Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers.

BACKGROUND: Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks. SUMMARY: In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches. KEY MESSAGES: Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

Endoscopic papillectomy for ampullary lesions of minor papilla.

BACKGROUND AND AIMS: Ampullary lesions (ALs) of the minor duodenal papilla are extremely rare. Endoscopic papillectomy (EP) is a routinely used treatment for AL of the major duodenal papilla, but the role of EP for minor AL has not been accurately studied. METHODS: We identified 20 patients with ALs of minor duodenal papilla in the multicentric database from the Endoscopic Papillectomy vs Surgical Ampullectomy vs Pancreatitcoduodenectomy for Ampullary Neoplasm study, which included 1422 EPs. We used propensity score matching (nearest-neighbor method) to match these cases with ALs of the major duodenal papilla based on age, sex, histologic subtype, and size of the lesion in a 1:2 ratio. Cohorts were compared by means of chi-square or Fisher exact test as well as Mann-Whitney U test. RESULTS: Propensity score-based matching identified a cohort of 60 (minor papilla 20, major papilla 40) patients with similar baseline characteristics. The most common histologic subtype of lesions of minor papilla was an ampullary adenoma in 12 patients (3 low-grade dysplasia and 9 high-grade dysplasia). Five patients revealed nonneoplastic lesions. Invasive cancer (T1a), adenomyoma, and neuroendocrine neoplasia were each found in 1 case. The rate of complete resection, en-bloc resection, and recurrences were similar between the groups. There were no severe adverse events after EP of lesions of minor papilla. One patient had delayed bleeding that could be treated by endoscopic hemostasis, and 2 patients showed a recurrence in surveillance endoscopy after a median follow-up of 21 months (interquartile range, 12-50 months). CONCLUSIONS: EP is safe and effective in ALs of the minor duodenal papilla. Such lesions could be managed according to guidelines for EP of major duodenal papilla.

[Interventional endoscopy in gastroenterology]. / Interventionelle Endoskopie in der Gastroenterologie.

Essential innovations in interventional endoscopy have significantly broadened the treatment armamentarium in gastroenterology. The treatment and complication management of intraepithelial neoplasms and early forms of cancer are increasingly being primarily addressed endoscopically. In cases of endoluminal lesions with no risk of lymph node or distant metastases, endoscopic mucosal resection and endoscopic submucosal dissection have become established as standards. For broad-based adenomas, coagulation of the resection margins should be performed in the case of a piecemeal resection. Submucosal lesions can be reached and resected by tunneling techniques. Peroral endoscopic myotomy in cases of achalasia is a new treatment option for hypertensive and hypercontractile motility disorders. In addition, endoscopic myotomy for gastroparesis has shown very promising results. In this article, new resection techniques and so-called third space endoscopy are presented and critically discussed.

Endoscopic papillectomy for ampullary lesions in patients with familial adenomatous polyposis compared with sporadic lesions: a propensity score-matched cohort.

BACKGROUND: Familial adenomatous polyposis (FAP) is a rare inherited syndrome that predisposes the patient to cancer. Treatment of FAP-related ampullary lesions is challenging and the role of endoscopic papillectomy has not been elucidated. We retrospectively analyzed the outcomes of endoscopic papillectomy in matched cohorts of FAP-related and sporadic ampullary lesions (SALs). METHODS: This retrospective multicenter study included 1422 endoscopic papillectomy procedures. Propensity score matching including age, sex, comorbidity, histologic subtype, and size was performed. Main outcomes were complete resection (R0), technical success, complications, and recurrence. RESULTS: Propensity score matching identified 202 patients (101 FAP, 101 SAL) with comparable baseline characteristics. FAP patients were mainly asymptomatic (79.2 % [95 %CI 71.2-87.3] vs. 46.5 % [95 %CI 36.6-56.4]); P < 0.001). The initial R0 rate was significantly lower in FAP patients (63.4 % [95 %CI 53.8-72.9] vs. 83.2 % [95 %CI 75.8-90.6]; P = 0.001). After repeated interventions (mean 1.30 per patient), R0 was comparable (FAP 93.1 % [95 %CI 88.0-98.1] vs. SAL 97.0 % [95 %CI 93.7-100]; P = 0.19). Adverse events occurred in 28.7 %. Pancreatitis and bleeding were the most common adverse events in both groups. Severe adverse events were rare (3.5 %). Overall, 21 FAP patients (20.8 % [95 %CI 12.7-28.8]) and 16 SAL patients (15.8 % [95 %CI 8.6-23.1]; P = 0.36) had recurrence. Recurrences occurred later in FAP patients (25 [95 %CI 18.3-31.7] vs. 2 [95 %CI CI 0.06-3.9] months). CONCLUSIONS: Endoscopic papillectomy was safe and effective in FAP-related ampullary lesions. Criteria for endoscopic resection of ampullary lesions can be extended to FAP patients. FAP patients have a lifetime risk of relapse even after complete resection, and require long-time surveillance.

Comparison between traumatic and atraumatic over-the-scope clips in patients with duodenal ulcer bleeding: a retrospective analysis with propensity score-based matching.

BACKGROUND AND AIMS: Over-the-scope clips (OTSCs) substantially improved the endoscopic armamentarium for the treatment of severe GI bleeding and can potentially overcome limitations of standard clips. Data indicate a superiority of OTSCs in hemostasis as first- and second-line therapy. However, the impact of the OTSC designs, in particular the traumatic (-t) or atraumatic (-a) type, in duodenal ulcer bleeding has not been analyzed so far. METHODS: This was a retrospective analysis of a prospective collected database from 2009 to 2020 of 6 German endoscopic centers. All patients who underwent emergency endoscopy and were treated using an OTSC for duodenal ulcer bleeding were included. OTSC-t and OTSC-a patients were compared by the Fisher exact test, χ2 test, or Mann-Whitney U test as appropriate. A propensity score-based 1:1 matching was performed to obtain equal distribution of baseline characteristics in both groups. RESULTS: The entire cohort comprised 173 patients (93 OTSC-a, 80 OTSC-t). Age, gender, anticoagulant therapy, Rockall score, and treatment regimen had similar distributions in the 2 groups. However, the OTSC-t group showed significantly more active bleeding ulcers (Forrest Ia/b). Matching identified 132 patients (66 in both groups) with comparable baseline characteristics. Initial bleeding hemostasis (OTSC-a, 90.9%; OTSC-t, 87.9%; P = .82) and 72-hour mortality (OTSC-a, 4.5%; OTSC-t, 6.0%; P > .99) were not significantly different, but the OTSC-t group revealed a clearly higher rate of recurrent bleeding (34.9% vs 7.6%, P < .001) and necessity of red blood cell transfusions (5.1 ± 3.4 vs 2.5 ± 2.4 concentrates, P < .001). CONCLUSIONS: For OTSC use, the OTSC-a should be the preferred option for duodenal ulcer bleeding.

[Endoscopic treatment for obesity and diabetes]. / Endoskopische Therapie bei Adipositas und Diabetes mellitus.

Obesity and diabetes are associated with increased mortality and morbidity. After failure of conservative therapy such as pharmacotherapy and lifestyle management, bariatric treatment is indicated for selected patients. Endoscopic techniques for weight reduction are well-established treatment for obese population who do not qualify for or are not willing to undergo bariatric surgery. This article is an overview of currently applied endoscopic techniques and summarized current published data.

Is CO2 insufflation an amelioration of routine colonoscopy?

BACKGROUND: The insufflation of gas during colonoscopy leads to distention of the colon with abdominal discomfort and pain for the patients. Use of CO2 during endoscopy is reported to minimize abdominal discomfort during and after endoscopy. Aim of this study was to find out whether this improvement leads to decreased dosage of sedation drugs in order to improve patient's safety and satisfaction. METHODS: In this double-blind, randomized and controlled study 150 Patients referred to colonoscopy were assigned to either CO2 or air insufflation. We recorded basic characteristics of colonoscopy and the amount of drugs used for sedation. Patients and investigators filled out questionnaires to record pain, abdominal bloating and flatulence. RESULTS: Seventy-two patients were randomized for examination with room air, 78 patients for use of CO2. We found no difference in basic characteristics of colonoscopy (cecal intubation time and procedure time). Both groups were administered the same amount of drugs for sedation. We found only slight improvement of pain, abdominal bloating and flatulence. CONCLUSIONS: The study revealed only moderate positive effects for use of CO2 during colonoscopy. We found only modest improvement of patient's comfort during and after colonoscopy. No reduced doses of drugs for sedation could be recorded.

Mobility-assisted on-demand routing algorithm for MANETs in the presence of location errors.

We propose a mobility-assisted on-demand routing algorithm for mobile ad hoc networks in the presence of location errors. Location awareness enables mobile nodes to predict their mobility and enhances routing performance by estimating link duration and selecting reliable routes. However, measured locations intrinsically include errors in measurement. Such errors degrade mobility prediction and have been ignored in previous work. To mitigate the impact of location errors on routing, we propose an on-demand routing algorithm taking into account location errors. To that end, we adopt the Kalman filter to estimate accurate locations and consider route confidence in discovering routes. Via simulations, we compare our algorithm and previous algorithms in various environments. Our proposed mobility prediction is robust to the location errors.

Design and fabrication of single-walled carbon nanonet flexible strain sensors.

This study presents a novel flexible strain sensor for real-time strain sensing. The material for strain sensing is single-walled carbon nanonets, grown using the alcohol catalytic chemical vapor deposition method, that were encapsulated between two layers of Parylene-C, with a polyimide layer as the sensing surface. All of the micro-fabrication was compatible with the standard IC process. Experimental results indicated that the gauge factor of the proposed strain sensor was larger than 4.5, approximately 2.0 times greater than those of commercial gauges. The results also demonstrated that the gauge factor is small when the growth time of SWCNNs is lengthier, and the gauge factor is large when the line width of the serpentine pattern of SWCNNs is small.