Artificial intelligence for detection of prostate cancer in biopsies during active surveillance.

OBJECTIVES: To evaluate a cancer detecting artificial intelligence (AI) algorithm on serial biopsies in patients with prostate cancer on active surveillance (AS). PATIENTS AND METHODS: A total of 180 patients in the Prostate Cancer Research International Active Surveillance (PRIAS) cohort were prospectively monitored using pre-defined criteria. Diagnostic and re-biopsy slides from 2011 to 2020 (n = 4744) were scanned and analysed by an in-house AI-based cancer detection algorithm. The algorithm was analysed for sensitivity, specificity, and for accuracy to predict need for active treatment. Prognostic properties of cancer size, prostate-specific antigen (PSA) level and PSA density at diagnosis were evaluated. RESULTS: The sensitivity and specificity of the AI algorithm was 0.96 and 0.73, respectively, for correct detection of cancer areas. Original pathology report diagnosis was used as the reference method. The area of cancer estimated by the pathologists correlated highly with the AI detected cancer size (r = 0.83). By using the AI algorithm, 63% of the slides would not need to be read by a pathologist as they were classed as benign, at the risk of missing 0.55% slides containing cancer. Biopsy cancer content and PSA density at diagnosis were found to be prognostic of whether the patient stayed on AS or was discontinued for active treatment. CONCLUSION: The AI-based biopsy cancer detection algorithm could be used to reduce the pathologists' workload in an AS cohort. The detected cancer amount correlated well with the cancer length measured by the pathologist and the algorithm performed well in finding even small areas of cancer. To our knowledge, this is the first report on an AI-based algorithm in digital pathology used to detect cancer in a cohort of patients on AS.

Expression of tSTAT3, pSTAT3727 , and pSTAT3 705 in the epithelial cells of hormone-naïve prostate cancer.

BACKGROUND: The signal transducer and activator of transcription 3 (STAT3) pathway is observed to be constitutively activated in several malignancies including prostate cancer (PCa). In the present study, we investigated the expression of total STAT3 (tSTAT3) and two forms of activated phosphorylated STAT3 (pSTAT3727 and pSTAT3705 ) in tissue microarrays (TMA) of two cohorts of localized hormone-naïve PCa patients and analyzed associations between the expression and disease outcome. METHODS: The expression of tSTAT3, pSTAT3727 , and pSTAT3705 was scored in the nuclei and cytoplasm of prostatic gland epithelial cells in two TMAs of paraffin-embedded prostatic tissue. The TMAs consisted of tissue originated from hormone-naïve radical prostatectomy patients from two different sites: Malmö, Sweden (n = 300) and Dublin, Ireland (n = 99). RESULTS: The nuclear expression levels of tSTAT3, pSTAT3727 , and pSTAT3705 in the epithelial cells of benign glands were significantly higher than in the cancerous glands. Cytoplasmic tSTAT3 levels were also higher in benign glands. Patients with low pSTAT3727 and pSTAT3705 levels in the cancerous glands showed reduced times to biochemical recurrence, compared with those with higher levels. No significant trends in nuclear nor in cytoplasmic tSTAT3 were observed in relation to biochemical recurrence in the Malmö cohort. Higher cytoplasmic tSTAT3 was associated with reduced time to biochemical recurrence in the Dublin cohort. Adding the tSTAT3 and pSTAT3 expression data to Gleason score or pathological T stage did not improve their prognostic values. CONCLUSIONS: Low pSTAT3727 and pSTAT3705 expression in epithelial cells of cancerous prostatic glands in hormone-naïve PCa was associated with faster disease progression. However, pSTAT3 and tSTAT3 expression did not improve the prognostic value of Gleason score or pathological T stage and may not be a good biomarker in the early hormone naïve stages of PCa.

Nuclear expression of pSTAT3Tyr705 and pSTAT3Ser727 in the stromal compartment of localized hormone-naïve prostate cancer.

BACKGROUND: The signal transducer and activator of transcription 3 (STAT3) is involved in the progression of different tumors including prostate cancer (PCa). The expression of STAT3 in benign and malignant epithelium has been described previously but it has not been described in the stromal compartment. The aim of the present study was to evaluate the nuclear expression and prognostic value of different forms of phosphorylated STAT3 in the stromal compartment of non-cancer and cancer areas of prostatic tissue. MATERIAL AND METHODS: Tissue microarray cores from radical prostatectomy of 225 patients with hormone-naïve localized PCa were immunostained for two phosphorylated forms of STAT3, pSTAT3Tyr705 and pSTAT3Ser727. The prognostic value of the expression levels was studied by Cox regression analysis and biochemical recurrence (BCR)-free survival illustrated by Kaplan-Meier curves. RESULTS: Expression of pSTAT3Tyr705 and pSTAT3Ser727 in the stromal compartment of cancer tissue was lower compared with non-cancer areas. In univariable and multivariable Cox regression analysis, expression levels of pSTAT3Tyr705 and STAT3Ser727 showed similar prognostic value as pathological T-stage, Gleason score and surgical margin status. Kaplan-Meier survival analysis showed that low nuclear expression levels of pSTAT3Tyr705 and pSTAT3Ser727 in stromal cells in cancer compartment and in non-cancer areas were related to BCR-free survival. CONCLUSIONS: Nuclear expression of pSTAT3Tyr705 and pSTAT3Ser727 in the stromal cells mirrors previous findings in the epithelial component in that it displays prognostic value in men undergoing radical prostatectomy for localized hormone-naïve PCa.

An Artificial Intelligence-based Support Tool for Automation and Standardisation of Gleason Grading in Prostate Biopsies.

BACKGROUND: Gleason grading is the standard diagnostic method for prostate cancer and is essential for determining prognosis and treatment. The dearth of expert pathologists, the inter- and intraobserver variability, as well as the labour intensity of Gleason grading all necessitate the development of a user-friendly tool for robust standardisation. OBJECTIVE: To develop an artificial intelligence (AI) algorithm, based on machine learning and convolutional neural networks, as a tool for improved standardisation in Gleason grading in prostate cancer biopsies. DESIGN, SETTING, AND PARTICIPANTS: A total of 698 prostate biopsy sections from 174 patients were used for training. The training sections were annotated by two senior consultant pathologists. The final algorithm was tested on 37 biopsy sections from 21 patients, with digitised slide images from two different scanners. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Correlation, sensitivity, and specificity parameters were calculated. RESULTS AND LIMITATIONS: The algorithm shows high accuracy in detecting cancer areas (sensitivity: 100%, specificity: 68%). Compared with the pathologists, the algorithm also performed well in detecting cancer areas (intraclass correlation coefficient [ICC]: 0.99) and assigning the Gleason patterns correctly: Gleason patterns 3 and 4 (ICC: 0.96 and 0.94, respectively), and to a lesser extent, Gleason pattern 5 (ICC: 0.82). Similar results were obtained using two different scanners. CONCLUSIONS: Our AI-based algorithm can reliably detect prostate cancer and quantify the Gleason patterns in core needle biopsies, with similar accuracy as pathologists. The results are reproducible on images from different scanners with a proven low level of intraobserver variability. We believe that this AI tool could be regarded as an efficient and interactive tool for pathologists. PATIENT SUMMARY: We developed a sensitive artificial intelligence tool for prostate biopsies, which detects and grades cancer with similar accuracy to pathologists. This tool holds promise to improve the diagnosis of prostate cancer.

Histological features of medullary carcinoma and prognosis in triple-negative basal-like carcinomas of the breast.

Medullary carcinomas have a better prognosis than other grade 3 mammary carcinomas, but they typically show basal-like biological features, which are associated with a poor prognosis. In this study we examined the associations and prognostic relevance of medullary histological features in a series of 165 invasive carcinomas with a basal-like phenotype: triple-negative (oestrogen receptor, progesterone receptor, HER2) and expressing at least one basal marker (CK5/6, CK14, CK17 or EGFR). The following histological features were associated with each other: prominent inflammation, anastomosing sheets, absence of fibrosis, absence of infiltrative margin and absence of gland formation. Prominent inflammation and anastomosing sheets in at least 30% of the tumour were associated with a better prognosis on univariate analysis. The combination of these two features (a simplified definition of medullary-like type) was present in 17% of tumours and was an independent prognostic factor on multivariate analysis. This simplified definition had good inter-observer reproducibility (κ=0.61) and is worthy of more detailed assessment in an unselected group of mammary carcinomas. A fibrotic focus was present in 36% of carcinomas. Only 3% of tumours with a fibrotic focus had features of medullary-like carcinomas. Fibrotic focus of greater than 30% of the tumour was associated with a poor prognosis. This study emphasizes the heterogeneity of morphology and behaviour of triple-negative basal-like carcinomas.

Expression of STAT3 in Prostate Cancer Metastases.

STAT3 and its upstream activator IL6R have been implicated in the progression of prostate cancer and are possible future therapeutic targets. We analyzed 223 metastatic samples from rapid autopsies of 71 patients who had died of castration-resistant prostate cancer (CRPC) to study protein and gene expression of pSTAT3 and IL6R. Immunohistochemical analysis revealed that 95% of metastases were positive for pSTAT3 and IL6R, with varying expression levels. Bone metastases showed significantly higher expression of both pSTAT3 and IL6R in comparison to lymph node and visceral metastases. STAT3 mRNA levels were significantly higher in bone than in lymph node and visceral metastases, whereas no significant difference in IL6R mRNA expression was observed. Our study strongly supports the suggested view of targeting STAT3 as a therapeutic option in patients with metastatic CRPC. PATIENT SUMMARY: We studied the levels of two proteins (pSTAT3 and IL6R) in metastases from patients who died from castration-resistant prostate cancer. We found high levels of pSTAT3and IL6R in bone metastases, suggesting that these proteins could be used as targets for new anticancer drugs.