Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation
This addresses the challenge of limited high-quality annotations for hepatic vessel segmentation in medical imaging, which is expertise-demanding and laborious, though it appears incremental as it builds on existing noisy label correction methods.
The paper tackles the problem of hepatic vessel segmentation from CT scans where high-quality labeled data is scarce, by developing a mean-teacher-assisted confident learning framework that transforms noisy labels into useful training data, achieving superior performance on two public datasets.
Manually segmenting the hepatic vessels from Computer Tomography (CT) is far more expertise-demanding and laborious than other structures due to the low-contrast and complex morphology of vessels, resulting in the extreme lack of high-quality labeled data. Without sufficient high-quality annotations, the usual data-driven learning-based approaches struggle with deficient training. On the other hand, directly introducing additional data with low-quality annotations may confuse the network, leading to undesirable performance degradation. To address this issue, we propose a novel mean-teacher-assisted confident learning framework to robustly exploit the noisy labeled data for the challenging hepatic vessel segmentation task. Specifically, with the adapted confident learning assisted by a third party, i.e., the weight-averaged teacher model, the noisy labels in the additional low-quality dataset can be transformed from "encumbrance" to "treasure" via progressive pixel-wise soft-correction, thus providing productive guidance. Extensive experiments using two public datasets demonstrate the superiority of the proposed framework as well as the effectiveness of each component.