DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentation

2025-11-12

AI Summary

In semi-supervised medical image segmentation, the teacher-student paradigm suffers from erroneous pseudo-labels and self-reinforcing bias due to image ambiguity. To address this, we propose the Dual-Teacher Feedback Model (DTFM), which establishes a closed-loop feedback mechanism: a feedback attributor identifies critical pseudo-labels driving student updates, while a feedback receiver localizes regions requiring correction. Two teachers employ dynamic cross-supervision to calibrate their disagreements, thereby avoiding systematic errors induced by conventional consistency regularization. Unlike unidirectional knowledge distillation, DTFM enables endogenous error correction of supervision signals. Evaluated on three major medical image segmentation benchmarks, DTFM significantly mitigates error propagation—achieving average Dice score improvements of 3.2–5.7% using only 10% labeled data—demonstrating superior robustness and generalization.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

The teacher-student paradigm has emerged as a canonical framework in semi-supervised learning. When applied to medical image segmentation, the paradigm faces challenges due to inherent image ambiguities, making it particularly vulnerable to erroneous supervision. Crucially, the student's iterative reconfirmation of these errors leads to self-reinforcing bias. While some studies attempt to mitigate this bias, they often rely on external modifications to the conventional teacher-student framework, overlooking its intrinsic potential for error correction. In response, this work introduces a feedback mechanism into the teacher-student framework to counteract error reconfirmations. Here, the student provides feedback on the changes induced by the teacher's pseudo-labels, enabling the teacher to refine these labels accordingly. We specify that this interaction hinges on two key components: the feedback attributor, which designates pseudo-labels triggering the student's update, and the feedback receiver, which determines where to apply this feedback. Building on this, a dual-teacher feedback model is further proposed, which allows more dynamics in the feedback loop and fosters more gains by resolving disagreements through cross-teacher supervision while avoiding consistent errors. Comprehensive evaluations on three medical image benchmarks demonstrate the method's effectiveness in addressing error propagation in semi-supervised medical image segmentation.

Problem

• Addresses error propagation in semi-supervised medical image segmentation
• Mitigates self-reinforcing bias from teacher-student pseudo-label errors
• Introduces feedback mechanisms to correct erroneous supervision dynamically

Innovation

• Introduces feedback mechanism into teacher-student framework
• Uses feedback attributor and receiver for error correction
• Implements dual-teacher model with cross-teacher supervision