Surgeon assessment of significant rectal polyps using white light endoscopy alone and in comparison to fluorescence-augmented AI lesion classification.

PURPOSE: Perioperative decision making for large (> 2 cm) rectal polyps with ambiguous features is complex. The most common intraprocedural assessment is clinician judgement alone while radiological and endoscopic biopsy can provide periprocedural detail. Fluorescence-augmented machine learning (FA-ML) methods may optimise local treatment strategy. METHODS: Surgeons of varying grades, all performing colonoscopies independently, were asked to visually judge endoscopic videos of large benign and early-stage malignant (potentially suitable for local excision) rectal lesions on an interactive video platform (Mindstamp) with results compared with and between final pathology, radiology and a novel FA-ML classifier. Statistical analyses of data used Fleiss Multi-rater Kappa scoring, Spearman Coefficient and Frequency tables. RESULTS: Thirty-two surgeons judged 14 ambiguous polyp videos (7 benign, 7 malignant). In all cancers, initial endoscopic biopsy had yielded false-negative results. Five of each lesion type had had a pre-excision MRI with a 60% false-positive malignancy prediction in benign lesions and a 60% over-staging and 40% equivocal rate in cancers. Average clinical visual cancer judgement accuracy was 49% (with only 'fair' inter-rater agreement), many reporting uncertainty and higher reported decision confidence did not correspond to higher accuracy. This compared to 86% ML accuracy. Size was misjudged visually by a mean of 20% with polyp size underestimated in 4/6 and overestimated in 2/6. Subjective narratives regarding decision-making requested for 7/14 lesions revealed wide rationale variation between participants. CONCLUSION: Current available clinical means of ambiguous rectal lesion assessment is suboptimal with wide inter-observer variation. Fluorescence based AI augmentation may advance this field via objective, explainable ML methods.

Geotemporal Fluorophore Biodistribution Mapping of Colorectal Cancer: Micro and Macroscopic Insights.

Fluorescence-guided oncology promises to improve both the detection and treatment of malignancy. We sought to investigate the temporal distribution of indocyanine green (ICG), an exogenous fluorophore in human colorectal cancer. This analysis aims to enhance our understanding of ICG's effectiveness in current tumour detection and inform potential future diagnostic and therapeutic enhancements. METHODS: Fifty consenting patients undergoing treatment for suspected/confirmed colorectal neoplasia provided near infrared (NIR) video and imagery of transanally recorded and ex vivo resected rectal lesions following intravenous ICG administration (0.25 mg/kg), with a subgroup providing tissue samples for microscopic (including near infrared) analysis. Computer vision techniques detailed macroscopic 'early' (<15 min post ICG administration) and 'late' (>2 h) tissue fluorescence appearances from surgical imagery with digital NIR scanning (Licor, Lincoln, NE, USA) and from microscopic analysis (Nikon, Tokyo, Japan) undertaken by a consultant pathologist detailing tissue-level fluorescence distribution over the same time. RESULTS: Significant intra-tumoural fluorescence heterogeneity was seen 'early' in malignant versus benign lesions. In all 'early' samples, fluorescence was predominantly within the tissue stroma, with uptake within plasma cells, blood vessels and lymphatics, but not within malignant or healthy glands. At 'late' stage observation, fluorescence was visualised non-uniformly within the intracellular cytoplasm of malignant tissue but not retained in benign glands. Fluorescence also accumulated within any present peritumoural inflammatory tissue. CONCLUSION: This study demonstrates the time course diffusion patterns of ICG through both benign and malignant tumours in vivo in human patients at both macroscopic and microscopic levels, demonstrating important cellular drivers and features of geolocalisation and how they differ longitudinally after exposure to ICG.

Clinical application of machine learning and computer vision to indocyanine green quantification for dynamic intraoperative tissue characterisation: how to do it.

INTRODUCTION: Indocyanine green (ICG) quantification and assessment by machine learning (ML) could discriminate tissue types through perfusion characterisation, including delineation of malignancy. Here, we detail the important challenges overcome before effective clinical validation of such capability in a prospective patient series of quantitative fluorescence angiograms regarding primary and secondary colorectal neoplasia. METHODS: ICG perfusion videos from 50 patients (37 with benign (13) and malignant (24) rectal tumours and 13 with colorectal liver metastases) of between 2- and 15-min duration following intravenously administered ICG were formally studied (clinicaltrials.gov: NCT04220242). Video quality with respect to interpretative ML reliability was studied observing practical, technical and technological aspects of fluorescence signal acquisition. Investigated parameters included ICG dosing and administration, distance-intensity fluorescent signal variation, tissue and camera movement (including real-time camera tracking) as well as sampling issues with user-selected digital tissue biopsy. Attenuating strategies for the identified problems were developed, applied and evaluated. ML methods to classify extracted data, including datasets with interrupted time-series lengths with inference simulated data were also evaluated. RESULTS: Definable, remediable challenges arose across both rectal and liver cohorts. Varying ICG dose by tissue type was identified as an important feature of real-time fluorescence quantification. Multi-region sampling within a lesion mitigated representation issues whilst distance-intensity relationships, as well as movement-instability issues, were demonstrated and ameliorated with post-processing techniques including normalisation and smoothing of extracted time-fluorescence curves. ML methods (automated feature extraction and classification) enabled ML algorithms glean excellent pathological categorisation results (AUC-ROC > 0.9, 37 rectal lesions) with imputation proving a robust method of compensation for interrupted time-series data with duration discrepancies. CONCLUSION: Purposeful clinical and data-processing protocols enable powerful pathological characterisation with existing clinical systems. Video analysis as shown can inform iterative and definitive clinical validation studies on how to close the translation gap between research applications and real-world, real-time clinical utility.

Beclometasone inhaler-induced recovery of refractory peri-ileostomy skin complications.

Peristomal skin complications (PSCs) are relatively common in ostomy patients, particularly in those with ileostomies. Non-healing irritation presents a clinical challenge and leads to pain and impaired quality of life for patients. METHODS: The cases of four ileostomy patients experiencing severe, challenging PSCs refractory to appliance changes, conventional dressings and barrier creams are discussed. FINDINGS: The cases of one male and one female patient with an end ileostomy post-subtotal colectomy for ulcerative colitis, one female with a defunctioning ileostomy post-anterior resection for sigmoid carcinoma and one male with an end ileostomy with a complex Crohn's surgical history are described. Two puffs of a 250 mcg metered dose beclometasone inhaler were applied to the affected skin once or twice daily. Treatment ranged from 6 to 21 days. Complete resolution was seen in all cases. CONCLUSION: Topical use of a beclometasone inhaler was effective for severe peri-ileostomy PSC secondary to four different aetiologies. Further studies are warranted to determine the effectiveness of this treatment in a larger patient cohort.

Real-time administration of indocyanine green in combination with computer vision and artificial intelligence for the identification and delineation of colorectal liver metastases.

Introduction: Fluorescence guided surgery for the identification of colorectal liver metastases (CRLM) can be better with low specificity and antecedent dosing impracticalities limiting indocyanine green (ICG) usefulness currently. We investigated the application of artificial intelligence methods (AIM) to demonstrate and characterise CLRMs based on dynamic signalling immediately following intraoperative ICG administration. Methods: Twenty-five patients with liver surface lesions (24 CRLM and 1 benign cyst) undergoing open/laparoscopic/robotic procedures were studied. ICG (0.05 mg/kg) was administered with near-infrared recording of fluorescence perfusion. User-selected region-of-interest (ROI) perfusion profiles were generated, milestones relating to ICG inflow/outflow extracted and used to train a machine learning (ML) classifier. 2D heatmaps were constructed in a subset using AIM to depict whole screen imaging based on dynamic tissue-ICG interaction. Fluorescence appearances were also assessed microscopically (using H&E and fresh-frozen preparations) to provide tissue-level explainability of such methods. Results: The ML algorithm correctly classified 97.2 % of CRLM ROIs (n = 132) and all benign lesion ROIs (n = 6) within 90-s of ICG administration following initial mathematical curve analysis identifying ICG inflow/outflow differentials between healthy liver and CRLMs. Time-fluorescence plots extracted for each pixel in 10 lesions enabled creation of 2D characterising heatmaps using flow parameters and through unsupervised ML. Microscopy confirmed statistically less CLRM fluorescence vs adjacent liver (mean ± std deviation signal/area 2.46 ± 9.56 vs 507.43 ± 160.82 respectively p < 0.001) with H&E diminishing ICG signal (n = 4). Conclusion: ML accurately identifies CRLMs from surrounding liver tissue enabling representative 2D mapping of such lesions from their fluorescence perfusion patterns using AIM. This may assist in reducing positive margin rates at metastatectomy and in identifying unexpected/occult malignancies.

Outcomes After Colonic Self-Expanding Metal Stent Insertion Without Fluoroscopy: A Surgeon-Led 10-Year Experience.

INTRODUCTION: Colonic self-expanding metal stents (SEMS) can be used to relieve malignant and benign large bowel obstruction (LBO) as a bridge to surgery (BTS) and for palliation. Guidelines suggest the use of fluoroscopic guidance for deployment. This may be difficult to obtain after hours and in certain centers. We aimed to determine the outcomes of stenting under endoscopic guidance alone. METHODS: All patients who underwent SEMS insertion in our tertiary referral center between August 2010 and June 2021 were identified from a prospectively maintained database. Patient demographics (age/gender), disease characteristics (benign versus malignant/location/stage), stenting intent (BTS versus palliative), and outcomes (technical success/stoma/time from stenting to resection/death/study end) were analyzed. RESULTS: Fifty-three (n = 39, 73.6% male) patients underwent SEMS insertion. Indications included colorectal carcinoma (n = 48, 90.6%), diverticular stricture (n = 3), and gynecological malignancy (n = 2). In five (9.4%) patients (four BTS and one palliative), SEMSs deployment was not completed because of the inability to pass the guidewire. All underwent emergency surgery. In the BTS cohort (n = 29, median 70.4 [range 40.3-91.8] years), 10 patients underwent neoadjuvant chemoradiotherapy. The permanent stoma rate was 20.7% (n = 6). There was no 30- or 90-d mortality. In the palliative cohort (n = 24, median age 77.1 [range 54.4-91.9]), 16 (66.7%) were deceased at the study end. The median time from stenting to death was 5.2 (2.3-7.9) months. CONCLUSIONS: SEMS placed under endoscopic visualization alone, palliatively and as a BTS, had acceptable stoma, morbidity, and mortality rates. These results show that SEMS insertion can be safely performed without fluoroscopy.

A fundamental change emerging in locally advanced rectal cancer management: a case report.

Treatment of locally advanced rectal cancer remains a challenge in colorectal surgery. It has had an evolving landscape over the past three decades. Implementation of total neoadjuvant therapy (TNT) as a novel approach to management has begun globally but long-term outcomes and data analysis to identify optimal schedules are eagerly awaited. We report a case of locally advanced rectal cancer management in a young male with a complete pathological response to TNT.

Ileo-ileal intussusception due to inflammatory fibroid polyp: a rare cause of small bowel obstruction in adults.

Intussusception in adults is a relatively uncommon occurrence for a cause of bowel obstruction, which can present acutely, chronically or in an acute on chronic fashion. It is clinically concerning because of the possibility of cancer acting as a lead point. Small bowel tumours are rare, mostly detected incidentally with small bowel obstruction. Inflammatory fibroid polyp (IFP) is a rare benign tumour of the small bowel, either detected incidentally on imaging or endoscopy carried out for other reasons, or presents with acute features. We present a case of small bowel intussusception caused by IFP within the distal third of the ileum as a leading point. The patient presented acutely with small bowel obstruction, on a background of recurrent non-specific abdominal pain over the preceding month, and the computed tomography scan revealed an intussusception that was timely managed with a laparoscopy-assisted small bowel segmental resection.

IL-36 signalling enhances a pro-tumorigenic phenotype in colon cancer cells with cancer cell growth restricted by administration of the IL-36R antagonist.

The IL-36 cytokines are a recently described subset of the IL-1 family of cytokines, shown to play a role in the pathogenesis of intestinal diseases such as Inflammatory Bowel Disease (IBD). Given the link between IBD and colitis -associated cancer, as well as the involvement of other IL-1 family members in intestinal tumorigenesis, the aim of this work was to investigate whether IL-36 cytokines play a role in the pathogenesis of colon cancer. Whilst research to date has focused on the role of IL-36 family members in augmenting the immune response to induce tumour rejection, very little remains known about IL-36R signalling in tumour cells in this context. In this study we demonstrate that expression of IL-36 family member mRNA and protein are significantly increased in colorectal cancer tissue compared to adjacent non-tumour. In vitro assays showed stimulation of colon cancer cell lines with IL-36R agonists resulted in the activation of the pro-tumorigenic phenotypes of increased cellular migration, invasion and proliferation in both 2D and 3D models. In addition, the IL-36 cytokines induced strong expression of pro-inflammatory chemokines in both human and murine cell lines. Intraperitoneal injection of IL-36Ra significantly reduced tumour burden using the subcutaneous CT26 tumour model in syngeneic Balb/mice, and this was associated with a decrease in Ki-67 expression by tumour cells in the IL-36Ra- treated group relative to untreated, suggesting the inhibition of the pro-proliferative signalling of IL-36 agonists resulted in the decreased tumour size. Moreover, colon cancer cells lacking the IL-36R also showed reduced tumour growth and reduced Ki-67 expression in vivo. Taken together, this data suggests that targeting IL-36R signalling may be a useful targeted therapy for colorectal cancer patients with IL-36R+ tumour cells.

Outcomes of the Macroscopically Normal Appendix Left in Situ in Patients with Suspected Appendicitis.

BACKGROUND: Right iliac fossa (RIF) pain is a common indication for laparoscopy to diagnose and treat appendicitis. When a macroscopically normal appendix is found, there is no standard consensus regarding excision. Some surgeons remove the appendix due to the risk of microscopic inflammation and to avoid a future, repeat laparoscopy for possible appendicitis. Alternatively, others leave the appendix in situ to avoid morbidity from a potentially unnecessary procedure. We aimed to evaluate the outcomes of patients with macroscopically normal appendices left in situ. METHODS: All emergency laparoscopies without appendicectomy between January 1st 2010- December 31st 2020 were identified from theatre records. All operative notes were individually evaluated and comments on the macroscopic appearance of the appendix and any intra-operative pathology were recorded. Only patients undergoing laparoscopy for suspected appendicitis with macroscopically normal appendices were included. RESULTS: A total of 120 patients [median age 21.68 (range 9-90.8) years] were included. The cohort was predominantly female (n=105, 87.5%). Forty-eight patients (40.0%) had a positive finding during index laparoscopy. During a median duration of 94.5 (range 8-131) months' follow-up, 16 patients (13.33%) underwent a repeat laparoscopy for recurrent RIF pain. Thirteen (10.8% of total cohort) subsequently underwent an appendicectomy. Histology confirmed acute appendicitis in six cases (4.17% of entire cohort). On subanalysis of smaller cohort, index laparoscopies with no positive findings (n=72), nine patients (12.5%) underwent appendicectomy with two (2.7%) appendices demonstrating appendicitis on histological examination. CONCLUSION: 87% of the total cohort with a normal appendix at laparoscopy for RIF pain did not undergo further laparoscopy. Less than 5% of the total cohort and 2.7% of subanalysis cohort had an appendicectomy for histologically-proven appendicitis within the follow-up period. From the evidence in this study, we conclude that leaving the appendix in situ unless macroscopically inflamed is a viable alternative to excision.

Intraprocedural Artificial Intelligence for Colorectal Cancer Detection and Characterisation in Endoscopy and Laparoscopy.

In this article, we provide an evidence-based primer of current tools and evolving concepts in the area of intraprocedural artificial intelligence (AI) methods in colonoscopy and laparoscopy as a 'procedure companion', with specific focus on colorectal cancer recognition and characterisation. These interventions are both likely beneficiaries from an impending rapid phase in technical and technological evolution. The domains where AI is most likely to impact are explored as well as the methodological pitfalls pertaining to AI methods. Such issues include the need for large volumes of data to train AI systems, questions surrounding false positive rates, explainability and interpretability as well as recent concerns surrounding instabilities in current deep learning (DL) models. The area of biophysics-inspired models, a potential remedy to some of these pitfalls, is explored as it could allow our understanding of the fundamental physiological differences between tissue types to be exploited in real time with the help of computer-assisted interpretation. Right now, such models can include data collected from dynamic fluorescence imaging in surgery to characterise lesions by their biology reducing the number of cases needed to build a reliable and interpretable classification system. Furthermore, instead of focussing on image-by-image analysis, such systems could analyse in a continuous fashion, more akin to how we view procedures in real life and make decisions in a manner more comparable to human decision-making. Synergistical approaches can ensure AI methods usefully embed within practice thus safeguarding against collapse of this exciting field of investigation as another 'boom and bust' cycle of AI endeavour.

Inter-user variation in the interpretation of near infrared perfusion imaging using indocyanine green in colorectal surgery.

INTRODUCTION: Despite increasing endorsement of near-infrared perfusion assessment using indocyanine green (ICG) during colorectal surgery, little work has yet been done regarding learning curve and interobserver variation most especially on surgical video reflective of real-world usage. METHODS: Surgeons with established expertise in ICG usage were invited to participate in the study along with others without such experience including trainees. All participants completed an opinion questionnaire and interpreted video presentations of fluorescence angiograms in a variety of colorectal case scenarios. An interactive video platform (Mindstamp) enabled dynamic annotation. Statistical analysis of data was performed using Kruskal-Wallis and Mann-Whitney testing as well as Intraclass Correlation Coefficients and Fleiss Multi-rater Kappa Scoring. RESULTS: Forty participants (six experts) completed questionnaire data and provided judgement of 14 videos (nine showing proximal colonic transection site perfusion, four showing completed anastomoses and one an acutely strangulated bowel). 70% felt > 10 cases were needed for competency in use with the majority of experts advocating > 50 (p < 0.05). Overall agreement among experts was "good" for videos showing colonic transection perfusion (versus "moderate" among in-experts) with experts clustering more distally. In contrast, there was no interpretation concordance among experts or in-experts when judging ICG perfusion sufficiency on a yes/no basis. CONCLUSION: Significant experience is recommended before reliance on ICG perfusion angiograms. ICG fluorescence assessment is prone to variable interpretation and influenced by experience and, perhaps, knowledge of preassessment operative steps suggesting a role for objective flow analysis with artificial intelligence methods as the next phase of this technology.

High-Risk Ileocolic Anastomoses for Crohn's Disease: When Is Diversion Indicated?

BACKGROUND AND AIMS: Patients with Crohn's disease undergoing ileocolectomy and primary anastomosis are often at increased risk of anastomotic leak. We aimed to determine whether diverting ileostomy was protective against anastomotic leak after ileocolic resection for Crohn's disease using a large international registry. METHODS: We analysed the National Surgical Quality Improvement Program Colectomy Module from 2012 to 2016. Multivariable logistic regression analysis and propensity-score matching were used to identify independent risk factors for leak, and to test the hypothesis that diverting ileostomy was protective against anastomotic leakage. RESULTS: A total of 4172 [92%] patients underwent primary anastomosis, and 365 [8%] underwent anastomosis plus ileostomy. The leak rates in the two groups were 4.5% and 2.7%, [p = 0.12], respectively. Multivariate analysis indicated ileostomy omission, emergency surgery, smoking, inpatient status, wound classification 3 or 4, weight loss, steroid use, and prolonged operative time were independently associated with leak. Patients with 0-6 risk factors had leak rates of 1.6%, 2.7%, 4.3%, 6.7%, 8.8%, 11.5%, and 14.3% [p ≤ 0.001], respectively. Following propensity-score matching, ileostomy reduced the risk of leak rate by 55% [p = 0.005]. Patients with primary anastomosis who leaked most frequently required reoperation [57.8%], but anastomosis plus ileostomy patients who leaked most frequently were managed by percutaneous drainage [70%], p = 0.04. CONCLUSIONS: After ileocolic resection for Crohn's disease, anastomotic leak may be predicted by simple addition of risk factors. We found that diverting ileostomy mitigated against leak, reducing both the leak rate and the likelihood of unplanned reoperations. Faecal diversion should be considered when ≥3 risk factors are present.

Aspects of the Natural History of Sessile Serrated Adenomas/Polyps: Risk Indicators for Carcinogenesis in the Colorectal Mucosa?

BACKGROUND: Sessile serrated adenomas/polyps are potentially premalignant colorectal lesions that are precursors to colorectal cancer arising via CpG island methylator phenotype. They are caused by the combination of a BRAF mutation and promoter hypermethylation. DNA methylation is an age-dependent phenomenon in the right colon, and we would expect the occurrence and severity of serrated neoplasia to reflect this. OBJECTIVE: The purpose of this study was to document the natural history of sessile serrated adenomas/polyps, including the ages at which they appear and the ranges of their number, size, and associated lesions. DESIGN: This was a retrospective cohort study. SETTINGS: The study was conducted at a tertiary referral center. PATIENTS: Consecutive patients with sessile serrated adenomas/polyps removed between 2006 and 2015 were included. Patients with IBD, familial adenomatous polyposis, Lynch syndrome, serrated polyposis, and hereditary nonpolyposis colorectal cancer were excluded. MAIN OUTCOME MEASURES: Age at which polyps were first diagnosed, location and size of polyps, demographics, and family history were measured. RESULTS: A total of 440 patients had 668 sessile serrated adenomas/polyps, 257 (58%) also had ≥1 adenoma, and 28 (6%) had a history of colorectal cancer. Mean age at diagnosis was 68 ± 11 years, and 45% were men. Two hundred had had ≥1 colonoscopy before the diagnosis of the first sessile serrated adenomas/polyps. A total of 136 patients (31%) had multiple sessile serrated adenomas/polyps, including 24% synchronous and 10% metachronous. The range of total cumulative sessile serrated adenomas/polyps was from 1 to 7. A total of 554 (83%) of 668 sessile serrated adenomas/polyps were right sided; 48% were ≥1 cm diameter and 22% were >2 cm. The size of the first sessile serrated adenomas/polyps in those diagnosed under age 50 years averaged 10 mm, those between 50 and 60 years averaged 12 mm, and those between 60 and 70 years averaged 12 mm. LIMITATIONS: No measurement of methylation or BRAF mutations in polyps or normal mucosa and a lack of subclassification of hyperplastic polyps limited this study. CONCLUSIONS: The age of onset of sessile serrated adenomas/polyps varies, but the pattern is consistent with increasing methylation in the mucosa. Early negative colonoscopies predict a low risk of methylator cancers. See Video Abstract at http://links.lww.com/DCR/A736.