An increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer ...variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading.
We digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50–69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa.
The AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994–0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972–0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95–0·97) for the independent test dataset and 0·87 (0·84–0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60–0·73).
An AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist.
Swedish Research Council, Swedish Cancer Society, Swedish eScience Research Center, EIT Health.
Effect of Dutasteride on the Risk of Prostate Cancer Andriole, Gerald L; Bostwick, David G; Brawley, Otis W ...
New England journal of medicine/The New England journal of medicine,
04/2010, Volume:
362, Issue:
13
Journal Article
Peer reviewed
Open access
Dutasteride, an inhibitor of 5α-reductase in the prostate, was tested in a large, randomized trial to determine its ability to prevent prostate cancer. Over the 4 years of the trial, dutasteride, as ...compared with placebo, reduced the relative risk of biopsy-detected prostate cancer by 23%. The reduction was limited mainly to tumors with Gleason scores of 5 or 6; by year 4, there were 12 tumors with Gleason scores of 8 to 10 in the dutasteride group but only 1 in the placebo group.
Dutasteride, an inhibitor of 5α-reductase in the prostate, reduced the relative risk of biopsy-detected prostate cancer by 23%; however, the reduction was limited mainly to tumors with Gleason scores of 5 or 6.
The 5α-reductase inhibitors that are used to treat benign prostatic hyperplasia block the conversion of testosterone to dihydrotestosterone and may reduce the risk of prostate cancer.
1
The results of the Prostate Cancer Prevention Trial showed that finasteride, as compared with placebo, reduced the risk of prostate cancer by 25%, but among the tumors that were detected, there was a 27% increase in the number of those that had Gleason scores of 7 to 10.
2
(The Gleason score is the sum of the two most common histologic patterns or grades in a prostate tumor, each of which is graded on a . . .
To compare a new staging, three-dimensional prostate mapping biopsy (3D-PMB) method with traditional transrectal ultrasound (TRUS) biopsy and assess its possible impact on patient management.
One ...hundred eighty patients with unilateral cancer on TRUS biopsy, who were considering conservative management, underwent restaging with 3D-PMB. The 3D-PMB was carried out transperineally using a brachytherapy grid under TRUS guidance. Biopsies were taken every 5 mm throughout the volume of the prostate, and labeling of the specimen coordinates allowed accurate reconstruction of the location and extent of a patient's cancer.
3D-PMB obtained a median of 50 cores (standard deviation, +/- 20.61). One hundred ten patients (61.1%) were positive bilaterally, and 41 patients (22.7%) had Gleason scores increased to 7 or higher. Thirty-six patients had negative results on 3D-PMB. Complications of 3D-PMB were self-limited and included 14 patients (7.7%) who required short-term indwelling catheter drainage and two patients with hematuria, one of whom required overnight bladder irrigation.
3D-PMB is a transperineal biopsy that can be safely used to accurately stage prostate cancer patients. At the present time, when patient management is increasingly based on the extent and characteristics of prostate cancer, 3D-PMB could have a profound effect on patient management.
Precursors of prostate cancer Bostwick, David G; Cheng, Liang
Histopathology,
January 2012, Volume:
60, Issue:
1
Journal Article
Peer reviewed
Bostwick D G & Cheng L (2012) Histopathology 60, 4–27 Precursors of prostate cancer
High‐grade prostatic intraepithelial neoplasia (PIN) is the only accepted precursor of prostatic adenocarcinoma, ...according to numerous studies of animal models and man; other proposed precursors include atrophy and malignancy‐associated changes (with no morphologic changes). PIN is characterized by progressive abnormalities of phenotype and genotype that are intermediate between benign prostatic epithelium and cancer, indicating impairment of cell differentiation and regulatory control with advancing stages of prostatic carcinogenesis. The only method of detection of PIN is biopsy because it does not significantly elevate serum prostate‐specific antigen concentration and cannot be detected by ultrasonography. The mean incidence of PIN in biopsies is 9% (range, 4%–16%), representing about 115 000 new cases of isolated PIN diagnosed each year in the United States. The clinical importance of PIN is its high predictive value as a marker for adenocarcinoma, and its identification warrants repeat biopsy for concurrent or subsequent carcinoma, especially when multifocal or observed in association with atypical small acinar proliferation (ASAP). Carcinoma develops in most patients with PIN within 10 years. Androgen deprivation therapy and radiation therapy decrease the prevalence and extent of PIN, suggesting that these forms of treatment may play a role in prevention of subsequent cancer. Multiple clinical trials to date of men with PIN have had modest success in delaying or preventing subsequent cancer.
Abstract Objective The ongoing REDUCE trial is a 4-yr, phase 3, placebo-controlled study to determine if daily dutasteride 0.5 mg reduces the risk of biopsy detectable prostate cancer. Prostate ...biopsies performed in all men prior to entry were centrally reviewed, thus allowing an examination of the relationship between inflammatory changes and lower urinary tract symptoms (LUTS). Methods Eligible men were aged 50–75 yr, with serum prostate-specific antigen ≥2.5 ng/ml and ≤10 ng/ml (50–60 yr), or ≥3.0 ng/ml and ≤10 ng/ml (>60 yr) and an International Prostate Symptom Score (IPSS) < 25 (or <20 if already on alpha-blocker therapy). Acute prostatitis was an exclusion criterion. For a given individual, inflammation was assessed across all cores and the amount of inflammation scored as none (0), mild (1), moderate (2), or marked (3). LUTS was assessed with the use of the IPSS. The relationship between inflammation scores (averaged over all cores) and total IPSS; grouped IPSS (0–3, 4–7, 8–11, 12–15, 16–19, ≥20); and irritative, obstructive, and nocturia subscores was determined by Spearman rank correlations. The relative contribution of inflammation, age, and body mass index was then examined with the use of linear regression analyses. Results Data were available for 8224 men. Statistically significant but relatively weak correlations were found between average and maximum chronic inflammation and IPSS variables (correlation coefficients, 0.057 and 0.036, respectively; p < 0.001 for total IPSS). Both age and average chronic inflammation were significant in the linear regression after adjustment for other covariates; for both variables, more severe inflammation was associated with higher IPSS scores. Conclusions In the REDUCE population, there is evidence of a relationship between the degree of LUTS and the degree of chronic inflammation. Study entry criteria that selected older men and decreased enrolment of men with a greater degree of inflammation and LUTS may have limited the strength of this relationship. The impact of baseline prostate inflammation on progression of LUTS and/or associated complications will be determined during 4-yr longitudinal follow-up.
Prostatic stromal proliferations: a review Bostwick, David G.; Egevad, Lars
Pathology,
January 2021, 2021-Jan, 2021-01-00, 20210101, 2021, Volume:
53, Issue:
1
Journal Article
Peer reviewed
Prostatic stromal proliferations account for the majority of benign tumour-like lesions in the prostate. The most common is nodular hyperplasia, seen in a majority of elderly men. Diagnostic ...difficulty is encountered with some variants, including stromal hyperplasia with atypia, characterised by degenerative changes of myofibroblasts. In contrast with benign stromal tumours, malignant stromal tumours of the prostate are rare, accounting for less than 0.1% of all prostatic malignancies. The most common are rhabdomyosarcoma (paediatric) and leiomyosarcoma (adults); others include phyllodes tumour and stromal sarcoma. Some authors lump malignant tumours with poor outcome (e.g., phyllodes tumour and stromal sarcoma) with benign stromal tumours (e.g., stromal hyperplasia with atypia, leiomyoma), considering them collectively to be of uncertain malignant potential, but this approach is discouraged. This review presents a contemporary approach to classification and diagnosis of prostatic stromal tumours.
High-grade prostatic intraepithelial neoplasia (HGPIN) is considered a precursor lesion of prostate cancer (PCa). The predictive value of ERG gene fusion in HGPIN for PCa was interrogated as a post ...hoc analysis in the context of a randomized clinical trial.
The GTx Protocol G300104 randomly assigned 1,590 men with biopsy-diagnosed HGPIN to receive toremifene or placebo for 3 years or until a diagnosis of PCa was made on prostate biopsy. As part of this phase III clinical trial, a central pathologist evaluated biopsies of patients with isolated HGPIN at baseline and 12, 24, and 36 months of follow-up. ERG immunohistochemistry was performed on biopsies from 461 patients and evaluated for protein overexpression.
ERG expression was detected in 11.1% of patients (51 of 461 patients) with isolated HGPIN. In the first year and during the 3-year clinical trial, 14.7% and 36.9% of 461 patients were diagnosed with PCa, respectively. Patients with ERG expression were more likely to develop PCa, with 27 (53%) of 51 ERG-positive and 143 (35%) of 410 ERG-negative patients experiencing progression to PCa (P = .014, Fisher's exact test). ERG expression was not associated with age, baseline PSA, Gleason score, or tumor volume.
This study underscores the necessity of more stringent follow-up for men with HGPIN that is also positive for ERG overexpression. Clinicians should consider molecular characterization of HGPIN as a means to improve risk stratification.
The Gleason score is the most important prognostic marker for prostate cancer patients, but it suffers from significant observer variability. Artificial intelligence (AI) systems based on deep ...learning can achieve pathologist-level performance at Gleason grading. However, the performance of such systems can degrade in the presence of artifacts, foreign tissue, or other anomalies. Pathologists integrating their expertise with feedback from an AI system could result in a synergy that outperforms both the individual pathologist and the system. Despite the hype around AI assistance, existing literature on this topic within the pathology domain is limited. We investigated the value of AI assistance for grading prostate biopsies. A panel of 14 observers graded 160 biopsies with and without AI assistance. Using AI, the agreement of the panel with an expert reference standard increased significantly (quadratically weighted Cohen's kappa, 0.799 vs. 0.872; p = 0.019). On an external validation set of 87 cases, the panel showed a significant increase in agreement with a panel of international experts in prostate pathology (quadratically weighted Cohen's kappa, 0.733 vs. 0.786; p = 0.003). In both experiments, on a group-level, AI-assisted pathologists outperformed the unassisted pathologists and the standalone AI system. Our results show the potential of AI systems for Gleason grading, but more importantly, show the benefits of pathologist-AI synergy.
CONTEXT Prostate safety is a primary concern when aging men receive testosterone replacement therapy (TRT), but little information is available regarding the effects of TRT on prostate tissue in men. ...OBJECTIVE To determine the effects of TRT on prostate tissue of aging men with low serum testosterone levels. DESIGN, SETTING, AND PARTICIPANTS Randomized, double-blind, placebo-controlled trial of 44 men, aged 44 to 78 years, with screening serum testosterone levels lower than 300 ng/dL (<10.4 nmol/L) and related symptoms, conducted at a US community-based research center between February 2003 and November 2004. INTERVENTION Participants were randomly assigned to receive 150 mg of testosterone enanthate or matching placebo intramuscularly every 2 weeks for 6 months. MAIN OUTCOME MEASURES The primary outcome measure was the 6-month change in prostate tissue androgen levels (testosterone and dihydrotestosterone). Secondary outcome measures included 6-month changes in prostate-related clinical features, histology, biomarkers, and epithelial cell gene expression. RESULTS Of the 44 men randomized, 40 had prostate biopsies performed both at baseline and at 6 months and qualified for per-protocol analysis (TRT, n = 21; placebo, n = 19). Testosterone replacement therapy increased serum testosterone levels to the mid-normal range (median at baseline, 282 ng/dL 9.8 nmol/L; median at 6 months, 640 ng/dL 22.2 nmol/L) with no significant change in serum testosterone levels in matched, placebo-treated men. However, median prostate tissue levels of testosterone (0.91 ng/g) and dihydrotestosterone (6.79 ng/g) did not change significantly in the TRT group. No treatment-related change was observed in prostate histology, tissue biomarkers (androgen receptor, Ki-67, CD34), gene expression (including AR, PSA, PAP2A, VEGF, NXK3, CLU Clusterin), or cancer incidence or severity. Treatment-related changes in prostate volume, serum prostate-specific antigen, voiding symptoms, and urinary flow were minor. CONCLUSIONS These preliminary data suggest that in aging men with late-onset hypogonadism, 6 months of TRT normalizes serum androgen levels but appears to have little effect on prostate tissue androgen levels and cellular functions. Establishment of prostate safety for large populations of older men undergoing longer duration of TRT requires further study. TRIAL REGISTRATION clinicaltrials.gov Identifier: NCT00161304
PDF
