Sherif Mehralivand1, Dong Yang2, Stephanie A Harmon1, Daguang Xu2, Ziyue Xu2, Holger Roth2, Samira Masoudi1, Thomas H Sanford3, Deepak Kesani1, Nathan S Lay1, Maria J Merino4, Bradford J Wood5, Peter A Pinto6, Peter L Choyke1, Baris Turkbey7. 1. Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, 10 Center Dr., MSC 1182, Building 10, Room B3B85, Bethesda, Maryland. 2. NVIDIA Corporation, Santa Clara, California. 3. Department of Urology, SUNY Upstate Medical University, Syracuse, New Yor. 4. Laboratory of Pathology, National Cancer Institute, National Institutes of Health, Bethesda, Maryland. 5. Center for Interventional Oncology, National Cancer Institute, National Institutes of Health, Bethesda, Maryland; Department of Radiology, Clinical Center, National Institutes of Health, Bethesda, Maryland. 6. Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland. 7. Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, 10 Center Dr., MSC 1182, Building 10, Room B3B85, Bethesda, Maryland. Electronic address: turkbeyi@mail.nih.gov.
Abstract
RATIONALE AND OBJECTIVES: Prostate MRI improves detection of clinically significant prostate cancer; however, its diagnostic performance has wide variation. Artificial intelligence (AI) has the potential to assist radiologists in the detection and classification of prostatic lesions. Herein, we aimed to develop and test a cascaded deep learning detection and classification system trained on biparametric prostate MRI using PI-RADS for assisting radiologists during prostate MRI read out. MATERIALS AND METHODS: T2-weighted, diffusion-weighted (ADC maps, high b value DWI) MRI scans obtained at 3 Tesla from two institutions (n = 1043 in-house and n = 347 Prostate-X, respectively) acquired between 2015 to 2019 were used for model training, validation, testing. All scans were retrospectively reevaluated by one radiologist. Suspicious lesions were contoured and assigned a PI-RADS category. A 3D U-Net-based deep neural network was used to train an algorithm for automated detection and segmentation of prostate MRI lesions. Two 3D residual neural network were used for a 4-class classification task to predict PI-RADS categories 2 to 5 and BPH. Training and validation used 89% (n = 1290 scans) of the data using 5 fold cross-validation, the remaining 11% (n = 150 scans) were used for independent testing. Algorithm performance at lesion level was assessed using sensitivities, positive predictive values (PPV), false discovery rates (FDR), classification accuracy, Dice similarity coefficient (DSC). Additional analysis was conducted to compare AI algorithm's lesion detection performance with targeted biopsy results. RESULTS: Median age was 66 years (IQR = 60-71), PSA 6.7 ng/ml (IQR = 4.7-9.9) from in-house cohort. In the independent test set, algorithm correctly detected 111 of 198 lesions leading to 56.1% (49.3%-62.6%) sensitivity. PPV was 62.7% (95% CI 54.7%-70.7%) with FDR of 37.3% (95% CI 29.3%-45.3%). Of 79 true positive lesions, 82.3% were tumor positive at targeted biopsy, whereas of 57 false negative lesions, 50.9% were benign at targeted biopsy. Median DSC for lesion segmentation was 0.359. Overall PI-RADS classification accuracy was 30.8% (95% CI 24.6%-37.8%). CONCLUSION: Our cascaded U-Net, residual network architecture can detect, classify cancer suspicious lesions at prostate MRI with good detection, reasonable classification performance metrics. Published by Elsevier Inc.
RATIONALE AND OBJECTIVES: Prostate MRI improves detection of clinically significant prostate cancer; however, its diagnostic performance has wide variation. Artificial intelligence (AI) has the potential to assist radiologists in the detection and classification of prostatic lesions. Herein, we aimed to develop and test a cascaded deep learning detection and classification system trained on biparametric prostate MRI using PI-RADS for assisting radiologists during prostate MRI read out. MATERIALS AND METHODS: T2-weighted, diffusion-weighted (ADC maps, high b value DWI) MRI scans obtained at 3 Tesla from two institutions (n = 1043 in-house and n = 347 Prostate-X, respectively) acquired between 2015 to 2019 were used for model training, validation, testing. All scans were retrospectively reevaluated by one radiologist. Suspicious lesions were contoured and assigned a PI-RADS category. A 3D U-Net-based deep neural network was used to train an algorithm for automated detection and segmentation of prostate MRI lesions. Two 3D residual neural network were used for a 4-class classification task to predict PI-RADS categories 2 to 5 and BPH. Training and validation used 89% (n = 1290 scans) of the data using 5 fold cross-validation, the remaining 11% (n = 150 scans) were used for independent testing. Algorithm performance at lesion level was assessed using sensitivities, positive predictive values (PPV), false discovery rates (FDR), classification accuracy, Dice similarity coefficient (DSC). Additional analysis was conducted to compare AI algorithm's lesion detection performance with targeted biopsy results. RESULTS: Median age was 66 years (IQR = 60-71), PSA 6.7 ng/ml (IQR = 4.7-9.9) from in-house cohort. In the independent test set, algorithm correctly detected 111 of 198 lesions leading to 56.1% (49.3%-62.6%) sensitivity. PPV was 62.7% (95% CI 54.7%-70.7%) with FDR of 37.3% (95% CI 29.3%-45.3%). Of 79 true positive lesions, 82.3% were tumor positive at targeted biopsy, whereas of 57 false negative lesions, 50.9% were benign at targeted biopsy. Median DSC for lesion segmentation was 0.359. Overall PI-RADS classification accuracy was 30.8% (95% CI 24.6%-37.8%). CONCLUSION: Our cascaded U-Net, residual network architecture can detect, classify cancer suspicious lesions at prostate MRI with good detection, reasonable classification performance metrics. Published by Elsevier Inc.
Entities:
Keywords:
Prostate cancer; artificial intelligence; biparametric; detection; magnetic resonance imaging
Authors: Hiroaki Takahashi; Kotaro Yoshida; Akira Kawashima; Nam Ju Lee; Adam T Froemming; Daniel A Adamo; Ashish Khandelwal; Candice W Bolan; Matthew T Heller; Robert P Hartman; Bohyun Kim; Kenneth A Philbrick; Rickey E Carter; Lance A Mynderse; Mitchell R Humphreys; Jason C Cai; Naoki Takahashi Journal: PLoS One Date: 2022-05-23 Impact factor: 3.752
Authors: Fabrizio Urraro; Valerio Nardone; Alfonso Reginelli; Carlo Varelli; Antonio Angrisani; Vittorio Patanè; Luca D'Ambrosio; Pietro Roccatagliata; Gaetano Maria Russo; Luigi Gallo; Marco De Chiara; Lucia Altucci; Salvatore Cappabianca Journal: Front Oncol Date: 2021-12-21 Impact factor: 6.244