A fully automatic computer aided diagnosis system for peripheral zone prostate cancer detection using multi-parametric magnetic resonance imaging. in Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society / Comput Med Imaging Graph. 2015 Dec;46 Pt 2:219-26. doi: 10.1016/j.compmedimag.2015.09.001. Epub 2015
2015
AOU San Luigi di Orbassano
Tipo pubblicazione
Research Support, Non-U.S. Gov't
Autori/Collaboratori (8)Vedi tutti...
Giannini V
Department of Radiology at Candiolo Cancer Institute-FPO, IRCCS, Strada Provinciale 142 km 3.95, 10060 Candiolo, Italy. Electronic address: valentina.giannini@ircc.it.
Mazzetti S
Department of Radiology at Candiolo Cancer Institute-FPO, IRCCS, Strada Provinciale 142 km 3.95, 10060 Candiolo, Italy.
Vignati A
Department of Radiology at Candiolo Cancer Institute-FPO, IRCCS, Strada Provinciale 142 km 3.95, 10060 Candiolo, Italy.
et alii...
Abstract
Multiparametric (mp)-Magnetic Resonance Imaging (MRI) is emerging as a powerful test to diagnose and stage prostate cancer (PCa). However, its interpretation is a time consuming and complex feat requiring dedicated radiologists. Computer-aided diagnosis (CAD) tools could allow better integration of data deriving from the different MRI sequences in order to obtain accurate, reproducible, non-operator dependent information useful to identify and stage PCa. In this paper, we present a fully automatic CAD system conceived as a 2-stage process. First, a malignancy probability map for all voxels within the prostate is created. Then, a candidate segmentation step is performed to highlight suspected areas, thus evaluating both the sensitivity and the number of false positive (FP) regions detected by the system. Training and testing of the CAD scheme is performed using whole-mount histological sections as the reference standard. On a cohort of 56 patients (i.e. 65 lesions) the area under the ROC curve obtained during the voxel-wise step was 0.91, while, in the second step, a per-patient sensitivity of 97% was reached, with a median number of FP equal to 3 in the whole prostate. The system here proposed could be potentially used as first or second reader to manage patients suspected to have PCa, thus reducing both the radiologist's reporting time and the inter-reader variability. As an innovative setup, it could also be used to help the radiologist in setting the MRI-guided biopsy target.
Accesso banca dati bibliografica
Accedi alla scheda bibliografica del documento in PUBMED
PMID : 26391055
DOI : 10.1016/j.compmedimag.2015.09.001
Keywords
SVM classifier; Prostate cancer; Multiparametric MRI; Image analysis; Computer aided detection; Sensitivity and Specificity; Reproducibility of Results; Prostatic Neoplasms/pathology; Prostate/pathology; Pattern Recognition, Automated/methods; Multimodal Imaging/methods; Male; Magnetic Resonance Imaging/methods; Imaging, Three-Dimensional; Image Interpretation, Computer-Assisted/methods; Image Enhancement/methods; Humans; Algorithms;