No abstract

Artificial intelligence is being increasingly seen as a useful tool in medicine. Specifically, these technologies have the objective to extract insights from complex datasets that cannot easily be analyzed by conventional statistical methods. While promising results have been obtained for various -omics datasets, radiological images, and histopathologic slides, analysis of videoendoscopic frames still represents a major challenge. In this context, videomics represents a burgeoning field wherein several methods of computer vision are systematically used to organize unstructured data from frames obtained during diagnostic videoendoscopy. Recent studies have focused on five broad tasks with increasing complexity: quality assessment of endoscopic images, classification of pathologic and nonpathologic frames, detection of lesions inside frames, segmentation of pathologic lesions, and in-depth characterization of neoplastic lesions. Herein, we present a broad overview of the field, with a focus on conceptual key points and future perspectives.

Background: Numerous options to manage local reconstruction following transoral partial glossectomy are possible. In this work, we present our experience using a matrix for mucosal regeneration, IntegraÒ, after transoral resections of squamous cell carcinoma of the oral tongue. Methods: A retrospective analysis of patients treated for tongue carcinoma and reconstruction with IntegraÒ, from September 2017 to September 2022. Functional outcomes were evaluated by measuring swallowing and speech abilities, tongue motility, and subjective quality of life. Results: The series accounts for 13 consecutive patients, staged from Tis to T3, no positive resection margins were found, average defect size was 17.8 cm2. The average histologically measured depth of invasion was 4.1 mm (range 2–12 mm), and no recurrences were observed during follow-up. All patients maintained excellent swallowing function, the average number of recognized words by an external listener during a phone call was 70.5 out of 75, the lingual motility test was good (a mean score of 4.5 out of 6 movements correctly executed) and subjective questionnaires results were optimal. Less satisfying functional results were recorded in elderly patients receiving a wider surgical resection. Conclusions: This reconstructive technique for allows obtaining optimal healing and functional outcomes in patients with tumors suitable for transoral glossectomy.