Introduction

Histological assessment in Inflammatory Bowel Disease (IBD) is often required with endoscopic diagnoses to establish disease activity. This is evident in patients where histological healing is a major therapeutic goal and when endoscopic healing can also exhibit microscopic disease. IBD can manifest in numerous landmark features which are structural and inflammatory related. Histological activity is determined through erosion/ulceration, architectural changes in tissue morphology, mucin depletion and presence of varied inflammatory cells the colonic crypts, Muscularis Mucosae (MM) and Lamina Propria (LP). Histological scoring systems vary in complexity and methodology and subject to discrepancies in inter-rater consensus. Our model aims to provide accurate measurements of key histological features in Ulcerative Colitis (UC) used in scoring systems as both a decision support tool for improving pathologist scoring alignment and sensitive quantitative metrics of inflammatory cells to evaluate disease activity.

Aims & Methods

We developed an ensemble of convolutional neural networks to identify cell types, tissue foreground, crypts, MM, and haemorrhage in H&E images of IBD biopsy data. Models were trained with expert-labelled annotations comprising 34,289 image-annotation pairs (80% training, 20% validation) from in-house and publicly available data. Model accuracy was assessed with 6,464 held-out image-annotation pairs from 26 Whole Slide Images (WSIs) from all sites of the large intestine commonly sampled during endoscopic investigation, while ground truth annotations were reviewed by GI-trained pathologists to certify accuracy. We used geospatial methods to derive boundaries of the LP from other predicted domains, associate cells to delineated regions, measure architectural changes and derive spatially differentiated metrics of inflammatory burden in 66 patients with confirmed UC.

Results

The AI model spatially differentiates and segments cell types and tissue compartments. This produces metrics for inflammatory cell counts in regions of interest such as crypts, LP, and MM. Goblet cell segmentation within crypts allows for measurement of mucin depletion. This can be visualized for pathologists where each inflammatory cell type across the WSI is represented as density metrics. Automated quantification of inflammatory cells across AI-identified tissue domains throughout the bowels of UC patients revealed large intra- and inter-patient variability.

Conclusion

Our AI model can measure histological healing by detecting architectural change, inflammatory cell number, goblet cell reduction and erosions and ulceration. This allows for metrics and visual overlays to assist with pathologist reading and quantifying changes in mucosal biopsies in a clinical trial setting which requires extremely sensitive tools only AI can provide.

Disclosure

DW/AM/RL/PA/PW and CL are employees at Perspectum Ltd. EF and RG are consultants for Perspectum Ltd. All other co-authors have no conflicts of interest to declare relevant to this work.

Introduction

Resection rates for Crohn's disease (CD) have decreased over time, while re-resection rates have remained stable at about one-third in historic cohorts. Medical treatment has been shown to influence the course of the disease.

Aims & Methods

We aimed to assess the impact of disease burden categorization on medication use and risk factors. This cohort study encompassed all CD patients undergoing primary intestinal resection in Eastern Denmark from 2010 to 2020 (46% of the Danish population, n=2,730,000). We isolated all patients with five years follow up and divided them into three groups based on post-operative disease burden: high (one or more resections after the initial resection), intermediate (recurrence without need for resection), and low (no recurrence within five years). Disease recurrence was defined based on colonoscopy (SES-CD≥3, Rutgeerts score ≥i2), inflammation or stenosis on imaging (MRI, CTA, IUS), fecal calprotectin ≥ 250 mg/kg, starting corticosteroids or re-resection due to disease activity. Medication was classified by potency, with each patient assigned to only one category (no therapy<corticosteroids<immunomodulators<biologics). We used nonparametric statistics and the Kruskal-Wallis test to compare outcomes across groups.

Results

Primary resection was performed on 631 patients due to disease activity. Patients were categorized into burden groups: high burden (n=59), intermediate (n=287), and low (n=170). The median age at diagnosis was 28.2 years (range: 21.6-43.9), with no significant differences between the three disease burden groups (p=0.069). Age at primary resection differed across groups: 38 years (25-53) for high burden, 32 (24-45) for intermediate, and 36 (27-47) for low burden (p=0.019). Smoking rates were highest in the high burden group (47%) versus intermediate (37%) and low (27%) (p=0.010).
Pre-resection medical consumption was similar across the three burden groups (p=0.2). Postoperatively, the high burden group used more biologics (54%) compared to the low burden group (16%). Additionally, 57% of the low burden group remained recurrence-free and unmedicated for five years (Table 1). In the high burden group, no patients received prophylactic biologics, compared to 8% in the intermediate and low burden groups (p=0.001). Disease location varied: colon resections were most common in the high burden group (31%), and small bowel disease, including ileocecal resections, predominated in the low burden group (47%) (p<0.001). Strictures were more common in the intermediate and low burden groups, while luminal disease was mostly seen in the high-risk group (p=0.046) (Table 1)

Table 1. Medical characteristics and Montreal classification

Conclusion

High burden patients relied more on biologics, while half of the low burden patients stayed recurrence-free unmedicated for five years, suggesting tailored treatments could improve post-resection CD management.

Introduction

The BIOSTOP Trial is a prospective, multicenter, randomized, controlled, open-label study conducted in Norway to evaluate the two-year outcomes of tumor necrosis factor-alpha (anti-TNF) antibody withdrawal in patients with ulcerative colitis (UC) in sustained clinical and endoscopic remission. Prior non-randomized studies have suggested that approximately half of such patients maintain remission after anti-TNF discontinuation and that reintroduction of anti-TNF therapy is generally effective and safe in the event of relapse.

Aims & Methods

A total of 174 UC patients in confirmed clinical and endoscopic remission were enrolled across 19 gastroenterology centers between June 2017 and December 2020 and randomized 1:1 to either continue or discontinue anti-TNF therapy. Eligibility criteria included at least 12 months of first-line anti-TNF maintenance treatment, clinical remission, fecal calprotectin <200 µg/g, and endoscopic remission (Mayo endoscopic score 0 or 1). Two-year follow-up data were available for 172 patients (86 in each group). In 156 of the patients endoscopies were available for central reading (77 in the withdrawal group and 79 in the maintenance group). The primary endpoint was sustained endoscopic remission at two years.

Results

At two years, central reading of follow-up colonoscopies confirmed endoscopic remission in 64 of 77 patients (83%, 95% CI 71.8 – 93.1) in the anti-TNF withdrawal group, compared to 77 of 79 patients (96 %, 95 % CI 92.1 – 100.8) in the anti-TNF maintenance group. The non-inferiority primary endpoint of the study was thus not met. During the study period, 48% of patients in the withdrawal group and 88% in the maintenance group remained in sustained clinical and endoscopic remission without relapse. Among the 45 patients in the withdrawal group who experienced endoscopic confirmed relapse, 28 (62%) resumed anti-TNF therapy, with 26 achieving both clinical and endoscopic remission. Additionally, 10 of 13 patients with mild relapses achieved endoscopic remission with optimized non-biologic therapy. There were no difference in serious adverse events between the groups.

Conclusion

After two years, 83% of patients in the anti-TNF withdrawal group and 96% in the maintenance group were in clinical and endoscopic remission, including those who experienced flares and achieved new remission after reintroduction of anti-TNF or optimized non-biologic therapy. Nearly half of the patients maintained remission without anti-TNF, and the majority of relapses were effectively managed. These findings suggest that anti-TNF withdrawal is a safe option for selected UC patients in confirmed remission, provided they are monitored closely.
Trial Registration: ClinicalTrials.gov Identifier: NCT03011268; EudraCT Number: 2016-001409-18. Trial completion date: 31 January 2025.

Disclosure

No disclosures

Introduction

High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. It has shown superiority over cytology for detecting high-grade squamous intraepithelial lesions (HSIL). Nevertheless, the visual characterization of these lesions remains challenging. Preliminary studies on applying deep learning models to HRA have revealed promising results. The impact of staining techniques and anal manipulation for the treatment of precursor lesions on the effectiveness of these algorithms has not been evaluated.

Aims & Methods

Our aim was to develop a deep learning system for automatic detection and differentiation of HSIL versus low-grade squamous intraepithelial lesions (LSIL) in HRA images in different subsets of patients (non-stained, acetic acid, lugol, and after manipulation).
A convolutional neural network (CNN) was developed based on 102 HRA exams from 88 patients from a Proctology high-volume center (GH Paris Saint-Joseph, Paris, France). A total of 27,770 images were included, 19,114 images containing HSIL and 8,656 LSIL. A patient-split five-fold cross-validation analysis was performed to assess the network's performance. Partial subanalyses were performed to evaluate the performance of the CNN in the subset of images with no staining (n=2,820), acetic acid (n=13,378), lugol (n=2,195), and after treatment of the anal canal (n=9,377). For these subanalyses, training, and testing datasets comprised 90% and 10% of the total number of images for each class. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated.

Results

The overall accuracy of the CNN in distinguishing HSIL from LSIL during the testing stage was 98.3%. The algorithm had an overall sensitivity and specificity of 97.4% and 99.2%, respectively. The accuracy of the CNN for detecting HSIL vs. LSIL varied between 91.5% (post-manipulation) and 100% (lugol) for the four categories of subanalysis. The AUC ranged between 0.95 and 1.00

Conclusion

The introduction of AI algorithms to HRA may enhance the early diagnosis of ASCC precursors, improving these patients' therapeutic course and prognosis. Staining techniques are essential during HRA exams. Our algorithm showed excellent performance for staining with both Lugol and acetic acid. Moreover, the CNN showed high-level performance in the post-manipulation/treatment images subset. This is extremely important as real-time AI models during HRA exams can help guide local treatment or detect relapsing disease.

References

1. Islami F, Ferlay J, Lortet-Tieulent J, Bray F, Jemal A (2017) Inter-
national trends in anal cancer incidence rates. Int J Epidemiol
46(3):924–938. https://doi.org/10.1093/ije/dyw276
2. Smittenaar CR, Petersen KA, Stewart K, Moitt N (2016) Cancer
incidence and mortality projections in the UK until 2035. Br J
Cancer 115(9):1147–1155. https://doi.org/10.1038/bjc.2016.304
3. Ebisch RMF, Rutten DWE, IntHout J et al (2017) Long-lasting
increased risk of human papillomavirus-related carcinomas and
premalignancies after cervical intraepithelial neoplasia grade 3:
a population-based cohort study. J Clin Oncol 35(22):2542–2550.
https://doi.org/10.1200/jco.2016.71.4543
4. Deshmukh AA, Suk R, Shiels MS et al (2020) Recent trends in
squamous cell carcinoma of the anus incidence and mortality in
the United States, 2001–2015. J Natl Cancer Inst 112(8):829–838.
https://doi.org/10.1093/jnci/djz219
5. Maugin F, Lesage AC, Hoyeau N et al (2020) Early detection of
anal high-grade squamous intraepithelial lesion: do we have an
impact on progression to invasive anal carcinoma? J Low Genit
Tract Dis 24(1):82–86.