Prostate cancer: Computer-aided diagnosis on multiparametric MRI

Laura Marin, Daniel Racoceanu, Raphaele Renard Penna, Malek Ezziane

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations


Prostate cancer (PCa) is one of the most common cancers in men, being also the second most deadly cancer after lung cancer. There is increasing interest in active surveillance and minimally invasive focal therapies in PCa to avoid morbidities associated with whole gland therapy. Tumor volume represents an essential prognostic factor of PCa and the definition of index lesion volume is critical for appropriate decision making, especially for image guide focal treatment or in case of active surveillance. Multi-parametric Magnetic Resonance Imaging (mp-MRI) is the modality of choice for the detection and the localization of PCa foci. However, little has been published on mp-MRI accuracy in determining PCa volume, especially at 3T. There is insufficient evidence and no consensus to determine which of the methods for measuring volume is optimal. The objective of this study concerns the elaboration of an algorithm for automatic interpretation of mp-MRI. We determine the accuracy of the proposed method by comparing the prostate tumor volume issued from the automated volumetric mp-MRI measurements of the tumoral region, with manual and semi-automated volumetric measurements done by and respectively with radiologists. Information issued from whole mount histopathology is used to validate the whole approach.

Original languageEnglish
Title of host publication13th International Conference on Medical Information Processing and Analysis
EditorsNatasha Lepore, Jorge Brieva, Juan David Garcia, Eduardo Romero
ISBN (Electronic)9781510616332
StatePublished - 2017
Event13th International Conference on Medical Information Processing and Analysis, SIPAIM 2017 - San Andres Island, Colombia
Duration: 5 Oct 20177 Oct 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


Conference13th International Conference on Medical Information Processing and Analysis, SIPAIM 2017
CitySan Andres Island


Dive into the research topics of 'Prostate cancer: Computer-aided diagnosis on multiparametric MRI'. Together they form a unique fingerprint.

Cite this