Multistage Artificial Intelligence Analysis System to Support Prostate Cancer Diagnostic Imaging - European Medical Journal

Continue

Multistage Artificial Intelligence Analysis System to Support Prostate Cancer Diagnostic Imaging

2 Mins
Radiology
Authors:
Jakub Suchánek,1 Leonardo Rundo,2 Aman Mehan,3 Chris Doran,4 Anwar Padhani,5, 6 Christof Kastner,7, 8 Tristan Barrett,2, 8 Evis Sala,2, 8, 9 *Antony Rix9

1. Department of Engineering, University of Cambridge, Cambridge, UK
2. Department of Radiology, Addenbrooke’s Hospital and University of Cambridge, Cambridge, UK
3. School of Clinical Medicine, University of Cambridge, Cambridge, UK
4. Sidney Sussex College, University of Cambridge, Cambridge, UK
5. Institute of Cancer Research, London, UK
6. Paul Strickland Scanner Centre, Mount Vernon Cancer Centre, Northwood, UK
7. Department of Urology, Addenbrooke’s Hospital, Cambridge, UK
8. CamPARI Prostate Cancer Group, Addenbrooke’s Hospital and University of Cambridge, Cambridge, UK
9. Lucida Medical Ltd, Cambridge, UK
*Correspondence to [email protected]

Disclosure:

Mr Suchánek had a paid internship with Granta Innovation. Dr Rundo had received consulting fees from Lucida Medical. Dr Mehan had an unpaid internship with Lucida Medical. Prof Padhani holds shares from Lucida Medical. Prof Sala has received consulting fees from Amazon; is employed by, holds shares in, and received consulting fees from Lucida Medical; and has received payment or honoraria for lectures from Siemens and GlaxoSmithKline. Dr Rix is employed by, has patent applications, receives supporting fees, and holds shares for both Lucida Medical and Granta Innovation. Outside this research, Dr Barrett has received research support from Cancer Research UK and Alliance for Cancer Early Detection (ACED); and has unpaid roles with NICE, RCR, NCCP Ireland. The other authors have declared no conflicts of interest.

Acknowledgements:

The authors would like to thank the European Society of Neuroradiology (ESNR) for its support of the ESNR diagnostic committee and the preparation and distribution of the survey.

Citation:
EMJ Radiol. ;2[1]:28-30. Abstract Review.
Keywords:
Artificial intelligence (AI), machine learning (ML), MRI, prostate cancer, radiomics, risk calculation, segmentation.

Each article is made available under the terms of the Creative Commons Attribution-Non Commercial 4.0 License.

­­ BACKGROUND AND AIMS

While prebiopsy multiparametric MRI (mpMRI) substantially improves detection of clinically significant prostate cancer (csPCa) and reduces unnecessary biopsies and diagnoses of insignificant cancer, there remain ongoing challenges with underdiagnosis, biopsy rates, and overdiagnosis. Major studies indicate that 21–49% of patients may still undergo a potentially avoidable biopsy,1-4 and up to 12% of csPCa may be missed.5

Artificial intelligence (AI) has the potential to support, and improve accuracy and consistency of, clinical interpretation of prostate MRI. This study compares a new AI-based system for detecting Gleason ≥3+4 csPCa using MRI, with human readers and existing computer-aided diagnosis (CAD) literature.

MATERIALS AND METHODS

An AI-based system was developed using a proprietary, multistage architecture designed to produce prostate segmentation for prostate-specific antigen density estimation and fusion biopsy, cancer risk calculation to help reduce unnecessary biopsies, and lesion identification to support biopsy targeting.

Data was obtained from open source, anonymised prostate MRI datasets and divided into training, development validation, and held-out test sets. Segmentation models were trained on axial T2-weighted imaging MRI data and accompanying prostate annotations, from the PROMISE12 and NCI-ISBI 2013 Challenge datasets,6,7 acquired using a variety of 1.5T and 3T scanners. Models for cancer assessment (risk calculation and lesion identification) were trained on PROSTATEx,8 an mpMRI dataset acquired at one centre on two 3T scanners (MAGNETOM Trio and MAGNETOM Skyra, Siemens, Munich, Germany), with histopathology findings from MR-guided biopsy as ground truth.

Accuracy was evaluated on development validation and held-out test sets and compared with literature on radiologist interpretations and similar AI/CAD approaches.

RESULTS

As a prebiopsy rule-out test, the system identified patients with Gleason ≥3+4 csPCa with sensitivity 93% (95% confidence interval: 82–100%), specificity 76% (64–87%), negative predictive value (NPV) 95% (88–100%), and receiver operating characteristic area under the curve (AUC) 0.92 (0.84–0.98), using axial biparametric MRI (bpMRI) data from the PROSTATEx combined development validation and held-out test sets (80 patients; 35% csPCa prevalence). Performance was higher on the 40 patient held-out test set. Performance results for the model using axial mpMRI data were similar. Radiologists at Likert/Prostate Imaging Reporting and Data System 3 (PI-RADS 3) thresholds achieved per-patient sensitivity of 88–93%, specificity of 18–68%, and NPV of 76-97%.1,3,4 Comparable AI/CAD publications report 93% sensitivity using held-out or blinded test data at specificity ranging from 6% to 42%.9,10 The achieved results, including mpMRI data, are summarised in Table 1.

Table 1: Performance of the proposed AI system for identifying patients with Gleason ≥3+4 cancer, compared with major radiology studies. AI: artificial intelligence; AUC: area under the curve; bpMRI: biparametric MRI; DV: development validation; mpMRI: multiparametric MRI; N/A: not available; NPV: negative predictive value.

Target identification was evaluated through submission to the PROSTATEx Grand Challenge, a blinded test with 208 radiologist-identified lesions from 140 patients. The system identified lesions containing csPCa with area under the curve 0.84, using bpMRI data. For prostate gland segmentation, the system achieved 92% average Dice score on held-out test cases from the PROMISE12 dataset (10 patients), in line with the state-of-the-art.

CONCLUSION

The AI system showed promising performance and specificity, suggesting it could help support exclusion of csPCa with high sensitivity and NPV, while assisting the identification of lesions to target for biopsy. Its accuracy appears to exceed published results for similar prostate CAD/AI systems. Limitations of this research include methodological and dataset differences between the reported studies, and small test set sizes. Workflow integration, training, and evaluation with larger, more diverse datasets and prospective studies are recommended, and regulatory approvals are planned. ■

References
Ahmed HU et al. Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. Lancet. 2017;389(10071):815-22. Kasivisvanathan V et al. MRI-targeted or standard biopsy for prostate-cancer diagnosis. New Engl J Med. 2018;378(19):1767-77. Rouvière O et al. Use of prostate systematic and targeted biopsy on the basis of multiparametric MRI in biopsy-naive patients (MRI-FIRST): a prospective, multicentre, paired diagnostic study. Lancet Oncol. 2019;20(1):100-9. van der Leest M et al. Head-to-head comparison of transrectal ultrasound-guided prostate biopsy versus multiparametric prostate resonance imaging with subsequent magnetic resonance-guided biopsy in biopsy-naive men with elevated prostate-specific antigen: a large prospective multicenter clinical study. Eur Urol. 2019;75(4):570-8. Drost FJ et al. Prostate MRI, with or without MRI-targeted biopsy, and systematic biopsy for detecting prostate cancer. Cochrane Database of Syst Rev. 2019;4(4):CD012663. Litjens G et al. Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med Image Anal. 2014;18(2):359-73. Bloch N et al. NCI-ISBI 2013 challenge: automated segmentation of prostate structures. The Cancer Imaging Archive. 2015;DOI:10.7937/K9/TCIA.2015.zF0vlOPv. Litjens G et al. Computer-aided detection of prostate cancer in MRI. IEEE Trans Med Imaging. 2014;33(5):1083-92. Thon A et al. Computer aided detection in prostate cancer diagnostics: a promising alternative to biopsy? A retrospective study from 104 lesions with histological ground truth. PLoS One. 2017;12(10):e0185995. Schelb P et al. Simulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessment. Eur Radiol. 2021;31:302-13

Rate this content's potential impact on patient outcomes

Average rating / 5. Vote count:

No votes so far! Be the first to rate this content.

Thank you!

Please share some more information on the rating you have given