Calibrating level set approach by granular computing in computed tomography abdominal organs segmentation

Automatic multi-organ segmentation from abdominal CT volumes with LLE-based graph partitioning and 3D Chan-Vese model

This paper presents a fully automatic method for multi-organ segmentation from 3D abdominal CT volumes. Firstly, spines and ribs are removed by exponential transformation and binarization to reduce the disturbance to subsequent segmentation. Then, a Local Linear Embedding (LLE)-based graph partitioning approach is employed to perform initial segmentation for liver, spleen, and bilateral kidneys simultaneously, and a novel segmentation refinement scheme is applied composed of hybrid intensity model, 3D Chan-Vese model, and histogram equalization-based organ separation algorithm. Finally, a pseudo-3D bottleneck detection algorithm is introduced for boundary correction. The proposed method does not require heavy training or registration process and is capable of dealing with shape and location variations as well as the weak boundaries of target organs. Experiments on XHCSU20 database show the proposed method is competitive with state-of-the-art methods with Dice similarity coefficients of 95.9%, 95.1%, 94.7%, and 94.5%, Jaccard indices of 92.2%, 90.8%, 90.0%, and 89.5%, and average symmetric surface distances of 1.1 mm, 1.0 mm, 0.9 mm and 1.1 mm, for liver, spleen, left and right kidneys, respectively, and the average running time is around 6 min for a CT volume. The accuracy, precision, recall, and specificity also maintain high values for each of the four organs. Moreover, experiments on SLIVER07 dataset prove its high efficiency and accuracy on liver-only segmentation.

Liver Tumor Segmentation in CT Scans Using Modified SegNet

The main cause of death related to cancer worldwide is from hepatic cancer. Detection of hepatic cancer early using computed tomography (CT) could prevent millions of patients' death every year. However, reading hundreds or even tens of those CT scans is an enormous burden for radiologists. Therefore, there is an immediate need is to read, detect, and evaluate CT scans automatically, quickly, and accurately. However, liver segmentation and extraction from the CT scans is a bottleneck for any system, and is still a challenging problem. In this work, a deep learning-based technique that was proposed for semantic pixel-wise classification of road scenes is adopted and modified to fit liver CT segmentation and classification. The architecture of the deep convolutional encoder-decoder is named SegNet, and consists of a hierarchical correspondence of encode-decoder layers. The proposed architecture was tested on a standard dataset for liver CT scans and achieved tumor accuracy of up to 99.9% in the training phase.

3D Segmentation Algorithms for Computerized Tomographic Imaging: a Systematic Literature Review

This paper presents a systematic literature review concerning 3D segmentation algorithms for computerized tomographic imaging. This analysis covers articles published in the range 2006-March 2018 found in four scientific databases (Science Direct, IEEEXplore, ACM, and PubMed), using the methodology for systematic review proposed by Kitchenham. We present the analyzed segmentation methods categorized according to its application, algorithmic strategy, validation, and use of prior knowledge, as well as its general conceptual description. Additionally, we present a general overview, discussions, and further prospects for the 3D segmentation methods applied for tomographic images.