TITLE:
A diffusion-weighted imaging based diagnostic system for early detection of prostate cancer
AUTHORS:
Ahmad Firjani, Ahmed Elnakib, Fahmi Khalifa, Georgy Gimel’farb, Mohamed Abou El-Ghar, Adel Elmaghraby, Ayman El-Baz
KEYWORDS:
Prostate Cancer; 3D Markov-Gibbs Random Field; Nonrigid Registration; Diffusion-Weighted Imaging
JOURNAL NAME:
Journal of Biomedical Science and Engineering,
Vol.6 No.3A,
March
29,
2013
ABSTRACT: A new framework for early diagnosis of prostate
cancer using Diffusion-Weighted Imaging (DWI) is proposed. The proposed
diagnostic approach consists of the following four steps to detect locations
that are suspicious for prostate cancer: 1) In the first step, we isolate the
prostate from the surrounding anatomical structures based on a Maximum A
Posteriori (MAP) estimate of a new log-likelihood function that accounts for
the shape priori, the spatial interaction, and the current appearance of
prostate tissues and its background (surrounding anatomical structures); 2) In
order to take into account any local deformation between the segmented
prostates at different b-values that could occur during the scanning process
due to local motion, a non-rigid registration algorithm is employed; 3) A
KNN-based classifier is used to classify the prostate into benign or
malignant based on three appearance features extracted from registered images;
and 4) The tumor boundaries are determined using a level set deformable model
controlled by the diffusion information and the spatial interactions between
the prostate voxels. Preliminary experiments on 28 patients (17 malignant and
11 benign) resulted in 100% correct classification, showing that the proposed
method is a promising supplement to current technologies (biopsy-based
diagnostic systems) for the early diagnosis of prostate cancer.