Search

Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

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 Cohens 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 Cohens 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.

Traumatic brain injuries represent a leading cause of death and disability in the paediatric and adult populations. Moderate-to-severe injuries are associated with blood–brain barrier dysfunction, the development of cerebral oedema, and neuroinflammation. Antagonists of the tachykinin NK1 receptor have been proposed as potential agents for the post-injury treatment of TBI. We report on the identification of EUC-001 as a potential clinical candidate for development as a novel TBI therapy. EUC-001 is a selective NK1 antagonist with a high affinity for the human NK1 receptor (Ki 5.75 × 10−10 M). It has sufficient aqueous solubility to enable intravenous administration, whilst still retaining good CNS penetration as evidenced by its ability to inhibit the gerbil foot-tapping response. Using an animal model of TBI, the post-injury administration of EUC-001 was shown to restore BBB function in a dose-dependent manner. EUC-001 was also able to ameliorate cerebral oedema. These effects were associated with a significant reduction in post-TBI mortality. In addition, EUC-001 was able to significantly reduce functional deficits, both motor and cognitive, that normally follow a severe injury. EUC-001 is proposed as an ideal candidate for clinical development for TBI. [ABSTRACT FROM AUTHOR]

Sudden infant death syndrome (SIDS) occurs more often in male than in female infants, suggesting involvement of the X‐chromosome. Histopathological studies have suggested that altered expression of the Neurokinin‐1 receptor may also play a role in the pathogenesis of SIDS. It was hypothesised that genetic variants in three X‐chromosome‐encoded microRNA (miRNA/miR), known to down‐regulate expression of the Neurokinin‐1 receptor, may contribute to SIDS. Aim: To identify sequence variants in the miRNAs within a study cohort (27 cases of SIDS and 28 controls) and determine if there was a difference in the frequencies in male and female SIDS infants. Methods: Genomic DNA prepared from stored blood spots was amplified and sequenced to identify genetic variants in miR500A, miR500B and miR320D2. Results: No novel variants in the miRNAs were identified in our study cohort. We identified one known single‐nucleotide polymorphism (SNP) in miR320D2: rs5907732 G/T, in both cases and controls. No significant difference in the SNP frequency was observed between male and female SIDS cases. Conclusion: This pilot study suggests that sequence variants in three miRNAs do not contribute to the reported higher prevalence of SIDS in male infants and do not contribute to the pathogenesis of SIDS in our cohort. [ABSTRACT FROM AUTHOR]