Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment
Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents an even more difficult scenario. To cope with this challenge, knowledge distillation has emerged as one promising strategy. However, recent efforts typically overlook the modality gaps and thus fail to learn invariant feature representations across different modalities. Such drawback consequently leads to limited performance for both teachers and students. To ameliorate these problems, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor. As a major contribution, we prove that our novel training paradigm ensures a tight evidence lower bound, thus theoretically certifying its effectiveness. Extensive experiments on different backbones validate that the proposed paradigm can enable invariant feature representations and produce a teacher with narrowed modality gaps. This further offers superior guidance for missing modality students, achieving an average improvement of 1.75 on dice score.
Code (0)
등록된 구현이 없습니다.
Tasks
Brain Tumor SegmentationKnowledge DistillationTumor SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Brain Tumor Segmentation on MRI with Missing Modalities
Brain Tumor Segmentation from magnetic resonance imaging (MRI) is a critical technique for early diagnosis. However, rather than having complete four modalities as in BraTS dataset, it is common to have missing modalitie…
Brain Tumor SegmentationDomain AdaptationSegmentationTumor SegmentationConditional generator and multi-sourcecorrelation guided brain tumor segmentation with missing MR modalities
Brain tumor is one of the most high-risk cancers which causes the 5-year survival rate of only about 36%. Accurate diagnosis of brain tumor is critical for the treatment planning. However, complete data are not always av…
Brain Tumor SegmentationSegmentationTumor SegmentationMeta-D: Metadata-Aware Architectures for Brain Tumor Analysis and Missing-Modality Segmentation
We present Meta-D, an architecture that explicitly leverages categorical scanner metadata such as MRI sequence and plane orientation to guide feature extraction for brain tumor analysis. We aim to improve the performance…
Brain Tumor SegmentationMedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment
Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI). However, in clinical practice, certain modalities of MRI may be missing, which presents a more difficult scenario. To cope with this c…
Brain Tumor SegmentationDomain AdaptationImage SegmentationKnowledge Distillation+4Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalities
Using multimodal Magnetic Resonance Imaging (MRI) is necessary for accurate brain tumor segmentation. The main problem is that not all types of MRIs are always available in clinical exams. Based on the fact that there is…
Brain Tumor SegmentationSegmentationTumor Segmentation