scholarly journals Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge

2022 ◽  
Author(s):  
Wouter Bulten ◽  
Kimmo Kartasalo ◽  
Po-Hsuan Cameron Chen ◽  
Peter Ström ◽  
Hans Pinckaers ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
United States ◽  
Clinical Trials ◽  
External Validation ◽  
Gleason Grading ◽  
Independent Validation ◽  
Prostate Biopsies ◽  
Algorithmic Approaches ◽  
Level Performance

AbstractArtificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge—the largest histopathology competition to date, joined by 1,290 developers—to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840–0.884) and 0.868 (95% CI, 0.835–0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

Enrollment disparities in cancer clinical trials leading to FDA approvals between 2008 and 2020.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e18501-e18501
Author(s):  
Ryan Huu-Tuan Nguyen ◽  
Yomaira Silva ◽  
Vijayakrishna K. Gadi
Keyword(s):  
Prostate Cancer ◽  
United States ◽  
Clinical Trials ◽  
Drug Approval ◽  
The United States ◽  
Cancer Clinical Trials ◽  
Cancer Prevalence ◽  
Fda Approval ◽  
The Us ◽  
Enrollment Data

e18501 Background: Cancer clinical trials based in the United States (US) have lacked adequate representation of racial and ethnic minorities, the elderly, and women. Pivotal clinical trials leading to United States Food and Drug Administration (FDA) approval are often multi-national trials and may also lack generalizability to underrepresented populations in the United States. We determined the racial, ethnic, age, and sex enrollment in pivotal trials relative to the US cancer population. Methods: We reviewed the FDA’s Drug Approvals and Databases for novel and new use drug approvals for breast, colorectal, lung, and prostate cancer indications from 2008 through 2020. Drugs@FDA was searched for drug approval summaries and FDA labels to identify clinical trials used to justify clinical efficacy that led to FDA approval. For eligible trials, enrollment data were obtained from FDA approval summaries, FDA labels, ClinicalTrials.gov, and corresponding journal manuscripts. Enrollment Fraction (EF) was calculated as enrollment in identified clinical trials divided by 2017 SEER cancer prevalence. All data sources were publicly available. Results: From 2008 through 2020, 60 drugs received novel or new use drug approval for breast, colorectal, lung, or prostate cancer indications based on 66 clinical trials with a total enrollment of 36,830. North America accounted for 9,259 (31%) enrollees of the 73% of trials reporting location of enrollment. Racial demographics were reported in 78% of manuscripts, 66% of ClinicalTrials.gov pages, and 98% of FDA labels or approval summaries. Compared with a 0.4% enrollment fraction among White patients, lower enrollment fractions were noted in Hispanic (0.2%, odds ratio [OR] vs White, 0.46; 95% confidence interval [CI], 0.43 to 0.49, P< 0.001) and Black (0.1%, OR 0.29; 95% CI 0.28 to 0.31, P< 0.001) patients. Elderly patients (age ≥ 65 years) were less likely than younger patients to be enrollees (EF 0.3% vs 0.9%, OR 0.27; 95% CI 0.26 to 0.27, P< 0.001) despite accounting for 61.3% of cancer prevalence. For colorectal and lung cancer trials, females were less likely than males (EF 0.7% vs 1.1%, OR 0.66; 95% CI 0.63 to 0.68, P< 0.001) to be enrolled. Conclusions: Black, Hispanic, elderly, and female patients were less likely to enroll in cancer clinical trials leading to FDA approvals from 2008 to 2020. Race and geographic enrollment data were inconsistently reported in journal manuscripts and ClinicalTrials.gov. The lack of appropriate representation of specific patient populations in these key clinical trials limits their generalizability. Future efforts must be made to ensure equitable access, representation, and reporting of enrollees that adequately represent the US population of patients with cancer.

Distribution and geographic accessibility of prostate cancer clinical trials in the United States.

2014 ◽  
Vol 32 (4_suppl) ◽  
pp. 59-59 ◽  
Author(s):  
Matt D. Galsky ◽  
Asma Latif ◽  
Kristian D. Stensland ◽  
Erin L. Moshier ◽  
Russell McBride ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
United States ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Geographic Distribution ◽  
The United States ◽  
First Line ◽  
Trial Site ◽  
Lorenz Curves ◽  
Number Of Patients

59 Background: An extremely small proportion of patients with cancer in the United States (US) enroll in clinical trials. While several barriers to trial accrual have been described, the geographic distribution and accessibility of clinical trial sites has not been comprehensively explored. Methods: ClinicalTrials.gov was queried to identify all active US clinical trials exploring first-line therapies for metastatic prostate cancer (PCa) on 9/16/2012. We evaluated the geographic distribution of trial sites and determined the relationship between the number of sites and the number of patients with advanced PCa per county and evaluated heterogeneity using Lorenz curves. We also estimated the minimum driving distance required to access a clinical trial site from each ZIP code in the continguous US; a distance >30 miles was defined as high travel burden consistent with prior studies. Results: We identified 958 sites associated with 42 PCa clinical trials (Table). The geographic distribution of clinical trial sites was very inhomogeneous with several states having only 1-2 trial sites. Among 3185 US counties, 2,669 (83.8%) had no clinical trials available for first-line treatment of metastatic PCa. Counties with larger populations of patients with advanced PCa had significantly higher numbers of clinical trial sites. For every 100 additional patients with advanced PCa per county, the number of available trial sites increased by 21.0% (95% CI: 16.5-25.7%). However, Lorenz curves indicated a high degree of inequality in trial accessibility (Gini index 0.71). Approximately 31% of the US population resided >30 miles from a PCa trial site. Conclusions: Clinical trials sites are poorly accessible, geographically, to a large subset of US PCa patients, a finding that likely contributes to dismal accrual. Innovative solutions are required to address geographic barriers to access. [Table: see text]

scholarly journals A Fully Automatic Artificial Intelligence System Able to Detect and Characterize Prostate Cancer Using Multiparametric MRI: Multicenter and Multi-Scanner Validation

2021 ◽  
Vol 11 ◽  
Author(s):  
Valentina Giannini ◽  
Simone Mazzetti ◽  
Arianna Defeudis ◽  
Giuseppe Stranieri ◽  
Marco Calandri ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
External Validation ◽  
Specific Antigen ◽  
Support Vector ◽  
Cad System ◽  
Intelligence System ◽  
Beneficial Impact ◽  
Aggressive Tumors ◽  
Validation Set

In the last years, the widespread use of the prostate-specific antigen (PSA) blood examination to triage patients who will enter the diagnostic/therapeutic path for prostate cancer (PCa) has almost halved PCa-specific mortality. As a counterpart, millions of men with clinically insignificant cancer not destined to cause death are treated, with no beneficial impact on overall survival. Therefore, there is a compelling need to develop tools that can help in stratifying patients according to their risk, to support physicians in the selection of the most appropriate treatment option for each individual patient. The aim of this study was to develop and validate on multivendor data a fully automated computer-aided diagnosis (CAD) system to detect and characterize PCas according to their aggressiveness. We propose a CAD system based on artificial intelligence algorithms that a) registers all images coming from different MRI sequences, b) provides candidates suspicious to be tumor, and c) provides an aggressiveness score of each candidate based on the results of a support vector machine classifier fed with radiomics features. The dataset was composed of 131 patients (149 tumors) from two different institutions that were divided in a training set, a narrow validation set, and an external validation set. The algorithm reached an area under the receiver operating characteristic (ROC) curve in distinguishing between low and high aggressive tumors of 0.96 and 0.81 on the training and validation sets, respectively. Moreover, when the output of the classifier was divided into three classes of risk, i.e., indolent, indeterminate, and aggressive, our method did not classify any aggressive tumor as indolent, meaning that, according to our score, all aggressive tumors would undergo treatment or further investigations. Our CAD performance is superior to that of previous studies and overcomes some of their limitations, such as the need to perform manual segmentation of the tumor or the fact that analysis is limited to single-center datasets. The results of this study are promising and could pave the way to a prediction tool for personalized decision making in patients harboring PCa.

Artificial Intelligence for automated Gleason Grading in prostate cancer biopsies

2019 ◽  
Vol 18 (1) ◽  
pp. e724
Author(s):  
F-E. Marginean ◽  
A. Krzyzanowska ◽  
I. Arvidsson ◽  
A. Simoulis ◽  
E. Sjöblom ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Gleason Grading

scholarly journals Predicting prostate cancer specific-mortality with artificial intelligence-based Gleason grading

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Ellery Wulczyn ◽  
Kunal Nagpal ◽  
Matthew Symonds ◽  
Melissa Moran ◽  
Markus Plass ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Risk Groups ◽  
Risk Scores ◽  
Pathology Report ◽  
Gleason Grading ◽  
Specific Mortality ◽  
Cancer Specific Mortality ◽  
Open Question

Abstract Background Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated Gleason grading on-par with expert pathologists, it remains an open question whether and to what extent A.I. grading translates to better prognostication. Methods In this study, we developed a system to predict prostate cancer-specific mortality via A.I.-based Gleason grading and subsequently evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2807 prostatectomy cases from a single European center with 5–25 years of follow-up (median: 13, interquartile range 9–17). Results Here, we show that the A.I.’s risk scores produced a C-index of 0.84 (95% CI 0.80–0.87) for prostate cancer-specific mortality. Upon discretizing these risk scores into risk groups analogous to pathologist Grade Groups (GG), the A.I. has a C-index of 0.82 (95% CI 0.78–0.85). On the subset of cases with a GG provided in the original pathology report (n = 1517), the A.I.’s C-indices are 0.87 and 0.85 for continuous and discrete grading, respectively, compared to 0.79 (95% CI 0.71–0.86) for GG obtained from the reports. These represent improvements of 0.08 (95% CI 0.01–0.15) and 0.07 (95% CI 0.00–0.14), respectively. Conclusions Our results suggest that A.I.-based Gleason grading can lead to effective risk stratification, and warrants further evaluation for improving disease management.

scholarly journals Artificial Intelligence Based Algorithms for Prostate Cancer Classification and Detection on Magnetic Resonance Imaging: A Narrative Review

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 959
Author(s):  
Jasper J. Twilt ◽  
Kicky G. van Leeuwen ◽  
Henkjan J. Huisman ◽  
Jurgen J. Fütterer ◽  
Maarten de Rooij
Keyword(s):  
Magnetic Resonance Imaging ◽  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Magnetic Resonance ◽  
External Validation ◽  
Lesion Detection ◽  
Resonance Imaging ◽  
Clinical Workflow ◽  
The Impact ◽  
Lesion Classification

Due to the upfront role of magnetic resonance imaging (MRI) for prostate cancer (PCa) diagnosis, a multitude of artificial intelligence (AI) applications have been suggested to aid in the diagnosis and detection of PCa. In this review, we provide an overview of the current field, including studies between 2018 and February 2021, describing AI algorithms for (1) lesion classification and (2) lesion detection for PCa. Our evaluation of 59 included studies showed that most research has been conducted for the task of PCa lesion classification (66%) followed by PCa lesion detection (34%). Studies showed large heterogeneity in cohort sizes, ranging between 18 to 499 patients (median = 162) combined with different approaches for performance validation. Furthermore, 85% of the studies reported on the stand-alone diagnostic accuracy, whereas 15% demonstrated the impact of AI on diagnostic thinking efficacy, indicating limited proof for the clinical utility of PCa AI applications. In order to introduce AI within the clinical workflow of PCa assessment, robustness and generalizability of AI applications need to be further validated utilizing external validation and clinical workflow experiments.

scholarly journals Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

2021 ◽  
Vol 11 ◽  
Author(s):  
Jake Kendrick ◽  
Roslyn Francis ◽  
Ghulam Mubashar Hassan ◽  
Pejman Rowshanfarzad ◽  
Robert Jeraj ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Metastatic Prostate Cancer ◽  
External Validation ◽  
Temporal Variations ◽  
The Body ◽  
Disease Spread ◽  
Imaging Biomarkers ◽  
Artificial Intelligence Techniques ◽  
Multiple Imaging

Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.

Independent validation of paige prostate: Assessing clinical benefit of an artificial intelligence tool within a digital diagnostic pathology laboratory workflow.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14076-e14076
Author(s):  
Christopher Kanan ◽  
Jillian Sue ◽  
Leo Grady ◽  
Thomas J. Fuchs ◽  
Sarat Chandarlapaty ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Needle Biopsy ◽  
Final Diagnosis ◽  
Pathology Laboratory ◽  
Independent Dataset ◽  
Prostate Needle Biopsy ◽  
Immunohistochemical Markers ◽  
Prostate Biopsies ◽  
The Subject

e14076 Background: The most common approach to diagnose prostate cancer is the “whole gland biopsy procedure,” in which numerous cores (≥12) are taken from different regions of the gland to maximize the chances of detecting small cancers; the presence of cancer in any of these cores is significant to the patient. If concerning features that are not fully diagnostic of cancer are identified, the pathologist may defer the final diagnosis until additional studies (e.g. immunohistochemistry) have been performed. We recently developed an artificial intelligence (AI)-based system for the assessment of cancer in prostate biopsies. Here, we investigated the performance of this test in an independent dataset of prostate cancers consecutively accrued. Methods: Two board-certified pathologists retrospectively reviewed 600 digitized hematoxylin-and-eosin (H&E) stained diagnostic prostate core needle biopsy slides from 100 consecutive patients, originally diagnosed at an independent hospital. Pathologists’ assessments were based on the H&E image alone; if further testing would be preferred, it was noted in the review notes. All images were assessed by Paige Prostate 1.0, an AI-based diagnostic tool; based on its outputs (either suspicious for cancer or not), the discordant images were re-reviewed by the pathologists and, in parallel, adjudicated with additional testing (e.g. ancillary immunohistochemical markers). Results: Paige Prostate's slide-level sensitivity was 98.9% and its specificity was 93.3% (100% and 78.0%, respectively, at the subject-level). The pathologists' average slide-level sensitivity and specificity without Paige Prostate was 90.9% and 98.6%, respectively. The sensitivity with their consensus read and Paige Prostate increased by 5.7% to 96.6% with only 0.8% decrease in specificity. In addition to new slide-level findings, benefits were also observed at the subject-level; with Paige, three new prostate cancer cases were discovered that were initially missed. Conclusions: The study reflects the potential benefits of the Paige Prostate system in the hands of experienced pathologists and validates the algorithm in a completely independent dataset. Paige Prostate can improve pathologists' sensitivity when reviewing digitized H&E prostate needle biopsy images with a minor impact on specificity.

scholarly journals 648 External Validation of The European Randomized Study of Screening for Prostate Cancer Risk Calculator 3 (ERSPC-RC3) In the Detection of Prostate Cancer and Avoiding Unnecessary Prostate Biopsies

2021 ◽  
Vol 108 (Supplement_2) ◽  
Author(s):  
C Desai ◽  
S A Ehsanullah ◽  
A Bhojwani ◽  
A Dhanasekaran
Keyword(s):  
Prostate Cancer ◽  
High Risk ◽  
Risk Group ◽  
Randomized Study ◽  
External Validation ◽  
Prostate Cancer Risk ◽  
Low Risk ◽  
Intermediate Risk ◽  
Risk Calculator ◽  
Prostate Biopsies

Abstract Introduction The Prostate Cancer Research Foundation – Stichting Wetenschappelijk Onderzoek Prostaatkanker group has devised the European Randomized Study of Screening for Prostate Cancer (CaP) Risk Calculator 3 (ERSPC-RC3) tool which aims to increase prostate cancer detection rates and avoid unnecessary prostate biopsies. We report the external validation and accuracy of the ERSPC-RC3 in our UK cohort. Method Retrospective data was collected for patients who had prostate biopsy at a multi-centre district general hospital over an 18-month period. The ERSPC-RC3 was applied to identify the probability of a positive biopsy for CaP (Gleason score ≥7). Results Out of 121 TRUS biopsies, 78 patients met the ERSPC-RC3 inclusion criteria. Patients were stratified as low-risk (detectable CaP risk &lt;12.5%) n = 10, intermediate-risk (detectable CaP risk 12.5-20%) n = 8, and high-risk (detectable CaP risk &gt;20%) n = 60 groups. All low-risk patients had a benign histology. Gleason 7 CaP was found in 37.5% from the intermediate-risk group and 41.7% in the high-risk group respectively. Conclusions Our results demonstrate that using ERSPC-RC3 could have prevented 44% (n = 34) of patients from having unnecessary biopsies. We recommend the use of ERSPC-RC3 to risk stratify patients being investigated for suspected CaP.

Sign in / Sign up

Export Citation Format

Share Document