1
|
Magoulianitis V, Yang J, Yang Y, Xue J, Kaneko M, Cacciamani G, Abreu A, Duddalwar V, Kuo CCJ, Gill IS, Nikias C. PCa-RadHop: A transparent and lightweight feed-forward method for clinically significant prostate cancer segmentation. Comput Med Imaging Graph 2024; 116:102408. [PMID: 38908295 DOI: 10.1016/j.compmedimag.2024.102408] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Revised: 05/30/2024] [Accepted: 05/31/2024] [Indexed: 06/24/2024]
Abstract
Prostate Cancer is one of the most frequently occurring cancers in men, with a low survival rate if not early diagnosed. PI-RADS reading has a high false positive rate, thus increasing the diagnostic incurred costs and patient discomfort. Deep learning (DL) models achieve a high segmentation performance, although require a large model size and complexity. Also, DL models lack of feature interpretability and are perceived as "black-boxes" in the medical field. PCa-RadHop pipeline is proposed in this work, aiming to provide a more transparent feature extraction process using a linear model. It adopts the recently introduced Green Learning (GL) paradigm, which offers a small model size and low complexity. PCa-RadHop consists of two stages: Stage-1 extracts data-driven radiomics features from the bi-parametric Magnetic Resonance Imaging (bp-MRI) input and predicts an initial heatmap. To reduce the false positive rate, a subsequent stage-2 is introduced to refine the predictions by including more contextual information and radiomics features from each already detected Region of Interest (ROI). Experiments on the largest publicly available dataset, PI-CAI, show a competitive performance standing of the proposed method among other deep DL models, achieving an area under the curve (AUC) of 0.807 among a cohort of 1,000 patients. Moreover, PCa-RadHop maintains orders of magnitude smaller model size and complexity.
Collapse
Affiliation(s)
- Vasileios Magoulianitis
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA.
| | - Jiaxin Yang
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| | - Yijing Yang
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| | - Jintang Xue
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| | - Masatomo Kaneko
- Department of Urology, Keck School of Medicine, University of Southern California (USC), 1975 Zonal Ave., Los Angeles, 90033, CA, USA
| | - Giovanni Cacciamani
- Department of Urology, Keck School of Medicine, University of Southern California (USC), 1975 Zonal Ave., Los Angeles, 90033, CA, USA
| | - Andre Abreu
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| | - Vinay Duddalwar
- Department of Urology, Keck School of Medicine, University of Southern California (USC), 1975 Zonal Ave., Los Angeles, 90033, CA, USA; Department of Radiology, Keck School of Medicine, University of Southern California (USC), 1975 Zonal Ave., Los Angeles, 90033, CA, USA
| | - C-C Jay Kuo
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| | - Inderbir S Gill
- Department of Urology, Keck School of Medicine, University of Southern California (USC), 1975 Zonal Ave., Los Angeles, 90033, CA, USA
| | - Chrysostomos Nikias
- Electrical and Computer Engineering Department, University of Southern California (USC), 3740 McClintock Ave., Los Angeles, 90089, CA, USA
| |
Collapse
|
2
|
Woernle A, Englman C, Dickinson L, Kirkham A, Punwani S, Haider A, Freeman A, Kasivisivanathan V, Emberton M, Hines J, Moore CM, Allen C, Giganti F. Picture Perfect: The Status of Image Quality in Prostate MRI. J Magn Reson Imaging 2024; 59:1930-1952. [PMID: 37804007 DOI: 10.1002/jmri.29025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2023] [Revised: 09/07/2023] [Accepted: 09/08/2023] [Indexed: 10/08/2023] Open
Abstract
Magnetic resonance imaging is the gold standard imaging modality for the diagnosis of prostate cancer (PCa). Image quality is a fundamental prerequisite for the ability to detect clinically significant disease. In this critical review, we separate the issue of image quality into quality improvement and quality assessment. Beginning with the evolution of technical recommendations for scan acquisition, we investigate the role of patient preparation, scanner factors, and more advanced sequences, including those featuring Artificial Intelligence (AI), in determining image quality. As means of quality appraisal, the published literature on scoring systems (including the Prostate Imaging Quality score), is evaluated. Finally, the application of AI and teaching courses as ways to facilitate quality assessment are discussed, encouraging the implementation of future image quality initiatives along the PCa diagnostic and monitoring pathway. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.
Collapse
Affiliation(s)
- Alexandre Woernle
- Faculty of Medical Sciences, University College London, London, UK
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Cameron Englman
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
- Division of Surgery & Interventional Science, University College London, London, UK
| | - Louise Dickinson
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Alex Kirkham
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Shonit Punwani
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
- Centre for Medical Imaging, University College London, London, UK
| | - Aiman Haider
- Department of Pathology, University College London Hospital NHS Foundation Trust, London, UK
| | - Alex Freeman
- Department of Pathology, University College London Hospital NHS Foundation Trust, London, UK
| | - Veeru Kasivisivanathan
- Division of Surgery & Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Mark Emberton
- Division of Surgery & Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - John Hines
- Faculty of Medical Sciences, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
- North East London Cancer Alliance & North Central London Cancer Alliance Urology, London, UK
| | - Caroline M Moore
- Division of Surgery & Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Clare Allen
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Francesco Giganti
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
- Division of Surgery & Interventional Science, University College London, London, UK
| |
Collapse
|
3
|
de Rooij M, Allen C, Twilt JJ, Thijssen LCP, Asbach P, Barrett T, Brembilla G, Emberton M, Gupta RT, Haider MA, Kasivisvanathan V, Løgager V, Moore CM, Padhani AR, Panebianco V, Puech P, Purysko AS, Renard-Penna R, Richenberg J, Salomon G, Sanguedolce F, Schoots IG, Thöny HC, Turkbey B, Villeirs G, Walz J, Barentsz J, Giganti F. PI-QUAL version 2: an update of a standardised scoring system for the assessment of image quality of prostate MRI. Eur Radiol 2024:10.1007/s00330-024-10795-4. [PMID: 38787428 DOI: 10.1007/s00330-024-10795-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2024] [Revised: 04/17/2024] [Accepted: 04/20/2024] [Indexed: 05/25/2024]
Abstract
Multiparametric MRI is the optimal primary investigation when prostate cancer is suspected, and its ability to rule in and rule out clinically significant disease relies on high-quality anatomical and functional images. Avenues for achieving consistent high-quality acquisitions include meticulous patient preparation, scanner setup, optimised pulse sequences, personnel training, and artificial intelligence systems. The impact of these interventions on the final images needs to be quantified. The prostate imaging quality (PI-QUAL) scoring system was the first standardised quantification method that demonstrated the potential for clinical benefit by relating image quality to cancer detection ability by MRI. We present the updated version of PI-QUAL (PI-QUAL v2) which applies to prostate MRI performed with or without intravenous contrast medium using a simplified 3-point scale focused on critical technical and qualitative image parameters. CLINICAL RELEVANCE STATEMENT: High image quality is crucial for prostate MRI, and the updated version of the PI-QUAL score (PI-QUAL v2) aims to address the limitations of version 1. It is now applicable to both multiparametric MRI and MRI without intravenous contrast medium. KEY POINTS: High-quality images are essential for prostate cancer diagnosis and management using MRI. PI-QUAL v2 simplifies image assessment and expands its applicability to prostate MRI without contrast medium. PI-QUAL v2 focuses on critical technical and qualitative image parameters and emphasises T2-WI and DWI.
Collapse
Affiliation(s)
- Maarten de Rooij
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Clare Allen
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Jasper J Twilt
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Linda C P Thijssen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Patrick Asbach
- Department of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
| | - Tristan Barrett
- Department of Radiology, Addenbrooke's Hospital and University of Cambridge, Cambridge, UK
| | - Giorgio Brembilla
- Department of Radiology, IRCCS San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy
| | - Mark Emberton
- Division of Surgery and Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Rajan T Gupta
- Department of Radiology, Duke University Medical Center, Durham, NC, USA
| | - Masoom A Haider
- Joint Department of Medical Imaging, Sinai Health System, Lunenfeld Tanenbaum Research Institute, University of Toronto, Toronto, Canada
| | - Veeru Kasivisvanathan
- Division of Surgery and Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Vibeke Løgager
- Department of Radiology, Herlev Gentofte University Hospital, Herlev, Denmark
| | - Caroline M Moore
- Division of Surgery and Interventional Science, University College London, London, UK
- Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Anwar R Padhani
- Paul Strickland Scanner Centre, Mount Vernon Hospital, Northwood, Middlesex, UK
| | - Valeria Panebianco
- Department of Radiological Sciences, Oncology and Pathology, Sapienza University/Policlinico Umberto I, Rome, Italy
| | - Philippe Puech
- Department of Radiology, CHU Lille, University Lille, Lille, France
| | - Andrei S Purysko
- Abdominal Imaging Section and Nuclear Radiology Department, Diagnostic Institute, and Glickman Urological and Kidney Institute Cleveland Clinic, Cleveland, OH, USA
| | | | - Jonathan Richenberg
- Department of Imaging, Sussex universities Hospitals NHS Foundation Trust, Brighton, UK
| | - Georg Salomon
- Martini Clinic (Prostate Cancer Centre), University of Hamburg, Hamburg, Germany
| | - Francesco Sanguedolce
- Department of Medicine, Surgery and Pharmacy, Università degli Studi di Sassari, Sassari, Italy
- Department of Urology, Fundació Puigvert, Barcelona, Spain
| | - Ivo G Schoots
- Department of Radiology & Nuclear Medicine, Erasmus University Medical Centre, Rotterdam, The Netherlands
- Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Harriet C Thöny
- Department of Diagnostic and Interventional Radiology, Fribourg Cantonal Hospital, Fribourg, Switzerland
| | - Baris Turkbey
- Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA
| | - Geert Villeirs
- Department of Medical Imaging, Ghent University Hospital, Ghent, Belgium
| | - Jochen Walz
- Department of Urology, Institut Paoli-Calmettes Cancer Centre, Marseille, France
| | | | - Francesco Giganti
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK.
- Division of Surgery and Interventional Science, University College London, London, UK.
| |
Collapse
|
4
|
Wenderott K, Krups J, Luetkens JA, Weigl M. Radiologists' perspectives on the workflow integration of an artificial intelligence-based computer-aided detection system: A qualitative study. APPLIED ERGONOMICS 2024; 117:104243. [PMID: 38306741 DOI: 10.1016/j.apergo.2024.104243] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 12/18/2023] [Accepted: 01/23/2024] [Indexed: 02/04/2024]
Abstract
In healthcare, artificial intelligence (AI) is expected to improve work processes, yet most research focuses on the technical features of AI rather than its real-world clinical implementation. To evaluate the implementation process of an AI-based computer-aided detection system (AI-CAD) for prostate MRI readings, we interviewed German radiologists in a pre-post design. We embedded our findings in the Model of Workflow Integration and the Technology Acceptance Model to analyze workflow effects, facilitators, and barriers. The most prominent barriers were: (i) a time delay in the work process, (ii) additional work steps to be taken, and (iii) an unstable performance of the AI-CAD. Most frequently named facilitators were (i) good self-organization, and (ii) good usability of the software. Our results underline the importance of a holistic approach to AI implementation considering the sociotechnical work system and provide valuable insights into key factors of the successful adoption of AI technologies in work systems.
Collapse
Affiliation(s)
- Katharina Wenderott
- Institute for Patient Safety, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany.
| | - Jim Krups
- Institute for Patient Safety, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany
| | - Julian A Luetkens
- Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Germany; Quantitative Imaging Lab Bonn (QILaB), University Hospital Bonn, Germany
| | - Matthias Weigl
- Institute for Patient Safety, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany
| |
Collapse
|
5
|
Wenderott K, Krups J, Luetkens JA, Gambashidze N, Weigl M. Prospective effects of an artificial intelligence-based computer-aided detection system for prostate imaging on routine workflow and radiologists' outcomes. Eur J Radiol 2024; 170:111252. [PMID: 38096741 DOI: 10.1016/j.ejrad.2023.111252] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Revised: 11/15/2023] [Accepted: 12/04/2023] [Indexed: 01/16/2024]
Abstract
OBJECTIVES Artificial intelligence (AI) is expected to alleviate the negative consequences of rising case numbers for radiologists. Currently, systematic evaluations of the impact of AI solutions in real-world radiological practice are missing. Our study addresses this gap by investigating the impact of the clinical implementation of an AI-based computer-aided detection system (CAD) for prostate MRI reading on clinicians' workflow, workflow throughput times, workload, and stress. MATERIALS AND METHODS CAD was newly implemented into radiology workflow and accompanied by a prospective pre-post study design. We assessed prostate MRI case readings using standardized work observations and questionnaires. The observation period was three months each in a single department. Workflow throughput times, PI-RADS score, CAD usage and radiologists' self-reported workload and stress were recorded. Linear mixed models were employed for effect identification. RESULTS In data analyses, 91 observed case readings (pre: 50, post: 41) were included. Variation of routine workflow was observed following CAD implementation. A non-significant increase in overall workflow throughput time was associated with CAD implementation (mean 16.99 ± 6.21 vs 18.77 ± 9.69 min, p = .51), along with an increase in diagnostic reading time for high suspicion cases (mean 15.73 ± 4.99 vs 23.07 ± 8.75 min, p = .02). Changes in radiologists' self-reported workload or stress were not found. CONCLUSION Implementation of an AI-based detection aid was associated with lower standardization and no effects over time on radiologists' workload or stress. Expectations of AI decreasing the workload of radiologists were not confirmed by our real-world study. PRE-REGISTRATION German register for clinical trials https://drks.de/; DRKS00027391.
Collapse
Affiliation(s)
| | - Jim Krups
- Institute for Patient Safety, University Hospital Bonn, Germany
| | - Julian A Luetkens
- Department of Radiology and Quantitative Imaging Lab Bonn (QILaB), University Hospital Bonn, Germany
| | | | - Matthias Weigl
- Institute for Patient Safety, University Hospital Bonn, Germany
| |
Collapse
|