Effectiveness and Cost-effectiveness of Artificial Intelligence-assisted Pathology for Prostate Cancer Diagnosis in Sweden: A Microsimulation Study.

BACKGROUND AND OBJECTIVE: Image-based artificial intelligence (AI) methods have shown high accuracy in prostate cancer (PCa) detection. Their impact on patient outcomes and cost effectiveness in comparison to human pathologists remains unknown. Our aim was to evaluate the effectiveness and cost-effectiveness of AI-assisted pathology for PCa diagnosis in Sweden. METHODS: We modeled quadrennial prostate-specific antigen (PSA) screening for men between the ages of 50 and 74 yr over a lifetime horizon using a health care perspective. Men with PSA ≥3 ng/ml were referred for standard biopsy (SBx), for which cores were either examined via AI followed by a pathologist for AI-labeled positive cores, or a pathologist alone. The AI performance characteristics were estimated using an internal STHLM3 validation data set. Outcome measures included the number of tests, PCa incidence and mortality, overdiagnosis, quality-adjusted life years (QALYs), and the potential reduction in pathologist-evaluated biopsy cores if AI were used. Cost-effectiveness was assessed using the incremental cost-effectiveness ratio. KEY FINDINGS AND LIMITATIONS: In comparison to a pathologist alone, the AI-assisted workflow increased the number of PSA tests, SBx procedures, and PCa deaths by ≤0.03%, and slightly reduced PCa incidence and overdiagnosis. AI would reduce the proportion of biopsy cores evaluated by a pathologist by 80%. At a cost of €10 per case, the AI-assisted workflow would cost less and result in <0.001% lower QALYs in comparison to a pathologist alone. The results were sensitive to the AI cost. CONCLUSIONS AND CLINICAL IMPLICATIONS: According to our model, AI-assisted pathology would significantly decrease the workload of pathologists, would not affect patient quality of life, and would yield cost savings in Sweden when compared to a human pathologist alone. PATIENT SUMMARY: We compared outcomes for prostate cancer patients and relevant costs for two methods of assessing prostate biopsies in Sweden: (1) artificial intelligence (AI) technology and review of positive biopsies by a human pathologist; and (2) a human pathologist alone for all biopsies. We found that addition of AI would reduce the pathology workload and save money, and would not affect patient outcomes when compared to a human pathologist alone. The results suggest that adding AI to prostate pathology in Sweden would save costs.

Temporal trend in risk of prostate cancer death in men with favourable-risk prostate cancer.

BACKGROUND AND OBJECTIVES: Changes in work-up and histopathological assessment have caused stage and grade migration in men with prostate cancer (PCa). The aim of this study was to assess temporal trends in risk of PCa death for men with favourable-risk PCa managed with primary radical prostatectomy or observation. METHODS AND MATERIAL: Men aged 75 or younger with Charlson Comorbidity index 0-1 diagnosed with favourable-risk PCa (T1-T2, prostate specific antigen [PSA] <20 ng/mL and Gleason score 6 or 7[3+4]) in the period 2000-2016 who were treated with primary radical prostatectomy or managed with observation in PCBaSe 4.0. Treatment groups were compared following propensity score matching, and risk of PCa death was estimated by use of Cox regression analyses. RESULTS: A total of 9,666 men were selected for each treatment strategy. The 7-year cumulative incidence of PCa death decreased in all risk and treatment groups. For example, the incidence in men diagnosed with low-risk PCa and managed with observation was 1.2% in 2000-2005, which decreased to 0.4% in 2011-2016. Corresponding incidences for men with intermediate-risk PCa managed with observation were 2.0% and 0.7%. The relative risk of PCa death was lower in men with low-risk PCa managed with radical prostatectomy compared to observation: in 2000-2005 hazard ratio (HR) 0.20 (95% confidence interval [CI] 0.10-0.38) and in 2011-2016 HR 0.35 (95% CI 0.05-2.26). Corresponding risks for men with intermediate-risk PCa were HR 0.28 (95% CI 0.16-0.47) and HR 0.21 (95% CI 0.04-1.18). The absolute risk reduction of radical prostatectomy compared to observation for men with low-risk PCa was 1% in 2000-2005 and 0.4% in 2011-2016, and for men with intermediate-risk PCa 1.1% in 2000-2005 and 0.7% in 2011-2016. CONCLUSION: Men diagnosed in 2011-2016 with low-risk and favourable intermediate-risk PCa have a similar relative benefit but smaller absolute benefit of curative treatment compared to men diagnosed in 2000-2005.

Prognosis of Gleason score 8 prostatic adenocarcinoma in needle biopsies: a nationwide population-based study.

A 5-tier grouping of Gleason scores has recently been proposed. Studies have indicated prognostic heterogeneity within these groups. We assessed prostate cancer-specific mortality (PCSM) and all-cause mortality (ACM) for men diagnosed with Gleason score 3 + 5 = 8, 4 + 4 = 8 and 5 + 3 = 8 acinar adenocarcinoma on needle biopsy in a population-based national cohort. The Prostate Cancer data Base Sweden 5.0 was used for survival analysis with PCSM and ACM at 5 and 10 years as endpoints. Multivariable Cox regression models controlling for socioeconomic factors, stage and primary treatment type were used for PCSM and ACM. Among 199,620 men reported with prostate cancer in 2000-2020, 172,112 were diagnosed on needle biopsy. In 18,281 (11%), there was a Gleason score of 8 in needle biopsies, including a Gleason score of 3 + 5, 4 + 4 and 5 + 3 in 11%, 86% and 2.3%, respectively. The primary treatment was androgen deprivation therapy (55%), deferred treatment (8%), radical prostatectomy (16%) or radical radiotherapy (21%). PCSM in men with Gleason scores of 3 + 5, 4 + 4 and 5 + 3 at 5 years of follow-up was 0.10 (95% CI 0.09-0.12), 0.22 (0.22-0.23) and 0.32 (0.27-0.36), respectively, and at 10 years 0.19 (0.17-0.22), 0.34 (0.33-0.35) and 0.44 (0.39-0.49), respectively. There was a significantly higher PCSM after 5 and 10 years in men with Gleason score 5 + 3 cancers than in those with 4 + 4 and in Gleason score 4 + 4 cancers than in those with 3 + 5. Grouping of Gleason scores will eliminate the prognostic granularity of Gleason scoring, thus diminishing the prognostic significance of this proposed grading system.

Gleason score 3+3=6 prostatic adenocarcinoma is not benign and the current debate is unhelpful to clinicians and patients.

Prostate adenocarcinoma is a common malignancy associated with a significant morbidity and mortality. In both prostate biopsies and radical prostatectomy specimens Gleason scoring informs both treatment and outcome prediction. The current convention is that in needle biopsies, Gleason patterns 3, 4 and 5 are considered to be malignant. Despite this there is debate as to whether or not Gleason score (GS) 3+3=6 should be diagnosed as cancer due to potential over-treatment and the psychological impact on patients. It is apparent that GS 3+3=6 is indolent disease with a low risk of metastasis. However, it does have the histological features of malignancy and is capable of infiltrating the prostate gland, extraprostatic extension, and metastatic spread. Furthermore GS 3+3=6 carcinoma has immunohistochemical and molecular genetic features similar to those of higher grade prostatic carcinoma. If GS 3+3=6 tumour is considered benign, the question arises should a benign label be given to the Gleason pattern 3 component of tumour that includes Gleason patterns of higher grade? This would seem a logical step as GS 3+3=6 cancers and the pattern 3 component in cancers with multiple patterns are morphologically identical. If pattern 3 is considered to be benign, then Gleason scoring would be limited to 4+4=8, 4+5=9, 5+4=9 and 5+5=10 which is clearly inappropriate. The correct strategy to address potential over-treatment of patients with low-grade cancer is clinician and patient education, not the recalibration of Gleason grading to reclassify malignant tumours as benign.

Prognosis of Gleason Score 9-10 Prostatic Adenocarcinoma in Needle Biopsies: A Nationwide Population-based Study.

BACKGROUND: Since 2014, prostate cancer is reported using five-tier grouping of Gleason scores. Studies have suggested prognostic heterogeneity within the groups. OBJECTIVE: We assessed the risk of prostate cancer death for men diagnosed with Gleason scores 4 + 5, 5 + 4, and 5 + 5 on needle biopsy in a population-based cohort. DESIGN, SETTING, AND PARTICIPANTS: We used the data from Prostate Cancer data Base Sweden (PCBaSe) 4.0 for a survival analysis. Among 199 620 men reported to have prostate cancer in 2000-2020, 172 112 were diagnosed on needle biopsy. The primary treatment was classified as androgen deprivation therapy (66%), deferred treatment (5%), radical prostatectomy (7%), or radical radiotherapy (21%). OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The risks of death from prostate cancer in men with Gleason score 9-10 at 5 and 10 yr were used as endpoints. Multivariable Cox regression models controlling for socioeconomic factors and primary treatment were used for time-to-event analyses of death from prostate cancer and death from any causes. RESULTS AND LIMITATIONS: A total of 20 419 (12%) men had a Gleason score of 9-10, including Gleason scores of 4 + 5, 5 + 4, and 5 + 5 in 14 333 (70%), 4223 (21%), and 1863 (9%) men, respectively. The risks of prostate cancer death for men with Gleason scores 4 + 5, 5 + 4, and 5 + 5 at 10 yr of follow-up were 0.45 (confidence interval [CI] 0.44-0.46), 0.56 (0.55-0.58), and 0.66 (0.63-0.68), respectively. The risks of death of any cause for men with Gleason scores 4 + 5, 5 + 4, and 5 + 5 at 10 yr were 0.73 (CI 0.72-0.74), 0.81 (0.80-0.83), and 0.87 (0.85-0.89), respectively. CONCLUSIONS: We demonstrate in the largest and most complete cohort analyzed to date that collapsing the Gleason scores by grouping results in loss of prognostic information in men with Gleason score 9-10 cancer. PATIENT SUMMARY: Survival of prostate cancer patients with the highest tumor grades varies depending on grade composition.

Assessing the Impact of Positive Surgical Margins on Mortality in Patients Who Underwent Robotic Radical Prostatectomy: 20 Years' Report from the EAU Robotic Urology Section Scientific Working Group.

BACKGROUND: Positive surgical margins (PSMs) are frequent in patients undergoing radical prostatectomy (RP). The impact of PSMs on cancer-specific (CSM) and overall (OM) mortality has not yet been proved definitively. OBJECTIVE: To evaluate whether the presence and the features of PSMs were associated with CSM and OM in patients who underwent robotic-assisted RP. DESIGN, SETTING, AND PARTICIPANTS: A cohort of 8141 patients underwent robotic-assisted RP with >10 yr of follow-up. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Cox multivariable analyses assessed the impact of margin status (positive vs negative) and PSM features (negative vs <3 mm vs >3 mm vs multifocal) on the risk of CSM, OM, and biochemical recurrence (BCR) after adjusting for potential confounders. We repeated our analyses after stratifying patients according to clinical (Cancer of the Prostate Risk Assessment [CAPRA] categories) and pathological characteristics (adverse: pT 3-4 and/or grade group [GG] 4-5 and/or pN1 and/or prostate-specific antigen [PSA] persistence). RESULTS AND LIMITATIONS: PSMs were found in 1348 patients (16%). Among these, 48 (3.6%) patients had multifocal PSMs. Overall, 1550 men experienced BCR and 898 men died, including 130 for prostate cancer. At Cox multivariable analyses, PSMs were associated with CSM in patients with adverse clinical (Intermediate risk: hazard ratio [HR]: 1.71, p = 0.048; high risk: HR: 2.20, p = 0.009) and pathological (HR: 1.79, p = 0.005) characteristics. Only multifocal PSMs were associated with CSM and OM in the whole population (HR for CSM: 4.68, p < 0.001; HR for OM: 1.82, p = 0.037) and in patients with adverse clinical (intermediate risk: HR for CSM: 7.26, p = 0.006; high risk: HR for CSM: 9.26, p < 0.001; HR for OM: 2.97, p = 0.006) and pathological (HR for CSM: 9.50, p < 0.001; HR for OM: 2.59, p = 0.001) characteristics. Potential limitations include a selection bias and a lack of information on the Gleason score at PSM location. CONCLUSIONS: We did not find an association between unifocal PSMs and mortality. Conversely, our results underscore the importance of avoiding multifocal PSMs in patients with adverse clinical (intermediate- and high-risk CAPRA score) and pathological (GG ≥4, pT ≥3, pN1, or PSA persistence) characteristics, to enhance overall survival and reduce CSM. PATIENT SUMMARY: In this study, we evaluated whether the presence and the characteristics of positive surgical margins were associated with mortality in patients who underwent robotic-assisted radical prostatectomy. We found that the presence of positive surgical margins, particularly multifocal margins, was associated with mortality only in patients with adverse clinical and pathological characteristics.

Prostate Cancer-specific and All-cause Mortality After Robot-assisted Radical Prostatectomy: 20 Years' Report from the European Association of Urology Robotic Urology Section Scientific Working Group.

BACKGROUND: Evidence on long-term oncological efficacy is available only for open radical prostatectomy but remains scarce for robot-assisted radical prostatectomy (RARP). OBJECTIVE: To validate the long-term survival rates after RARP and provide stratified outcomes based on contemporary prostate cancer (PCa) risk-stratification tools. DESIGN, SETTING, AND PARTICIPANTS: A retrospective analysis of the European Association of Urology (EAU) Robotic Urology Section Scientific Working Group international multicenter database for RARP was performed. Patients who underwent RARP at seven pioneer robotic urology programs in Europe and the USA between 2002 and 2012 were included. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary outcomes were PCa-specific mortality and all-cause mortality. The probability of cancer-specific survival (CSS) was estimated with the competing risks method, and the probability of overall survival (OS) was estimated with the Kaplan-Meier method. RESULTS AND LIMITATIONS: A total of 9876 patients who underwent RARP between 2002 and 2012 were included. Within follow-up, 1071 deaths occurred and 159 were due to PCa. At 15 yr of follow-up, CSS and OS were 97.6% (97.2%, 98.0%) and 85.5% (84.6%, 86.4%), respectively. Stratified analyses based on EAU risk groups at diagnosis and pT stage showed favorable survival rates, with low-risk (n = 4601, 46.6%), intermediate-risk (n = 4056, 41.1%), and high-risk (n = 1219, 12.3%) patients demonstrating CSS rates of 99%, 98%, and 90% at 15 yr, respectively. Notably, patients with pT3a disease had similar survival outcomes to those with pT2 disease, with worse CSS in patients with pT3b PCa (98.9% vs 97.4% vs 86.5%). Multivariable analyses identified age, prostate-specific antigen, biopsy Gleason grade group, clinical T stage, and treatment year as independent predictors of worse oncological outcomes. CONCLUSIONS: Our multicenter study with long-term follow-up confirms favorable survival outcomes after RARP for localized PCa. Patients with low- and intermediate-risk disease face a higher risk of mortality from causes other than PCa. On the contrary, high-risk patients have a significantly higher risk of PCa-specific mortality. PATIENT SUMMARY: In the present study, we reported the outcomes of patients with prostate cancer (PCa) who underwent robot-assisted radical prostatectomy between 10 and 20 yr ago, and we found a very low probability of dying from PCa in patients with low- and intermediate-risk PCa.

Deciphering the Role of p60AmotL2 in Epithelial Extrusion and Cell Detachment.

Preserving an accurate cell count is crucial for maintaining homeostasis. Apical extrusion, a process in which redundant cells are eliminated by neighboring cells, plays a key role in this regard. Recent studies have revealed that apical extrusion can also be triggered in cells transformed by oncogenes, suggesting it may be a mechanism through which tumor cells escape their microenvironment. In previous work, we demonstrated that p60AmotL2 modulates the E-cadherin function by inhibiting its connection to radial actin filaments. This isoform of AmotL2 is expressed in invasive breast and colon tumors and promotes invasion in vitro and in vivo. Transcriptionally regulated by c-Fos, p60AmotL2 is induced by local stress signals such as severe hypoxia. In this study, we investigated the normal role of p60AmotL2 in epithelial tissues. We found that this isoform is predominantly expressed in the gut, where cells experience rapid turnover. Through time-lapse imaging, we present evidence that cells expressing p60AmotL2 are extruded by their normal neighboring cells. Based on these findings, we hypothesize that tumor cells exploit this pathway to detach from normal epithelia and invade surrounding tissues.

Web-grading-a tool to test personal grading of renal and prostate cancer.

Only a few pathologists have the opportunity to verify their personal grading through objective assessment. This study introduces a web-based grading platform to facilitate and validate the grading of renal cell carcinoma and prostate cancer. Two representative images of two clinically annotated cohorts of 100 cases each of prostate and renal cell carcinoma were used. Each participant was asked to grade a tumor series utilizing a three tiered grading system. Finally, a Kaplan-Meier curve was drawn, and the log-rank test was used for statistical testing of the p-value. The grading of 22 participants (68%) achieved prognostic significance. Further analysis highlighted that only two pathologists were able to reliably separate low- and high-grade tumors from intermediate grades. The limitations of this study are the low number of participants in each of the cohorts and the potential selection bias of the tumor images. This web-based grading portal facilitates the assessment of the validity of grading by individual pathologists. The observation that most participants can only successfully identify high- or low-grade tumors but cannot discriminate between more subtle intermediate grades does indicate that there is a need for the development of more formal training programs for tumor grading.

Surveillance for Nonmuscle Invasive Bladder Cancer: Identifying the Point of Diminishing Returns.

OBJECTIVE: To characterize first and second recurrence patterns using 26years of cohort-level follow-up and microsimulation modeling. METHODS: Patients diagnosed with nonmuscle-invasive bladder cancer in Stockholm County between 1995 and 1996 were included. Clinical, pathological, and longitudinal follow-up data were gathered. Logistic regressions, Kaplan Meier curves, and Cox proportional hazards models were run to generate assumptions for a microsimulation model, simulating first and second recurrence and progression for 10,000 patients. RESULTS: Three hundred eighty-six patients were included: 67.4% were male; >50% were TaLG; and 37.5% were American Urological Association high-risk. Median time to recurrence was 300days. Three patients had missing data. Cohort follow-up has been carried out for 26years. For simulated first-recurrences, low-risk patients recurred at 56.6% over 15years of follow-up, with 2.2% muscle-invasive (MI) progression; intermediate-risk patients recurred at 62.8%, with 4.3% MI progression; high-risk patients recurred at 48.7% over 15years, with MI progression at 14.3%. For second recurrences, 70.7%, 75.7%, and 84.7% of low, medium, and high-risk patients recurred. No patients were seen to have first recurrences after 9years, with low, but notable, rates beyond 5years. CONCLUSION: These data suggest that low-, intermediate-, and high-risk patients without recurrence at 5years may be potentially transitioned to less invasive monitoring.

Clinicopathologic Significance of Anterior Prostate Cancer: Comparison With Posterior Prostate Cancer in the Era of Multiparametric Magnetic Resonance Imaging.

Anterior prostate cancer (APC) has been considered an indolent tumor, most commonly arising in the transition zone (TZ). More recently, detection of APC has been facilitated through multiparametric magnetic resonance imaging and improved biopsy techniques, enabling earlier detection. The pathologic features and clinical significance of pure APC in a large contemporary series of well-characterized tumors have, to date, not been elucidated. Cases with APC defined as cancer present anterior to the urethra only were identified from 1761 consecutive radical prostatectomy specimens accessioned between January 2015 and August 2016. The clinicopathologic features of these cases were compared with those of pure posterior prostate cancer (PPC) and the features of anterior peripheral zone (APZ) cancers were compared with those of TZ cancers. In addition, the tumor series from 2015 to 2016 was compared with a cohort of 1054 patients accessioned before the utilization of multiparametric magnetic resonance imaging in the routine workup of patients with prostate cancer. In the 2015-2016 series, there were 188 (10.7%) patients with APC compared with 5.4% in the series from the pre-multiparametric magnetic resonance imaging era. No difference was observed between APC and PPC with regards to patient age or mean serum prostate-specific antigen at presentation. Mean tumor volume and positive surgical margin (PSM) rates were significantly higher in APC. In contrast, PPC was more commonly high grade with more frequent extraprostatic extension (EPE). None of the cases of APC had infiltration of the seminal vesicle or lymph node involvement, in contrast to PPC, with almost 14% of cases in each category. The 3- and 5-year biochemical recurrence-free survival was significantly higher in APC when compared with PPC, although this was not retained on multivariable analysis which included tumor location. On division of APCs according to anatomic zone of origin, 45% were APZ cancer and 37% TZ cancer. On comparison of APZ and TZ cancers, there were no significant differences in mean age and serum prostate-specific antigen at presentation as well as tumor volume, Gleason score, and PSM rate. High-grade malignancy (Gleason score >3 + 4=7) was seen in 26% of TZ cancers which compared with 44% of APZ cancers and 56% of PPC cancers. The rate of EPE was significantly higher in APZ when compared with TZ cancer ( P< 0.0005); however, the biochemical recurrence rate was not significantly different between the groups. The prevalence of APC in radical prostatectomy specimens has increased in recent times, in association with earlier detection at a stage amenable to curative surgical treatment. APC, when compared with PPC, is less commonly high grade with less frequent EPE, despite the APC group having larger tumors and a higher PSM rate at presentation. However, not all anterior cancers are indolent. Anterior cancers are more commonly seen in the APZ than the TZ and APZ cancers appear more locally aggressive than TZ cancers.

Application of Genomic Sequencing to Refine Patient Stratification for Adjuvant Therapy in Renal Cell Carcinoma.

PURPOSE: Patients with resected localized clear-cell renal cell carcinoma (ccRCC) remain at variable risk of recurrence. Incorporation of biomarkers may refine risk prediction and inform adjuvant treatment decisions. We explored the role of tumor genomics in this setting, leveraging the largest cohort to date of localized ccRCC tissues subjected to targeted gene sequencing. EXPERIMENTAL DESIGN: The somatic mutation status of 12 genes was determined in 943 ccRCC cases from a multinational cohort of patients, and associations to outcomes were examined in a Discovery (n = 469) and Validation (n = 474) framework. RESULTS: Tumors containing a von-Hippel Lindau (VHL) mutation alone were associated with significantly improved outcomes in comparison with tumors containing a VHL plus additional mutations. Within the Discovery cohort, those with VHL+0, VHL+1, VHL+2, and VHL+≥3 tumors had disease-free survival (DFS) rates of 90.8%, 80.1%, 68.2%, and 50.7% respectively, at 5 years. This trend was replicated in the Validation cohort. Notably, these genomically defined groups were independent of tumor mutational burden. Amongst patients eligible for adjuvant therapy, those with a VHL+0 tumor (29%) had a 5-year DFS rate of 79.3% and could, therefore, potentially be spared further treatment. Conversely, patients with VHL+2 and VHL+≥3 tumors (32%) had equivalent DFS rates of 45.6% and 35.3%, respectively, and should be prioritized for adjuvant therapy. CONCLUSIONS: Genomic characterization of ccRCC identified biologically distinct groups of patients with divergent relapse rates. These groups account for the ∼80% of cases with VHL mutations and could be used to personalize adjuvant treatment discussions with patients as well as inform future adjuvant trial design.

Interobserver reproducibility of cribriform cancer in prostate needle biopsies and validation of International Society of Urological Pathology criteria.

AIMS: There is strong evidence that cribriform morphology indicates a worse prognosis of prostatic adenocarcinoma. Our aim was to investigate its interobserver reproducibility in prostate needle biopsies. METHODS AND RESULTS: A panel of nine prostate pathology experts from five continents independently reviewed 304 digitised biopsies for cribriform cancer according to recent International Society of Urological Pathology criteria. The biopsies were collected from a series of 702 biopsies that were reviewed by one of the panellists for enrichment of high-grade cancer and potentially cribriform structures. A 2/3 consensus diagnosis of cribriform and noncribriform cancer was reached in 90% (272/304) of the biopsies with a mean kappa value of 0.56 (95% confidence interval 0.52-0.61). The prevalence of consensus cribriform cancers was estimated to 4%, 12%, 21%, and 20% of Gleason scores 7 (3 + 4), 7 (4 + 3), 8, and 9-10, respectively. More than two cribriform structures per level or a largest cribriform mass with ≥9 lumina or a diameter of ≥0.5 mm predicted a consensus diagnosis of cribriform cancer in 88% (70/80), 84% (87/103), and 90% (56/62), respectively, and noncribriform cancer in 3% (2/80), 5% (5/103), and 2% (1/62), respectively (all P < 0.01). CONCLUSION: Cribriform prostate cancer was seen in a minority of needle biopsies with high-grade cancer. Stringent diagnostic criteria enabled the identification of cribriform patterns and the generation of a large set of consensus cases for standardisation.

Computational pathology in 2030: a Delphi study forecasting the role of AI in pathology within the next decade.

BACKGROUND: Artificial intelligence (AI) is rapidly fuelling a fundamental transformation in the practice of pathology. However, clinical integration remains challenging, with no AI algorithms to date in routine adoption within typical anatomic pathology (AP) laboratories. This survey gathered current expert perspectives and expectations regarding the role of AI in AP from those with first-hand computational pathology and AI experience. METHODS: Perspectives were solicited using the Delphi method from 24 subject matter experts between December 2020 and February 2021 regarding the anticipated role of AI in pathology by the year 2030. The study consisted of three consecutive rounds: 1) an open-ended, free response questionnaire generating a list of survey items; 2) a Likert-scale survey scored by experts and analysed for consensus; and 3) a repeat survey of items not reaching consensus to obtain further expert consensus. FINDINGS: Consensus opinions were reached on 141 of 180 survey items (78.3%). Experts agreed that AI would be routinely and impactfully used within AP laboratory and pathologist clinical workflows by 2030. High consensus was reached on 100 items across nine categories encompassing the impact of AI on (1) pathology key performance indicators (KPIs) and (2) the pathology workforce and specific tasks performed by (3) pathologists and (4) AP lab technicians, as well as (5) specific AI applications and their likelihood of routine use by 2030, (6) AI's role in integrated diagnostics, (7) pathology tasks likely to be fully automated using AI, and (8) regulatory/legal and (9) ethical aspects of AI integration in pathology. INTERPRETATION: This systematic consensus study details the expected short-to-mid-term impact of AI on pathology practice. These findings provide timely and relevant information regarding future care delivery in pathology and raise key practical, ethical, and legal challenges that must be addressed prior to AI's successful clinical implementation. FUNDING: No specific funding was provided for this study.

Use of the ISUP e-learning module improves interrater reliability in prostate cancer grading.

AIMS: Prostate cancer (PCa) grading is an important prognostic parameter, but is subject to considerable observer variation. Previous studies have shown that interobserver variability decreases after participants were trained using an e-learning module. However, since the publication of these studies, grading of PCa has been enhanced by adopting the International Society of Urological Pathology (ISUP) 2014 grading classification. This study investigates the effect of training on interobserver variability of PCa grading, using the ISUP Education web e-learning on Gleason grading. METHODS: The ISUP Education Prostate Test B Module was distributed among Dutch pathologists. The module uses images graded by the ISUP consensus panel consisting of 24 expert uropathologists. Participants graded the same 10 images before and after e-learning. We included those who completed the tests before and after training. We evaluated variation in PCa grading in a fully crossed study design, using linearly weighted kappa values for each pathologist, comparing them to other pathologists and to the ISUP consensus panel. We analysed the improvement in median weighted kappas before and after training, using Wilcoxon's signed rank-test. RESULTS: We included 42 pathologists. Inter-rater reliability between pathologists improved from 0.70 before training to 0.74 after training (p=0.01). When compared with the ISUP consensus panel, five pathologists improved significantly, whereas the kappa of one pathologist was significantly lower after training. All pathologists who improved significantly, graded with less than substantial agreement before training. CONCLUSIONS: ISUP Prostate Test B e-learning reduces variability in PCa grading. E-learning is a cost-effective method for standardisation of pathology.