PO.BCS02.04 · 生物信息与计算
CorrectionNet：一种用于改进医学图像分割的轻量级残差精修框架
CorrectionNet: A lightweight residual refinement framework for improving medical image segmentation
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
准确且可重复的图像分割对于肿瘤影像任务至关重要，包括肿瘤勾画、治疗计划制定和定量疗效评估。尽管现代深度学习框架（如nn-UNet）具有强大的基线性能，自动分割仍经常表现出系统性的边界误差以及对小型或浸润性肿瘤区域的分割不足，导致耗费高昂的人工校正工作。我们提出CorrectionNet，一种轻量级、模块化的精修框架，设计用于在现有分割模型之上运行。该方法围绕初始分割提取基于图像块的感兴趣区域，并将多模态影像与基础模型的概率图共同输入一个浅层3D U-Net。CorrectionNet不预测完整的掩膜，而是学习残差连接，使其能够修正高置信度的假阳性/假阴性，并改善边界的规整性，同时保留整体肿瘤结构。训练聚焦于基础模型可能错误或不确定的体素，从而实现高效的学习行为和极小的计算开销。在当前的定量评估中，CorrectionNet相对于nnU-Net保持了整体病灶Dice性能（ΔDice = −0.0002 ± 0.0024，p = 0.18），同时在边界精度上取得了可测量的改进（ΔHD95 = −0.089 ± 0.786 mm；单侧p = 0.03）。近半数（47.7%）的局部体素编辑代表真正的错误校正，模型表现出对消除假阳性边界过度分割的强烈偏好（FP修正精度 = 81.5%）。CorrectionNet的超参数进一步使研究人员或临床医生能够调节假阳性去除与假阴性恢复之间的平衡，以适应多样的肿瘤形态和临床优先事项。总体而言，CorrectionNet为肿瘤学分割工作流提供了一个实用且可扩展的精修层。通过在不重新训练或替换基础模型的情况下改善局部边界保真度，它有望减少人工编辑工作量并促进自动分割的临床部署。
查看英文原文 English abstract
Accurate and reproducible image segmentation is crucial for oncologic imaging tasks, including tumor delineation, treatment planning, and quantitative response assessment. Despite strong baseline performance from modern deep learning frameworks such as nn-Unet, automated segmentations frequently exhibit systematic boundary errors and under-segmentation of small or infiltrative tumor regions, resulting in costly manual correction efforts. We present CorrectionNet, a lightweight and modular refinement framework designed to work on top of existing segmentation models. The method extracts patch-based regions of interest around the initial segmentation and inputs both multimodal imaging and base-model probability maps to a shallow 3D U-Net. Instead of predicting full masks, CorrectionNet learns residual connections, enabling it to fix high-confidence false positives/negatives and improve boundary regularity while preserving the global tumor structure. Training focuses on voxels where the base model is likely incorrect or uncertain, yielding efficient learning behavior and minimal computational overhead. In current quantitative evaluations, CorrectionNet maintained whole-lesion Dice performance relative to nnU-Net (ΔDice = −0.0002 ± 0.0024, p = 0.18) while achieving measurable improvements in boundary accuracy (ΔHD95 = −0.089 ± 0.786 mm; one-sided p = 0.03). Nearly half of all local voxel edits (47.7%) represented true error corrections, with the model showing a strong preference for eliminating false-positive boundary over-segmentation (FP fix precision = 81.5%). CorrectionNet hyperparameters further enable researchers or clinicians to tune the balance between false-positive removal and false-negative recovery, accommodating diverse tumor morphologies and clinical priorities. Overall, CorrectionNet provides a practical and scalable refinement layer for oncology segmentation workflows. By improving local boundary fidelity without retraining or replacing base models, it has the potential to reduce manual editing effort and enhance clinical deployment of automated segmentation.
利益披露 Disclosure
A. Azar, None..
C. Lin, None..
N. Kim, None.