PEMMA: Parameter-Efficient Multi-Modal Adaptation for Medical Image Segmentation
원문 초록
Imaging modalities such as Computed Tomography (CT) and Positron Emission Tomography (PET) are key in cancer detection, inspiring Deep Neural Networks (DNN) models that merge these scans for tumor segmentation. When both CT and PET scans are available, it is common to combine them as two channels of the input to the segmentation model. However, this method requires both scan types during training and inference, posing a challenge due to the limited availability of PET scans, thereby sometimes limiting the process to CT scans only. Hence, there is a need to develop a flexible DNN architecture that can be trained/updated using only CT scans but can effectively utilize 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 to also incorporate PET scans. The benefits of the proposed approach are two-fold. Firstly, we leverage the inherent modularity of the transformer architecture and perform low-rank adaptation (LoRA) of the attention weights to achieve parameter-efficient adaptation. Secondly, since the PEMMA framework attempts to minimize cross modal entanglement, it is possible to subsequently update the combined model using only one modality, without causing catastrophic forgetting of the other modality. Our proposed method achieves comparable results with the performance of early fusion techniques with just 8% of the trainable parameters, especially with a remarkable +28% improvement on the average dice score on PET scans when trained on a single modality.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Prompting
TextBraTS: Text-Guided Volumetric Brain Tumor Segmentation with Innovative Dataset Development and Fusion Module Exploration
Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention
DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling
MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation
A Cascaded Deep-Learning Framework for Segmentation of Metastatic Brain Tumors Before and After Stereotactic Radiation Therapy
토론
이 논문과 연결된 포럼 글이 아직 없습니다.