mlsanityData to 14 Oct 2026

Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy

arXiv 2011.08065 ↗First posted 23 Oct 2020physics.med-ph cs.CV cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

Gastrointestinal (GI) pathologies are periodically screened, biopsied, and resected using surgical tools. Usually the procedures and the treated or resected areas are not specifically tracked or analysed during or after colonoscopies. Information regarding disease borders, development and amount and size of the resected area get lost. This can lead to poor follow-up and bothersome reassessment difficulties post-treatment. To improve the current standard and also to foster more research on the topic we have released the ``Kvasir-Instrument'' dataset which consists of 590 annotated frames containing GI procedure tools such as snares, balloons and biopsy forceps, etc. Beside of the images, the dataset includes ground truth masks and bounding boxes and has been verified by two expert GI endoscopists. Additionally, we provide a baseline for the segmentation of the GI tools to promote research and algorithm development. We obtained a dice coefficient score of 0.9158 and a Jaccard index of 0.8578 using a classical U-Net architecture. A similar dice coefficient score was observed for DoubleUNet. The qualitative results showed that the model did not work for the images with specularity and the frames with multiple instruments, while the best result for both methods was observed on all other types of images. Both, qualitative and quantitative results show that the model performs reasonably good, but there is a large potential for further improvements. Benchmarking using the dataset provides an opportunity for researchers to contribute to the field of automatic endoscopic diagnostic and therapeutic tool segmentation for GI endoscopy.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 10; 2024: 11; 2025: 15; 2026: 9.

54 papers.

Sort:

By area:

  1. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 219
  2. 2022EndoMapper dataset of complete calibrated endoscopy procedurescited by 53
  3. 2023Segment Anything Model for Medical Images?cited by 39
  4. 2022Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentationcited by 28
  5. 2023What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentationcited by 24
  6. 2024Kvasir-VQA: A Text-Image Pair GI Tract Datasetcited by 23
  7. 2023LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Roomscited by 21
  8. 2023Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the artcited by 18
  9. 2021NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopycited by 16
  10. 2023DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentationcited by 16
  11. 2021Meta-learning with implicit gradients in a few-shot setting for medical image segmentationcited by 15
  12. 2024ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modelingcited by 14
38 more
  1. 2024Frontiers in Intelligent Colonoscopycited by 14
  2. 2025EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysiscited by 14
  3. 2024Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentationcited by 12
  4. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  5. 2024Adapting the Segment Anything Model During Usage in Novel Situationscited by 9
  6. 2025Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Modelscited by 9
  7. 2023Whether and When does Endoscopy Domain Pretraining Make Sense?cited by 8
  8. 2025Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Reviewcited by 8
  9. 2025MedSG-Bench: A Benchmark for Medical Image Sequences Groundingcited by 8
  10. 2024SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy datacited by 7
  11. 2023Stable Segment Anything Modelcited by 6
  12. 2024Generative Medical Segmentationcited by 6
  13. 2025Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Modelscited by 5
  14. 2021Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagationcited by 3
  15. 2023Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challengescited by 3
  16. 2024MoPEFT: A Mixture-of-PEFTs for the Segment Anything Modelcited by 3
  17. 2025Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentationcited by 3
  18. 2025Medico 2025: Visual Question Answering for Gastrointestinal Imagingcited by 3
  19. 2025Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRAcited by 2
  20. 2025Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQAcited by 2
  21. 2026Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecturecited by 2
  22. 2023UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answeringcited by 1
  23. 2024A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Modelscited by 1
  24. 2025Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generationcited by 1
  25. 2025Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoningcited by 1
  26. 2026SAGE: An Expert-Annotated South Asian GI Endoscopy Dataset for Multimodal Learning and Hallucination Analysiscited by 1
  27. 2021PAANet: Progressive Alternating Attention for Automatic Medical Image Segmentationcited by 0
  28. 2022Performance Comparison of Deep Learning Architectures for Artifact Removal in Gastrointestinal Endoscopic Imagingcited by 0
  29. 2022PlutoNet: An Efficient Polyp Segmentation Network with Modified Partial Decoder and Decoder Consistency Trainingcited by 0
  30. 2022EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)cited by 0
  31. 2024Polyp and Surgical Instrument Segmentation with Double Encoder-Decoder Networkscited by 0
  32. 2025VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentationcited by 0
  33. 2025Querying GI Endoscopy Images: A VQA Approachcited by 0
  34. 2025MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopycited by 0
  35. 2025Improved Segmentation of Polyps and Visual Explainability Analysiscited by 0
  36. 2026Seeing Through the Tool: A Controlled Benchmark for Occlusion Robustness in Foundation Segmentation Modelscited by 0
  37. 2026RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answeringcited by 0
  38. 2026Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentationcited by 0

50 most cited of 54 All 54 (JSON)