Independent real‐world application of a clinical‐grade automated prostate cancer detection system

Abstract

Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed by diagnostic variability, histopathology caseload, and shortage of pathologists. We sought to define the performance of an AI-based automated prostate cancer detection system, Paige Prostate, when applied to independent real-world data. The algorithm was employed to classify slides into two categories: benign (no further review needed) or suspicious (additional histologic and/or immunohistochemical analysis required). We assessed the sensitivity, specificity, positive predictive values (PPVs), and negative predictive values (NPVs) of a local pathologist, two central pathologists, and Paige Prostate in the diagnosis of 600 transrectal ultrasound-guided prostate needle core biopsy regions ('part-specimens') from 100 consecutive patients, and to ascertain the impact of Paige Prostate on diagnostic accuracy and efficiency. Paige Prostate displayed high sensitivity (0.99; CI 0.96-1.0), NPV (1.0; CI 0.98-1.0), and specificity (0.93; CI 0.90-0.96) at the part-specimen level. At the patient level, Paige Prostate displayed optimal sensitivity (1.0; CI 0.93-1.0) and NPV (1.0; CI 0.91-1.0) at a specificity of 0.78 (CI 0.64-0.89). The 27 part-specimens considered by Paige Prostate as suspicious, whose final diagnosis was benign, were found to comprise atrophy (n = 14), atrophy and apical prostate tissue (n = 1), apical/benign prostate tissue (n = 9), adenosis (n = 2), and post-atrophic hyperplasia (n = 1). Paige Prostate resulted in the identification of four additional patients whose diagnoses were upgraded from benign/suspicious to malignant. Additionally, this AI-based test provided an estimated 65.5% reduction of the diagnostic time for the material analyzed. Given its optimal sensitivity and NPV, Paige Prostate has the potential to be employed for the automated identification of patients whose histologic slides could forgo full histopathologic review. In addition to providing incremental improvements in diagnostic accuracy and efficiency, this AI-based system identified patients whose prostate cancers were not initially diagnosed by three experienced histopathologists.

Computer-aided scoring of erb-b2 receptor tyrosine kinase 2 (HER2) gene amplification status in breast cancer

“…Indeed, a recent study found that application of IA in real-world clinical practice reduced diagnostic time by 65%. 25 Likewise, Hossain and colleagues reported that the application of the LD IA for HER2 DISH also reduced diagnostic time, from 3 to 20 min per manual score compared with 1 min for the algorithm to quantify the HER2/Chr17 ratio after pathologist annotation. 24 Thus, it will be critical for future studies to address the value of the uPath HER2 DISH IA in increasing workflow efficiencies, as demonstrating reduction of diagnostic interpretation time has substantial value for both the patient and oncologist.…”

Prostate-Specific Membrane Antigen Is a Biomarker for Residual Disease following Neoadjuvant Intense Androgen Deprivation Therapy in Prostate Cancer

“…Significantly, there is an unmet opportunity for artificial intelligence-driven efforts to use anti-PSMA IHC for refining algorithms used for detecting suspicious regions in treated prostate tumors, as PSMA demonstrates superior specificity for tumor than many IHC markers. 23–25 Current diagnostic efforts continue to be plagued by atypical histologies requiring additional expert pathological review, with these tumors more likely to be misclassified by automated systems or without specialized immunostains. 18,26 In the current study, we showed that anti-PSMA IHC alone had 97% sensitivity and 82% specificity for detecting residual disease when each ROI was separately examined by an expert prostate pathologist using H&E and other confirmatory stains.…”

Cultivating Clinical Clarity through Computer Vision: A Current Perspective on Whole Slide Imaging and Artificial Intelligence

“…The Paige Prostate ® system, successor to prototypal version Paige Prostate Alpha ® , was subject to extensive multinational validation spanning ≥150 different institutions and a diversity of clinical and demographic characteristics from ≥7000 patients including differing tumor sizes, grades, and patient ethnicities [ 23 , 83 , 84 , 85 , 86 , 87 ]. The system achieved a sensitivity of 97.7% and a specificity of 99.3% in detecting cancer in 1876 prostate CNB WSIs, also demonstrating 99% sensitivity and 93% specificity at part-specimen level while upgrading pathologist-ascribed benign/suspicious patient diagnosis to malignant after identification [ 84 , 85 ].…”