ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Quality
Not on the map. Why?
Abstract (arXiv)
Assessing the quality of automatic image segmentation is crucial in clinical practice, but often very challenging due to the limited availability of ground truth annotations. Reverse Classification Accuracy (RCA) is an approach that estimates the quality of new predictions on unseen samples by training a segmenter on those predictions, and then evaluating it against existing annotated images. In this work we introduce ConfIC-RCA (Conformal In-Context RCA), a novel method for automatically estimating segmentation quality with statistical guarantees in the absence of ground-truth annotations, which consists of two main innovations. First, In-Context RCA, which leverages recent in-context learning models for image segmentation and incorporates retrieval-augmentation techniques to select the most relevant reference images. This approach enables efficient quality estimation with minimal reference data while avoiding the need of training additional models. Second, we introduce Conformal RCA, which extends both the original RCA framework and In-Context RCA to go beyond point estimation. Using tools from split conformal prediction, Conformal RCA produces prediction intervals for segmentation quality providing statistical guarantees that the true score lies within the estimated interval with a user-specified probability. Validated across 10 different medical imaging tasks in various organs and modalities, our methods demonstrate robust performance and computational efficiency, offering a promising solution for automated quality control in clinical workflows, where fast and reliable segmentation assessment is essential. The code is available at https://github.com/mcosarinsky/Conformal-In-Context-RCA
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 65 references that are in the map. First posted on arXiv 6 Mar 2025.
Builds on
37 of 65 references.
References · 37
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2023Segment Anythingcited by 8,158
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
- 2016Distribution-Free Predictive Inference For Regressioncited by 657
- 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
- 2019Conformalized Quantile Regressioncited by 620
25 more
- 2024The Faiss librarycited by 370
- 2022Conformal prediction beyond exchangeabilitycited by 348
- 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
- 2024Medical SAM 2: Segment medical images as video via Segment Anything Model 2cited by 151
- 2024Exploring scalable medical image encoders beyond text supervisioncited by 129
- 2019PHiSeg: Capturing Uncertainty in Medical Image Segmentationcited by 128
- 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
- 2023Class-Conditional Conformal Prediction with Many Classescited by 109
- 2023UniverSeg: Universal Medical Image Segmentationcited by 90
- 2022Towards a Guideline for Evaluation Metrics in Medical Image Segmentationcited by 58
- 2024MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imagingcited by 45
- 2017Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truthcited by 35
- 2021NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentationcited by 33
- 2023CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray imagescited by 33
- 2018Real-time Prediction of Segmentation Qualitycited by 23
- 2020Deep Generative Model-based Quality Control for Cardiac MRI Segmentationcited by 21
- 2024Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Modelscited by 20
- 2024On Temperature Scaling and Conformal Prediction of Deep Classifierscited by 13
- 2022Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scorescited by 10
- 2021A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentationcited by 9
- 2019An Alarm System For Segmentation Algorithm Based On Shape Modelcited by 8
- 2024Conformal Performance Range Prediction for Segmentation Output Quality Controlcited by 8
- 2024PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Imagescited by 8
- 2021Efficient Model Monitoring for Quality Control in Cardiac Image Segmentationcited by 6
- 2023Unsupervised bias discovery in medical image segmentationcited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.