# Double Banking on Knowledge: Customized Modulation and Prototypes for Multi-Modality Semi-supervised Medical Image Segmentation

arXiv: https://arxiv.org/abs/2410.17565 · HTML: https://mlsanity.com/paper/2410.17565/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://mlsanity.com/paper/2001.03111/) (2020)
- [Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization](https://mlsanity.com/paper/2112.11177/) (2021)
- [Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation](https://mlsanity.com/paper/2106.08752/) (2021)
- [Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration](https://mlsanity.com/paper/2208.03901/) (2022)
- [Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging](https://mlsanity.com/paper/2206.03709/) (2022)

## Abstract (arXiv)

Multi-modality (MM) semi-supervised learning (SSL) based medical image segmentation has recently gained increasing attention for its ability to utilize MM data and reduce reliance on labeled images. However, current methods face several challenges: (1) Complex network designs hinder scalability to scenarios with more than two modalities. (2) Focusing solely on modality-invariant representation while neglecting modality-specific features, leads to incomplete MM learning. (3) Leveraging unlabeled data with generative methods can be unreliable for SSL. To address these problems, we propose Double Bank Dual Consistency (DBDC), a novel MM-SSL approach for medical image segmentation. To address challenge (1), we propose a modality all-in-one segmentation network that accommodates data from any number of modalities, removing the limitation on modality count. To address challenge (2), we design two learnable plug-in banks, Modality-Level Modulation bank (MLMB) and Modality-Level Prototype (MLPB) bank, to capture both modality-invariant and modality-specific knowledge. These banks are updated using our proposed Modality Prototype Contrastive Learning (MPCL). Additionally, we design Modality Adaptive Weighting (MAW) to dynamically adjust learning weights for each modality, ensuring balanced MM learning as different modalities learn at different rates. Finally, to address challenge (3), we introduce a Dual Consistency (DC) strategy that enforces consistency at both the image and feature levels without relying on generative methods. We evaluate our method on a 2-to-4 modality segmentation task using three open-source datasets, and extensive experiments show that our method outperforms state-of-the-art approaches.