Accurate Segmentation of CT Male Pelvic Organs via Regression-Based Deformable Models and Multi-Task Random Forests

IEEE Transactions on Medical Imaging
Yaozong GaoDinggang Shen

Abstract

Segmenting male pelvic organs from CT images is a prerequisite for prostate cancer radiotherapy. The efficacy of radiation treatment highly depends on segmentation accuracy. However, accurate segmentation of male pelvic organs is challenging due to low tissue contrast of CT images, as well as large variations of shape and appearance of the pelvic organs. Among existing segmentation methods, deformable models are the most popular, as shape prior can be easily incorporated to regularize the segmentation. Nonetheless, the sensitivity to initialization often limits their performance, especially for segmenting organs with large shape variations. In this paper, we propose a novel approach to guide deformable models, thus making them robust against arbitrary initializations. Specifically, we learn a displacement regressor, which predicts 3D displacement from any image voxel to the target organ boundary based on the local patch appearance. This regressor provides a non-local external force for each vertex of deformable model, thus overcoming the initialization problem suffered by the traditional deformable models. To learn a reliable displacement regressor, two strategies are particularly proposed. 1) A multi-task random forest is prop...Continue Reading

References

May 15, 2018·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society· Zhensong Wang Dinggang Shen
Jul 6, 2017·IEEE Transactions on Medical Imaging·Marie BiethBjoern Menze
Nov 23, 2018·Physics in Medicine and Biology·Meghan W MacomberMatthew J Nyflot
Dec 14, 2018·Physics in Medicine and Biology·Anjali BalagopalSteve Jiang
Nov 26, 2020·Journal of Applied Clinical Medical Physics·Marta CasatiStefania Pallotta

Citations

May 26, 2001·Clinical Oncology : a Journal of the Royal College of Radiologists·A G Macdonald, J D Bissett
Apr 6, 2004·Medical Image Analysis·Dinggang ShenChristos Davatzikos
Mar 10, 2005·IEEE Transactions on Medical Imaging·Daniel FreedmanGeorge T Y Chen
Dec 8, 2005·Physics in Medicine and Biology·Mark FoskeySarang Joshi
Mar 10, 2006·IEEE Transactions on Medical Imaging·Yiqiang Zhan, Dinggang Shen
Aug 8, 2007·IEEE Transactions on Medical Imaging·Yiqiang ZhanChristos Davatzikos
Apr 2, 2009·IEEE Transactions on Medical Imaging·Jiamin Liu, Jayaram K Udupa
Jul 17, 2010·Medical Image Analysis·Siqi ChenRichard J Radke
Aug 21, 2010·IEEE Transactions on Pattern Analysis and Machine Intelligence·Zhuowen Tu, Xiang Bai
Oct 4, 2011·Medical Image Analysis·Shaoting ZhangXiang Sean Zhou
Feb 22, 2012·Physics in Medicine and Biology·Wei LiDinggang Shen
Sep 11, 2012·Medical Image Analysis·Shaoting ZhangDimitris N Metaxas
Dec 4, 2012·IEEE Transactions on Medical Imaging·Shu LiaoDinggang Shen
Aug 5, 2015·IEEE Transactions on Medical Imaging·Tri HuynhAlzheimer's Disease Neuroimaging Initiative
Nov 19, 2015·Physics in Medicine and Biology·Yaozong Gao, Dinggang Shen

Related Concepts

Prostatic Neoplasms
Biologic Segmentation
Classification
Three-dimensional
X-Ray Computed Tomography
Image Interpretation, Computer-Assisted
Prostate Carcinoma
Organ
Neural Network Simulation
Prostate

Trending Feeds

COVID-19

Coronaviruses encompass a large family of viruses that cause the common cold as well as more serious diseases, such as the ongoing outbreak of coronavirus disease 2019 (COVID-19; formally known as 2019-nCoV). Coronaviruses can spread from animals to humans; symptoms include fever, cough, shortness of breath, and breathing difficulties; in more severe cases, infection can lead to death. This feed covers recent research on COVID-19.

Sexual Dimorphism in Neurodegeneration

There exist sex differences in neurodevelopmental and neurodegenerative disorders. For instance, multiple sclerosis is more common in women, whereas Parkinson’s disease is more common in men. Here is the latest research on sexual dimorphism in neurodegeneration

HLA Genetic Variation

HLA genetic variation has been found to confer risk for a wide variety of diseases. Identifying these associations and understanding their molecular mechanisms is ongoing and holds promise for the development of therapeutics. Find the latest research on HLA genetic variation here.

Super-resolution Microscopy

Super-resolution microscopy is the term commonly given to fluorescence microscopy techniques with resolutions that are not limited by the diffraction of light. Here are the latest discoveries pertaining to super-resolution microscopy.

Genetic Screens in iPSC-derived Brain Cells

Genetic screening is a critical tool that can be employed to define and understand gene function and interaction. This feed focuses on genetic screens conducted using induced pluripotent stem cell (iPSC)-derived brain cells.

Brain Lower Grade Glioma

Low grade gliomas in the brain form from oligodendrocytes and astrocytes and are the slowest-growing glioma in adults. Discover the latest research on these brain tumors here.

CD4/CD8 Signaling

Cluster of differentiation 4 and 8 (CD8 and CD8) are glycoproteins founds on the surface of immune cells. Here is the latest research on their role in cell signaling pathways.

Alignment-free Sequence Analysis Tools

Alignment-free sequence analyses have been applied to problems ranging from whole-genome phylogeny to the classification of protein families, identification of horizontally transferred genes, and detection of recombined sequences. Here is the latest research.

Chronic Fatigue Syndrome

Chronic fatigue syndrome is a disease characterized by unexplained disabling fatigue; the pathology of which is incompletely understood. Discover the latest research on chronic fatigue syndrome here.

Related Papers

IEEE Transactions on Medical Imaging
Tri HuynhAlzheimer's Disease Neuroimaging Initiative
Medical Image Computing and Computer-assisted Intervention : MICCAI
Yaozong GaoDinggang Shen
Medical Image Computing and Computer-assisted Intervention : MICCAI
Wei LiDinggang Shen
© 2020 Meta ULC. All rights reserved