Investigation of MRI Prostate Localization using Different MRI Modality Scans
Authors:
- 22 April 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
According to the data of World Cancer Research Fund International prostate cancer is the second most common after lung cancer and the fifth most common cause of cancer death amongst men. Prostate cancer is also the fourth most frequent tumor between both genders worldwide. Biopsy is the only way to detect prostate cancer so far. Statistics show that it is able to detect only 70-80% of clinically significant cancer cases. Multi parametric magnetic resonance imaging technique comes to play to help in determining the location to perform biopsy on. The first step to automating the detection of the location is applying prostate segmentation on magnetic resonance images. The fact that there is lack of standardization of signal intensity to acquire those images burdens the problem of automated prostate segmentation. Authors review the results of Prostate MR Image Segmentation (PROMISE12) challenge, designed to evaluate and compare different prostate segmentation algorithms, and provide insights on automated prostate segmentation by applying best open source algorithm under different circumstances. Authors applied selected algorithm on two different datasets and showed how segmentation results can be improved by applying even the most primitive image stretching techniques. Authors also showed that algorithm is promising in segmenting unseen dataset.Keywords
This publication has 8 references indexed in Scilit:
- Evaluating the Role of mpMRI in Prostate Cancer Assessment.Expert Review of Medical Devices, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challengeMedical Image Analysis, 2014
- A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography imagesComputer Methods and Programs in Biomedicine, 2012
- Patient Specific Prostate Segmentation in 3-D Magnetic Resonance ImagesIEEE Transactions on Medical Imaging, 2012
- Comparison and Evaluation of Methods for Liver Segmentation From CT DatasetsIEEE Transactions on Medical Imaging, 2009
- Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual informationMedical Physics, 2008
- The Predictive Sample Reuse Method with ApplicationsJournal of the American Statistical Association, 1975