Computer‐aided diagnosis: detection and localization of prostate cancer within the peripheral zone

Abstract

We propose a methodology for prostate cancer detection and localization within the peripheral zone based on combining multiple segmentation techniques. We extract four image features using Gaussian and median filters. Subsequently, we use each image feature separately to generate binary segmentations. Finally, we take the intersection of all four binary segmentations, incorporating a model of the peripheral zone, and perform erosion to remove small false-positive regions. The initial evaluation of this method is based on 275 MRI images from 37 patients, and 86% of the slices were classified correctly with 87% and 86% sensitivity and specificity achieved, respectively. This paper makes two contributions: firstly, a novel computer-aided diagnosis approach, which is based on combining multiple segmentation techniques using only a small number of simple image features, and secondly, the development of the proposed method and its application in prostate cancer detection and localization using a single MRI modality with the results comparable with the state-of-the-art multimodality and advanced computer vision methods in the literature. Copyright © 2015 John Wiley & Sons, Ltd.

Computer-aided detection of prostate cancer in T2-weighted MRI within the peripheral zone

“…Since segmenting the PZ manually is time consuming, we employed the 2D model developed by Rampun et al [18], which uses a quadratic equation based on the central coordinates of the prostate gland, the left-most and rightmost coordinates of the prostate gland boundary. This allows us to model a priori general knowledge of radiologists which is similar to the methods of Makni et al [19] and Liu et al [20].…”

“…This allows us to model a priori general knowledge of radiologists which is similar to the methods of Makni et al [19] and Liu et al [20]. Figure 2 shows example MRI images with the ground truth location of the prostate gland, central/transitional zone (CZ) and tumor (T) represented in red, yellow and green respectively, while the magenta line is the estimated boundary of the PZ based on the method given in [18]. Our study is only within the segmented PZ which is under the magenta line in Figure 2.…”

Computer aided diagnosis of prostate cancer: A texton based approach

“…We employed the 2D model developed by Rampun et al 26 to estimate the area of the PZ. The method uses a quadratic equation based on the central coordinates of the prostate gland, the left-most and right-most coordinates of the prostate gland boundary (each prostate boundary was provided by a radiologist).…”

Confidence Analysis for Breast Mass Image Classification

“…CAD systems have been shown to have great potential in providing support to doctors such as performing routine work, quantifying tissue changes that correspond with tumour grade in an accurate and reproducible manner and extracting biomarkers which are otherwise difficult for human doctors [1,2,3,4,5,6,7]. This will ultimately benefit patients and health systems.…”