TY - JOUR
T1 - Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet
AU - Cao, Ruiming
AU - Mohammadian Bajgiran, Amirhossein
AU - Afshari Mirak, Sohrab
AU - Shakeri, Sepideh
AU - Zhong, Xinran
AU - Enzmann, Dieter
AU - Raman, Steven
AU - Sung, Kyunghyun
N1 - Funding Information:
This work was supported by the Integrated Diagnostics Program, Department of Radiological Sciences and Pathology, David Geffen School of Medicine, UCLA.
Funding Information:
Manuscript received January 18, 2019; revised February 15, 2019; accepted February 19, 2019. Date of publication February 27, 2019; date of current version October 25, 2019. This work was supported by the Integrated Diagnostics Program, Department of Radiological Sciences and Pathology, David Geffen School of Medicine, UCLA. (Corresponding author: Ruiming Cao.) R. Cao is with the Department of Radiology, University of California at Los Angeles, Los Angeles, CA 90095 USA, and also with the Department of Computer Science, University of California at Los Angeles, Los Angeles, CA 90095 USA (e-mail: ruimingc@ucla.edu).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Multi-parametric MRI (mp-MRI) is considered the best non-invasive imaging modality for diagnosing prostate cancer (PCa). However, mp-MRI for PCa diagnosis is currently limited by the qualitative or semi-quantitative interpretation criteria, leading to inter-reader variability and a suboptimal ability to assess lesion aggressiveness. Convolutional neural networks (CNNs) are a powerful method to automatically learn the discriminative features for various tasks, including cancer detection. We propose a novel multi-class CNN, FocalNet, to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS). FocalNet characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI. We collected a prostate mp-MRI dataset from 417 patients who underwent 3T mp-MRI exams prior to robotic-assisted laparoscopic prostatectomy. FocalNet was trained and evaluated in this large study cohort with fivefold cross validation. In the free-response receiver operating characteristics (FROC) analysis for lesion detection, FocalNet achieved 89.7% and 87.9% sensitivity for index lesions and clinically significant lesions at one false positive per patient, respectively. For the GS classification, evaluated by the receiver operating characteristics (ROC) analysis, FocalNet received the area under the curve of 0.81 and 0.79 for the classifications of clinically significant PCa (GS ≥ 3 + 4) and PCa with GS ≥ 4 + 3, respectively. With the comparison to the prospective performance of radiologists using the current diagnostic guideline, FocalNet demonstrated comparable detection sensitivity for index lesions and clinically significant lesions, only 3.4% and 1.5% lower than highly experienced radiologists without statistical significance.
AB - Multi-parametric MRI (mp-MRI) is considered the best non-invasive imaging modality for diagnosing prostate cancer (PCa). However, mp-MRI for PCa diagnosis is currently limited by the qualitative or semi-quantitative interpretation criteria, leading to inter-reader variability and a suboptimal ability to assess lesion aggressiveness. Convolutional neural networks (CNNs) are a powerful method to automatically learn the discriminative features for various tasks, including cancer detection. We propose a novel multi-class CNN, FocalNet, to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS). FocalNet characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI. We collected a prostate mp-MRI dataset from 417 patients who underwent 3T mp-MRI exams prior to robotic-assisted laparoscopic prostatectomy. FocalNet was trained and evaluated in this large study cohort with fivefold cross validation. In the free-response receiver operating characteristics (FROC) analysis for lesion detection, FocalNet achieved 89.7% and 87.9% sensitivity for index lesions and clinically significant lesions at one false positive per patient, respectively. For the GS classification, evaluated by the receiver operating characteristics (ROC) analysis, FocalNet received the area under the curve of 0.81 and 0.79 for the classifications of clinically significant PCa (GS ≥ 3 + 4) and PCa with GS ≥ 4 + 3, respectively. With the comparison to the prospective performance of radiologists using the current diagnostic guideline, FocalNet demonstrated comparable detection sensitivity for index lesions and clinically significant lesions, only 3.4% and 1.5% lower than highly experienced radiologists without statistical significance.
KW - Prostate cancer
KW - computer-aided detection and diagnosis
KW - convolutional neural network
KW - magnetic resonance imaging
UR - http://www.scopus.com/inward/record.url?scp=85072620682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072620682&partnerID=8YFLogxK
U2 - 10.1109/TMI.2019.2901928
DO - 10.1109/TMI.2019.2901928
M3 - Article
C2 - 30835218
AN - SCOPUS:85072620682
SN - 0278-0062
VL - 38
SP - 2496
EP - 2506
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 11
M1 - 8653866
ER -