1
|
Roest C, Fransen SJ, Kwee TC, Yakar D. Comparative Performance of Deep Learning and Radiologists for the Diagnosis and Localization of Clinically Significant Prostate Cancer at MRI: A Systematic Review. Life (Basel) 2022; 12:life12101490. [PMID: 36294928 PMCID: PMC9605624 DOI: 10.3390/life12101490] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Revised: 09/19/2022] [Accepted: 09/20/2022] [Indexed: 11/16/2022] Open
Abstract
Background: Deep learning (DL)-based models have demonstrated an ability to automatically diagnose clinically significant prostate cancer (PCa) on MRI scans and are regularly reported to approach expert performance. The aim of this work was to systematically review the literature comparing deep learning (DL) systems to radiologists in order to evaluate the comparative performance of current state-of-the-art deep learning models and radiologists. Methods: This systematic review was conducted in accordance with the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Studies investigating DL models for diagnosing clinically significant (cs) PCa on MRI were included. The quality and risk of bias of each study were assessed using the checklist for AI in medical imaging (CLAIM) and QUADAS-2, respectively. Patient level and lesion-based diagnostic performance were separately evaluated by comparing the sensitivity achieved by DL and radiologists at an identical specificity and the false positives per patient, respectively. Results: The final selection consisted of eight studies with a combined 7337 patients. The median study quality with CLAIM was 74.1% (IQR: 70.6–77.6). DL achieved an identical patient-level performance to the radiologists for PI-RADS ≥ 3 (both 97.7%, SD = 2.1%). DL had a lower sensitivity for PI-RADS ≥ 4 (84.2% vs. 88.8%, p = 0.43). The sensitivity of DL for lesion localization was also between 2% and 12.5% lower than that of the radiologists. Conclusions: DL models for the diagnosis of csPCa on MRI appear to approach the performance of experts but currently have a lower sensitivity compared to experienced radiologists. There is a need for studies with larger datasets and for validation on external data.
Collapse
|
2
|
Prostate minimally invasive procedures: complications and normal vs. abnormal findings on multiparametric magnetic resonance imaging (mpMRI). ABDOMINAL RADIOLOGY (NEW YORK) 2021; 46:4388-4400. [PMID: 33977352 PMCID: PMC8346422 DOI: 10.1007/s00261-021-03097-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Revised: 03/29/2021] [Accepted: 04/19/2021] [Indexed: 11/25/2022]
Abstract
Minimally invasive alternatives to traditional prostate surgery are increasingly utilized to treat benign prostatic hyperplasia and localized prostate cancer in select patients. Advantages of these treatments over prostatectomy include lower risk of complication, shorter length of hospital stay, and a more favorable safety profile. Multiparametric magnetic resonance imaging (mpMRI) has become a widely accepted imaging modality for evaluation of the prostate gland and provides both anatomical and functional information. As prostate mpMRI and minimally invasive prostate procedure volumes increase, it is important for radiologists to be familiar with normal post-procedure imaging findings and potential complications. This paper reviews the indications, procedural concepts, common post-procedure imaging findings, and potential complications of prostatic artery embolization, prostatic urethral lift, irreversible electroporation, photodynamic therapy, high-intensity focused ultrasound, focal cryotherapy, and focal laser ablation.
Collapse
|
3
|
Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review. Cancers (Basel) 2021; 13:cancers13030552. [PMID: 33535569 PMCID: PMC7867056 DOI: 10.3390/cancers13030552] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2020] [Revised: 01/18/2021] [Accepted: 01/27/2021] [Indexed: 12/11/2022] Open
Abstract
Simple Summary The increasing interest in implementing artificial intelligence in radiomic models has occurred alongside advancement in the tools used for computer-aided diagnosis. Such tools typically apply both statistical and machine learning methodologies to assess the various modalities used in medical image analysis. Specific to prostate cancer, the radiomics pipeline has multiple facets that are amenable to improvement. This review discusses the steps of a magnetic resonance imaging based radiomics pipeline. Present successes, existing opportunities for refinement, and the most pertinent pending steps leading to clinical validation are highlighted. Abstract The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.
Collapse
|
4
|
Wadera A, Alabousi M, Pozdnyakov A, Kashif Al-Ghita M, Jafri A, McInnes MD, Schieda N, van der Pol CB, Salameh JP, Samoilov L, Gusenbauer K, Alabousi A. Impact of PI-RADS Category 3 lesions on the diagnostic accuracy of MRI for detecting prostate cancer and the prevalence of prostate cancer within each PI-RADS category: A systematic review and meta-analysis. Br J Radiol 2020; 94:20191050. [PMID: 33002371 DOI: 10.1259/bjr.20191050] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022] Open
Abstract
OBJECTIVE To evaluate Prostate Imaging Reporting and Data System (PI-RADS) category 3 lesions' impact on the diagnostic test accuracy (DTA) of MRI for prostate cancer (PC) and to derive the prevalence of PC within each PI-RADS category. METHODS MEDLINE and Embase were searched until April 10, 2020 for studies reporting on the DTA of MRI by PI-RADS category. Accuracy metrics were calculated using a bivariate random-effects meta-analysis with PI-RADS three lesions treated as a positive test, negative test, and excluded from the analysis. Differences in DTA were assessed utilizing meta-regression. PC prevalence within each PI-RADS category was estimated with a proportional meta-analysis. RESULTS In total, 26 studies reporting on 12,913 patients (4,853 with PC) were included. Sensitivities for PC in the positive, negative, and excluded test groups were 96% (95% confidence interval [CI] 92-98), 82% (CI 75-87), and 95% (CI 91-97), respectively. Specificities for the positive, negative, and excluded test groups were 33% (CI 23-44), 71% (CI 62-79), and 52% (CI 37-66), respectively. Meta-regression demonstrated higher sensitivity (p < 0.001) and lower specificity (p < 0.001) in the positive test group compared to the negative group. Clinically significant PC prevalences were 5.9% (CI 0-17.1), 11.4% (CI 6.5-17.3), 24.9% (CI 18.4-32.0), 55.7% (CI 47.8-63.5), and 81.4% (CI 75.9-86.4) for PI-RADS categories 1, 2, 3, 4 and 5, respectively. CONCLUSION PI-RADS category 3 lesions can significantly impact the DTA of MRI for PC detection. A low prevalence of clinically significant PC is noted in PI-RADS category 1 and 2 cases. ADVANCES IN KNOWLEDGE Inclusion or exclusion of PI-RADS category 3 lesions impacts the DTA of MRI for PC detection.
Collapse
Affiliation(s)
- Akshay Wadera
- Department of Radiology, McMaster University, Hamilton, ON, Canada
| | - Mostafa Alabousi
- Department of Radiology, McMaster University, Hamilton, ON, Canada
| | - Alex Pozdnyakov
- Faculty of Medicine, McMaster University, Hamilton, ON, Canada
| | | | - Ali Jafri
- Department of Medicine, New York Institute of Technology School of Osteopathic Medicine, Glen Head, NY, United States
| | - Matthew Df McInnes
- The Ottawa Hospital Research Institute, Clinical Epidemiology Program, Ottawa, ON, Canada.,Department of Radiology, University of Ottawa, The Ottawa Hospital, Ottawa, ON, Canada
| | - Nicola Schieda
- Department of Radiology, University of Ottawa, The Ottawa Hospital, Ottawa, ON, Canada
| | | | - Jean-Paul Salameh
- Department of Medicine, Clinical Epidemiology and Public Health, University of Ottawa, Ottawa, ON, Canada
| | - Lucy Samoilov
- Department of Radiology, McMaster University, Hamilton, ON, Canada
| | | | - Abdullah Alabousi
- Department of Radiology, McMaster University, St. Joseph's Healthcare Hamilton, Hamilton, ON, Canada
| |
Collapse
|
5
|
Bardis MD, Houshyar R, Chang PD, Ushinsky A, Glavis-Bloom J, Chahine C, Bui TL, Rupasinghe M, Filippi CG, Chow DS. Applications of Artificial Intelligence to Prostate Multiparametric MRI (mpMRI): Current and Emerging Trends. Cancers (Basel) 2020; 12:E1204. [PMID: 32403240 PMCID: PMC7281682 DOI: 10.3390/cancers12051204] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Revised: 05/02/2020] [Accepted: 05/08/2020] [Indexed: 01/13/2023] Open
Abstract
Prostate carcinoma is one of the most prevalent cancers worldwide. Multiparametric magnetic resonance imaging (mpMRI) is a non-invasive tool that can improve prostate lesion detection, classification, and volume quantification. Machine learning (ML), a branch of artificial intelligence, can rapidly and accurately analyze mpMRI images. ML could provide better standardization and consistency in identifying prostate lesions and enhance prostate carcinoma management. This review summarizes ML applications to prostate mpMRI and focuses on prostate organ segmentation, lesion detection and segmentation, and lesion characterization. A literature search was conducted to find studies that have applied ML methods to prostate mpMRI. To date, prostate organ segmentation and volume approximation have been well executed using various ML techniques. Prostate lesion detection and segmentation are much more challenging tasks for ML and were attempted in several studies. They largely remain unsolved problems due to data scarcity and the limitations of current ML algorithms. By contrast, prostate lesion characterization has been successfully completed in several studies because of better data availability. Overall, ML is well situated to become a tool that enhances radiologists' accuracy and speed.
Collapse
Affiliation(s)
- Michelle D. Bardis
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Roozbeh Houshyar
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Peter D. Chang
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Alexander Ushinsky
- Mallinckrodt Institute of Radiology, Washington University Saint Louis, St. Louis, MO 63110, USA;
| | - Justin Glavis-Bloom
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Chantal Chahine
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Thanh-Lan Bui
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | - Mark Rupasinghe
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| | | | - Daniel S. Chow
- Department of Radiology, University of California, Irvine, Orange, CA 92868-3201, USA; (R.H.); (P.D.C.); (J.G.-B.); (C.C.); (T.-L.B.); (M.R.); (D.S.C.)
| |
Collapse
|