In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Medical image registration is an important task in medical image processing. It refers to the process of aligning data sets, possibly from different modalities (e.g., magnetic resonance and computed tomography), different time points (e.g., follow-up scans), and/or different subjects (in case of population studies). A large number of methods for image registration are described in the literature. Unfortunately, there is not one method that works for all applications. We have therefore developed elastix, a publicly available computer program for intensity-based medical image registration. The software consists of a collection of algorithms that are commonly used to solve medical image registration problems. The modular design of elastix allows the user to quickly configure, test, and compare different registration methods for a specific application. The command-line interface enables automated processing of large numbers of data sets, by means of scripting. The usage of elastix for comparing different registration methods is illustrated with three example experiments, in which individual components of the registration method are varied.

elastix : A Toolbox for Intensity-Based Medical Image Registration

This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Participants were also allowed to use additional proprietary training data for that purpose. All teams then had to apply their methods to 10 test datasets and submit the obtained results. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to reference segmentations five error measures that highlight different aspects of segmentation accuracy. All measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets

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 algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community.

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

https://engineering.case.edu/centers/ccipd/sites/ccipd.case.edu/files/Evaluation_of_prostate_segmentation_algorithms_for_MRI.pdf

Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge.

A system and method for using pre-procedural images for registration for image-guided therapy (IGT), also referred to as image-guided intervention (IGI), in percutaneous surgical application. Pseudo-features and patient abdomen and organ surfaces are used for registration and to establish the relationship needed for guidance. Three-dimensional visualizations of the vasculature, tumor(s), and organs may be generated for enhanced guidance information. The invention facilitates extensive pre-procedural planning, thereby significantly reducing procedural times. It also minimizes the patient exposure to radiation.

System and method for abdominal surface matching using pseudo-features

In this paper, we evaluate a semi-automatic liver segmentation method based on a level-set approach and a dynamically adapted speed func- tion. The approach also relies on a-priori anatomic information to reduce leak- age at the liver-rib interface. The numerical algorithms have been integrated into a complete system that permits loading DICOM images, segmenting these images, and visualizing the liver surface. Although the normal operation of the system assumes manual contour corrections, such corrections were not allowed for this evaluation. Results show that except for cases with large tumors that ex- tend to the liver surface, the method we propose is comparable to a human rater.

/pdf/semi-automatic-segmentation-of-the-liver-and-its-evaluation-itgedqhz57.pdf

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

A system and method to conduct image segmentation by imaging target morphological shapes evolving from one 2-dimension (2-D) image slice to one or more nearby neighboring 2-D images taken from a 3-dimension (3-D) image. One area defined by a user as a target on an image slice can be found in a corresponding area on a nearby neighboring image slice by using a deformation field generated with deformable image registration procedure between these two image slices. It allows the user to distinguish target and background areas with the same or similar image intensities.

Image segmentation of organs and anatomical structures

Interactive image-guided liver surgery (Linasys device, Pathfinder Therapeutics, Inc., Nashville, TN) requires a user-oriented,
easy-to-use, fast segmentation preoperative surgical planning system. This system needs to build liver models
displaying the liver surface, tumors, and the vascular system of the liver. A robust and efficient tool for this purpose was
developed and evaluated. For the liver surface or other bulk shape organ segmentation, the delineation was conducted on
multiple slices of a CT image volume with a region growing algorithm. This algorithm incorporates both spatial and
temporal information of a propagating front to advance the segmenting contour. The user can reduce the number of
delineation slices during the processing by using interpolation. When comparing our liver segmentation results to those
from MeVis (Breman, Germany), the average overlap percentage was 94.6%. For portal and hepatic vein segmentation,
three-dimensional region growing based on image intensity was used. All second generation branches can be identified
without time-consuming image filtering and manual editing. The two veins are separated by using mutually exclusive
region growing. The tool can be used to conduct segmentation and modeling of the liver, veins, and other organs and can
prepare image data for export to Linasys within one hour.

Senhu Li

Papers

Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets

System and method for abdominal surface matching using pseudo-features

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

Image segmentation of organs and anatomical structures

Development of preoperative liver and vascular system segmentation and modeling tool for image-guided surgery and surgical planning