The development of artificial intelligence (AI) algorithms has permeated the medical field with great success. The widespread use of AI technology in diagnosing and treating several types of cancer, especially colorectal cancer (CRC), is now attracting substantial attention. CRC, which represents the third most commonly diagnosed malignancy in both men and women, is considered a leading cause of cancer-related deaths globally. Our review herein aims to provide in-depth knowledge and analysis of the AI applications in CRC screening, diagnosis, and treatment based on current literature. We also explore the role of recent advances in AI systems regarding medical diagnosis and therapy, with several promising results. CRC is a highly preventable disease, and AI-assisted techniques in routine screening represent a pivotal step in declining incidence rates of this malignancy. So far, computer-aided detection and characterization systems have been developed to increase the detection rate of adenomas. Furthermore, CRC treatment enters a new era with robotic surgery and novel computer-assisted drug delivery techniques. At the same time, healthcare is rapidly moving toward precision or personalized medicine. Machine learning models have the potential to contribute to individual-based cancer care and transform the future of medicine.

Anastomotic leakage (AL) remains one of the most severe complications following colorectal cancer (CRC) surgery. Indeed, leaks that may occur after any type of intestinal anastomosis are commonly associated with a higher reoperation rate and an increased risk of postoperative morbidity and mortality. At first, our review aims to identify specific preoperative, intraoperative and perioperative factors that eventually lead to the development of anastomotic dehiscence based on the current literature. We will also investigate the role of several biomarkers in predicting the presence of ALs following colorectal surgery. Despite significant improvements in perioperative care, advances in surgical techniques, and a high index of suspicion of this complication, the incidence of AL remained stable during the last decades. Thus, gaining a better knowledge of the risk factors that influence the AL rates may help identify high-risk surgical patients requiring more intensive perioperative surveillance. Furthermore, prompt diagnosis of this severe complication may help improve patient survival. To date, several studies have identified predictive biomarkers of ALs, which are most commonly associated with the inflammatory response to colorectal surgery. Interestingly, early diagnosis and evaluation of the severity of this complication may offer a significant opportunity to guide clinical judgement and decision-making.

Focal nodular hyperplasia (FNH) is the second most common benign hepatic tumor and can rarely present as an exophytic solitary mass attached to the liver by a stalk. Most FNH cases are usually detected as incidental findings during surgery, imaging or physical examination and have a high female predominance. However, the pedunculated forms of FNH are particularly rare and commonly associated with severe complications and diagnostic challenges. Hence, our study aims to provide a comprehensive summary of the available data on the pedunculated FNH cases among adults and children. Furthermore, we will highlight the role of different therapeutic options in treating this clinical entity. The use of imaging techniques is considered a significant addition to the diagnostic toolbox. Regarding the optimal treatment strategy, the main indications for surgery were the presence of symptoms, diagnostic uncertainty and increased risk of complications, based on the current literature. Herein, we also propose a management algorithm for patients with suspected FNH lesions. Therefore, a high index of suspicion and awareness of this pathology and its life-threatening complications, as an uncommon etiology of acute abdomen, is of utmost importance in order to achieve better clinical outcomes.