinical workflow, including clinical context summarization, radiation treatment plan suggestion, and plan-guided target volume segmentation by leveraging the capabilities of LMM. In particular, to perform consecutive clinical tasks without error accumulation, we present a novel Consistency Embedding Fine-Tuning (CEFTune) technique, which boosts LMM's robustness to noisy inputs while preserving the consistency of handling clean inputs. We further extend this concept to LMM-driven segmentation framework, leading to a novel Consistency Embedding Segmentation (CESEG) techniques. Experimental results including multi-centre validation confirm that our RO-LMM with CEFTune and CESEG results in promising performance for multiple clinical tasks with generalization capabilities.