Podcast: Covid-19 in Italy
By Andrea Gavazzi, Urological Surgeon, Florence, Italy
BJUI Podcasts are available on iTunes: https://itunes.apple.com/gb/podcast/bju-international/id1309570262
Posts
What’s the diagnosis?
This image is taken from Chen et al, BJUI 2020
Article of the week: External validation of novel magnetic resonance imaging‐based models for prostate cancer prediction
Every week, the Editor-in-Chief selects an Article of the Week from the current issue of BJUI. The abstract is reproduced below and you can click on the button to read the full article, which is freely available to all readers for at least 30 days from the time of this post.
In addition to this post, there is an editorial written by a prominent member of the urological community and a visual abstract created by trainee urologists. Please use the comment buttons below to join the conversation.
If you only have time to read one article this week, we recommend this one.
External validation of novel magnetic resonance imaging‐based models for prostate cancer prediction
Lukas Püllen*, Jan P. Radtke*†, Manuel Wiesenfarth‡, Monique J. Roobol§, Jan F.M. Verbeek§, Axel Wetter¶, Nika Guberina¶, Abhishek Pandey**, Clemens Hüttenbrink**, Stephan Tschirdewahn*, Sascha Pahernik**, Boris A. Hadaschik* and Florian A. Distler**
*Department of Urology, University Hospital Essen, Nordrhein-Westfalen, †Department of Radiology, German Cancer Research Centre (DKFZ), ‡Division of Biostatistics, German Cancer Research Centre (DKFZ), Heidelberg, Germany, §Department of Urology, Erasmus University Medical Centre, Rotterdam, The Netherlands, ¶Department of Radiology, University Hospital Essen, Nordrhein-Westfalen, and **Department of Urology, Paracelsus Medical University, Nuremberg, Nürnberg, Germany
Abstract
Objectives
To validate, in an external cohort, three novel risk models, including the recently updated European Randomized Study of Screening for Prostate Cancer (ERSPC) risk calculator, that combine multiparametric magnetic resonance imaging (mpMRI) and clinical variables to predict clinically significant prostate cancer (PCa).
Patients and Methods
We retrospectively analysed 307 men who underwent mpMRI prior to transperineal ultrasound fusion biopsy between October 2015 and July 2018 at two German centres. mpMRI was rated by Prostate Imaging Reporting and Data System (PI‐RADS) v2.0 and clinically significant PCa was defined as International Society of Urological Pathology Gleason grade group ≥2. The prediction performance of the three models (MRI‐ERSPC‐3/4, and two risk models published by Radtke et al. and Distler et al., ModRad and ModDis) were compared using receiver‐operating characteristic (ROC) curve analyses, with area under the ROC curve (AUC), calibration curve analyses and decision curves used to assess net benefit.
Results
The AUCs of the three novel models (MRI‐ERSPC‐3/4, ModRad and ModDis) were 0.82, 0.85 and 0.83, respectively. Calibration curve analyses showed the best intercept for MRI‐ERSPC‐3 and ‐4 of 0.35 and 0.76. Net benefit analyses indicated clear benefit of the MRI‐ERSPC‐3/4 risk models compared with the other two validated models. The MRI‐ERSPC‐3/4 risk models demonstrated a discrimination benefit for a risk threshold of up to 15% for clinically significant PCa as compared to the other risk models.
Conclusion
In our external validation of three novel prostate cancer risk models, which incorporate mpMRI findings, a head‐to‐head comparison indicated that the MRI‐ERSPC‐3/4 risk model in particular could help to reduce unnecessary biopsies.
Editorial: Magnetic resonance imaging as a personalised tool to safely avoid prostate biopsy
Identifying men at risk of developing clinically significant prostate cancer (csPCa) who are either biopsy naïve or have undergone a prior negative systematic biopsy remains a dilemma for urologists seeking to utilise clinical resources in a cost‐conscious and safe manner. Clinical and demographic factors including DRE findings, serum PSA concentrations, race/ethnicity, and family history, guide shared decision‐making to pursue an initial or repeat prostate biopsy. Despite thoughtful risk assessments, the screening tools implemented often lead to biopsies where a majority demonstrates benign pathology findings or indolent forms of PCa that would not mandate immediate, definitive intervention. Hence, various risk models (RMs) have been proposed to stratify men who have a greater likelihood of harbouring csPCa, and several now incorporate findings from multiparametric MRI (mpMRI) by assessing suspicious lesion characteristics into their algorithms. While promising, most of these models were generated using single‐institution retrospective data and lack the external validation that could make them more generalisable and widely adopted in clinical practice.
In the present issue, Püllen et al. [1] evaluate three RMs that incorporate mpMRI findings using a cohort of 307 men who were biopsy naïve or had previously undergone a negative prostate biopsy. Risk of csPCa according to the MRI‐European Randomized Prostate Screening for Prostate Cancer Risk Calculators 3 and 4 (MRI‐ERSPC‐3/4) [2], Radtke’s RM (ModRAD) [3], and Distler’s RM (ModDis) [4] were compared to final pathology after TRUS‐guided perineal prostate biopsy with MRI‐fusion targeted sampling, as indicated using a Prostate Imaging‐Reporting and Data System version 2 (PI‐RADSv2) score ≥3 as the threshold.
The cohort had a median age of 67 years, median PSA concentration of 8.8 ng/mL, and there were 453 PI‐RADSv2 ≥3 lesions, which is consistent with a typical at‐risk screening population. Amongst these men, 134 (40%) harboured csPCa defined as a Gleason Grade Group ≥2. All three RMs performed similarly on receiver operating curve analyses with area under the curve for prediction nearing 0.85 for finding csPCa in both biopsy naïve and prior negative‐biopsy patients. Using a 15% risk threshold, the adapted MRI‐ERSPC‐3/4 RM would have safely avoided 30% of biopsies with 6% of csPCa diagnoses being missed, whereas the ModRad and ModDis RMs would have only avoided 17% and 6% of unnecessary biopsies, respectively, albeit with far fewer occult cases of csPCa.
The integration of mpMRI in the pre‐biopsy setting is being more widely adopted into the clinical landscape, with emerging support largely due to its value in detecting csPCa, but also the recognised high negative predictive value potentiating the safe avoidance or deferral of prostate biopsy [5]. Performing a prostate biopsy in all men with a clinical screening positive PSA and/or DRE carries a significant public health burden, and harbours recognised clinical morbidity without definitive overall survival benefit for many. Hence, integration of MRI findings, importantly the lack of highly suspicious lesions, is of interest in RM assessment to determine which patients would be benefited most from prostate biopsy while sparing some from biopsy, without compromising detection of csPCa and oncological outcomes.
For patients who forgo prostate biopsy based upon factors such as nomogram‐predicted risk of harbouring csPCa, the appropriate timing for performing repeat evaluation with biomarkers and/or MRI is not well defined. Various models have shown much higher rates of biopsy avoidance if accepting some level of missed csPCa [6]. With the awareness that some men who would theoretically avoid a biopsy based on these RMs may actually harbour csPCa, should these men undergo repeat MRI as standard or would serial PSA assessment drive biopsy detection of their csPCa with adequate lead time for definitive treatment? Prospective investigations assessing the clinical course of patients with negative MRI findings who avoid or defer biopsy are critical to determine the real‐world applicability of such RMs. The true value of these RMs and nomograms should balance their public health cost and morbidity benefit with potential oncological risk.
by Zachary A. Glaser and Soroush Rais‐Bahrami
References
- , , et al. External validation of novel magnetic resonance imaging‐based models for prostate cancer prediction. BJU Int 2020; 125: 407– 16
- , , et al. Prediction of high‐grade prostate cancer following multiparametric magnetic resonance imaging: improving the Rotterdam European randomized study of screening for prostate cancer risk calculators. Eur Urol 2019; 75: 310– 8
- , , et al. Combined clinical parameters and multiparametric magnetic resonance imaging for advanced risk modeling of prostate cancer‐patient‐tailored risk stratification can reduce unnecessary biopsies. Eur Urol 2017; 72: 888– 96
- , , et al. The value of PSA density in combination with PI‐RADS for the accuracy of prostate cancer prediction. J Urol 2017; 198: 575– 82
- , , et al. Comparison of MR/ultrasound fusion‐guided biopsy with ultrasound‐guided biopsy for the diagnosis of prostate cancer. JAMA 2015; 313: 390– 7
- , , et al. A Magnetic resonance imaging‐based prediction model for prostate biopsy risk stratification. JAMA Oncol 2018; 4: 678– 85
Article of the month: Guideline of guidelines: social media in urology
Every month, the Editor-in-Chief selects an Article of the Month from the current issue of BJUI. The abstract is reproduced below and you can click on the button to read the full article, which is freely available to all readers for at least 30 days from the time of this post. For more guide Click here touroftoowoomba .
In addition to the article itself, there is a visual abstract prepared by members of the urological community, and a video recorded by the authors; we invite you to use the comment tools at the bottom of each post to join the conversation.
If you only have time to read one article this month, we recommend this one.
Guideline of guidelines: social media in urology
Jacob Taylor*, Stacy Loeb*†‡
*Department of Urology, †Population Health, NYU School of Medicine, and ‡Manhattan Veterans Affairs Medical Center, New York, NY, USA
Abstract
The use of social media is rapidly expanding. This technology revolution is changing the way healthcare providers share information with colleagues, patients, and other stakeholders. As social media use increases in urology, maintaining a professional online identity and interacting appropriately with one’s network are vital to engaging positively and protecting patient health information. There are many opportunities for collaboration and exchange of ideas, but pitfalls exist without adherence to proper online etiquette. The purpose of this article is to review professional guidelines on the use of social media in urology, and outline best practice principles that urologists and other healthcare providers can reference when engaging in online networks.
Video: Guideline of guidelines: social media in urology
Guideline of guidelines: social media in urology
Abstract
The use of social media is rapidly expanding. This technology revolution is changing the way healthcare providers share information with colleagues, patients, and other stakeholders. As social media use increases in urology, maintaining a professional online identity and interacting appropriately with one’s network are vital to engaging positively and protecting patient health information. There are many opportunities for collaboration and exchange of ideas, but pitfalls exist without adherence to proper online etiquette. The purpose of this article is to review professional guidelines on the use of social media in urology, and outline best practice principles that urologists and other healthcare providers can reference when engaging in online networks.
Article of the week: Using spatial tracking with magnetic resonance imaging/ultrasound‐guided biopsy to identify unilateral prostate cancer
Every week, the Editor-in-Chief selects an Article of the Week from the current issue of BJUI. The abstract is reproduced below and you can click on the button to read the full article, which is freely available to all readers for at least 30 days from the time of this post.
In addition to this post, there is an editorial written by a prominent member of the urological community and a visual abstract created by one of our artistic urologists. Please use the comment buttons below to join the conversation.
If you only have time to read one article this week, we recommend this one.
Using spatial tracking with magnetic resonance imaging/ultrasound‐guided biopsy to identify unilateral prostate cancer
Steve R. Zhou*, Alan M. Priester†‡, Rajiv Jayadevan†, David C. Johnson§, Jason J. Yang*, Jorge Ballon*, Shyam Natarajan†‡ and Leonard S. Marks†
*David Geffen School of Medicine, University of California, †Department of Urology, University of California, ‡Department of Bioengineering, University of California, Los Angeles, CA, and §Department of Urology, University of
North Carolina, Chapel Hill, NC, USA
Abstract
Objectives
To create reliable predictive metrics of unilateral disease using spatial tracking from a fusion device, thereby improving patient selection for hemi‐gland ablation of prostate cancer.
Patients and Methods
We identified patients who received magnetic resonance imaging (MRI)/ultrasound‐guided biopsy and radical prostatectomy at a single institution between 2011 and 2018. In addition to standard clinical features, we extracted quantitative features related to biopsy core and MRI target locations predictive of tumour unilaterality. Classification and Regression Tree (CART) analysis was used to create a decision tree (DT) for identifying cancer laterality. We evaluated concordance of model‐determined laterality with final surgical pathology.
Results
A total of 173 patients were identified with biopsy coordinates and surgical pathology available. Based on CART analysis, in addition to biopsy‐ and MRI‐confirmed disease unilaterality, patients should be further screened for cancer detected within 7 mm of midline in a 40 mL prostate, which equates to the central third of any‐sized prostate by radius. The area under the curve for this DT was 0.82. Standard diagnostics and the DT correctly identified disease laterality in 73% and 80% of patients, respectively (P = 0.13). Of the patients identified as unilateral by standard diagnostics, 47% had undetected contralateral disease or were otherwise incorrectly identified. This error rate was reduced to 17% (P = 0.01) with the DT.
Conclusion
Using spatial tracking from fusion devices, a DT was more reliable for identifying laterality of prostate cancer compared to standard diagnostics. Patients with cancer detected within the central third of the prostate by radius are poor hemi‐gland ablation candidates due to the risk of midline extension of tumour.
Editorial: Can artificial intelligence optimize case selection for hemi‐gland ablation?
The victory of ‘AlphaGo’ over humans in Go, one of the most complex games with more than 10170 board configurations, has yielded tremendous attention worldwide [1]. The later version, ‘AlphaGo Zero’, has brought artificial intelligence (AI) to the next level by demonstrating an absolute superiority, winning 100‐0 against the champion‐defeating AlphaGo [2]. It is exciting, and perhaps shocking, to realize what AI can achieve.
In this issue of BJUI, the study by Zhou et al. [3] is the first to utilize AI to optimize case selection for hemi‐gland ablation. In this study, classification and regression tree (CART) analysis, which is a form of supervised machine‐learning algorithm, was used to identify laterality of prostate cancer. In the conventional approach, case selection was based on biopsy results and MRI findings. For the CART model, in addition to the common clinical variables (i.e. age, PSA, prostate volume, biopsy and MRI results), biopsy coordinate‐derived spatial features were also used as model inputs. The model output was the probability of unilateral clinically significant prostate cancer considered suitable for hemi‐gland ablation. Whole‐mount prostatectomy specimens were used as the standard of reference. The CART model correctly identified laterality in 80% of the cases, compared to 73% with the conventional approach. The positive predictive value of the CART model was 83%, compared to 53% with the conventional approach. The superiority of the CART model has been demonstrated, and the area under curve was 0.82.
Artifical intelligence has been widely adopted in the field of Urology [4]. For prostate cancer detection in particular, our group evaluated the diagnostic performances of four machine‐learning models based on clinical variables in a biopsy cohort of 1625 men [5]. The machine‐learning models achieved excellent performances in detecting clinically significant prostate cancer, with an accuracy of up to 95.3%. Algohary et al. [6] constructed three machine‐learning models to identify the presence of clinically significant prostate cancer based on MRI radiomic features in patients who underwent active surveillance. When compared with the Prostate Imaging–Reporting and Data System (PI‐RADS) scoring system, the machine‐learning models were able to improve overall accuracy by 30–80%.
Fehr et al. [7] developed an automated system to classify Gleason scores based on MRI images. The automated system could distinguish between Gleason scores of 6 and 7 or above cancers with an accuracy of up to 93%. The differentiation between Gleason score 3+4 and 4+3 disease also yielded an accuracy of up to 93%. Importantly, the performance of AI and machine‐learning models is highly dependent on the quality and accuracy of the data being input. In terms of prostate cancer detection, either mapping biopsy or whole‐mount prostatectomy specimens should be considered to represent the ‘ground truth’.
There are a number of challenges in implementing AI in clinical practice. First, decision‐making in healthcare requires logical deduction and explanation. The data processing in AI, however, is often described as a ‘black box’. Taking AlphaGo as an example, some ‘moves’ were considered incomprehensible even by world‐class players. Second, although results from AI are promising, there is in general a lack of regulations and standards to assess its safety, efficacy and validity. Liability issues can be problematic in case of medical mishaps. Third, doctors are human. Conflict of interest does exist, and how we can utilize AI in a complementary rather than a competitive manner is a challenging obstacle to overcome.
Nevertheless, AI has huge potential in improving healthcare. Collaborative effort is needed globally to develop and optimize AI systems, and to increase its acceptability and practicality upon implementation. Future studies answering clinically important questions using appropriate standards of reference will be of paramount importance in paving the way for the AI era in urology.
by Jeremy Yuen‐Chun Teoh, Edmund Chiong and Chi‐Fai Ng
References
- , , et al. Mastering the game of Go with deep neural networks and tree search. Nature 2016; 529: 484– 9
- , , et al. Mastering the game of Go without human knowledge. Nature 2017; 550: 354– 9
- , , et al. Using spatial tracking with magnetic resonance imaging/ultrasound‐guided biopsy to identify unilateral prostate cancer. BJU Int 2020; 125: 399– 406
- , , et al. Current status of artificial intelligence applications in urology and their potential to influence clinical practice. BJU Int 2019; 124: 567– 77
- , , . Diagnosis of prostate cancer in a Chinese population by using machine learning methods. Conf Proc IEEE Eng Med Biol Soc 2018; 2018: 1– 4
- , , et al. Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings. J Magn Reson Imaging 2018; 48: 818– 28
- , , et al. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci USA 2015; 112: E6265– 73