Zhongzhou Zhang

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) Multiple networks assignment 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 a novel unified all-in-one framework for MM-SSLmedical image segmentation. To address challenge (1), we propose a modality all-in-one segmentation network based on standard U-Net architecture that accepts data from all 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. The source code is publicly available at https://github.com/CYYukio/Double-Knowledge-Banking.

Knowledge Tracing (KT) aims to trace changes in students’ knowledge states throughout their entire learning process by analyzing their historical learning data and predicting their future learning performance. Existing forgetting curve theory–based knowledge tracing models only consider the general forgetting caused by time intervals, ignoring the specific influences in KT task. First, the discriminative information in forgetting curve is personalized due to the difference of students. Second, the relationship between knowledge concepts could contribute to the generalized features in the forgetting process. Considering these two aspects, we propose a Concept-Driven Personalized Forgetting (CPF) knowledge tracing model, which integrates the relationships between knowledge concepts and the personalization of students in cognitive abilities. First, personalized cognitive abilities are integrated into the learning and forgetting processes. Individual cognitive differences are modeled to dynamically adjust learning gains and forgetting rates based on students’ knowledge mastery and learning strategies, which enables a more personalized learning experience. Second, the hierarchical relationships among knowledge concepts are considered by designing a precursor-successor knowledge concept matrix. In this way, the potential impact of forgetting prior knowledge concepts on subsequent ones is also integrated in KT task. Furthermore, the proposed personalized forgetting mechanism not only could be applied into the learning of specific knowledge concepts but also in the forgetting-review mechanism of life-long learning process. Extensive experimental results on several public datasets show that our CPF outperforms current forgetting curve theory–based methods in predicting student performance, demonstrating CPF can better simulate changes in students’ knowledge state through the personalized forgetting mechanism. Our code is publicly available at https://github.com/lqr-1169/CPF .