MRI‐based prostate cancer detection with high‐level representation and hierarchical classification

• Published in: Medical physics (Lancaster) Vol. 44; no. 3; pp. 1028 - 1039
• Main Authors: Zhu, Yulian, Wang, Li, Liu, Mingxia, Qian, Chunjun, Yousuf, Ambereen, Oto, Aytekin, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: United States 01.03.2017
• Subjects: Datasets as Topic; deep learning; hierarchical classification; Humans; Image Interpretation, Computer-Assisted - methods; magnetic resonance imaging (MRI); Magnetic Resonance Imaging - methods; Male; Neural Networks (Computer); Prostate - diagnostic imaging; prostate cancer detection; Prostatic Neoplasms - diagnostic imaging; random forest; Sensitivity and Specificity; magnetic resonance imaging (MRI); deep learning; random forest; prostate cancer detection; hierarchical classification
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1002/mp.12116

Purpose Extracting the high‐level feature representation by using deep neural networks for detection of prostate cancer, and then based on high‐level feature representation constructing hierarchical classification to refine the detection results. Methods High‐level feature representation is first learned by a deep learning network, where multiparametric MR images are used as the input data. Then, based on the learned high‐level features, a hierarchical classification method is developed, where multiple random forest classifiers are iteratively constructed to refine the detection results of prostate cancer. Results The experiments were carried on 21 real patient subjects, and the proposed method achieves an averaged section‐based evaluation (SBE) of 89.90%, an averaged sensitivity of 91.51%, and an averaged specificity of 88.47%. Conclusions The high‐level features learned from our proposed method can achieve better performance than the conventional handcrafted features (e.g., LBP and Haar‐like features) in detecting prostate cancer regions, also the context features obtained from the proposed hierarchical classification approach are effective in refining cancer detection result.