Autonomous Detection and Classification of PI-RADS Lesions in an MRI Screening Population Incorporating Multicenter-Labeled Deep Learning and Biparametric Imaging: Proof of Concept.
- Winkel DJ Department of Radiology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- Wetterauer C Department of Urology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- Matthias MO Department of Urology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- Lou B Siemens Healthineers, Medical Imaging Technologies Princeton, Princeton, NJ 08540, USA.
- Shi B Siemens Healthineers, Medical Imaging Technologies Princeton, Princeton, NJ 08540, USA.
- Kamen A Siemens Healthineers, Medical Imaging Technologies Princeton, Princeton, NJ 08540, USA.
- Comaniciu D Siemens Healthineers, Medical Imaging Technologies Princeton, Princeton, NJ 08540, USA.
- Seifert HH Department of Urology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- Rentsch CA Department of Urology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- Boll DT Department of Radiology, University Hospital of Basel, 4051 Basel, Basel-Stadt, Switzerland.
- 2020-11-18
Published in:
- Diagnostics (Basel, Switzerland). - 2020
English
BACKGROUND
Opportunistic prostate cancer (PCa) screening is a controversial topic. Magnetic resonance imaging (MRI) has proven to detect prostate cancer with a high sensitivity and specificity, leading to the idea to perform an image-guided prostate cancer (PCa) screening; Methods: We evaluated a prospectively enrolled cohort of 49 healthy men participating in a dedicated image-guided PCa screening trial employing a biparametric MRI (bpMRI) protocol consisting of T2-weighted (T2w) and diffusion weighted imaging (DWI) sequences. Datasets were analyzed both by human readers and by a fully automated artificial intelligence (AI) software using deep learning (DL). Agreement between the algorithm and the reports-serving as the ground truth-was compared on a per-case and per-lesion level using metrics of diagnostic accuracy and k statistics; Results: The DL method yielded an 87% sensitivity (33/38) and 50% specificity (5/10) with a k of 0.42. 12/28 (43%) Prostate Imaging Reporting and Data System (PI-RADS) 3, 16/22 (73%) PI-RADS 4, and 5/5 (100%) PI-RADS 5 lesions were detected compared to the ground truth. Targeted biopsy revealed PCa in six participants, all correctly diagnosed by both the human readers and AI.
CONCLUSIONS
The results of our study show that in our AI-assisted, image-guided prostate cancer screening the software solution was able to identify highly suspicious lesions and has the potential to effectively guide the targeted-biopsy workflow.
Opportunistic prostate cancer (PCa) screening is a controversial topic. Magnetic resonance imaging (MRI) has proven to detect prostate cancer with a high sensitivity and specificity, leading to the idea to perform an image-guided prostate cancer (PCa) screening; Methods: We evaluated a prospectively enrolled cohort of 49 healthy men participating in a dedicated image-guided PCa screening trial employing a biparametric MRI (bpMRI) protocol consisting of T2-weighted (T2w) and diffusion weighted imaging (DWI) sequences. Datasets were analyzed both by human readers and by a fully automated artificial intelligence (AI) software using deep learning (DL). Agreement between the algorithm and the reports-serving as the ground truth-was compared on a per-case and per-lesion level using metrics of diagnostic accuracy and k statistics; Results: The DL method yielded an 87% sensitivity (33/38) and 50% specificity (5/10) with a k of 0.42. 12/28 (43%) Prostate Imaging Reporting and Data System (PI-RADS) 3, 16/22 (73%) PI-RADS 4, and 5/5 (100%) PI-RADS 5 lesions were detected compared to the ground truth. Targeted biopsy revealed PCa in six participants, all correctly diagnosed by both the human readers and AI.
CONCLUSIONS
The results of our study show that in our AI-assisted, image-guided prostate cancer screening the software solution was able to identify highly suspicious lesions and has the potential to effectively guide the targeted-biopsy workflow.
- Language
-
- English
- Open access status
- gold
- Identifiers
-
- DOI 10.3390/diagnostics10110951
- PMID 33202680
- Persistent URL
- https://folia.unifr.ch/global/documents/250804
Statistics
Document views: 26
File downloads:
- Full-text: 0