Comparing radiomic classifiers and classifier ensembles for detection of peripheral zone prostate tumors on T2-weighted MRI: a multi-site study.
Satish E ViswanathPrathyush V ChirraMichael C YimNeil M RofskyAndrei S PuryskoMark A RosenB Nicolas BlochAnant MadabhushiPublished in: BMC medical imaging (2019)
Our results therefore suggest that simpler classifiers (such as QDA and its ensemble variants) may be more robust, accurate, and efficient for prostate cancer CAD problems, especially in the context of multi-site validation.