Semi-Automated 3D Segmentation of Pelvic Region Bones in CT Volumes for the Annotation of Machine Learning Datasets (original) (raw)
Related papers
A Region-Based Algorithm for Automatic Bone Segmentation in Volumetric CT
In Computed Tomography (CT), bone segmentation is considered an important step to extract bone parameters, which are frequently useful for computer-aided diagnosis, surgery and treatment of many diseases such as osteoporosis. Consequently, the development of accurate and reliable segmentation techniques is essential, since it often provides a great impact on quantitative image analysis and diagnosis outcome. This chapter presents an automated multistep approach for bone segmentation in volumetric CT datasets. It starts with a three-dimensional (3D) watershed operation on an image gradient magnitude. The outcome of the watershed algorithm is an over-partioning image of many 3D regions that can be merged, yielding a meaningful image partitioning. In order to reduce the number of regions, a merging procedure was performed that merges neighbouring regions presenting a mean intensity distribution difference of ±15%. Finally, once all bones have been distinguished in high contrast, the final 3D bone segmentation was achieved by selecting all regions with bone fragments, using the information retrieved by a threshold mask. The bones contours were accurately defined according to the watershed regions outlines instead of considering the thresholding segmentation result. This new method was tested to segment the rib cage on 185 CT images, acquired at the São João Hospital of Porto (Portugal) and evaluated using the dice similarity coefficient as a statistical validation metric, leading to a coefficient mean score of 0.89. This could represent a step forward towards accurate and automatic quantitative analysis in clinical environments and decreasing time-consumption, user dependence and subjectivity.
Automated bone segmentation from Pelvic CT images
Bioinformatics and Biomeidcine …, 2008
Segmentation of bone tissue from Pelvic CT images is a crucial step in developing an automated system for assisting experts with diagnostic decisions for traumatic pelvic injuries. The method proposed in this paper combines Wavelet processing, Laplacian filtering, morphology operations, a series of region growing techniques and gradient based segmentation methods to create an automated segmentation system. The method, tested against a database of pelvic injury CT images, provides promising results. This computationally efficient method sets the grounds for creating an automated decision making system that will be able to provide physicians with reliable recommendations for the treatment of traumatic pelvic injuries.
Segmentation and Analysis of CT Images for Bone Fracture Detection and Labeling
Medical Imaging, 2019
Developing computerized solutions for several orthopedic healthcare practices is one of the emerging fields in computer science. Development of expert systems such as CAD for fracture reduction surgery, automated preoperative surgical planners, outcome prediction systems, intra-operative assistant systems, and virtual reality (VR)-based simulators for surgical skill training
Segmentation of bones in medical dual-energy computed tomography volumes using the 3D U-Net
Physica Medica
Deep learning algorithms have improved the speed and quality of segmentation for certain tasks in medical imaging. The aim of this work is to design and evaluate an algorithm capable of segmenting bones in dual-energy CT data sets. A convolutional neural network based on the 3D U-Net architecture was implemented and evaluated using high tube voltage images, mixed images and dual-energy images from 30 patients. The network performed well on all the data sets; the mean Dice coefficient for the test data was larger than 0.963. Of special interest is that it performed better on dual-energy CT volumes compared to mixed images that mimicked images taken at 120 kV. The corresponding increase in the Dice coefficient from 0.965 to 0.966 was small since the enhancements were mainly at the edges of the bones. The method can easily be extended to the segmentation of multi-energy CT data.
BMC Medical Informatics and Decision Making, 2009
Background: The analysis of pelvic CT scans is a crucial step for detecting and assessing the severity of Traumatic Pelvic Injuries. Automating the processing of pelvic CT scans could impact decision accuracy, decrease the time for decision making, and reduce health care cost. This paper discusses a method to automate the segmentation of bone from pelvic CT images. Accurate segmentation of bone is very important for developing an automated assisted-decision support system for Traumatic Pelvic Injury diagnosis and treatment.
Performance benchmarking of liver CT image segmentation and volume estimation
Medical Imaging 2008: PACS and Imaging Informatics, 2008
In recent years more and more computer aided diagnosis (CAD) systems are being used routinely in hospitals. Imagebased knowledge discovery plays important roles in many CAD applications, which have great potential to be integrated into the next-generation picture archiving and communication systems (PACS). Robust medical image segmentation tools are essentials for such discovery in many CAD applications. In this paper we present a platform with necessary tools for performance benchmarking for algorithms of liver segmentation and volume estimation used for liver transplantation planning. It includes an abdominal computer tomography (CT) image database (DB), annotation tools, a ground truth DB, and performance measure protocols. The proposed architecture is generic and can be used for other organs and imaging modalities. In the current study, approximately 70 sets of abdominal CT images with normal livers have been collected and a user-friendly annotation tool is developed to generate ground truth data for a variety of organs, including 2D contours of liver, two kidneys, spleen, aorta and spinal canal. Abdominal organ segmentation algorithms using 2D atlases and 3D probabilistic atlases can be evaluated on the platform. Preliminary benchmark results from the liver segmentation algorithms which make use of statistical knowledge extracted from the abdominal CT image DB are also reported. We target to increase the CT scans to about 300 sets in the near future and plan to make the DBs built available to medical imaging research community for performance benchmarking of liver segmentation algorithms.
Performance benchmarking of liver CT image segmentation and volume estimation
Proc. of SPIE Vol
In recent years more and more computer aided diagnosis (CAD) systems are being used routinely in hospitals. Imagebased knowledge discovery plays important roles in many CAD applications, which have great potential to be integrated into the next-generation picture archiving and communication systems (PACS). Robust medical image segmentation tools are essentials for such discovery in many CAD applications. In this paper we present a platform with necessary tools for performance benchmarking for algorithms of liver segmentation and volume estimation used for liver transplantation planning. It includes an abdominal computer tomography (CT) image database (DB), annotation tools, a ground truth DB, and performance measure protocols. The proposed architecture is generic and can be used for other organs and imaging modalities. In the current study, approximately 70 sets of abdominal CT images with normal livers have been collected and a user-friendly annotation tool is developed to generate ground truth data for a variety of organs, including 2D contours of liver, two kidneys, spleen, aorta and spinal canal. Abdominal organ segmentation algorithms using 2D atlases and 3D probabilistic atlases can be evaluated on the platform. Preliminary benchmark results from the liver segmentation algorithms which make use of statistical knowledge extracted from the abdominal CT image DB are also reported. We target to increase the CT scans to about 300 sets in the near future and plan to make the DBs built available to medical imaging research community for performance benchmarking of liver segmentation algorithms.
bioRxiv, 2021
Segmenting bone from background is required to quantify bone architecture in computed tomography (CT) image data. A deep learning approach using convolutional neural networks (CNN) is a promising alternative method for automatic segmentation. The study objectives were to evaluate the performance of CNNs in automatic segmentation of human vertebral body (micro-CT) and femoral neck (nano-CT) data and to investigate the performance of CNNs to segment data across scanners. Scans of human L1 vertebral bodies (microCT [North Star Imaging], n=28, 53μm3) and femoral necks (nano-CT [GE], n=28, 27μm3) were used for evaluation. Six slices were selected for each scan and then manually segmented to create ground truth masks (Dragonfly 4.0, ORS). Two-dimensional U-Net CNNs were trained in Dragonfly 4.0 with images of the [FN] femoral necks only, [VB] vertebral bodies only, and [F+V] combined CT data. Global (i.e., Otsu and Yen) and local (i.e., Otsu r = 100) thresholding methods were applied to e...
A 3D statistical shape model of the pelvic bone for segmentation
Medical Imaging 2004: Image Processing, 2004
Statistical models of shape are a promising approach for robust and automatic segmentation of medical image data. This work describes the construction of a statistical shape model of the pelvic bone. An interactive approach is proposed for solving the correspondence problem which is able to handle shapes of arbitrary topology, suitable for the genus 3 surface of the pelvic bone. Moreover it allows to specify corresponding anatomical features as boundary constraints to the matching process. The model's capability for segmentation was tested on a set of 23 CT data sets. Quantitative results will be presented, showing that the model is well suited for segmentation purposes.
Scientific Reports
Although CT radiomics has shown promising results in the evaluation of vertebral fractures, the need for manual segmentation of fractured vertebrae limited the routine clinical implementation of radiomics. Therefore, automated segmentation of fractured vertebrae is needed for successful clinical use of radiomics. In this study, we aimed to develop and validate an automated algorithm for segmentation of fractured vertebral bodies on CT, and to evaluate the applicability of the algorithm in a radiomics prediction model to differentiate benign and malignant fractures. A convolutional neural network was trained to perform automated segmentation of fractured vertebral bodies using 341 vertebrae with benign or malignant fractures from 158 patients, and was validated on independent test sets (internal test, 86 vertebrae [59 patients]; external test, 102 vertebrae [59 patients]). Then, a radiomics model predicting fracture malignancy on CT was constructed, and the prediction performance was...