Pai, Reetesh K.

Abstract Deep learning may detect biologically important signals embedded in tumor morphologic features that confer distinct prognoses. Tumor morphologic features were quantified to enhance patient risk stratification within DNA mismatch repair (MMR) groups using deep learning. Using a quantitative segmentation algorithm (QuantCRC) that identifies 15 distinct morphologic features, we analyzed 402 resected stage III colon carcinomas [191 deficient (d)-MMR; 189 proficient (p)-MMR] from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy. Results were validated in an independent cohort (176 d-MMR; 1,094 p-MMR). Association of morphologic features with clinicopathologic variables, MMR, KRAS, BRAFV600E, and time-to-recurrence (TTR) was determined. Multivariable Cox proportional hazards models were developed to predict TTR. Tumor morphologic features differed significantly by MMR status. Cancers with p-MMR had more immature desmoplastic stroma. Tumors with d-MMR had increased inflammatory stroma, epithelial tumor-infiltrating lymphocytes (TIL), high-grade histology, mucin, and signet ring cells. Stromal subtype did not differ by BRAFV600E or KRAS status. In p-MMR tumors, multivariable analysis identified tumor-stroma ratio (TSR) as the strongest feature associated with TTR [HRadj 2.02; 95% confidence interval (CI), 1.14–3.57; P = 0.018; 3-year recurrence: 40.2% vs. 20.4%; Q1 vs. Q2–4]. Among d-MMR tumors, extent of inflammatory stroma (continuous HRadj 0.98; 95% CI, 0.96–0.99; P = 0.028; 3-year recurrence: 13.3% vs. 33.4%, Q4 vs. Q1) and N stage were the most robust prognostically. Association of TSR with TTR was independently validated. In conclusion, QuantCRC can quantify morphologic differences within MMR groups in routine tumor sections to determine their relative contributions to patient prognosis, and may elucidate relevant pathophysiologic mechanisms driving prognosis. Significance: A deep learning algorithm can quantify tumor morphologic features that may reflect underlying mechanisms driving prognosis within MMR groups. TSR was the most robust morphologic feature associated with TTR in p-MMR colon cancers. Extent of inflammatory stroma and N stage were the strongest prognostic features in d-MMR tumors. TIL density was not independently prognostic in either MMR group.

Abstract Purpose: There is a need to improve current risk stratification of stage II colorectal cancer to better inform risk of recurrence and guide adjuvant chemotherapy. We sought to examine whether integration of QuantCRC, a digital pathology biomarker utilizing hematoxylin and eosin–stained slides, provides improved risk stratification over current American Society of Clinical Oncology (ASCO) guidelines. Experimental Design: ASCO and QuantCRC-integrated schemes were applied to a cohort of 398 mismatch-repair proficient (MMRP) stage II colorectal cancers from three large academic medical centers. The ASCO stage II scheme was taken from recent guidelines. The QuantCRC-integrated scheme utilized pT3 versus pT4 and a QuantCRC-derived risk classification. Evaluation of recurrence-free survival (RFS) according to these risk schemes was compared using the log-rank test and HR. Results: Integration of QuantCRC provides improved risk stratification compared with the ASCO scheme for stage II MMRP colorectal cancers. The QuantCRC-integrated scheme placed more stage II tumors in the low-risk group compared with the ASCO scheme (62.5% vs. 42.2%) without compromising excellent 3-year RFS. The QuantCRC-integrated scheme provided larger HR for both intermediate-risk (2.27; 95% CI, 1.32–3.91; P = 0.003) and high-risk (3.27; 95% CI, 1.42–7.55; P = 0.006) groups compared with ASCO intermediate-risk (1.58; 95% CI, 0.87–2.87; P = 0.1) and high-risk (2.24; 95% CI, 1.09–4.62; P = 0.03) groups. The QuantCRC-integrated risk groups remained prognostic in the subgroup of patients that did not receive any adjuvant chemotherapy. Conclusions: Incorporation of QuantCRC into risk stratification provides a powerful predictor of RFS that has potential to guide subsequent treatment and surveillance for stage II MMRP colorectal cancers.

200 Background: We developed and validated a quantitative segmentation algorithm (QuantCRC) to predict disease recurrence in stage I-III colorectal cancer patients (pts) based on the analysis of digitized hematoxylin and eosin (H+E) stained pathology slides. In this study, we aim to determine if QuantCRC analysis on pre-treated RC biopsies can predict pathological complete response (pCR) after NAT which include total neoadjuvant therapy (TNT), chemoradiation (CRT) and others. Methods: Stage II-IV RC pts treated with curative intent modalities between 2005-2023 at Mayo Clinic and University of Pittsburgh were evaluated. Eligible pts had pre and post-treatment tissue available for analysis. Clinical characteristics, treatment, and outcome data were extracted from the medical record. QuantCRC extracted 15 features: %tumor, %stroma, tumor:stroma ratio, %TB/PDC, %mucin, %necrosis, %high-grade, %signet ring cells, tumor-infiltrating lymphocytes (TILs) per cm2 of a tumor, %immature stroma (tumor bed), %inflammatory stroma (tumor bed), %mature stroma (tumor bed), %immature (stromal region), %inflammatory (stromal region), and %mature (stromal region). The associations between the QuantCRC features and pCR were evaluated using Wilcoxon rank-sum tests and logistic regression models while adjusting for primary tumor location and NAT. Results: The identified 288 pts had the following demographics: median age 60, 59% male, 52% distal tumor, 42% TNT. Pts who achieved pCR had smaller pre-treatment tumors (p=0.03), higher TILS, and lower %immature (stroma) (Table 1). After multivariable adjustment, higher TILS and lower %immature (stroma) remain to be significantly associated with a higher likelihood of pCR. A higher %mature (stroma) and %mature stroma (tumor bed) were also identified, in multivariable models, to be associated with a higher rate of pCR. NAT protocol and tumor location (proximal vs. distal) were not associated with pCR. Conclusions: The ability to integrate pathological features with AI may allow for personalized treatment. Using this technology, we recognize that patients who harbor a more mature stromal archetype and inflammatory tumor predisposition, are more likely to achieve pCR to conventional NAT. These pathological features are not currently incorporated into risk stratification in RC. Additional validation and integration into current risk stratification methods is warranted. [Table: see text]

162 Background: There is a need to improve current risk stratification of stage II and III colorectal cancer (CRC) to better inform risk of recurrence and guide adjuvant chemotherapy. The purpose of this study is to examine whether integration of QuantCRC, an AI-based digital pathology biomarker utilizing hematoxylin and eosin-stained slides, provides improved risk stratification over current American Society of Clinical Oncology (ASCO) guidelines. Methods: ASCO and QuantCRC-integrated risk schemes were applied to an observational cohort of 1,068 stage II and III CRCs. The stage II integrated scheme utilizes pT3 vs. pT4 and QuantCRC-derived risk groups. The stage III integrated scheme utilizes pT1-3 vs. pT4, pN1 vs. pN2, and QuantCRC-derived risk groups. Performance metrics included log-rank test, hazard ratios and Somers’ Dxy rank correlation. Results: Integration of QuantCRC provides improved risk stratification compared to the ASCO scheme for stage II and III CRC. The QuantCRC-integrated scheme placed more stage II tumors in the low-risk group compared to the ASCO scheme (69.3% vs. 60.4%) without decreased 3-year RFS. The QuantCRC-integrated scheme provided larger hazard ratios (HR) for both intermediate-risk (3.04, 95%CI 1.81-5.10, P=2.8x10-5) and high-risk (4.62, 95%CI 2.02-10.61, P=0.0003) groups compared to ASCO intermediate-risk (2.09, 95%CI 1.21-3.63, P=0.008) and high-risk (3.08, 95%CI 1.57-6.01, P=0.001) groups. The QuantCRC-integrated scheme for stage III tumors identified a small group of 80/518 (15.4%) CRCs at very high risk of recurrence with HR of 4.08 (95%CI 2.68-6.23, P=6.5x10-11) compared to a HR of 2.42 (95%CI 1.72-3.38, P=3.1x10-7) for 228/518 (44.0%) high-risk CRCs in the ASCO scheme. QuantCRC-integrated risk groups remained prognostic in stage III CRCs when stratified by presence or absence of any adjuvant chemotherapy. No difference in RFS were seen in QuantCRC-integrated low-risk and intermediate-risk stage III CRCs stratified by 3 vs. 6-months of oxaliplatin-based adjuvant chemotherapy suggesting that these two groups can be treated with 3-months of adjuvant therapy. Conclusions: Incorporation of QuantCRC into risk stratification provides a powerful predictor of RFS that has potential to guide subsequent treatment and surveillance.

Abstract Purpose: To assess whether MUC1 peptide vaccine produces an immune response and prevents subsequent colon adenoma formation. Patients and Methods: Multicenter, double-blind, placebo-controlled randomized trial in individuals age 40 to 70 with diagnosis of an advanced adenoma ≤1 year from randomization. Vaccine was administered at 0, 2, and 10 weeks with a booster injection at week 53. Adenoma recurrence was assessed ≥1 year from randomization. The primary endpoint was vaccine immunogenicity at 12 weeks defined by anti-MUC1 ratio ≥2.0. Results: Fifty-three participants received the MUC1 vaccine and 50 placebo. Thirteen of 52 (25%) MUC1 vaccine recipients had a ≥2-fold increase in MUC1 IgG (range, 2.9–17.3) at week 12 versus 0/50 placebo recipients (one-sided Fisher exact P < 0.0001). Of 13 responders at week 12, 11 (84.6%) responded to a booster injection at week 52 with a ≥2-fold increase in MUC1 IgG measured at week 55. Recurrent adenoma was observed in 31 of 47 (66.0%) in the placebo group versus 27 of 48 (56.3%) in the MUC1 group [adjusted relative risk (aRR), 0.83; 95% confidence interval (CI), 0.60–1.14; P = 0.25]. Adenoma recurrence occurred in 3/11 (27.3%) immune responders at week 12 and week 55 (aRR, 0.41; 95% CI, 0.15–1.11; P = 0.08 compared with placebo). There was no difference in serious adverse events. Conclusions: An immune response was observed only in vaccine recipients. Adenoma recurrence was not different than placebo, but a 38% absolute reduction in adenoma recurrence compared with placebo was observed in participants who had an immune response at week 12 and with the booster injection.

Abstract Background The operating properties of histologic indices are poorly characterized in Crohn’s disease (CD) and no validated index exists. We assessed the reliability and responsiveness of histologic indices/items, developed an exploratory index, and compared different methods of scoring. Methods Using baseline and week 12 histologic image sets from the EXTEND placebo-controlled trial, blinded central readers scored 4 histologic indices (the Global Histologic Activity Score [GHAS], Geboes Score [GS], Robarts Histopathology Index [RHI], and Nancy Index [NHI]) and 3 additional novel items identified by an expert panel (mucin depletion, basal plasmacytosis, and pyloric gland metaplasia in the ileum). Reliability and responsiveness were evaluated for a global score (4 colonic segments + ileum), colonic score (4 colonic segments) and ileal score (ileum only) using the intraclass correlation coefficient (ICC) and area under the receiver operating curve (AUC), respectively. Change was defined using treatment assignment and improvement in histologic disease activity as measured on a 100-mm visual analogue scale (VAS) in responsiveness testing. Exploratory indices were developed using backward stepwise linear regression analysis. Candidate independent variables were items with an ICC ≥0.4 and AUC ≥0.56. The VAS served as the dependent variable. Results Paired histologic images were analysed from 55 subjects. Inter-rater reliability was substantial to almost perfect (ICC=0.73-0.85) and responsiveness was small to large (treatment assignment AUC=0.50-0.65; VAS AUC=0.71-0.94). The GHAS, GS, RHI, and NHI reached the minimum threshold for reliability (ICC ≥0.4) and responsiveness (AUC ≥0.56) regardless of whether the global and colonic scores were calculated using the worst affected segment, average of the included segments, or sum of the included segments (Table 1-3). Five items were tested as candidate predictors. Three exploratory indices were developed, each consisting of 3 items: a global index (neutrophils in the lamina propria, neutrophils in the epithelium, and erosion/ulceration), colonic index (chronic inflammatory infiltrate, neutrophils in the lamina propria, and erosion/ulceration) and ileal index (chronic inflammatory infiltrate, neutrophils in the epithelium, and erosion/ulceration). The novel indices highly correlated with the GHAS, GS, RHI, and NHI, with correlation coefficients ≥0.80 (Table 4). Conclusion The 4 existing indices were similarly reliable and responsive in measuring CD histologic activity, regardless of the method for calculating global and colonic scores and could be used in clinical trials. Attempts at novel index development did not offer benefit over current histologic indices.

Immune checkpoint inhibitor-associated colitis (ICIC) affects approximately 15% of cancer patients treated with immunotherapy. Although histological evaluation is potentially valuable for both the diagnosis of ICIC and evaluation of disease activity, use in clinical practice is heterogeneous. We aimed to develop expert recommendations to standardize histological assessment of disease activity in patients with ICIC. Using the modified Research and Development/University of California Los Angeles (RAND/UCLA) appropriateness methodology, an international panel of 11 pathologists rated the appropriateness of 99 statements on a 9-point Likert scale during two rounds of anonymous voting. Results were discussed between rounds using moderated videoconferences. There are currently no disease-specific instruments for assessing histological features of ICIC. The panel considered that colonoscopy with at least three biopsies per segment from a total of at least five segments, including both endoscopically normal and inflamed areas, was appropriate for tissue acquisition. They agreed that biopsies should be oriented such that the long axis of the colonic crypts is visualized and should be stained with hematoxylin and eosin. Histological items that the panel voted were appropriate to evaluate in ICIC included the degree of structural/architectural change, chronic inflammatory infiltrate, lamina propria and intraepithelial neutrophils, crypt abscesses and destruction, erosions/ulcerations, apoptosis, surface intraepithelial lymphocytosis, and subepithelial collagen thickness. The appropriateness of routine immunohistochemistry was uncertain. These expert recommendations will help standardize assessment of histological activity in patients with ICIC. The panel also identified the development and validation of an ICIC-specific histological index as a research priority.

Abstract Background Eosinophils have been implicated in the pathogenesis of ulcerative colitis and have been associated with disease course and therapeutic response. However, associations between eosinophil density, histologic activity, and clinical features have not been rigorously studied. Methods A deep learning algorithm was trained to identify eosinophils in colonic biopsies and validated against pathologists’ interpretations. The algorithm was applied to sigmoid colon biopsies from a cross-sectional cohort of 88 ulcerative colitis patients with histologically active disease as measured by the Geboes score and Robarts histopathology index (RHI). Associations between eosinophil density, histologic activity, and clinical features were determined. Results The eosinophil deep learning algorithm demonstrated almost perfect agreement with manual eosinophil counts determined by 4 pathologists (interclass correlation coefficients: 0.805–0.917). Eosinophil density varied widely across patients (median 113.5 cells per mm2, interquartile range 108.9). There was no association between eosinophil density and RHI (P = 0.5). Significant differences in eosinophil density were seen between patients with Montreal E3 vs E2 disease (146.2 cells per mm2 vs 88.2 cells per mm2, P = 0.005). Patients on corticosteroids had significantly lower eosinophil density (62.9 cells per mm2 vs 124.1 cells per mm2, P = 0.006). No association between eosinophil density and biologic use was observed (P = 0.5). Conclusions We developed a deep learning algorithm to quantify eosinophils in colonic biopsies. Eosinophil density did not correlate with histologic activity but did correlate with disease extent and corticosteroid use. Future studies applying this algorithm in larger cohorts with longitudinal follow-up are needed to further elucidate the role of eosinophils in ulcerative colitis.

Objective Effective medical therapy and validated trial outcomes are lacking for small bowel Crohn’s disease (CD) strictures. Histopathology of surgically resected specimens is the gold standard for correlation with imaging techniques. However, no validated histopathological scoring systems are currently available for small bowel stricturing disease. We convened an expert panel to evaluate the appropriateness of histopathology scoring systems and items generated based on panel opinion. Design Modified RAND/University of California Los Angeles methodology was used to determine the appropriateness of 313 candidate items related to assessment of CD small bowel strictures. Results In this exercise, diagnosis of naïve and anastomotic strictures required increased bowel wall thickness, decreased luminal diameter or internal circumference, and fibrosis of the submucosa. Specific definitions for stricture features and technical sampling parameters were also identified. Histopathologically, a stricture was defined as increased thickness of all layers of the bowel wall, fibrosis of the submucosa and bowel wall, and muscularisation of the submucosa. Active mucosal inflammatory disease was defined as neutrophilic inflammation in the lamina propria and any crypt or intact surface epithelium, erosion, ulcer and fistula. Chronic mucosal inflammatory disease was defined as crypt architectural distortion and loss, pyloric gland metaplasia, Paneth cell hyperplasia, basal lymphoplasmacytosis, plasmacytosis and fibrosis, or prominent lymphoid aggregates at the mucosa/submucosa interface. None of the scoring systems used to assess CD strictures were considered appropriate for clinical trials. Conclusion Standardised assessment of gross pathology and histopathology of CD small bowel strictures will improve clinical trial efficiency and aid drug development.

Abstract Background and Aims To correlate histologic activity in surveillance colonoscopies with the development of colorectal neoplasia in ulcerative colitis [UC]. Methods Colorectal biopsies during surveillance [N = 764] from 52 UC patients with colorectal neoplasia were compared to 122 patients without neoplasia enrolled in a prospective natural history registry. All biopsies were scored using validated histologic scoring systems (Geboes score, Nancy histopathologic index [NHI], and Robarts histopathologic index [RHI]). Clinical, endoscopic, and histologic data were correlated with the development of colorectal neoplasia. Results In multivariable analysis, mean RHI (hazard ratio [HR] 1.07 for each 1-unit increase in RHI, 95% confidence interval [CI] 1.03–1.12, p = 0.002) and mean NHI [HR 1.89 for each 1-unit increase in NHI, 95% CI 1.34–2.67, p = 0.002] for the entire surveillance period were significantly associated with colorectal neoplasia development. Shorter surveillance interval and increasing age were associated with increased risk of neoplasia development whereas mean Mayo endoscopic score was not significant. To generate a clinically useful measure of neoplasia risk, mean histologic activity in the preceding 5 years before the study endpoint was correlated with neoplasia development. In the preceding 5 years of surveillance, a mean RHI ≥ 8 had a 7.53-fold increased risk [95% CI 2.56–12.16, p < 0.001] and mean NHI ≥ 1.9 had a 5.89-fold increased risk [95% CI 2.18–15.92, p < 0.001] of developing colorectal neoplasia. Conclusions Persistent histologic activity during multiple surveillance episodes is an independent predictor of colorectal neoplasia. Mean RHI and mean NHI during a 5-year colonoscopic surveillance period can be used to assess risk for colorectal neoplasia and optimize UC surveillance.