# Efficient Parameter Adaptation for Multi-Modal Medical Image Segmentation and Prognosis

arXiv: https://arxiv.org/abs/2504.13645 · HTML: https://mlsanity.com/paper/2504.13645/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes](https://mlsanity.com/paper/1904.00445/) (2019)
- [A Unified Continual Learning Framework with General Parameter-Efficient Tuning](https://mlsanity.com/paper/2303.10070/) (2023)
- [Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity](https://mlsanity.com/paper/2305.08252/) (2023)
- [Unified Multi-Modal Image Synthesis for Missing Modality Imputation](https://mlsanity.com/paper/2304.05340/) (2023)
- [Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans](https://mlsanity.com/paper/2302.00162/) (2023)
- [Medical Image Segmentation on MRI Images with Missing Modalities: A Review](https://mlsanity.com/paper/2203.06217/) (2022)
- [TMSS: An End-to-End Transformer-based Multimodal Network for Segmentation and Survival Prediction](https://mlsanity.com/paper/2209.05036/) (2022)
- [An Ensemble Approach for Patient Prognosis of Head and Neck Tumor Using Multimodal Data](https://mlsanity.com/paper/2202.12537/) (2022)
- [Missing-modality Enabled Multi-modal Fusion Architecture for Medical Data](https://mlsanity.com/paper/2309.15529/) (2023)
- [Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing](https://mlsanity.com/paper/2310.04801/) (2023)
- [Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective](https://mlsanity.com/paper/2407.17120/) (2024)
- [Increasing Textual Context Size Boosts Medical Image-Text Matching](https://mlsanity.com/paper/2303.13340/) (2023)

## Abstract (arXiv)

Cancer detection and prognosis relies heavily on medical imaging, particularly CT and PET scans. Deep Neural Networks (DNNs) have shown promise in tumor segmentation by fusing information from these modalities. However, a critical bottleneck exists: the dependency on CT-PET data concurrently for training and inference, posing a challenge due to the limited availability of PET scans. Hence, there is a clear need for a flexible and efficient framework that can be trained with the widely available CT scans and can be still adapted for PET scans when they become available. In this work, we propose a parameter-efficient multi-modal adaptation (PEMMA) framework for lightweight upgrading of a transformer-based segmentation model trained only on CT scans such that it can be efficiently adapted for use with PET scans when they become available. This framework is further extended to perform prognosis task maintaining the same efficient cross-modal fine-tuning approach. The proposed approach is tested with two well-known segementation backbones, namely UNETR and Swin UNETR. Our approach offers two main advantages. Firstly, we leverage the inherent modularity of the transformer architecture and perform low-rank adaptation (LoRA) as well as decomposed low-rank adaptation (DoRA) of the attention weights to achieve parameter-efficient adaptation. Secondly, by minimizing cross-modal entanglement, PEMMA allows updates using only one modality without causing catastrophic forgetting in the other. Our method achieves comparable performance to early fusion, but with only 8% of the trainable parameters, and demonstrates a significant +28% Dice score improvement on PET scans when trained with a single modality. Furthermore, in prognosis, our method improves the concordance index by +10% when adapting a CT-pretrained model to include PET scans, and by +23% when adapting for both PET and EHR data.