A5035439896- Thermoregulation and physiological responses
- Surgical Simulation and Training
- Cardiac, Anesthesia and Surgical Outcomes
- Climate Change and Health Impacts
- Artificial Intelligence in Healthcare and Education
- Colorectal Cancer Surgical Treatments
- Enhanced Recovery After Surgery
- Hemodynamic Monitoring and Therapy
- Infrared Thermography in Medicine
University at Buffalo, State University of New York
2023-2024
Jacobs (United States)
2023-2024
Buffalo General Medical Center
2023
Left-sided colorectal surgery demonstrates high anastomotic leak rates, with tissue ischemia thought to influence outcomes. Indocyanine green is commonly used for perfusion assessment, but evidence remains mixed whether it reduces leaks. Laser speckle contrast imaging provides dye-free assessment in real-time through heat maps and quantification. This study investigates the efficacy of advanced visualization (indocyanine versus laser imaging), utility quantification determining ischemic...
Abstract Surgical artificial intelligence (AI) has the potential to improve patient safety and clinical outcomes. To date, training such AI models identify tissue anatomy requires annotations by expensive rate-limiting surgical domain experts. Herein, we demonstrate validate a methodology obtain high quality through crowdsourcing of non-experts, real-time deployment multimodal model in colorectal surgery.
Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal for videos still lack capabilities to understand and engage conversations about surgical videos. One major contributing factor is absence of datasets field. In this paper, we create a new dataset, Surg-QA, consisting 102,000 video-instruction pairs, largest its kind so far. To...