Real-time near infrared artificial intelligence using scalable non-expert crowdsourcing in colorectal surgery

Surgical artificial intelligence (AI) has the potential to improve patient safety and clinical outcomes. To date, training such AI models to identify tissue anatomy requires annotations by expensive and rate-limiting surgical domain experts. Herein, we demonstrate and validate a methodology to obtain high quality surgical tissue annotations through crowdsourcing of non-experts, and real-time deployment of multimodal surgical anatomy AI model in colorectal surgery.

Family history of cancer in benign brain tumor subtypes versus gliomas

Purpose: Family history is associated with gliomas, but this association has not been established for benign brain tumors. Using information from newly diagnosed primary brain tumor patients, we describe patterns of family cancer histories in patients with benign brain tumors and compare those to patients with gliomas. Methods: Newly diagnosed primary brain tumor patients were identified as part of the Ohio Brain Tumor Study. Each patient was asked to participate in a telephone interview about personal medical history, family history of cancer, and other exposures. Information was available from 33 acoustic neuroma (65%), 78 meningioma (65%), 49 pituitary adenoma (73.1%), and 152 glioma patients (58.2%). The association between family history of cancer and each subtype was compared with gliomas using unconditional logistic regression models generating odds ratios (ORs) and 95% confidence intervals. Results: There was no significant difference in family history of cancer between patients with glioma and benign subtypes. Conclusion: The results suggest that benign brain tumor may have an association with family history of cancer. More studies are warranted to disentangle the potential genetic and/or environmental causes for these diseases.