Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists.

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.

Biological background of colorectal polyps and carcinomas with heterotopic ossification: A national study and literature review.

The biological mechanisms and potential clinical impact of heterotopic ossification (HO) in colorectal neoplasms are not fully understood. This study investigates the clinicopathological characteristics of colorectal neoplasms associated with HO and examines the potential role of the bone morphogenetic protein (BMP) pathway in development of HO. An artificial intelligence (AI) based classification of colorectal cancers (CRC) exhibiting HO and their association with consensus molecular subtypes (CMS) is performed. The study included 77 cases via the Dutch nationwide Pathology databank. Immunohistochemistry for BMP2, SMAD4, and Osterix was performed. An AI algorithm assessed the tumour-stroma ratio to approximate the CMS. A literature search yielded 96 case reports, which were analysed and compared with our cases for clinicopathological parameters. HO was more frequently observed in our cohort in traditional serrated adenomas (25%), tubulovillous adenomas (25%) and juvenile polyps (25%), while in the literature it was most often seen in juvenile polyps (38.2%) and inflammatory polyps (29.4%). In both cohorts, carcinomas were mostly conventional (>60%) followed by mucinous and serrated adenocarcinomas. Higher expression of BMP2, SMAD4, and Osterix was observed in tumour and/or stromal cells directly surrounding bone, indicating activation of the BMP pathway. The tumour-stroma analysis appointed >50% of the cases to the mesenchymal subtype (CMS4) (59%). HO has a predilection for serrated and juvenile/inflammatory polyps, mucinous and serrated adenocarcinomas. BMP signalling is activated and seems to play a role in formation of HO in colorectal neoplasms. In line with TGFß/BMP pathway activation associated with CMS4 CRC, HO seems associated with CMS4.

The effectiveness of neoadjuvant chemoradiotherapy in oesophageal adenocarcinoma with presence of extracellular mucin, signet-ring cells, and/or poorly cohesive cells.

Oesophageal adenocarcinomas may show different histopathological patterns, including excessive acellular mucin pools, signet-ring cells (SRCs), and poorly cohesive cells (PCCs). These components have been suggested to correlate with poor outcomes after neoadjuvant chemoradiotherapy (nCRT), which might influence patient management. However, these factors have not been studied independently of each other with adjustment for tumour differentiation grade (i.e. the presence of well-formed glands), which is a possible confounder. We studied the pre- and post-treatment presence of extracellular mucin, SRCs, and/or PCCs in relation to pathological response and prognosis after nCRT in patients with oesophageal or oesophagogastric junction adenocarcinoma. A total of 325 patients were retrospectively identified from institutional databases of two university hospitals. All patients were scheduled for ChemoRadiotherapy for Oesophageal cancer followed by Surgery Study (CROSS) nCRT and oesophagectomy between 2001 and 2019. Percentages of well-formed glands, extracellular mucin, SRCs, and PCCs were scored in pre-treatment biopsies and post-treatment resection specimens. The association between histopathological factors (≥1 and >10%) and tumour regression grade 3-4 (i.e. >10% residual tumour), overall survival, and disease-free survival (DFS) was evaluated, adjusted for tumour differentiation grade amongst other clinicopathological variables. In pre-treatment biopsies, ≥1% extracellular mucin was present in 66 of 325 patients (20%); ≥1% SRCs in 43 of 325 (13%), and ≥1% PCCs in 126 of 325 (39%). We show that pre-treatment histopathological factors were unrelated to tumour regression grade. Pre-treatment presence of >10% PCCs was associated with lower DFS (hazard ratio [HR] 1.73, 95% CI 1.19-2.53). Patients with post-treatment presence of ≥1% SRCs had higher risk of death (HR 1.81, 95% CI 1.10-2.99). In conclusion, pre-treatment presence of extracellular mucin, SRCs, and/or PCCs is unrelated to pathological response. The presence of these factors should not be an argument to refrain from CROSS. At least 10% PCCs pre-treatment and any SRCs post-treatment, irrespective of the tumour differentiation grade, seem indicative of inferior prognosis, but require further validation in larger cohorts.