Dottorato in EPATO-GASTROENTEROLOGIA SPERIMENTALE E CLINICA

Titolo della tesi: CLINICAL OUTCOMES OF ARTIFICIAL INTELLIGENCE IN GASTROINTESTINAL ENDOSCOPY

Colonoscopy and polypectomy are the mainstay in the prevention of colorectal cancer (CRC), and have been shown to reduce its incidence and mortality[1–3]. The development of quality improvement programs and performance measures, their measurement with audit and eventual retraining have led to an increase in adenoma detection rate (ADR), directly associated with a decrease in interval cancer (i.e. a cancer arising in the interval time between two screening colonoscopies)[4–6]. Notwithstanding the increasing awareness and the ever-improving quality, a substantial rate of colorectal neoplasia is still missed during colonoscopy, variably reported between 5 and 25%, leading to a interval colorectal cancer rate ranging between 0.5 and 1 per 1000 person-years[7]. The main reasons identified for colorectal neoplasia miss rate are both failure in recognising a lesion although fully visible on the endoscopy screen, due to attention or recognition issues, and failure to expose enough colorectal mucosa. While mucosal exposure depends on the endoscopist examination technique and the eventual use of recently developed add-on devices, failure to recognise a polyp when visible on the endoscopy screen can be addressed and improved by the application of Artificial Intelligence (AI), or “deep learning” systems[8,9]. Contrary to human-programmed computer systems, "deep learning" systems autonomously learn to distinguish the characteristics within the images provided using multiple levels of processing[10]. In this way, AI systems are able to recognize discriminatory characteristics between images that differ from those commonly used and elaborated by the human mind. In addition, an AI system developed with deep learning techniques can acquire an image processing speed so fast that it can be used in real time during an endoscopic examination. Consequently, AI systems have been recently developed that are capable of flagging with a box the suspect area during the endoscopic examination, coupled with a sound alarm. These systems have shown a high accuracy when retrospectively applied to still images or stored videos, and more recently have been tested in trials in real time during endoscopic examinations[10]. The other domain in which AI is believed to have a considerable impact on everyday clinical practice is lesion characterization and aid in “optical diagnosis”. When considering the magnitude of colonoscopies performed, covering between 1% and 6% of the target general population per year, the financial and economic burden is relevant [11]. A relevant contribution of such burden is represented by the post-polypectomy histology cost, mostly attributed to diminutive polyps that represent over 90% of all the resected lesions [12–14]. By predicting in vivo histology, such pathology costs may be averted by the implementation of two separate but synergistic strategies, namely the ‘leave-in-situ’ strategy for <5 mm hyperplastic lesions in the rectosigmoid tract, and ‘resect and discard’ for the other diminutive lesions [15,16]. Despite the very promising accuracy rates by experts, the accuracy of optical diagnosis in community setting has been suboptimal, preventing the implementation of these cost-saving interventions[17,18]. In addition, the clinical relevance of these lesions has been debated, being mostly represented by either non-advanced adenomas or indolent hyperplastic polyps. In addition, the role of pathology as reference standard has been questioned because of possible high interobserver agreement, inadequate orientation or insufficient material[19]. By automatizing the perception phase, AI may overcome both of these pitfalls in detection and characterization. Namely, Computer Aided Detection (CADe) based on deep learning can recognize in real-time lesions that are present on the screen and that may have been missed by the endoscopist. Similarly, Computer Aided Characterization (CADx) can predict the histology of the lesion providing the correct classification to the endoscopist [8]. Aim of this project is to research the clinical applications of CADe and CADx in gastrointestinal endoscopy and specifically for colorectal neoplasia. In detail, this research project will focus on summarizing the literature through systematic reviews and metanalysis that will aim to give a broad picture of the current state-of-the-art, and to further research AI applications in gastrointestinal endoscopy through clinically oriented, randomised controlled trials that will focus on its clinical outcomes.