Helena Järemo

Background and Objective Diagnostic needle biopsies that miss clinically significant prostate cancers (PCa) likely sample benign tissue adjacent to cancer. Such samples may contain changes indicating the presence of cancer elsewhere in the organ. Our goal is to evaluate if artificial intelligence (AI) can identify morphological characteristics in benign biopsies of men with raised PSA that predict the future detection of clinically significant PCa during a 30-month follow-up. Methods A retrospective cohort of 232 patients with raised PSA and benign needle biopsies, paired by age, year of diagnosis and PSA levels was collected. Half were diagnosed with PCa within 30 months, while the other half remained cancer-free for at least eight years. AI model performance was assessed using the area under the receiver operating characteristic curve (AUC) and attention maps were used to visualise the morphological patterns relevant for cancer diagnosis as captured by the model. Key findings and Limitations The AI model could identify patients that were later diagnosed with PCa from their initial benign biopsies with an AUC of 0.82. Distinctive morphological patterns, such as altered stromal collagen and changes in glandular epithelial cell composition, were revealed. Conclusions and Clinical Implications AI applied to standard haematoxylin-eosin sections identifies patients initially diagnosed as negative but later found to have clinically significant PCa. Morphological patterns offer insights into the long-ranging effects of PCa in the benign parts of the tumour-bearing organ. Patient Summary Using AI, we identified subtle changes in normal prostate tissue suggesting the presence of tumours elsewhere in the prostate. This could aid in the early identification of potentially high-risk tumours, limiting overuse of prostate biopsies.

MicroRNAs (miRNAs) are aberrantly expressed in prostate cancer (PC), but comprehensive knowledge about their levels and function in metastatic PC is lacking. Here, we explored the differential expression of miRNA profiles during PC progression to bone metastasis, and further focused on the downregulation of miRNA-23c and -4328 and their impact on PC growth in experimental models. Using microarray screening, the levels of 1510 miRNAs were compared between bone metastases (n = 14), localized PC (n = 7) and benign prostate tissue (n = 7). Differentially expressed miRNAs (n = 4 increased and n = 75 decreased, p < 0.05) were identified, of which miRNA-1, -23c, -143-3p, -143-5p, -145-3p, -205-5p, -221-3p, -222-3p and -4328 showed consistent downregulation during disease progression (benign > localized PC > bone metastases). The downregulation of miRNA-23c and -4328 was confirmed by reverse transcription and quantitative polymerase chain reaction analysis of 67 metastasis, 12 localized PC and 12 benign prostate tissue samples. The stable overexpression of miRNA-23c and -4328 in the 22Rv1 and PC-3 cell lines resulted in reduced PC cell growth in vitro, and in the secretion of high levels of miRNA-23c (but not -4328) in extracellular vesicles. However, no tumor suppressive effects were observed from miRNA-23c overexpression in PC-3 cells subcutaneously grown in mice. In conclusion, bone metastases display a profound reduction of miRNA levels compared to localized PC and benign disease. The downregulation of those miRNAs, including miRNA-23c and -4328, may lead to a loss of tumor suppressive effects and provide biomarker and therapeutic possibilities that deserve to be further explored.