Intraoperative near infrared functional imaging of rectal cancer using artificial intelligence methods - now and near future state of the art.

Colorectal cancer remains a major cause of cancer death and morbidity worldwide. Surgery is a major treatment modality for primary and, increasingly, secondary curative therapy. However, with more patients being diagnosed with early stage and premalignant disease manifesting as large polyps, greater accuracy in diagnostic and therapeutic precision is needed right from the time of first endoscopic encounter. Rapid advancements in the field of artificial intelligence (AI), coupled with widespread availability of near infrared imaging (currently based around indocyanine green (ICG)) can enable colonoscopic tissue classification and prognostic stratification for significant polyps, in a similar manner to contemporary dynamic radiological perfusion imaging but with the advantage of being able to do so directly within interventional procedural time frames. It can provide an explainable method for immediate digital biopsies that could guide or even replace traditional forceps biopsies and provide guidance re margins (both areas where current practice is only approximately 80% accurate prior to definitive excision). Here, we discuss the concept and practice of AI enhanced ICG perfusion analysis for rectal cancer surgery while highlighting recent and essential near-future advancements. These include breakthrough developments in computer vision and time series analysis that allow for real-time quantification and classification of fluorescent perfusion signals of rectal cancer tissue intraoperatively that accurately distinguish between normal, benign, and malignant tissues in situ endoscopically, which are now undergoing international prospective validation (the Horizon Europe CLASSICA study). Next stage advancements may include detailed digital characterisation of small rectal malignancy based on intraoperative assessment of specific intratumoral fluorescent signal pattern. This could include T staging and intratumoral molecular process profiling (e.g. regarding angiogenesis, differentiation, inflammatory component, and tumour to stroma ratio) with the potential to accurately predict the microscopic local response to nonsurgical treatment enabling personalised therapy via decision support tools. Such advancements are also applicable to the next generation fluorophores and imaging agents currently emerging from clinical trials. In addition, by providing an understandable, applicable method for detailed tissue characterisation visually, such technology paves the way for acceptance of other AI methodology during surgery including, potentially, deep learning methods based on whole screen/video detailing.

CLASSICA: Validating artificial intelligence in classifying cancer in real time during surgery.

AIM: Treatment pathways for significant rectal polyps differ depending on the underlying pathology, but pre-excision profiling is imperfect. It has been demonstrated that differences in fluorescence perfusion signals following injection of indocyanine green (ICG) can be analysed mathematically and, with the assistance of artificial intelligence (AI), used to classify tumours endoscopically as benign or malignant. This study aims to validate this method of characterization across multiple clinical sites regarding its generalizability, usability and accuracy while developing clinical-grade software to enable it to become a useful method. METHODS: The CLASSICA study is a prospective, unblinded multicentre European observational study aimed to validate the use of AI analysis of ICG fluorescence for intra-operative tissue characterization. Six hundred patients undergoing transanal endoscopic evaluation of significant rectal polyps and tumours will be enrolled in at least five clinical sites across the European Union over a 4-year period. Video recordings will be analysed regarding dynamic fluorescence patterns centrally as software is developed to enable analysis with automatic classification to happen locally. AI-based classification and subsequently guided intervention will be compared with the current standard of care including biopsies, final specimen pathology and patient outcomes. DISCUSSION: CLASSICA will validate the use of AI in the analysis of ICG fluorescence for the purposes of classifying significant rectal polyps and tumours endoscopically. Follow-on studies will compare AI-guided targeted biopsy or, indeed, AI characterization alone with traditional biopsy and AI-guided local excision versus traditional excision with regard to marginal clearance and recurrence.

Aerosols, airflow, and airspace contamination during laparoscopy.

Laparoscopic surgery has been undermined throughout the COVID-19 pandemic by concerns that it may generate an infectious risk to the operating team through aerosolization of peritoneal particles. There is anyway a need for increased awareness and understanding of the occupational hazard for surgical teams regarding unfiltered escape of pollutants generated by surgical smoke and other microbials. Here, the aerosol-generating nature of this access modality was confirmed through repeatable real-time methodology both qualitatively and quantitively to inform best practice and additional engineering solutions to optimize the operating room environment.

Laparoscopic surgery has been undermined throughout the COVID-19 pandemic by concerns that it may generate an infectious risk to the operating team through aerosolization of peritoneal particles. There is anyway a need for increased awareness and understanding of the occupational hazard for surgical teams regarding unfiltered escape of pollutants generated by surgical smoke and other microbials. Here, the aerosol-generating nature of this access modality was confirmed through repeatable real-time methodology both qualitatively and quantitively to inform best practice and additional engineering solutions to optimize the operating room environment.

Solving the problems of gas leakage at laparoscopy.

Gas leakage during minimally invasive surgery is an aerosolization hazard. Sensitive optical and thermographic imaging can demonstrate and differentiate between mechanistic categories, enabling engineering solutions to fortify surgical care against pollutants and pathogens affecting operating room teams. Areas for improvement.

Multicentre phase II trial of near-infrared imaging in elective colorectal surgery.

BACKGROUND: Decreasing anastomotic leak rates remain a major goal in colorectal surgery. Assessing intraoperative perfusion by indocyanine green (ICG) with near-infrared (NIR) visualization may assist in selection of intestinal transection level and subsequent anastomotic vascular sufficiency. This study examined the use of NIR-ICG imaging in colorectal surgery. METHODS: This was a prospective phase II study (NCT02459405) of non-selected patients undergoing any elective colorectal operation with anastomosis over a 3-year interval in three tertiary hospitals. A standard protocol was followed to assess NIR-ICG perfusion before and after anastomosis construction in comparison with standard operator visual assessment alone. RESULTS: Five hundred and four patients (median age 64 years, 279 men) having surgery for neoplastic (330) and benign (174) pathology were studied. Some 425 operations (85·3 per cent) were started laparoscopically, with a conversion rate of 5·9 per cent. In all, 220 patients (43·7 per cent) underwent high anterior resection or reversal of Hartmann's operation, and 90 (17·9 per cent) low anterior resection. ICG angiography was achieved in every patient, with a median interval of 29 s to visualization of the signal after injection. NIR-ICG assessment resulted in a change in the site of bowel division in 29 patients (5·8 per cent) with no subsequent leaks in these patients. Leak rates were 2·4 per cent overall (12 of 504), 2·6 per cent for colorectal anastomoses and 3 per cent for low anterior resection. When NIR-ICG imaging was used, the anastomotic leak rates were lower than those in the participating centres from over 1000 similar operations performed with identical technique but without NIR-ICG technology. CONCLUSION: Routine NIR-ICG assessment in patients undergoing elective colorectal surgery is feasible. NIR-ICG use may change intraoperative decisions, which may lead to a reduction in anastomotic leak rates.

IntAct: intra-operative fluorescence angiography to prevent anastomotic leak in rectal cancer surgery: a randomized controlled trial.

AIM: Anastomotic leak (AL) is a major complication of rectal cancer surgery. Despite advances in surgical practice, the rates of AL have remained static, at around 10-15%. The aetiology of AL is multifactorial, but one of the most crucial risk factors, which is mostly under the control of the surgeon, is blood supply to the anastomosis. The MRC/NIHR IntAct study will determine whether assessment of anastomotic perfusion using a fluorescent dye (indocyanine green) and near-infrared laparoscopy can minimize the rate of AL leak compared with conventional white-light laparoscopy. Two mechanistic sub-studies will explore the role of the rectal microbiome in AL and the predictive value of CT angiography/perfusion studies. METHOD: IntAct is a prospective, unblinded, parallel-group, multicentre, European, randomized controlled trial comparing surgery with intra-operative fluorescence angiography (IFA) against standard care (surgery with no IFA). The primary end-point is rate of clinical AL at 90 days following surgery. Secondary end-points include all AL (clinical and radiological), change in planned anastomosis, complications and re-interventions, use of stoma, cost-effectiveness of the intervention and quality of life. Patients should have a diagnosis of adenocarcinoma of the rectum suitable for potentially curative surgery by anterior resection. Over 3 years, 880 patients from 25 European centres will be recruited and followed up for 90 days. DISCUSSION: IntAct will rigorously evaluate the use of IFA in rectal cancer surgery and explore the role of the microbiome in AL and the predictive value of preoperative CT angiography/perfusion scanning.

A collaborative review of the current concepts and challenges of anastomotic leaks in colorectal surgery.

The reduction of the incidence, detection and treatment of anastomotic leakage (AL) continues to challenge the colorectal surgical community. AL is not consistently defined and reported in clinical studies, its occurrence is variably reported and its impact on longterm morbidity and health-care resources has received relatively little attention. Controversy continues regarding the best strategies to reduce the risk. Diagnostic tests lack sensitivity and specificity, resulting in delayed diagnosis and increased morbidity. Intra-operative fluorescence angiography has recently been introduced as a means of real-time assessment of anastomotic perfusion and preliminary evidence suggests that it may reduce the rate of AL. In addition, concepts are emerging about the role of the rectal mucosal microbiome in AL and the possible role of new prophylactic therapies. In January 2016 a meeting of expert colorectal surgeons and pathologists was held in London, UK, to identify the ongoing controversies surrounding AL in colorectal surgery. The outcome of the meeting is presented in the form of research challenges that need to be addressed.

Near-infrared laparoscopic fluorescence for pelvic side wall delta mapping in patients with rectal cancer--'PINPOINT' nodal assessment.

Low rectal cancers metastase lymphatically to the pelvic side wall in addition to cephalad spread alongside the superior rectal/inferior mesenteric arterial axis. Radical surgery in the West has focused resectional intent and effort on the midline en bloc oncological package by Total Mesorectal Excision. While neoadjuvant chemo/radiotherapy (now often administered to patients with radiologically locally advanced cancer) may contribute significant therapeutic effect to the lateral pelvic side walls, many patients with earlier preoperative stage low rectal cancer are offered surgery first (and indeed solely). Furthermore, some of those pretreated may have residual in situ lateral nodal disease and so risk understaging and undertreatment. Routine extended lymphadenectomy is on the other hand unproven with respect to survival benefit and has likely no added role in the absence of definite (rather than possible) side-wall involvement. Near-infrared fluorescence pelvic side-wall delta mapping, as illustrated here in five patients undergoing abdominoperineal resection for rectal cancer after neoadjuvant therapy, may give the technological capacity to identify tumor site-draining nodes on the pelvic side and the focus the operating surgeon on this potential target for surgical resection (whether by berry picking or nerve sparing clearance) and prompt individualized diagnostic and therapeutic selection.