1
|
Yan W, Chiu B, Shen Z, Yang Q, Syer T, Min Z, Punwani S, Emberton M, Atkinson D, Barratt DC, Hu Y. Combiner and HyperCombiner networks: Rules to combine multimodality MR images for prostate cancer localisation. Med Image Anal 2024; 91:103030. [PMID: 37995627 DOI: 10.1016/j.media.2023.103030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2022] [Revised: 09/22/2023] [Accepted: 11/13/2023] [Indexed: 11/25/2023]
Abstract
One of the distinct characteristics of radiologists reading multiparametric prostate MR scans, using reporting systems like PI-RADS v2.1, is to score individual types of MR modalities, including T2-weighted, diffusion-weighted, and dynamic contrast-enhanced, and then combine these image-modality-specific scores using standardised decision rules to predict the likelihood of clinically significant cancer. This work aims to demonstrate that it is feasible for low-dimensional parametric models to model such decision rules in the proposed Combiner networks, without compromising the accuracy of predicting radiologic labels. First, we demonstrate that either a linear mixture model or a nonlinear stacking model is sufficient to model PI-RADS decision rules for localising prostate cancer. Second, parameters of these combining models are proposed as hyperparameters, weighing independent representations of individual image modalities in the Combiner network training, as opposed to end-to-end modality ensemble. A HyperCombiner network is developed to train a single image segmentation network that can be conditioned on these hyperparameters during inference for much-improved efficiency. Experimental results based on 751 cases from 651 patients compare the proposed rule-modelling approaches with other commonly-adopted end-to-end networks, in this downstream application of automating radiologist labelling on multiparametric MR. By acquiring and interpreting the modality combining rules, specifically the linear-weights or odds ratios associated with individual image modalities, three clinical applications are quantitatively presented and contextualised in the prostate cancer segmentation application, including modality availability assessment, importance quantification and rule discovery.
Collapse
Affiliation(s)
- Wen Yan
- Department of Electrical Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Hong Kong China; Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| | - Bernard Chiu
- Department of Electrical Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Hong Kong China; Department of Physics & Computer Science, Wilfrid Laurier University, 75 University Avenue West Waterloo, Ontario N2L 3C5, Canada.
| | - Ziyi Shen
- Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| | - Qianye Yang
- Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| | - Tom Syer
- Centre for Medical Imaging, Division of Medicine, University College London, London W1 W 7TS, UK.
| | - Zhe Min
- Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| | - Shonit Punwani
- Centre for Medical Imaging, Division of Medicine, University College London, London W1 W 7TS, UK.
| | - Mark Emberton
- Division of Surgery & Interventional Science, University College London, Gower St, WC1E 6BT, London, UK.
| | - David Atkinson
- Centre for Medical Imaging, Division of Medicine, University College London, London W1 W 7TS, UK.
| | - Dean C Barratt
- Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| | - Yipeng Hu
- Centre for Medical Image Computing; Department of Medical Physics & Biomedical Engineering; Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, Gower St, WC1E 6BT, London, UK.
| |
Collapse
|
2
|
Zhang Y, Yang H, Li Z, Gao C, Chen Y, Huang Y, Yue X, Shu C, Wei Y, Cui F, Xu M. A radiomics approach based on MR imaging for classification of deficiency and excess syndrome of traditional Chinese medicine in prostate cancer. Heliyon 2023; 9:e23242. [PMID: 38144279 PMCID: PMC10746512 DOI: 10.1016/j.heliyon.2023.e23242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2023] [Revised: 11/28/2023] [Accepted: 11/29/2023] [Indexed: 12/26/2023] Open
Abstract
Objective To explore the potential imaging biomarkers for predicting Traditional Chinese medicine (TCM) deficiency and excess syndrome in prostate cancer (PCa) patients by radiomics approach based on MR imaging. Methods A total of 121 PCa patients from 2 centers were divided into 1 training cohort with 84 PCa patients and 1 validation cohort with 37 PCa patients. The PCa patients were divided into deficiency and excess syndrome group according to TCM syndrome differentiation. Radiomic features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging and apparent diffusion coefficient images originated from diffusion-weighted imaging. A radiomic signature was constructed after reduction of dimension in training group by the minimum redundancy maximum relevance and the least absolute shrinkage and selection operator. The performance of the model was evaluated by receiver operating characteristic (ROC) curve and calibration curve. Results The radiomic scores of PCa with TCM excess syndrome group were statistically higher than those of PCa with TCM deficiency syndrome group among T2WI, diffusion-weighted imaging and apparent diffusion coefficient imaging models. The area under ROC curves for T2WI, diffusion-weighted imaging and apparent diffusion coefficient imaging models were 0.824, 0.824, 0.847 in the training cohort and 0.759, 0.750, 0.809 in the validation cohort, respectively. The apparent diffusion coefficient imaging model had the best discrimination in separating patients with TCM excess syndrome and deficiency syndrome, and its accuracy was 0.788, 0.778 in the training and validation cohort, respectively. The calibration curve demonstrated that there was a high consistency between the prediction of radiomic scores and the actual classification of TCM's deficiency and excess syndrome in PCa. Conclusion The radiomic signature based on MR imaging can be performed as a non-invasive, potential approach to discriminate TCM deficiency syndrome from excess syndrome in PCa, in which apparent diffusion coefficient imaging model has the best diagnostic efficiency.
Collapse
Affiliation(s)
- Yongsheng Zhang
- Department of Radiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Huan Yang
- Department of Acupuncture and Moxibustion, Community Health Service of Xiaohehushu District, Hangzhou, 310005, China
| | - Zhiping Li
- Department of Radiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Chen Gao
- Department of Radiology, The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, 310006, China
| | - Yin Chen
- Department of Urology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Yasheng Huang
- Department of Urology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Xianjie Yue
- Department of Radiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Chang Shu
- Department of Pathology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Yuguo Wei
- Advanced Analytics, Global Medical Service, GE Healthcare, Hangzhou, 310007, China
| | - Feng Cui
- Department of Radiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, 310007, China
| | - Maosheng Xu
- Department of Radiology, The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, 310006, China
| |
Collapse
|
3
|
Chen J, Feng B, Hu M, Huang F, Chen Y, Ma X, Long W. A transfer learning nomogram for predicting prostate cancer and benign conditions on MRI. BMC Med Imaging 2023; 23:200. [PMID: 38036991 PMCID: PMC10691068 DOI: 10.1186/s12880-023-01163-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2023] [Accepted: 11/27/2023] [Indexed: 12/02/2023] Open
Abstract
BACKGROUND Deep learning has been used to detect or characterize prostate cancer (PCa) on medical images. The present study was designed to develop an integrated transfer learning nomogram (TLN) for the prediction of PCa and benign conditions (BCs) on magnetic resonance imaging (MRI). METHODS In this retrospective study, a total of 709 patients with pathologically confirmed PCa and BCs from two institutions were included and divided into training (n = 309), internal validation (n = 200), and external validation (n = 200) cohorts. A transfer learning signature (TLS) that was pretrained with the whole slide images of PCa and fine-tuned on prebiopsy MRI images was constructed. A TLN that integrated the TLS, the Prostate Imaging-Reporting and Data System (PI-RADS) score, and the clinical factor was developed by multivariate logistic regression. The performance of the TLS, clinical model (CM), and TLN were evaluated in the validation cohorts using the receiver operating characteristic (ROC) curve, the Delong test, the integrated discrimination improvement (IDI), and decision curve analysis. RESULTS TLS, PI-RADS score, and age were selected for TLN construction. The TLN yielded areas under the curve of 0.9757 (95% CI, 0.9613-0.9902), 0.9255 (95% CI, 0.8873-0.9638), and 0.8766 (95% CI, 0.8267-0.9264) in the training, internal validation, and external validation cohorts, respectively, for the discrimination of PCa and BCs. The TLN outperformed the TLS and the CM in both the internal and external validation cohorts. The decision curve showed that the TLN added more net benefit than the CM. CONCLUSIONS The proposed TLN has the potential to be used as a noninvasive tool for PCa and BCs differentiation.
Collapse
Affiliation(s)
- Junhao Chen
- Department of Medical Imaging Center, The First Affiliated Hospital of Jinan University, 613 West Huangpu Street, Tianhe District, Guangzhou, Guangdong Province, 510630, PR China
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong Province, 529000, PR China
| | - Bao Feng
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong Province, 529000, PR China
- Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology, Guilin, Guangxi Province, 541004, PR China
| | - Maoqing Hu
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong Province, 529000, PR China
| | - Feidong Huang
- School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, Guangxi Province, 541004, PR China
| | - Yehang Chen
- Laboratory of Artificial Intelligence of Biomedicine, Guilin University of Aerospace Technology, Guilin, Guangxi Province, 541004, PR China
| | - Xilun Ma
- Department of Radiology, The First Affiliated Hospital of Shantou University Medical College, Shantou, Guangdong Province, 515000, PR China
| | - Wansheng Long
- Department of Medical Imaging Center, The First Affiliated Hospital of Jinan University, 613 West Huangpu Street, Tianhe District, Guangzhou, Guangdong Province, 510630, PR China.
- Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong Province, 529000, PR China.
- Department of Radiology, Jiangmen Central Hospital, 23#, North Road, Pengjiang Zone, Jiangmen, Guangdong Province, 529000, PR China.
| |
Collapse
|
4
|
Lee EJ, Hwang J, Park S, Bae SH, Lim J, Chang YW, Hong SS, Oh E, Nam BD, Jeong J, Sung JK, Nickel D. Utility of accelerated T2-weighted turbo spin-echo imaging with deep learning reconstruction in female pelvic MRI: a multi-reader study. Eur Radiol 2023; 33:7697-7706. [PMID: 37314472 DOI: 10.1007/s00330-023-09781-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 03/24/2023] [Accepted: 03/28/2023] [Indexed: 06/15/2023]
Abstract
OBJECTIVES To determine the clinical feasibility of T2-weighted turbo spin-echo (T2-TSE) imaging with deep learning reconstruction (DLR) in female pelvic MRI compared with conventional T2 TSE in terms of image quality and scan time. METHODS Between May 2021 and September 2021, 52 women (mean age, 44 years ± 12) who underwent 3-T pelvic MRI with additional T2-TSE using a DLR algorithm were included in this single-center prospective study with patient's informed consents. Conventional, DLR, and DLR T2-TSE images with reduced scan times were independently assessed and compared by four radiologists. The overall image quality, differentiation of anatomic details, lesion conspicuity, and artifacts were evaluated using a 5-point scale. Inter-observer agreement of the qualitative scores was compared and reader protocol preferences were then evaluated. RESULTS In the qualitative analysis of all readers, fast DLR T2-TSE showed significantly better overall image quality, differentiation of anatomic regions, lesion conspicuity, and lesser artifacts than conventional T2-TSE and DLR T2-TSE, despite approximately 50% reduction in scan time (all p < 0.05). The inter-reader agreement for the qualitative analysis was moderate to good. All readers preferred DLR over conventional T2-TSE regardless of scan time and preferred fast DLR T2-TSE (57.7-78.8%), except for one who preferred DLR over fast DLR T2-TSE (53.8% vs. 46.1%). CONCLUSION In female pelvic MRI, image quality and accelerated image acquisition for T2-TSE can be significantly improved by using DLR compared to conventional T2-TSE. Fast DLR T2-TSE was non-inferior to DLR T2-TSE in terms of reader preference and image quality. CLINICAL RELEVANCE STATEMENT DLR of T2-TSE in female pelvic MRI enables fast imaging along with maintaining optimal image quality compared with parallel imaging-based conventional T2-TSE. KEY POINTS • Conventional T2 turbo spin-echo based on parallel imaging has limitations for accelerated image acquisition while maintaining good image quality. • Deep learning image reconstruction showed better image quality in both images obtained using the same or accelerated image acquisition parameters compared with conventional T2 turbo spin-echo in female pelvic MRI. • Deep learning image reconstruction enables accelerated image acquisition while maintaining good image quality in the T2-TSE of female pelvic MRI.
Collapse
Affiliation(s)
- Eun Ji Lee
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Jiyoung Hwang
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea.
| | - Suyeon Park
- Department of Biostatistics, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, Seoul, Korea
| | - Sung Hwan Bae
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Jiyun Lim
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Yun-Woo Chang
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Seong Sook Hong
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Eunsun Oh
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Bo Da Nam
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | - Jewon Jeong
- Department of Radiology, Soonchunhyang University Seoul Hospital, Soonchunhyang University College of Medicine, 59 Daesakwan-Ro, Yongsan-Ku, Seoul, 04401, Korea
| | | | - Dominik Nickel
- MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| |
Collapse
|
5
|
Abstract
OBJECTIVE To comprehensively review the literature on the integration of MRI as a diagnostic tool in prostate cancer screening and offer practical recommendations for optimising its use. METHODS Existing research studies, clinical guidelines and expert opinions were reviewed to support the optimisation standards for MRI use in screening. Consolidated screening principles were used to make appropriate recommendations regarding the integration of MRI into the diagnostic pathway. RESULTS To strike a balance between the potential benefits of early detection on mortality and minimising the harm of over-diagnosing indolent cancers, it is necessary to have a clear understanding of the context of MRI use. The key to optimisation is patient selections and MRI-targeted biopsies. For men at higher-than-average risk, it is essential to use screening-specific MRI protocols and establish accuracy levels and interpretation criteria. Optimisation of readings by the automation of data acquisition, image quality monitoring, post-processing, radiologist certification and deep-learning computer-aided software is needed. The optimal utilisation of MRI involves its integration into a multistep diagnostic pathway, supported by a quality-assured and cost-effective infrastructure that ensures community-wide access to imaging. CONCLUSION MRI in the prostate cancer screening pathway can bring substantial diagnostic benefits. By carefully considering its advantages, limitations and safety concerns and integrating it into a multistep diagnostic pathway, clinicians can improve outcomes while minimising harm to screening participants. CLINICAL RELEVANCE STATEMENT The manuscript discusses the role of MRI in prostate cancer screening, highlighting its potential to improve accuracy and reduce overdiagnosis. It emphasises the importance of optimising protocols and integrating MRI into a multistep diagnostic pathway for successfully delivering screening benefits. KEY POINTS • Population screening for prostate cancer is a new indication for prostate MRI that allows the detection of high-risk cancers while reducing the need for biopsies and associated harm. • To optimise prostate cancer screening using MRI, it is essential to redefine MRI protocols; establish accuracy levels, reliability and interpretation criteria; and optimise reading (including post-processing, image quality, radiologist certification, and deep-learning computer-aided software). • The optimal utilisation of MRI for prostate cancer screening would involve its integration into a multistep diagnostic pathway, supported by a quality-assured and cost-effective infrastructure that ensures community-wide access to imaging.
Collapse
Affiliation(s)
- Anwar R Padhani
- Paul Strickland Scanner Centre, Mount Vernon Cancer Centre, Northwood, UK.
| | - Ivo G Schoots
- Department of Radiology and Nuclear Medicine, Erasmus University Medical Centre, Rotterdam, The Netherlands
- Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands
| |
Collapse
|
6
|
Jaouen T, Souchon R, Moldovan PC, Bratan F, Duran A, Hoang-Dinh A, Di Franco F, Debeer S, Dubreuil-Chambardel M, Arfi N, Ruffion A, Colombel M, Crouzet S, Gonindard-Melodelima C, Rouvière O. Characterization of high-grade prostate cancer at multiparametric MRI using a radiomic-based computer-aided diagnosis system as standalone and second reader. Diagn Interv Imaging 2023; 104:465-476. [PMID: 37345961 DOI: 10.1016/j.diii.2023.04.006] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Revised: 04/16/2023] [Accepted: 04/18/2023] [Indexed: 06/23/2023]
Abstract
PURPOSE The purpose of this study was to develop and test across various scanners a zone-specific region-of-interest (ROI)-based computer-aided diagnosis system (CAD) aimed at characterizing, on MRI, International Society of Urological Pathology (ISUP) grade≥2 prostate cancers. MATERIALS AND METHODS ROI-based quantitative models were selected in multi-vendor training (265 pre-prostatectomy MRIs) and pre-test (112 pre-biopsy MRIs) datasets. The best peripheral and transition zone models were combined and retrospectively assessed in internal (158 pre-biopsy MRIs) and external (104 pre-biopsy MRIs) test datasets. Two radiologists (R1/R2) retrospectively delineated the lesions targeted at biopsy in test datasets. The CAD area under the receiver operating characteristic curve (AUC) for characterizing ISUP≥2 cancers was compared to that of the Prostate Imaging-Reporting and Data System version2 (PI-RADSv2) score prospectively assigned to targeted lesions. RESULTS The best models used the 25th apparent diffusion coefficient (ADC) percentile in transition zone and the 2nd ADC percentile and normalized wash-in rate in peripheral zone. The PI-RADSv2 AUCs were 82% (95% confidence interval [CI]: 74-87) and 86% (95% CI: 81-91) in the internal and external test datasets respectively. They were not different from the CAD AUCs obtained with R1 and R2 delineations, in the internal (82% [95% CI: 76-89], P = 0.95 and 85% [95% CI: 78-91], P = 0.55) and external (82% [95% CI: 74-91], P = 0.41 and 86% [95% CI:78-95], P = 0.98) test datasets. The CAD yielded sensitivities of 86-89% and 90-91%, and specificities of 64-65% and 69-75% in the internal and external test datasets respectively. CONCLUSION The CAD performance for characterizing ISUP grade≥2 prostate cancers on MRI is not different from that of PI-RADSv2 score across two test datasets.
Collapse
Affiliation(s)
| | | | - Paul C Moldovan
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon, 69003, France
| | - Flavie Bratan
- Hôpital Saint Joseph Saint Luc, Department of Radiology, Lyon, 69007, France
| | - Audrey Duran
- Univ Lyon, CNRS, Inserm, INSA Lyon, UCBL, CREATIS, UMR5220, U1294, Villeurbanne, 69100, France
| | - Au Hoang-Dinh
- INSERM, LabTAU, U1032, Lyon, 69003, France; Hanoi Medical University, Department of Radiology, Hanoi, 116001, Vietnam
| | - Florian Di Franco
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon, 69003, France
| | - Sabine Debeer
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon, 69003, France
| | - Marine Dubreuil-Chambardel
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon, 69003, France
| | - Nicolas Arfi
- Hôpital Saint Joseph Saint Luc, Department of Urology, Lyon, 69007, France
| | - Alain Ruffion
- Hospices Civils de Lyon, Centre Hospitalier Lyon Sud, Department of Urology, Pierre-Bénite, 69310, France; Equipe 2 - Centre d'Innovation en Cancérologie de Lyon (EA 3738 CICLY), Pierre-Bénite, 69310, France; Université de Lyon, Lyon, 69003, France; Université Lyon 1, Lyon, 69003, France; Faculté de Médecine Lyon Sud, Pierre-Bénite, 69310, France
| | - Marc Colombel
- Université de Lyon, Lyon, 69003, France; Université Lyon 1, Lyon, 69003, France; Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Urology, Lyon, 69003, France; Faculté de Médecine Lyon Est, Lyon, 69003, France
| | - Sébastien Crouzet
- INSERM, LabTAU, U1032, Lyon, 69003, France; Université de Lyon, Lyon, 69003, France; Université Lyon 1, Lyon, 69003, France; Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Urology, Lyon, 69003, France; Faculté de Médecine Lyon Est, Lyon, 69003, France
| | - Christelle Gonindard-Melodelima
- Université Grenoble Alpes, Laboratoire d'Ecologie Alpine, BP 53, Grenoble 38041, France; CNRS, UMR 5553, BP 53, Grenoble, 38041, France
| | - Olivier Rouvière
- INSERM, LabTAU, U1032, Lyon, 69003, France; Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon, 69003, France; Université de Lyon, Lyon, 69003, France; Université Lyon 1, Lyon, 69003, France; Faculté de Médecine Lyon Est, Lyon, 69003, France.
| |
Collapse
|
7
|
Zhang KS, Mayer P, Glemser PA, Tavakoli AA, Keymling M, Rotkopf LT, Meinzer C, Görtz M, Kauczor HU, Hielscher T, Stenzinger A, Bonekamp D, Hohenfellner M, Schlemmer HP. Are T2WI PI-RADS sub-scores of transition zone prostate lesions biased by DWI information? A multi-reader, single-center study. Eur J Radiol 2023; 167:111026. [PMID: 37639843 DOI: 10.1016/j.ejrad.2023.111026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Revised: 07/18/2023] [Accepted: 08/04/2023] [Indexed: 08/31/2023]
Abstract
PURPOSE According to PI-RADS v2.1, T2-weighted imaging (T2WI) is the dominant sequence for transition zone (TZ) lesions. This study aimed to assess, whether diffusion-weighted imaging (DWI) information influences the assignment of T2WI scores. METHOD Out of 283 prostate MRI examinations with correlated biopsy results, fourty-four patients were selected retrospectively: first, 22 patients with a TZ lesion with T2WI and DWI scores ≥ 4, to represent lesions with unequivocal suspicion on T2WI and DWI. Second, 22 additional patients with TZ lesions of similar T2WI appearance but with corresponding DWI score ≤ 3 were added as control. Four residents and one board-certified radiologist each performed two assessments of the included patients: First, only T2WI was available (T2-only read); second, both T2WI and DWI sequences were available (biparametric read). Lesion scores were assessed using Wilcoxon signed-rank test, inter-reader agreement using weighted kappa and Kendall's W statistics, and sensitivity/specificity using McNemar test. RESULTS The T2WI scores were significantly different between the T2-only and biparametric read for 3 out of 4 residents (p ≤ 0.049) but not for the radiologist. The overall PI-RADS scores derived from the two reading sessions differed considerably for 35/220 cases (all readers pooled). Inter-reader agreement was fair for the T2WI and overall PI-RADS scores (mean kappa 0.27-0.30) and moderate for the DWI scores (mean kappa 0.43). CONCLUSIONS For inexperienced readers, assessment of T2WI is variable and potentially biased by availability of DWI information, which can lead to changes of overall PI-RADS score and consequently clinical management. Assessment of T2WI should be performed before reviewing DWI to ensure non-biased interpretation of TZ lesions in the dominant sequence.
Collapse
Affiliation(s)
- Kevin Sun Zhang
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Philipp Mayer
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; Department of Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany
| | | | - Anoshirwan Andrej Tavakoli
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; Department of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Mannheim, Germany
| | - Myriam Keymling
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Lukas Thomas Rotkopf
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Clara Meinzer
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Magdalena Görtz
- Department of Urology, University of Heidelberg Medical Center, Heidelberg, Germany; Junior Clinical Cooperation Unit 'Multiparametric Methods for Early Detection of Prostate Cancer, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Hans-Ulrich Kauczor
- Department of Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Thomas Hielscher
- Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Albrecht Stenzinger
- Institute of Pathology, University of Heidelberg Medical Center, Heidelberg, Germany
| | - David Bonekamp
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; German Cancer Consortium (DKTK), Germany; National Center for Tumor Diseases (NCT) Heidelberg, Heidelberg, Germany; Heidelberg University Medical School, Heidelberg, Germany.
| | - Markus Hohenfellner
- Department of Urology, University of Heidelberg Medical Center, Heidelberg, Germany
| | - Heinz-Peter Schlemmer
- Division of Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; German Cancer Consortium (DKTK), Germany; National Center for Tumor Diseases (NCT) Heidelberg, Heidelberg, Germany
| |
Collapse
|
8
|
Zhao LT, Liu ZY, Xie WF, Shao LZ, Lu J, Tian J, Liu JG. What benefit can be obtained from magnetic resonance imaging diagnosis with artificial intelligence in prostate cancer compared with clinical assessments? Mil Med Res 2023; 10:29. [PMID: 37357263 DOI: 10.1186/s40779-023-00464-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Accepted: 06/07/2023] [Indexed: 06/27/2023] Open
Abstract
The present study aimed to explore the potential of artificial intelligence (AI) methodology based on magnetic resonance (MR) images to aid in the management of prostate cancer (PCa). To this end, we reviewed and summarized the studies comparing the diagnostic and predictive performance for PCa between AI and common clinical assessment methods based on MR images and/or clinical characteristics, thereby investigating whether AI methods are generally superior to common clinical assessment methods for the diagnosis and prediction fields of PCa. First, we found that, in the included studies of the present study, AI methods were generally equal to or better than the clinical assessment methods for the risk assessment of PCa, such as risk stratification of prostate lesions and the prediction of therapeutic outcomes or PCa progression. In particular, for the diagnosis of clinically significant PCa, the AI methods achieved a higher summary receiver operator characteristic curve (SROC-AUC) than that of the clinical assessment methods (0.87 vs. 0.82). For the prediction of adverse pathology, the AI methods also achieved a higher SROC-AUC than that of the clinical assessment methods (0.86 vs. 0.75). Second, as revealed by the radiomics quality score (RQS), the studies included in the present study presented a relatively high total average RQS of 15.2 (11.0-20.0). Further, the scores of the individual RQS elements implied that the AI models in these studies were constructed with relatively perfect and standard radiomics processes, but the exact generalizability and clinical practicality of the AI models should be further validated using higher levels of evidence, such as prospective studies and open-testing datasets.
Collapse
Affiliation(s)
- Li-Tao Zhao
- School of Engineering Medicine, Beihang University, Beijing, 100191, China
- School of Biological Science and Medical Engineering, Beihang University, Beijing, 100191, China
| | - Zhen-Yu Liu
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Beijing, 100190, China
- University of Chinese Academy of Sciences, Beijing, 100080, China
| | - Wan-Fang Xie
- School of Engineering Medicine, Beihang University, Beijing, 100191, China
- School of Biological Science and Medical Engineering, Beihang University, Beijing, 100191, China
| | - Li-Zhi Shao
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Beijing, 100190, China
| | - Jian Lu
- Department of Urology, Peking University Third Hospital, Peking University, 100191, Beijing, China.
| | - Jie Tian
- School of Engineering Medicine, Beihang University, Beijing, 100191, China.
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Beijing, 100190, China.
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of the People's Republic of China, 100191, Beijing, China.
| | - Jian-Gang Liu
- School of Engineering Medicine, Beihang University, Beijing, 100191, China.
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of the People's Republic of China, 100191, Beijing, China.
- Beijing Engineering Research Center of Cardiovascular Wisdom Diagnosis and Treatment, Beijing, 100029, China.
| |
Collapse
|
9
|
Karagoz A, Alis D, Seker ME, Zeybel G, Yergin M, Oksuz I, Karaarslan E. Anatomically guided self-adapting deep neural network for clinically significant prostate cancer detection on bi-parametric MRI: a multi-center study. Insights Imaging 2023; 14:110. [PMID: 37337101 DOI: 10.1186/s13244-023-01439-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2023] [Accepted: 04/17/2023] [Indexed: 06/21/2023] Open
Abstract
OBJECTIVE To evaluate the effectiveness of a self-adapting deep network, trained on large-scale bi-parametric MRI data, in detecting clinically significant prostate cancer (csPCa) in external multi-center data from men of diverse demographics; to investigate the advantages of transfer learning. METHODS We used two samples: (i) Publicly available multi-center and multi-vendor Prostate Imaging: Cancer AI (PI-CAI) training data, consisting of 1500 bi-parametric MRI scans, along with its unseen validation and testing samples; (ii) In-house multi-center testing and transfer learning data, comprising 1036 and 200 bi-parametric MRI scans. We trained a self-adapting 3D nnU-Net model using probabilistic prostate masks on the PI-CAI data and evaluated its performance on the hidden validation and testing samples and the in-house data with and without transfer learning. We used the area under the receiver operating characteristic (AUROC) curve to evaluate patient-level performance in detecting csPCa. RESULTS The PI-CAI training data had 425 scans with csPCa, while the in-house testing and fine-tuning data had 288 and 50 scans with csPCa, respectively. The nnU-Net model achieved an AUROC of 0.888 and 0.889 on the hidden validation and testing data. The model performed with an AUROC of 0.886 on the in-house testing data, with a slight decrease in performance to 0.870 using transfer learning. CONCLUSIONS The state-of-the-art deep learning method using prostate masks trained on large-scale bi-parametric MRI data provides high performance in detecting csPCa in internal and external testing data with different characteristics, demonstrating the robustness and generalizability of deep learning within and across datasets. CLINICAL RELEVANCE STATEMENT A self-adapting deep network, utilizing prostate masks and trained on large-scale bi-parametric MRI data, is effective in accurately detecting clinically significant prostate cancer across diverse datasets, highlighting the potential of deep learning methods for improving prostate cancer detection in clinical practice.
Collapse
Affiliation(s)
- Ahmet Karagoz
- Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey
- Artificial Intelligence and Information Technologies, Hevi AI Health, Istanbul, Turkey
| | - Deniz Alis
- Artificial Intelligence and Information Technologies, Hevi AI Health, Istanbul, Turkey.
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey.
| | - Mustafa Ege Seker
- School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Gokberk Zeybel
- School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Mert Yergin
- Artificial Intelligence and Information Technologies, Hevi AI Health, Istanbul, Turkey
| | - Ilkay Oksuz
- Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey
| | - Ercan Karaarslan
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| |
Collapse
|
10
|
Kim H, Kang SW, Kim JH, Nagar H, Sabuncu M, Margolis DJA, Kim CK. The role of AI in prostate MRI quality and interpretation: Opportunities and challenges. Eur J Radiol 2023; 165:110887. [PMID: 37245342 DOI: 10.1016/j.ejrad.2023.110887] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2023] [Revised: 05/06/2023] [Accepted: 05/20/2023] [Indexed: 05/30/2023]
Abstract
Prostate MRI plays an important role in imaging the prostate gland and surrounding tissues, particularly in the diagnosis and management of prostate cancer. With the widespread adoption of multiparametric magnetic resonance imaging in recent years, the concerns surrounding the variability of imaging quality have garnered increased attention. Several factors contribute to the inconsistency of image quality, such as acquisition parameters, scanner differences and interobserver variabilities. While efforts have been made to standardize image acquisition and interpretation via the development of systems, such as PI-RADS and PI-QUAL, the scoring systems still depend on the subjective experience and acumen of humans. Artificial intelligence (AI) has been increasingly used in many applications, including medical imaging, due to its ability to automate tasks and lower human error rates. These advantages have the potential to standardize the tasks of image interpretation and quality control of prostate MRI. Despite its potential, thorough validation is required before the implementation of AI in clinical practice. In this article, we explore the opportunities and challenges of AI, with a focus on the interpretation and quality of prostate MRI.
Collapse
Affiliation(s)
- Heejong Kim
- Department of Radiology, Weill Cornell Medical College, 525 E 68th St Box 141, New York, NY 10021, United States
| | - Shin Won Kang
- Research Institute for Future Medicine, Samsung Medical Center, Republic of Korea
| | - Jae-Hun Kim
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea
| | - Himanshu Nagar
- Department of Radiation Oncology, Weill Cornell Medical College, 525 E 68th St, New York, NY 10021, United States
| | - Mert Sabuncu
- Department of Radiology, Weill Cornell Medical College, 525 E 68th St Box 141, New York, NY 10021, United States
| | - Daniel J A Margolis
- Department of Radiology, Weill Cornell Medical College, 525 E 68th St Box 141, New York, NY 10021, United States.
| | - Chan Kyo Kim
- Department of Radiology and Center for Imaging Science, Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea
| |
Collapse
|
11
|
Arslan A, Alis D, Erdemli S, Seker ME, Zeybel G, Sirolu S, Kurtcan S, Karaarslan E. Does deep learning software improve the consistency and performance of radiologists with various levels of experience in assessing bi-parametric prostate MRI? Insights Imaging 2023; 14:48. [PMID: 36939953 PMCID: PMC10027972 DOI: 10.1186/s13244-023-01386-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Accepted: 02/04/2023] [Indexed: 03/21/2023] Open
Abstract
OBJECTIVE To investigate whether commercially available deep learning (DL) software improves the Prostate Imaging-Reporting and Data System (PI-RADS) scoring consistency on bi-parametric MRI among radiologists with various levels of experience; to assess whether the DL software improves the performance of the radiologists in identifying clinically significant prostate cancer (csPCa). METHODS We retrospectively enrolled consecutive men who underwent bi-parametric prostate MRI at a 3 T scanner due to suspicion of PCa. Four radiologists with 2, 3, 5, and > 20 years of experience evaluated the bi-parametric prostate MRI scans with and without the DL software. Whole-mount pathology or MRI/ultrasound fusion-guided biopsy was the reference. The area under the receiver operating curve (AUROC) was calculated for each radiologist with and without the DL software and compared using De Long's test. In addition, the inter-rater agreement was investigated using kappa statistics. RESULTS In all, 153 men with a mean age of 63.59 ± 7.56 years (range 53-80) were enrolled in the study. In the study sample, 45 men (29.80%) had clinically significant PCa. During the reading with the DL software, the radiologists changed their initial scores in 1/153 (0.65%), 2/153 (1.3%), 0/153 (0%), and 3/153 (1.9%) of the patients, yielding no significant increase in the AUROC (p > 0.05). Fleiss' kappa scores among the radiologists were 0.39 and 0.40 with and without the DL software (p = 0.56). CONCLUSIONS The commercially available DL software does not increase the consistency of the bi-parametric PI-RADS scoring or csPCa detection performance of radiologists with varying levels of experience.
Collapse
Affiliation(s)
- Aydan Arslan
- Department of Radiology, Umraniye Training and Research Hospital, Istanbul, Turkey
| | - Deniz Alis
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey.
| | - Servet Erdemli
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Mustafa Ege Seker
- School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Gokberk Zeybel
- School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Sabri Sirolu
- Department of Radiology, Istanbul Sisli Hamidiye Etfal Training and Research Hospital, Istanbul, Turkey
| | - Serpil Kurtcan
- Department of Radiology, Acibadem Healthcare Group, Istanbul, Turkey
| | - Ercan Karaarslan
- Department of Radiology, School of Medicine, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| |
Collapse
|
12
|
Jiang W, Lin Y, Vardhanabhuti V, Ming Y, Cao P. Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network. Diagnostics (Basel) 2023; 13:diagnostics13040615. [PMID: 36832103 PMCID: PMC9955952 DOI: 10.3390/diagnostics13040615] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Revised: 01/27/2023] [Accepted: 01/28/2023] [Indexed: 02/11/2023] Open
Abstract
MRI is the primary imaging approach for diagnosing prostate cancer. Prostate Imaging Reporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamental MRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks show great promise in automatic lesion segmentation and classification, which help to ease the burden on radiologists and reduce inter-reader variability. In this study, we proposed a novel multi-branch network, MiniSegCaps, for prostate cancer segmentation and PI-RADS classification on mpMRI. MiniSeg branch outputted the segmentation in conjunction with PI-RADS prediction, guided by the attention map from the CapsuleNet. CapsuleNet branch exploited the relative spatial information of prostate cancer to anatomical structures, such as the zonal location of the lesion, which also reduced the sample size requirement in training due to its equivariance properties. In addition, a gated recurrent unit (GRU) is adopted to exploit spatial knowledge across slices, improving through-plane consistency. Based on the clinical reports, we established a prostate mpMRI database from 462 patients paired with radiologically estimated annotations. MiniSegCaps was trained and evaluated with fivefold cross-validation. On 93 testing cases, our model achieved a 0.712 dice coefficient on lesion segmentation, 89.18% accuracy, and 92.52% sensitivity on PI-RADS classification (PI-RADS ≥ 4) in patient-level evaluation, significantly outperforming existing methods. In addition, a graphical user interface (GUI) integrated into the clinical workflow can automatically produce diagnosis reports based on the results from MiniSegCaps.
Collapse
|
13
|
Rouvière O, Jaouen T, Baseilhac P, Benomar ML, Escande R, Crouzet S, Souchon R. Artificial intelligence algorithms aimed at characterizing or detecting prostate cancer on MRI: How accurate are they when tested on independent cohorts? – A systematic review. Diagn Interv Imaging 2022; 104:221-234. [PMID: 36517398 DOI: 10.1016/j.diii.2022.11.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2022] [Accepted: 11/22/2022] [Indexed: 12/14/2022]
Abstract
PURPOSE The purpose of this study was to perform a systematic review of the literature on the diagnostic performance, in independent test cohorts, of artificial intelligence (AI)-based algorithms aimed at characterizing/detecting prostate cancer on magnetic resonance imaging (MRI). MATERIALS AND METHODS Medline, Embase and Web of Science were searched for studies published between January 2018 and September 2022, using a histological reference standard, and assessing prostate cancer characterization/detection by AI-based MRI algorithms in test cohorts composed of more than 40 patients and with at least one of the following independency criteria as compared to the training cohort: different institution, different population type, different MRI vendor, different magnetic field strength or strict temporal splitting. RESULTS Thirty-five studies were selected. The overall risk of bias was low. However, 23 studies did not use predefined diagnostic thresholds, which may have optimistically biased the results. Test cohorts fulfilled one to three of the five independency criteria. The diagnostic performance of the algorithms used as standalones was good, challenging that of human reading. In the 12 studies with predefined diagnostic thresholds, radiomics-based computer-aided diagnosis systems (assessing regions-of-interest drawn by the radiologist) tended to provide more robust results than deep learning-based computer-aided detection systems (providing probability maps). Two of the six studies comparing unassisted and assisted reading showed significant improvement due to the algorithm, mostly by reducing false positive findings. CONCLUSION Prostate MRI AI-based algorithms showed promising results, especially for the relatively simple task of characterizing predefined lesions. The best management of discrepancies between human reading and algorithm findings still needs to be defined.
Collapse
Affiliation(s)
- Olivier Rouvière
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon 69003, France; Université Lyon 1, Faculté de médecine Lyon Est, Lyon 69003, France; LabTAU, INSERM, U1032, Lyon 69003, France.
| | | | - Pierre Baseilhac
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon 69003, France
| | - Mohammed Lamine Benomar
- LabTAU, INSERM, U1032, Lyon 69003, France; University of Ain Temouchent, Faculty of Science and Technology, Algeria
| | - Raphael Escande
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Vascular and Urinary Imaging, Lyon 69003, France
| | - Sébastien Crouzet
- Université Lyon 1, Faculté de médecine Lyon Est, Lyon 69003, France; LabTAU, INSERM, U1032, Lyon 69003, France; Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Urology, Lyon 69003, France
| | | |
Collapse
|
14
|
Li C, Li W, Liu C, Zheng H, Cai J, Wang S. Artificial intelligence in multi-parametric magnetic resonance imaging: A review. Med Phys 2022; 49:e1024-e1054. [PMID: 35980348 DOI: 10.1002/mp.15936] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Revised: 08/01/2022] [Accepted: 08/04/2022] [Indexed: 11/06/2022] Open
Abstract
Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Cheng Li
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China
| | - Wen Li
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Chenyang Liu
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Hairong Zheng
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China
| | - Jing Cai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Shanshan Wang
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.,Peng Cheng Laboratory, Shenzhen, 518066, China.,Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, 510080, China
| |
Collapse
|
15
|
Labus S, Altmann MM, Huisman H, Tong A, Penzkofer T, Choi MH, Shabunin I, Winkel DJ, Xing P, Szolar DH, Shea SM, Grimm R, von Busch H, Kamen A, Herold T, Baumann C. A concurrent, deep learning-based computer-aided detection system for prostate multiparametric MRI: a performance study involving experienced and less-experienced radiologists. Eur Radiol 2022; 33:64-76. [PMID: 35900376 DOI: 10.1007/s00330-022-08978-y] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2022] [Revised: 06/16/2022] [Accepted: 06/21/2022] [Indexed: 11/04/2022]
Abstract
OBJECTIVES To evaluate the effect of a deep learning-based computer-aided diagnosis (DL-CAD) system on experienced and less-experienced radiologists in reading prostate mpMRI. METHODS In this retrospective, multi-reader multi-case study, a consecutive set of 184 patients examined between 01/2018 and 08/2019 were enrolled. Ground truth was combined targeted and 12-core systematic transrectal ultrasound-guided biopsy. Four radiologists, two experienced and two less-experienced, evaluated each case twice, once without (DL-CAD-) and once assisted by DL-CAD (DL-CAD+). ROC analysis, sensitivities, specificities, PPV and NPV were calculated to compare the diagnostic accuracy for the diagnosis of prostate cancer (PCa) between the two groups (DL-CAD- vs. DL-CAD+). Spearman's correlation coefficients were evaluated to assess the relationship between PI-RADS category and Gleason score (GS). Also, the median reading times were compared for the two reading groups. RESULTS In total, 172 patients were included in the final analysis. With DL-CAD assistance, the overall AUC of the less-experienced radiologists increased significantly from 0.66 to 0.80 (p = 0.001; cutoff ISUP GG ≥ 1) and from 0.68 to 0.80 (p = 0.002; cutoff ISUP GG ≥ 2). Experienced radiologists showed an AUC increase from 0.81 to 0.86 (p = 0.146; cutoff ISUP GG ≥ 1) and from 0.81 to 0.84 (p = 0.433; cutoff ISUP GG ≥ 2). Furthermore, the correlation between PI-RADS category and GS improved significantly in the DL-CAD + group (0.45 vs. 0.57; p = 0.03), while the median reading time was reduced from 157 to 150 s (p = 0.023). CONCLUSIONS DL-CAD assistance increased the mean detection performance, with the most significant benefit for the less-experienced radiologist; with the help of DL-CAD less-experienced radiologists reached performances comparable to that of experienced radiologists. KEY POINTS • DL-CAD used as a concurrent reading aid helps radiologists to distinguish between benign and cancerous lesions in prostate MRI. • With the help of DL-CAD, less-experienced radiologists may achieve detection performances comparable to that of experienced radiologists. • DL-CAD assistance increases the correlation between PI-RADS category and cancer grade.
Collapse
Affiliation(s)
- Sandra Labus
- Department of Radiology, Helios Klinikum Berlin-Buch, Schwanebecker Ch 50, 13125, Berlin, Germany.
| | - Martin M Altmann
- Department of Radiology, Helios Klinikum Berlin-Buch, Schwanebecker Ch 50, 13125, Berlin, Germany
| | - Henkjan Huisman
- Radboud University Medical Center, Nijmegen, The Netherlands
| | - Angela Tong
- Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA
| | | | - Moon Hyung Choi
- Eunpyeong St. Mary's Hospital, The Catholic University of Korea, Seoul, Republic of Korea
| | | | - David J Winkel
- Department of Radiology, University Hospital of Basel, Basel, Switzerland
| | - Pengyi Xing
- Department of Radiology, Changhai Hospital, Shanghai, China
| | | | | | - Robert Grimm
- Diagnostic Imaging, Siemens Healthcare, Erlangen, Germany
| | | | - Ali Kamen
- Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ, USA
| | - Thomas Herold
- Department of Radiology, Helios Klinikum Berlin-Buch, Schwanebecker Ch 50, 13125, Berlin, Germany
| | - Clemens Baumann
- Department of Radiology, Helios Klinikum Berlin-Buch, Schwanebecker Ch 50, 13125, Berlin, Germany
| |
Collapse
|
16
|
Nowier A, Mazhar H, Salah R, Shabayek M. Performance of multi-parametric magnetic resonance imaging through PIRADS scoring system in biopsy naïve patients with suspicious prostate cancer. Arab J Urol 2022; 20:121-125. [PMID: 35935910 PMCID: PMC9354643 DOI: 10.1080/2090598x.2022.2067615] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
Background Use of multi-parametric magnetic resonance imaging (mp-MRI) and Prostate Imaging Reporting and Data System (PI-RADS) scoring system allowed more precise detection of prostate cancer (PCa). Our study aimed at evaluating the diagnostic performance of mp-MRI in detection of PCa. Methods Eighty-six patients suspected to have prostate cancer were enrolled. All patients underwent mp-MRI followed by systematic and targeted trans-rectal ultrasound (TRUS) guided prostate biopsies. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of mp-MRI were evaluated. Results Forty-six patients (53.5%) had prostate cancer on targeted and systematic TRUS biopsies. On mp-MRI, 96.6% of lesions with PI-RADS < 3 revealed to be benign by TRUS biopsy, 73.3% of lesions with PI-RADS 4 showed ISUP grades ≥1, whereas all PI-RADS 5 lesions showed high ISUP grades ≥ 3. For PI-RADS 3 lesions, 62.5% of them revealed to be benign and 37.5% showed ISUP grades ≥1 by TRUS biopsy. PI-RADS scores ˃3 had 69.57% sensitivity and 85% specificity for detection of PCa. On adding the equivocal PI-RADS 3 lesions, PI-RADS scores ≥3 had higher sensitivity (97.83%), but at the cost of lower specificity (32.5%). Conclusion Mp-MRI using PI-RADS V2 scoring system categories ≤3 and >3 could help in detection of PCa. PI-RADS 3 lesions are equivocal. Including PI-RADS lesions ≥3 demonstrated higher sensitivity, but at the cost of lower specificity for mp-MRI in diagnosis for Pca. Abbreviations CDR: cancer detection rates; DRE: digital rectal examination; ISUP: international society of urological pathology; mp-MRI: multi-parametric magnetic resonance imaging; NPV: negative predictive value; PCa: prosatate cancer; PI-RADS: Prostate Imaging Reporting and Data System; PPV: Positive predictive value; PSA: prostate specific antigen; TRUS: transrectal ultrasound.
Collapse
Affiliation(s)
- Amr Nowier
- Department of Urology, Faculty of Medicine Ain-Shams University, Cairo, Egypt
| | - Hesham Mazhar
- Department of Urology, Faculty of Medicine Ain-Shams University, Cairo, Egypt
| | - Rasha Salah
- Department of Radiology, Faculty of Medicine, Ain-Shams University, Cairo, Egypt
| | - Mohamed Shabayek
- Department of Urology, Faculty of Medicine Ain-Shams University, Cairo, Egypt
| |
Collapse
|
17
|
Piotrowski A, Siegel F. [What can machines do?]. ACTA ACUST UNITED AC 2021;:1-6. [PMID: 34729002 DOI: 10.1007/s41972-021-00148-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/06/2021] [Indexed: 11/08/2022]
Abstract
Mit zunehmender Rechen- und Speicherkapazität hält in der Medizin fast unaufhaltsam die Anwendung von Big Data und künstlicher Intelligenz Einzug. Haupteinsatzgebiete sind bisher v. a. in der Radiologie und Pathologie, jedoch auch in weiteren Bereichen wie der Genomsequenzierung bis hin zur Psychiatrie zu finden. Durch die Auswertung von immer größeren Datenmengen wird nach Mustern gesucht, die die Arbeit der Ärzte erleichtern können, indem sie eine Vorselektion betreiben. Darüber hinaus bestehen auch Bemühungen bisher unerkannte Zusammenhänge aufzudecken. Große Datenmengen werden von den Patienten selbst über sog. Wearables erfasst. Wie können diese Daten sinnvoll genutzt werden? Welche Gefahren bestehen? Auch in der Urologie gibt es Bestrebungen, eine Verbesserung der Behandlung von z. B. Harnwegsinfektionen oder Nierensteinen durch den Einsatz von vernetzten Computersystemen zu erreichen. Auf dem Gebiet von Big Data und Künstlicher Intelligenz sind in den nächsten Jahren große Fortschritte zu erwarten. Es wird auch zu einer erheblichen Erweiterung der Einsatzgebiete kommen, und wir sind somit erst am Anfang der Entwicklung.
Collapse
|