We Care Each Pixel: Calibrating on Medical Segmentation Model

• URL: http://arxiv.org/abs/2503.05107v1
• Date: Fri, 07 Mar 2025 03:06:03 GMT
• Title: We Care Each Pixel: Calibrating on Medical Segmentation Model
• Authors: Wenhao Liang, Wei Zhang, Yue Lin, Miao Xu, Olaf Maennel, Weitong Chen,
• Abstract summary: pixel-wise Expected Error (pECE) is a novel metric that measures miscalibration at the pixel level.<n>We also introduce a morphological adaptation strategy that applies morphological operations to ground-truth masks before computing calibration losses.<n>Our method not only enhances segmentation performance but also improves calibration quality, yielding more trustworthy confidence estimates.
• Score: 15.826029150910566
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions. While common metrics such as Accuracy, DSC, IoU, and HD primarily quantify spatial agreement between predictions and ground-truth labels, they do not assess the calibration quality of segmentation models, which is crucial for clinical reliability. To address this limitation, we propose pixel-wise Expected Calibration Error (pECE), a novel metric that explicitly measures miscalibration at the pixel level, thereby ensuring both spatial precision and confidence reliability. We further introduce a morphological adaptation strategy that applies morphological operations to ground-truth masks before computing calibration losses, particularly benefiting margin-based losses such as Margin SVLS and NACL. Additionally, we present the Signed Distance Calibration Loss (SDC), which aligns boundary geometry with calibration objectives by penalizing discrepancies between predicted and ground-truth signed distance functions (SDFs). Extensive experiments demonstrate that our method not only enhances segmentation performance but also improves calibration quality, yielding more trustworthy confidence estimates. Code is available at: https://github.com/EagleAdelaide/SDC-Loss.

Related papers

• Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors [22.39558434131574]
  We introduce the concept of consistency as an alternative perspective on model calibration. We propose a post-hoc calibration method called Consistency (CC) which adjusts confidence based on the model's consistency across inputs. We show that performing perturbations at the logit level significantly improves computational efficiency.
  arXiv  Detail & Related papers  (2024-10-16T06:55:02Z)
• Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation [17.263160921956445]
  We propose to use marginal L1 average calibration error (mL1-ACE) as a novel auxiliary loss function to improve pixel-wise calibration without compromising segmentation quality. We show that this loss, despite using hard binning, is directly differentiable, bypassing the need for approximate but differentiable surrogate or soft binning approaches.
  arXiv  Detail & Related papers  (2024-03-11T14:31:03Z)
• PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation [87.69789891809562]
  Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. The calibration of predictive uncertainty in the target domain, a crucial aspect of the safe deployment of UDA models, has received limited attention. We propose PseudoCal, a source-free calibration method that exclusively relies on unlabeled target data.
  arXiv  Detail & Related papers  (2023-07-14T17:21:41Z)
• Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty [52.03490691733464]
  We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks. By leveraging subjective logic theory, we explicitly model probability and uncertainty for the problem of medical image segmentation. DeviS incorporates an uncertainty-aware filtering module, which utilizes the metric of uncertainty-calibrated error to filter reliable data.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• On Calibrating Semantic Segmentation Models: Analyses and An Algorithm [51.85289816613351]
  We study the problem of semantic segmentation calibration. Model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. We propose a simple, unifying, and effective approach, namely selective scaling.
  arXiv  Detail & Related papers  (2022-12-22T22:05:16Z)
• DOMINO: Domain-aware Model Calibration in Medical Image Segmentation [51.346121016559024]
  Modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. We propose DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our results show that DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation.
  arXiv  Detail & Related papers  (2022-09-13T15:31:52Z)
• Confidence Calibration for Object Detection and Segmentation [6.700433100198165]
  This chapter focuses on the investigation of confidence calibration for object detection and segmentation models. We introduce the concept of multivariate confidence calibration that is an extension of well-known calibration methods. We show that especially object detection as well as instance segmentation models are intrinsically miscalibrated.
  arXiv  Detail & Related papers  (2022-02-25T15:59:51Z)
• Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation [2.6465053740712157]
  The Dice similarity coefficient (DSC) is a widely used metric and loss function for biomedical image segmentation. In this study, we identify poor calibration as an emerging challenge of deep learning based biomedical image segmentation. We provide a simple yet effective extension of the DSC loss, named the DSC++ loss, that selectively modulates the penalty associated with overconfident, incorrect predictions.
  arXiv  Detail & Related papers  (2021-10-31T16:02:02Z)
• Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction [65.44752447868626]
  We propose collaborative boundaryaware context encoding networks called AEP-Net for error prediction task. Specifically, we propose a collaborative feature transformation branch for better feature fusion between images and masks, and precise localization of error regions. The AEP-Net achieves an average DSC of 0.8358, 0.8164 for error prediction task, and shows a high Pearson correlation coefficient of 0.9873.
  arXiv  Detail & Related papers  (2020-06-25T12:42:01Z)
• Calibrating Deep Neural Networks using Focal Loss [77.92765139898906]
  Miscalibration is a mismatch between a model's confidence and its correctness. We show that focal loss allows us to learn models that are already very well calibrated. We show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases.
  arXiv  Detail & Related papers  (2020-02-21T17:35:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.