1
|
Paulson N, Zeevi T, Papademetris M, Leapman MS, Onofrey JA, Sprenkle PC, Humphrey PA, Staib LH, Levi AW. Prediction of Adverse Pathology at Radical Prostatectomy in Grade Group 2 and 3 Prostate Biopsies Using Machine Learning. JCO Clin Cancer Inform 2022; 6:e2200016. [PMID: 36179281 DOI: 10.1200/cci.22.00016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
PURPOSE There is ongoing clinical need to improve estimates of disease outcome in prostate cancer. Machine learning (ML) approaches to pathologic diagnosis and prognosis are a promising and increasingly used strategy. In this study, we use an ML algorithm for prediction of adverse outcomes at radical prostatectomy (RP) using whole-slide images (WSIs) of prostate biopsies with Grade Group (GG) 2 or 3 disease. METHODS We performed a retrospective review of prostate biopsies collected at our institution which had corresponding RP, GG 2 or 3 disease one or more cores, and no biopsies with higher than GG 3 disease. A hematoxylin and eosin-stained core needle biopsy from each site with GG 2 or 3 disease was scanned and used as the sole input for the algorithm. The ML pipeline had three phases: image preprocessing, feature extraction, and adverse outcome prediction. First, patches were extracted from each biopsy scan. Subsequently, the pre-trained Visual Geometry Group-16 convolutional neural network was used for feature extraction. A representative feature vector was then used as input to an Extreme Gradient Boosting classifier for predicting the binary adverse outcome. We subsequently assessed patient clinical risk using CAPRA score for comparison with the ML pipeline results. RESULTS The data set included 361 WSIs from 107 patients (56 with adverse pathology at RP). The area under the receiver operating characteristic curves for the ML classification were 0.72 (95% CI, 0.62 to 0.81), 0.65 (95% CI, 0.53 to 0.79) and 0.89 (95% CI, 0.79 to 1.00) for the entire cohort, and GG 2 and GG 3 patients, respectively, similar to the performance of the CAPRA clinical risk assessment. CONCLUSION We provide evidence for the potential of ML algorithms to use WSIs of needle core prostate biopsies to estimate clinically relevant prostate cancer outcomes.
Collapse
Affiliation(s)
| | - Tal Zeevi
- Yale School of Medicine, New Haven, CT
| | | | | | | | | | | | | | | |
Collapse
|
2
|
Bell PD, Teramoto Y, Gurung PMS, Yang Z, Miyamoto H. Limited Adenocarcinoma of the Prostate on Needle Core Biopsy. Arch Pathol Lab Med 2022; 146:469-477. [PMID: 35020802 DOI: 10.5858/arpa.2020-0835-oa] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/05/2021] [Indexed: 12/09/2022]
Abstract
CONTEXT.— Grading small foci of prostate cancer on a needle biopsy is often difficult, yet the clinical significance of accurate grading remains uncertain. OBJECTIVE.— To assess if grading of limited adenocarcinoma on prostate biopsy specimen is critical. DESIGN.— We studied 295 consecutive patients undergoing extended-sextant biopsy with only 1-core involvement of adenocarcinoma, followed by radical prostatectomy. RESULTS.— The linear tumor lengths on these biopsy specimens were: less than 1 mm (n = 114); 1 mm or more or less than 2 mm (n = 82); 2 mm or more or less than 3 mm (n = 35); and 3 mm or more (n = 64). Longer length was strongly associated with higher Grade Group (GG) on biopsy or prostatectomy specimen, higher risk of extraprostatic extension/seminal vesicle invasion and positive surgical margin, and larger estimated tumor volume. When cases were compared based on biopsy specimen GG, higher grade was strongly associated with higher prostatectomy specimen GG, higher incidence of pT3/pT3b disease, and larger tumor volume. Outcome analysis further showed significantly higher risks for biochemical recurrence after radical prostatectomy in patients with 1 mm or more, 2 mm or more, 3 mm or more, GG2-4, GG3-4, GG4, less than 1 mm/GG2-4, less than 1 mm/GG3-4, less than 2 mm/GG3-4, 3 mm or more/GG2-4, or 3 mm or more/GG3-4 tumor on biopsy specimens, compared with respective control subgroups. In particular, 3 mm or more, GG3, and GG4 on biopsy specimens showed significance as independent prognosticators by multivariate analysis. Meanwhile, there were no significant differences in the rate of upgrading or downgrading after radical prostatectomy among those subgrouped by biopsy specimen tumor length (eg, <1 mm [44.7%] versus ≥1/<2 mm [41.5%] versus ≥2/<3 mm [45.7%] versus ≥3 mm [46.9%]). CONCLUSIONS.— These results indicate that pathologists still need to make maximum efforts to grade relatively small prostate cancer on biopsy specimens.
Collapse
Affiliation(s)
- Phoenix D Bell
- From the Department of Pathology & Laboratory Medicine (Bell, Teramoto, Yang, Miyamoto), at the University of Rochester Medical Center, Rochester, New York
| | - Yuki Teramoto
- From the Department of Pathology & Laboratory Medicine (Bell, Teramoto, Yang, Miyamoto), at the University of Rochester Medical Center, Rochester, New York.,The James P. Wilmot Cancer Institute (Teramoto, Miyamoto), at the University of Rochester Medical Center, Rochester, New York
| | - Pratik M S Gurung
- The Department of Urology (Gurung, Miyamoto), at the University of Rochester Medical Center, Rochester, New York
| | - Zhiming Yang
- From the Department of Pathology & Laboratory Medicine (Bell, Teramoto, Yang, Miyamoto), at the University of Rochester Medical Center, Rochester, New York
| | - Hiroshi Miyamoto
- From the Department of Pathology & Laboratory Medicine (Bell, Teramoto, Yang, Miyamoto), at the University of Rochester Medical Center, Rochester, New York.,The James P. Wilmot Cancer Institute (Teramoto, Miyamoto), at the University of Rochester Medical Center, Rochester, New York.,The Department of Urology (Gurung, Miyamoto), at the University of Rochester Medical Center, Rochester, New York
| |
Collapse
|
3
|
Paulson N, Vollmer RT, Humphrey PA, Sprenkle PC, Onofrey J, Huber S, Amirkhiz K, Levi AW. Extent of High-Grade Prostatic Adenocarcinoma in Multiparametric Magnetic Resonance Imaging-Targeted Biopsy Enhances Prediction of Pathologic Stage. Arch Pathol Lab Med 2021; 146:201-204. [PMID: 34015819 DOI: 10.5858/arpa.2020-0568-oa] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/11/2021] [Indexed: 11/06/2022]
Abstract
CONTEXT.— Multiparametric magnetic resonance imaging (mpMRI) of prostate with targeted biopsy has enhanced detection of high-grade prostatic adenocarcinoma (HG PCa). However, utility of amount of HG PCa (Gleason pattern 4/5) in mpMRI-targeted biopsies versus standard 12-core biopsies in predicting adverse outcomes on radical prostatectomy (RP) is unknown. OBJECTIVE.— To examine the utility of amount of HG PCa in mpMRI-targeted biopsies versus standard 12-core biopsies in predicting adverse RP outcomes. DESIGN.— We performed a retrospective review of prostate biopsies, which had corresponding RP, 1 or more mpMRI-targeted biopsy, and grade group 2 disease or higher. For the 169 cases identified, total millimeters of carcinoma and HG PCa, and longest length HG PCa in a single core were recorded for 12-core biopsies and each set of mpMRI-targeted biopsies. For RP specimens, Gleason grade, extraprostatic extension, seminal vesicle involvement, and lymph node metastasis were recorded. The main outcome studied was prostate-confined disease at RP. A logistic regression model was used to test which pre-RP variables related to this outcome. RESULTS.— Univariate analysis showed significant associations with adverse RP outcomes in 5 of 8 quantifiable variables; longest millimeter HG PCa in a single 12-core biopsy, highest grade group in any core, and total millimeter HG in mpMRI-targeted biopsies showed no statistical association (P = .54, P = .13, and P = .55, respectively). In multivariate analysis, total millimeter carcinoma in all cores, highest GrGrp in any core, and longest millimeter HG PCa in a single mpMRI-targeted core provided additional predictive value (P < .001, P = .004, and P = .03, respectively). CONCLUSIONS.— Quantitation of HG PCa in mpMRI-targeted biopsies provides additional value over 12-core biopsies alone in predicting nonorgan confined prostate cancer at RP. Linear millimeters of HG PCa in mpMRI-targeted biopsies is a significant parameter associated with higher pathologic stage and could be of value in risk models.
Collapse
Affiliation(s)
- Nathan Paulson
- From the Department of Pathology (Paulson, Humphrey, Levi), Yale University School of Medicine, New Haven, Connecticut
| | - Robin T Vollmer
- the Department of Pathology, Veterans Affairs and Duke University Medical Centers, Durham, North Carolina (Vollmer)
| | - Peter A Humphrey
- From the Department of Pathology (Paulson, Humphrey, Levi), Yale University School of Medicine, New Haven, Connecticut
| | - Preston C Sprenkle
- Department of Urology (Sprenkle, Onofrey, Amirkhiz), Yale University School of Medicine, New Haven, Connecticut
| | - John Onofrey
- Department of Urology (Sprenkle, Onofrey, Amirkhiz), Yale University School of Medicine, New Haven, Connecticut.,Radiology & Biomedical Imaging (Onofrey, Huber), Yale University School of Medicine, New Haven, Connecticut
| | - Steffen Huber
- Radiology & Biomedical Imaging (Onofrey, Huber), Yale University School of Medicine, New Haven, Connecticut
| | - Kamyar Amirkhiz
- Department of Urology (Sprenkle, Onofrey, Amirkhiz), Yale University School of Medicine, New Haven, Connecticut
| | - Angelique W Levi
- From the Department of Pathology (Paulson, Humphrey, Levi), Yale University School of Medicine, New Haven, Connecticut
| |
Collapse
|
4
|
Vollmer R. An Algorithm for Predicting the Probability of Adverse Prostatectomy Results. Am J Clin Pathol 2021; 155:470. [PMID: 33236072 DOI: 10.1093/ajcp/aqaa178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
|
5
|
Similarities and Differences in the 2019 ISUP and GUPS Recommendations on Prostate Cancer Grading: A Guide for Practicing Pathologists. Adv Anat Pathol 2021; 28:1-7. [PMID: 33027069 DOI: 10.1097/pap.0000000000000287] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
Abstract
Contemporary subspecialization of practice in prostate pathology has seen a transition to complex, nuanced reporting, where a growing number of histopathologic parameters may signal differences in patient management. In this context, the International Society of Urological Pathology (ISUP) and the Genitourinary Pathology Society (GUPS) both published proceedings papers on the grading of prostate cancer in 2019. Overall, the 2 prostate cancer grading manuscripts reached many of the same conclusions and recommendations. Yet, each consensus was conducted somewhat differently, and in a couple of key areas, each reached different conclusions and recommendations. Herein, sourced from the experience and viewpoints of members of both societies, we provide the practicing pathologist a summary of the shared recommendations, and of the discordances. It is anticipated that these 2 documents will inform future iterations of recommendations and guidelines for reporting prostate cancer by organizations such as the College of American Pathologists, the Royal College of Pathologists, and the European Society of Pathology, which will promote best practices for their respective constituents. Our goal is to provide the practicing pathologist a useful catalog of the main points of both, allowing each practitioner to make informed decisions and understand any divergent opinions as may arise between observers for individual cases.
Collapse
|