• Corpus ID: 67855790

A large annotated medical image dataset for the development and evaluation of segmentation algorithms

  title={A large annotated medical image dataset for the development and evaluation of segmentation algorithms},
  author={Amber L. Simpson and Michela Antonelli and Spyridon Bakas and Michel Bilello and Keyvan Farahani and Bram van Ginneken and Annette Kopp-Schneider and Bennett A. Landman and Geert J. S. Litjens and Bjoern H Menze and Olaf Ronneberger and Ronald M. Summers and Patrick Bilic and Patrick Ferdinand Christ and Richard Kinh Gian Do and Marc J. Gollub and Jennifer Golia-Pernicka and Stephan Heckers and William R. Jarnagin and Maureen McHugo and Sandy Napel and Eugene Vorontsov and Lena Maier-Hein and M. Jorge Cardoso},
Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation… 

Figures from this paper

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

This paper presents a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarized both the technical novelties and empirical results and analyzed the limitations and several unsolved problems of existing approaches.

Going to Extremes: Weakly Supervised Medical Image Segmentation

This work suggests using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation.

Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets

This work gives the first attempt to conjecture that the different distribution is the key reason for ‘catastrophic forgetting’ that commonly exists in IL methods, and verify that IL has the natural adaptability to medical image scenarios.

Learning Incrementally to Segment Multiple Organs in a CT Image

While IL is notorious for its ‘catastrophic forgetting’ weakness in the context of natural image analysis, it is experimentally discover that such a weakness mostly disappears for CT multi-organ segmentation.

Interactive segmentation of medical images through fully convolutional neural networks

A deep learning (DL) based semi-automated segmentation approach that aims to be a "smart" interactive tool for region of interest delineation in medical images and demonstrates its use for segmenting multiple organs on computed tomography of the abdomen.

Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks

An automatic CT segmentation method based on weakly supervised learning, by which one could train an accurate segmentation model only with weak annotations in the form of bounding boxes, which is accurate, efficient, and suitable for clinical use.

Small Segment Emphasized Performance Evaluation Metric for Medical Images

  • R. AmmuN. Sinha
  • Medicine
    2020 International Conference on Signal Processing and Communications (SPCOM)
  • 2020
The proposed metric, SSEGEP (Smatt SEGment Emphasized Performance evaluation metric), is found to perform better for the images having multiple segments for a single label and where the regions of interest are not localized.

Benefits of Linear Conditioning with Metadata for Image Segmentation

This work adapts a linear conditioning method called FiLM (Feature-wise Linear Modulation) for image segmentation tasks, enables integrating metadata into segmentation models for better performance and assess the relevance of segmentation FiLM layers for tackling common challenges in medical imaging.

A novel shape-based loss function for machine learning-based seminal organ segmentation in medical imaging

The quantitative evaluation of the segmentation results indicated that the proposed PCA-based loss function would lead to significant improvements in organ/structure segmentations from medical images, including improvements in hippocampus and heart segmentation from MR and CT images.

Deep semantic segmentation of natural and medical images: a review

This review categorizes the leading deep learning-based medical and non-medical image segmentation solutions into six main groups of deep architectural, data synthesis- based, loss function-based, sequenced models, weakly supervised, and multi-task methods.



Deep learning and its application to medical image segmentation

This article describes how to build a 3D fully convolutional network (FCN) that can process 3D images in order to produce automatic semantic segmentations and shows state-of-the-art performance in multi-organ segmentation.

The Liver Tumor Segmentation Benchmark (LiTS)

A review of semantic segmentation using deep neural networks

The field of semantic segmentation as pertaining to deep convolutional neural networks is reviewed and comprehensive coverage of the top approaches is provided and the strengths, weaknesses and major challenges are summarized.

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

The set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences are reported, finding that different algorithms worked best for different sub-regions, but that no single algorithm ranked in the top for all sub-Regions simultaneously.

Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features

This set of labels and features should enable direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as performance evaluation of computer-aided segmentation methods.

Semi-automatic Segmentation of the Liver and its Evaluation on the MICCAI 2007 Grand Challenge Data Set

Results show that except for cases with large tumors that ex- tend to the liver surface, the method proposed is comparable to a human rat, and also relies on a-priori anatomic information to reduce leak- age at the liver-rib interface.

Why rankings of biomedical image analysis competitions should be interpreted with care

It is demonstrated that outcome varies based on the metrics used and that limited information reporting hampers reproducibility, and recommend best practice guidelines and define open research questions to be addressed in the future.

Benchmark for Algorithms Segmenting the Left Atrium From 3D CT and MRI Datasets

A standardisation framework can be used to label and further analyse anatomical regions of the LA by performing the standardisation directly on the left atrial surface, including meshes exported from different electroanatomical mapping systems.

The Pascal Visual Object Classes Challenge: A Retrospective

A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.

Segmentation of the heart and great vessels in CT images using a model-based adaptation framework