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 ...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.展开更多
文摘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.
