ABSTRACT
BACKGROUND: Microsatellite instability (MSI)/mismatch repair deficiency (dMMR) is a key genetic feature which should be tested in every patient with colorectal cancer (CRC) according to medical guidelines. Artificial intelligence (AI) methods can detect MSI/dMMR directly in routine pathology slides, but the test performance has not been systematically investigated with predefined test thresholds. METHOD: We trained and validated AI-based MSI/dMMR detectors and evaluated predefined performance metrics using nine patient cohorts of 8343 patients across different countries and ethnicities. RESULTS: Classifiers achieved clinical-grade performance, yielding an area under the receiver operating curve (AUROC) of up to 0.96 without using any manual annotations. Subsequently, we show that the AI system can be applied as a rule-out test: by using cohort-specific thresholds, on average 52.73% of tumors in each surgical cohort [total number of MSI/dMMR = 1020, microsatellite stable (MSS)/ proficient mismatch repair (pMMR) = 7323 patients] could be identified as MSS/pMMR with a fixed sensitivity at 95%. In an additional cohort of N = 1530 (MSI/dMMR = 211, MSS/pMMR = 1319) endoscopy biopsy samples, the system achieved an AUROC of 0.89, and the cohort-specific threshold ruled out 44.12% of tumors with a fixed sensitivity at 95%. As a more robust alternative to cohort-specific thresholds, we showed that with a fixed threshold of 0.25 for all the cohorts, we can rule-out 25.51% in surgical specimens and 6.10% in biopsies. INTERPRETATION: When applied in a clinical setting, this means that the AI system can rule out MSI/dMMR in a quarter (with global thresholds) or half of all CRC patients (with local fine-tuning), thereby reducing cost and turnaround time for molecular profiling.
Subject(s)
Colorectal Neoplasms , Microsatellite Instability , Artificial Intelligence , Colorectal Neoplasms/diagnosis , Colorectal Neoplasms/genetics , Colorectal Neoplasms/pathology , DNA Mismatch Repair/genetics , Early Detection of Cancer , HumansABSTRACT
Intravenous injection of platelet activating factor (PAF) in rats produced hypotension, neutrophilia, gastric congestion, and sloughing of the gastric epithelium. The congestion was quantified by measuring hemoglobin in the gastric mucosa. Other lesions were quantified by scores of gross pathology and histopathology. PAF-induced changes in neutrophil levels were prevented by pretreatment with the PAF-antagonist Ro24-4736, but not by the PAF-antagonist CV-3988. Both PAF antagonists reduced the hypotension, the amount of hemoglobin in the gastric mucosa, and the PAF-induced gastric pathology. These results suggest that PAF receptors involved in PAF-induced neutrophil mobilization respond differently from PAF receptors in the gastrointestinal and cardiovascular systems.
Subject(s)
Gastric Mucosa/drug effects , Gastrointestinal Hemorrhage/chemically induced , Neutrophils/drug effects , Phenanthridines/pharmacology , Phospholipid Ethers/pharmacology , Platelet Activating Factor/antagonists & inhibitors , Triazines/pharmacology , Animals , Gastrointestinal Hemorrhage/drug therapy , Hemoglobins/metabolism , Hypotension/chemically induced , Hypotension/drug therapy , Injections, Intravenous , Male , Platelet Activating Factor/administration & dosage , Platelet Activating Factor/toxicity , Rats , Rats, Sprague-DawleyABSTRACT
The anti-inflammatory activity of the IL-1 receptor antagonist, IL-1ra, was evaluated in the acetic acid (HOAc)-induced model of colitis in rats. Animals treated with 10 mg/kg IL-1ra or vehicle were evaluated for general health, acute phase response, and colonic in flammation 24 hours after the initiation of inflammation. A significant decrease in the accumulation of neutrophils in the colonic mucosa as measured by myeloperoxidase activity was seen in animals with HOAc induced colitis that were treated intraperitoneally with IL-1ra when compared to animals with colitis that had been treated with vehicle. IL-1ra also reduced colonic necrosis measured grossly, although there was no effect on the histology IL-1ra had a modest effect on the HOAc-induced acute phase response, as indicated by changes in the serum iron, albumin and transferrin, but the results were not statistically significant. The number of circulating erythrocytes and neutrophils was significantly increased in animals with HOAc-induced colitis and treated with IL-1ra, suggesting that IL-1ra under these experimental conditions inhibited the migration of neutrophils to the injured colon and also the overall intestinal necrosis in the colon as assessed by gross pathology. IL-1ra may be useful as an intestinal anti-inflammatory agent.
