mlsanityData to 13 Oct 2026

Towards a Guideline for Evaluation Metrics in Medical Image Segmentation

arXiv 2202.05273 ↗First posted 10 Feb 2022eess.IV cs.CV cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

In the last decade, research on artificial intelligence has seen rapid growth with deep learning models, especially in the field of medical image segmentation. Various studies demonstrated that these models have powerful prediction capabilities and achieved similar results as clinicians. However, recent studies revealed that the evaluation in image segmentation studies lacks reliable model performance assessment and showed statistical bias by incorrect metric implementation or usage. Thus, this work provides an overview and interpretation guide on the following metrics for medical image segmentation evaluation in binary as well as multi-class problems: Dice similarity coefficient, Jaccard, Sensitivity, Specificity, Rand index, ROC curves, Cohen's Kappa, and Hausdorff distance. As a summary, we propose a guideline for standardized medical image segmentation evaluation to improve evaluation quality, reproducibility, and comparability in the research field.

Key facts. Cited by 60 papers in the map (data through 13 Oct 2026). Builds on 13 of its 55 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

13 of 55 references.

References · 13

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  2. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,183
  3. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 422
  4. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 197
  5. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 171
  6. 2019Deep Semantic Segmentation of Natural and Medical Images: A Reviewcited by 125
  7. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  8. 2019Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directionscited by 24
  9. 2019MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learningcited by 18
  10. 2021Rethinking Semantic Segmentation Evaluation for Explainability and Model Selectioncited by 11
  11. 2022MISeval: a Metric Library for Medical Image Segmentation Evaluationcited by 9
  12. 2022An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networkscited by 8
1 more
  1. 2021Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning Modelscited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 10; 2025: 23; 2026: 23.

60 papers.

Sort:

By area:

  1. 2024An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusioncited by 16
  2. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  3. 2025Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challengecited by 6
  4. 2023Improving Knot Prediction in Wood Logs with Longitudinal Feature Propagationcited by 4
  5. 2024Seg-metrics: a Python package to compute segmentation metricscited by 4
  6. 2024Demystifying the Effect of Receptive Field Size in U-Net Models for Medical Image Segmentationcited by 3
  7. 2024Understanding implementation pitfalls of distance-based metrics for image segmentationcited by 3
  8. 2025Deep learning approaches to surgical video segmentation and object detection: A Scoping Reviewcited by 3
  9. 2025ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Qualitycited by 3
  10. 2022MISm: A Medical Image Segmentation Metric for Evaluation of weak labeled Datacited by 2
  11. 2024BenchCloudVision: A Benchmark Analysis of Deep Learning Approaches for Cloud Detection and Segmentation in Remote Sensing Imagerycited by 2
  12. 2025Semi-Supervised Medical Image Segmentation via Dual Networkscited by 2
38 more
  1. 2025Metric Design != Metric Behavior: Improving Metric Selection for the Unbiased Evaluation of Dimensionality Reductioncited by 2
  2. 2025Absolute Evaluation Measures for Machine Learning: A Surveycited by 2
  3. 2025Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?cited by 2
  4. 2025Towards the Automatic Segmentation, Modeling and Meshing of the Aortic Vessel Tree from Multicenter Acquisitions: An Overview of the SEG.A. 2023 Segmentation of the Aorta Challengecited by 2
  5. 2025Deep Unsupervised Anomaly Detection in Brain Imaging: Large-Scale Benchmarking and Bias Analysiscited by 2
  6. 2025Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challengescited by 2
  7. 2023Robust Tumor Segmentation with Hyperspectral Imaging and Graph Neural Networkscited by 1
  8. 2024Exploring the Role of Convolutional Neural Networks (CNN) in Dental Radiography Segmentation: A Comprehensive Systematic Literature Reviewcited by 1
  9. 2024CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesionscited by 1
  10. 2024DualSwinUnet++: An Enhanced Swin-Unet Architecture With Dual Decoders For PTMC Segmentationcited by 1
  11. 2024Continuous and complete liver vessel segmentation with graph-attention guided diffusioncited by 1
  12. 2026From Cold Start to Active Learning: Embedding-Based Scan Selection for Medical Image Segmentationcited by 1
  13. 2023Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear Detectioncited by 0
  14. 2024AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Reviewcited by 0
  15. 2025DiffRenderGAN: Addressing Training Data Scarcity in Deep Segmentation Networks for Quantitative Nanomaterial Analysis through Differentiable Rendering and Generative Modellingcited by 0
  16. 2025An Efficient Plugin Method for Metric Optimization of Black-Box Modelscited by 0
  17. 2025Manifold Learning for Hyperspectral Imagescited by 0
  18. 2025Enhancing Orthopox Image Classification Using Hybrid Machine Learning and Deep Learning Modelscited by 0
  19. 2025Out-of-distribution data supervision towards biomedical semantic segmentationcited by 0
  20. 2025Object segmentation in the wild with foundation models: application to vision assisted neuro-prostheses for upper limbscited by 0
  21. 2025High-Throughput Low-Cost Segmentation of Brightfield Microscopy Live Cell Imagescited by 0
  22. 2025Robust Small Methane Plume Segmentation in Satellite Imagerycited by 0
  23. 2025Stress-testing cross-cancer generalizability of 3D nnU-Net for PET-CT tumor segmentation: multi-cohort evaluation with novel oesophageal and lung cancer datasetscited by 0
  24. 2025Systematic Evaluation of Attribution Methods: Eliminating Threshold Bias and Revealing Method-Dependent Performance Patternscited by 0
  25. 2025MeshMetrics: A Precise Implementation of Distance-Based Image Segmentation Metricscited by 0
  26. 2025TreeNet: Layered Decision Ensemblescited by 0
  27. 2026Explainable Deep Radiogenomic Molecular Imaging for MGMT Methylation Prediction in Glioblastomacited by 0
  28. 2026Jordan-Segmentable Masks: A Topology-Aware definition for characterizing Binary Image Segmentationcited by 0
  29. 2026Evaluating Deep Learning-Based Nerve Segmentation in Brachial Plexus Ultrasound Under Realistic Data Constraintscited by 0
  30. 2026ROIX-Comp: Optimizing X-ray Computed Tomography Imaging Strategy for Data Reduction and Reconstructioncited by 0
  31. 2026Learning Pore-scale Multiphase Flow from 4D Velocimetrycited by 0
  32. 2026Ordinal Semantic Segmentation Applied to Medical and Odontological Imagescited by 0
  33. 2026A Two-Stage Deep Learning Framework for Segmentation of Ten Gastrointestinal Organs from Coronal MR Enterographycited by 0
  34. 2026Mammographic Lesion Segmentation with Lightweight Models: A Comparative Studycited by 0
  35. 2026NucEval: A Robust Evaluation Framework for Nuclear Instance Segmentationcited by 0
  36. 2026Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance imagescited by 0
  37. 2026Deep Learning-Based Automated Quantification of TIMI Myocardial Perfusion Frame Count (DL-TMPFC) from Coronary Angiography: A Novel Framework for Rapid Assessment of Microvascular Dysfunctioncited by 0
  38. 2026POPSICLE: Benchmark Datasets for Segmentation and Localization in CryoETcited by 0

50 most cited of 60 All 60 (JSON)