Non-neoplastic colorectal disease biopsies: evaluation and differential diagnosis

The Histology-Driven Differential Diagnosis in Bowel Inflammatory Conditions Is Not All That Obvious: Evidence from a Survey Based on Digital Slides

(1) Background: when the pathologist faces histologic slides from colonoscopies in daily practice, given the large number of entities and etiologies under inflammatory bowel conditions, in-depth definition of the histological spectrum and the recommendations of current guidelines are often not enough to conclusively define a diagnostic framework. Histological patterns should be organized hierarchically in flowcharts that consider the correlation with clinical data. We conducted an online survey asking a group of gastroenteropathologists to apply a pattern classification based on the most significant lesions in colitis differential diagnosis: crypt distortion and activity. (2) Methods: digital slides from 20 endoscopy samples were analyzed by twenty pathologists and classified according to the occurrence of crypt distortion (nondestructive-destructive colitis) and subsequently to the evidence of activity (ND1-2-3, D1-2). (3) Results: in 8 out of 20 (40%) cases, the participants reached a full agreement regarding the evaluation of crypt distortion (5 cases: nondestructive colitis; 3 cases: destructive colitis). The calculated agreement was k = 0.432. In the second-level quiz (ND1-2-3 and D1-2), full agreement between participants was achieved for 7 of the 28 (25%) possible classifications, with k = 0.229. (4) Conclusions: The findings from this survey are indicative of an unexpectedly low consensus, even among dedicated pathologists, about the recognition of histological changes that are commonly considered critical lesions in the histologic identification of bowel non-neoplastic diseases. In our opinion, these divergences imply a significant risk of misdiagnosis of bowel inflammatory conditions, hampering the usefulness of histological assessment.

Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study

BACKGROUND

Histopathological examination is a crucial step in the diagnosis and treatment of many major diseases. Aiming to facilitate diagnostic decision making and improve the workload of pathologists, we developed an artificial intelligence (AI)-based prescreening tool that analyses whole-slide images (WSIs) of large-bowel biopsies to identify typical, non-neoplastic, and neoplastic biopsies.

METHODS

This retrospective cohort study was conducted with an internal development cohort of slides acquired from a hospital in the UK and three external validation cohorts of WSIs acquired from two hospitals in the UK and one clinical laboratory in Portugal. To learn the differential histological patterns from digitised WSIs of large-bowel biopsy slides, our proposed weakly supervised deep-learning model (Colorectal AI Model for Abnormality Detection [CAIMAN]) used slide-level diagnostic labels and no detailed cell or region-level annotations. The method was developed with an internal development cohort of 5054 biopsy slides from 2080 patients that were labelled with corresponding diagnostic categories assigned by pathologists. The three external validation cohorts, with a total of 1536 slides, were used for independent validation of CAIMAN. Each WSI was classified into one of three classes (ie, typical, atypical non-neoplastic, and atypical neoplastic). Prediction scores of image tiles were aggregated into three prediction scores for the whole slide, one for its likelihood of being typical, one for its likelihood of being non-neoplastic, and one for its likelihood of being neoplastic. The assessment of the external validation cohorts was conducted by the trained and frozen CAIMAN model. To evaluate model performance, we calculated area under the convex hull of the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and specificity compared with our previously published iterative draw and rank sampling (IDaRS) algorithm. We also generated heat maps and saliency maps to analyse and visualise the relationship between the WSI diagnostic labels and spatial features of the tissue microenvironment. The main outcome of this study was the ability of CAIMAN to accurately identify typical and atypical WSIs of colon biopsies, which could potentially facilitate automatic removing of typical biopsies from the diagnostic workload in clinics.

FINDINGS

A randomly selected subset of all large bowel biopsies was obtained between Jan 1, 2012, and Dec 31, 2017. The AI training, validation, and assessments were done between Jan 1, 2021, and Sept 30, 2022. WSIs with diagnostic labels were collected between Jan 1 and Sept 30, 2022. Our analysis showed no statistically significant differences across prediction scores from CAIMAN for typical and atypical classes based on anatomical sites of the biopsy. At 0·99 sensitivity, CAIMAN (specificity 0·5592) was more accurate than an IDaRS-based weakly supervised WSI-classification pipeline (0·4629) in identifying typical and atypical biopsies on cross-validation in the internal development cohort (p<0·0001). At 0·99 sensitivity, CAIMAN was also more accurate than IDaRS for two external validation cohorts (p<0·0001), but not for a third external validation cohort (p=0·10). CAIMAN provided higher specificity than IDaRS at some high-sensitivity thresholds (0·7763 vs 0·6222 for 0·95 sensitivity, 0·7126 vs 0·5407 for 0·97 sensitivity, and 0·5615 vs 0·3970 for 0·99 sensitivity on one of the external validation cohorts) and showed high classification performance in distinguishing between neoplastic biopsies (AUROC 0·9928, 95% CI 0·9927-0·9929), inflammatory biopsies (0·9658, 0·9655-0·9661), and atypical biopsies (0·9789, 0·9786-0·9792). On the three external validation cohorts, CAIMAN had AUROC values of 0·9431 (95% CI 0·9165-0·9697), 0·9576 (0·9568-0·9584), and 0·9636 (0·9615-0·9657) for the detection of atypical biopsies. Saliency maps supported the representation of disease heterogeneity in model predictions and its association with relevant histological features.

INTERPRETATION

CAIMAN, with its high sensitivity in detecting atypical large-bowel biopsies, might be a promising improvement in clinical workflow efficiency and diagnostic decision making in prescreening of typical colorectal biopsies.

FUNDING

The Pathology Image Data Lake for Analytics, Knowledge and Education Centre of Excellence; the UK Government's Industrial Strategy Challenge Fund; and Innovate UK on behalf of UK Research and Innovation.

Histopathological assessment of the microscopic activity in inflammatory bowel diseases: What are we looking for?

Advances in diagnostics of inflammatory bowel diseases (IBD) and improved treatment strategies allowed the establishment of new therapeutic endpoints. Currently, it is desirable not only to cease clinical symptoms, but mainly to achieve endoscopic remission, a macroscopic normalization of the bowel mucosa. However, up to one-third of IBD patients in remission exhibit persisting microscopic activity of the disease. The evidence suggests a better predictive value of histology for the development of clinical complications such as clinical relapse, surgical intervention, need for therapy escalation, or development of colorectal cancer. The proper assessment of microscopic inflammatory activity thus became an important part of the overall histopathological evaluation of colonic biopsies and many histopathological scoring indices have been established. Nonetheless, a majority of them have not been validated and no scoring index became a part of the routine bioptic practice. This review summarizes a predictive value of microscopic disease activity assessment for the subsequent clinical course of IBD, describes the most commonly used scoring indices for Crohn's disease and ulcerative colitis, and comments on current limitations and unresolved issues.

Intramucosal Calprotectin Expression in Inflammatory Bowel Disease (IBD) and Non-IBD Colorectal Inflammation

BACKGROUND: Inflammatory bowel disease (IBD) diagnosis remains a challenge accompanied with high numbers of misdiagnosis causing suboptimal management. Tons of trials have been conducted to improve the diagnostic accuracy, one of which is the use of biomarker such as calprotectin. Calprotectin can be detected in tissue (intramucosal) and is becoming a potential marker of IBD. AIM: This study aims to determine intramucosal calprotectin expression in IBD, non-IBD colitis, and control. METHODS: This analytic retrospective study included consecutively sampled IBD and non-IBD colitis colorectal biopsy specimens, and control group obtained from Cipto Mangunkusumo Hospital registered from 2017 to 2019. Cases were included in the study if specimens were indicative of IBD and non-IBD clinically and histopathologically and no abnormality were found histopathologically in the control group. Specimens with non-adequate data from the hospital medical records or with missing tissue slides were excluded from the study. Calprotectin immunostaining was conducted to evaluate mean intramucosal calprotectin expression (cell/HPF) in each group. RESULTS: Most of the samples from IBD and non-IBD group (45 samples each) showed mild active inflammation. Mucosal calprotectin expression in aforementioned groups was higher than that of control group (p < 0.001). Subjects with active inflammation showed higher calprotectin expression compared to those with inactive inflammation (p < 0.001). Calprotectin expression was also related to activity grade. CONCLUSION: Higher calprotectin expression showed significant association with the presence of inflammation and disease activity. However, the application of intramucosal calprotectin immunohistochemistry test to determine inflammatory etiology (IBD vs. non-IBD) still needs to be further evaluated.

Utilizing Deep Learning to Analyze Whole Slide Images of Colonic Biopsies for Associations Between Eosinophil Density and Clinicopathologic Features in Active Ulcerative Colitis

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.

Multiple Primary Tumors Originating From the Prostate and Colorectum A Clinical-Pathological and Therapeutic Challenge

Considering that the incidence of colorectal (CRC) and prostatic cancer (PC) increases with age, metachronous and synchronous tumors can often affect the same patient. Despite the importance of this subject for the diagnosis and management of oncologic patients, in medical literature the data are scarce. The aim of the study was to evaluate the incidence and the characteristics of double/multiple primary malignant tumors (D/MPMTs) with colorectal and prostatic origin, in patients admitted to a reference hospital in West Romania. A 4-year retrospective observational study (2016–2019) was conducted by analyzing the medical records of all patients admitted in the hospital. Demographic and clinical data, as well as tumor-related parameters, were extracted. We identified 413 consecutive hospitalized patients with PC, and 21 (5%) of them also had a primary CRC. At the time of diagnosis, the mean age of the patients with PC was 71.2 ± 6 years, and 71.8 ± 10 years for patients with CRC. Synchronous PC and CRC tumors were identified in 3/21 cases and metachronous tumors in 18/21 cases. Prostate cancer was the first tumor to be diagnosed in 13/18 cases and CRC in 5/18 cases. The most frequent subtype of PC was acinar adenocarcinoma (90%) and for CRC cases, conventional adenocarcinoma (90%). Prostate and colorectal cancers tend to co-occur in a single patient. The diagnosis of one of these two types of tumors should imply the screening for the other one, because these patients require a multidisciplinary and personalized approach.