Artificial Intelligence Enabled Histological Prediction of Remission or Activity and Clinical Outcomes in Ulcerative Colitis.

BACKGROUND & AIMS: Microscopic inflammation has significant prognostic value in ulcerative colitis (UC); however, its assessment is complex with high interobserver variability. We aimed to develop and validate an artificial intelligence (AI) computer-aided diagnosis system to evaluate UC biopsies and predict prognosis. METHODS: A total of 535 digitalized biopsies (273 patients) were graded according to the PICaSSO Histologic Remission Index (PHRI), Robarts, and Nancy Histological Index. A convolutional neural network classifier was trained to distinguish remission from activity on a subset of 118 biopsies, calibrated on 42 and tested on 375. The model was additionally tested to predict the corresponding endoscopic assessment and occurrence of flares at 12 months. The system output was compared with human assessment. Diagnostic performance was reported as sensitivity, specificity, prognostic prediction through Kaplan-Meier, and hazard ratios of flares between active and remission groups. We externally validated the model in 154 biopsies (58 patients) with similar characteristics but more histologically active patients. RESULTS: The system distinguished histological activity/remission with sensitivity and specificity of 89% and 85% (PHRI), 94% and 76% (Robarts Histological Index), and 89% and 79% (Nancy Histological Index). The model predicted the corresponding endoscopic remission/activity with 79% and 82% accuracy for UC endoscopic index of severity and Paddington International virtual ChromoendoScopy ScOre, respectively. The hazard ratio for disease flare-up between histological activity/remission groups according to pathologist-assessed PHRI was 3.56, and 4.64 for AI-assessed PHRI. Both histology and outcome prediction were confirmed in the external validation cohort. CONCLUSION: We developed and validated an AI model that distinguishes histologic remission/activity in biopsies of UC and predicts flare-ups. This can expedite, standardize, and enhance histologic assessment in practice and trials.

A virtual chromoendoscopy artificial intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in ulcerative colitis.

BACKGROUND: Endoscopic and histological remission (ER, HR) are therapeutic targets in ulcerative colitis (UC). Virtual chromoendoscopy (VCE) improves endoscopic assessment and the prediction of histology; however, interobserver variability limits standardized endoscopic assessment. We aimed to develop an artificial intelligence (AI) tool to distinguish ER/activity, and predict histology and risk of flare from white-light endoscopy (WLE) and VCE videos. METHODS: 1090 endoscopic videos (67 280 frames) from 283 patients were used to develop a convolutional neural network (CNN). UC endoscopic activity was graded by experts using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Paddington International virtual ChromoendoScopy ScOre (PICaSSO). The CNN was trained to distinguish ER/activity on endoscopy videos, and retrained to predict HR/activity, defined according to multiple indices, and predict outcome; CNN and human agreement was measured. RESULTS: The AI system detected ER (UCEIS ≤ 1) in WLE videos with 72 % sensitivity, 87 % specificity, and an area under the receiver operating characteristic curve (AUROC) of 0.85; for detection of ER in VCE videos (PICaSSO ≤ 3), the sensitivity was 79 %, specificity 95 %, and the AUROC 0.94. The prediction of HR was similar between WLE and VCE videos (accuracies ranging from 80 % to 85 %). The model's stratification of risk of flare was similar to that of physician-assessed endoscopy scores. CONCLUSIONS: Our system accurately distinguished ER/activity and predicted HR and clinical outcome from colonoscopy videos. This is the first computer model developed to detect inflammation/healing on VCE using the PICaSSO and the first computer tool to provide endoscopic, histologic, and clinical assessment.

Esophageal epidermoid metaplasia. An unusual find.

A 62-year-old woman presented with an episode of upper gastrointestinal bleeding. Upper endoscopy revealed white exudates at the middle and lower third of the esophagus. Biopsies proved epidermoid metaplasia of the esophagus with low-grade dysplasia. We discuss the risk factors, preneoplastic potential and available treatments of this entity.

MICIL: Multiple-Instance Class-Incremental Learning for skin cancer whole slide images.

Artificial intelligence (AI) agents encounter the problem of catastrophic forgetting when they are trained in sequentially with new data batches. This issue poses a barrier to the implementation of AI-based models in tasks that involve ongoing evolution, such as cancer prediction. Moreover, whole slide images (WSI) play a crucial role in cancer management, and their automated analysis has become increasingly popular in assisting pathologists during the diagnosis process. Incremental learning (IL) techniques aim to develop algorithms capable of retaining previously acquired information while also acquiring new insights to predict future data. Deep IL techniques need to address the challenges posed by the gigapixel scale of WSIs, which often necessitates the use of multiple instance learning (MIL) frameworks. In this paper, we introduce an IL algorithm tailored for analyzing WSIs within a MIL paradigm. The proposed Multiple Instance Class-Incremental Learning (MICIL) algorithm combines MIL with class-IL for the first time, allowing for the incremental prediction of multiple skin cancer subtypes from WSIs within a class-IL scenario. Our framework incorporates knowledge distillation and data rehearsal, along with a novel embedding-level distillation, aiming to preserve the latent space at the aggregated WSI level. Results demonstrate the algorithm's effectiveness in addressing the challenge of balancing IL-specific metrics, such as intransigence and forgetting, and solving the plasticity-stability dilemma.

Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease.

Integrating artificial intelligence into inflammatory bowel disease (IBD) has the potential to revolutionise clinical practice and research. Artificial intelligence harnesses advanced algorithms to deliver accurate assessments of IBD endoscopy and histology, offering precise evaluations of disease activity, standardised scoring, and outcome prediction. Furthermore, artificial intelligence offers the potential for a holistic endo-histo-omics approach by interlacing and harmonising endoscopy, histology, and omics data towards precision medicine. The emerging applications of artificial intelligence could pave the way for personalised medicine in IBD, offering patient stratification for the most beneficial therapy with minimal risk. Although artificial intelligence holds promise, challenges remain, including data quality, standardisation, reproducibility, scarcity of randomised controlled trials, clinical implementation, ethical concerns, legal liability, and regulatory issues. The development of standardised guidelines and interdisciplinary collaboration, including policy makers and regulatory agencies, is crucial for addressing these challenges and advancing artificial intelligence in IBD clinical practice and trials.

Unusual extraconal orbital location of a cavernous hemangioma.

Cavernous hemangioma is the most common benign orbital and vascular tumor in adults. It is mostly located intraconally. Nevertheless, when the location is extraconal, the displacement of the globe is opposite the tumor's position. We describe an unusual presentation of this tumor in a 75-year-old female. The only symptom was the presence of epiphora. In the clinical examination, a mass was palpated on the lower orbital rim of the right eye. The magnetic resonance imaging (MRI) showed a well-circumscribed ovoid mass with a strong T2 hyperintensity and progressive contrast filling in T1. Excisional biopsy was performed, which confirmed the diagnosis of cavernous hemangioma. At five months of follow-up, there was no evidence of new symptoms.

Priapism Produced by Penile Metastasis from Colon Cancer.

INTRODUCTION AND OBJECTIVE: The penile metastasis is a rare clinical entity. The objective is to present the first documented case report of penile metastasis from right colon. CLINICAL CASE: A case of a 78-year-old man who was diagnosed with penile metastasis from right colon. The patient came to our consultation complaining of colic pain in the kidney and swelling of the penile which finally result in a malignant priapism. The diagnosis was histopathologic and was treated with chemotherapy and died few months later. CONCLUSION: Metastatic lesions in the penile are extremely rare; only 300 cases have been reported in the literature. It is a sign of bad prognosis. The mechanism of metastatic spread to the penis is not well established. Even there are several treatment options, is usually paliative.

Constrained multiple instance learning for ulcerative colitis prediction using histological images.

BACKGROUND AND OBJECTIVE: Ulcerative colitis (UC) is an inflammatory bowel disease (IBD) affecting the colon and the rectum characterized by a remitting-relapsing course. To detect mucosal inflammation associated with UC, histology is considered the most stringent criteria. In turn, histologic remission (HR) correlates with improved clinical outcomes and has been recently recognized as a desirable treatment target. The leading biomarker for assessing histologic remission is the presence or absence of neutrophils. Therefore, the finding of this cell in specific colon structures indicates that the patient has UC activity. However, no previous studies based on deep learning have been developed to identify UC based on neutrophils detection using whole-slide images (WSI). METHODS: The methodological core of this work is a novel multiple instance learning (MIL) framework with location constraints able to determine the presence of UC activity using WSI. In particular, we put forward an effective way to introduce constraints about positive instances to effectively explore additional weakly supervised information that is easy to obtain and enjoy a significant boost to the learning process. In addition, we propose a new weighted embedding to enlarge the relevance of the positive instances. RESULTS: Extensive experiments on a multi-center dataset of colon and rectum WSIs, PICASSO-MIL, demonstrate that using the location information we can improve considerably the results at WSI-level. In comparison with prior MIL settings, our method allows for 10% improvements in bag-level accuracy. CONCLUSION: Our model, which introduces a new form of constraints, surpass the results achieved from current state-of-the-art methods that focus on the MIL paradigm. Our method can be applied to other histological concerns where the morphological features determining a positive WSI are tiny and similar to others in the image.

EDA, EDAR, EDARADD and WNT10A allelic variants in patients with ectodermal derivative impairment in the Spanish population.

BACKGROUND: Ectodermal dysplasias (ED) are a group of genetic conditions affecting the development and/or homeostasis of two or more ectodermal derivatives. An attenuated phenotype is considered a non-syndromic trait when the patient is affected by only one impaired ectodermal structure, such as in non-syndromic tooth agenesis (NSTA) disorder. Hypohidrotic ectodermal dysplasia (HED) is the most highly represented ED. X-linked hypohidrotic ectodermal dysplasia (XLHED) is the most common subtype, with an incidence of 1/50,000-100,000 males, and is associated with the EDA gene (Xq12-q13.1); the dominant and recessive subtypes involve the EDAR (2q13) and EDARADD (1q42.3) genes, respectively. The WNT10A gene (2q35) is associated more frequently with NSTA. Our goal was to determine the mutational spectrum in a cohort of 72 Spanish patients affected by one or more ectodermal derivative impairments referred to as HED (63/72) or NSTA (9 /72) to establish the prevalence of the allelic variants of the four most frequently associated genes. Sanger sequencing of the EDA, EDAR, EDARADD and WNT10A genes and multiplex ligation-dependent probe amplification (MLPA) were performed. RESULTS: A total of 61 children and 11 adults, comprising 50 males and 22 females, were included. The average ages were 5.4 and 40.2 years for children and adults, respectively. A molecular basis was identified in 51/72 patients, including 47/63 HED patients, for whom EDA was the most frequently involved gene, and 4/9 NSTA patients, most of whom had variants of WNT10A. Among all the patients, 37/51 had variants of EDA, 8/51 had variants of the WNT10A gene, 4/51 had variants of EDAR and 5/51 had variants of EDARADD. In 42/51 of cases, the variants were inherited according to an X-linked pattern (27/42), with the remaining showing an autosomal dominant (10/42) or autosomal recessive (5/42) pattern. Among the NSTA patients, 3/9 carried pathogenic variants of WNT10A and 1/9 carried EDA variants. A total of 60 variants were detected in 51 patients, 46 of which were different, and out of these 46 variants, 12 were novel. CONCLUSIONS: This is the only molecular study conducted to date in the Spanish population affected by ED. The EDA, EDAR, EDARADD and WNT10A genes constitute the molecular basis in 70.8% of patients with a 74.6% yield in HED and 44.4% in NSTA. Twelve novel variants were identified. The WNT10A gene has been confirmed as the second molecular candidate that has been identified and accounts for one-half of non-EDA patients and one-third of NSTA patients. Further studies using next generation sequencing (NGS) will help to identify other contributory genes in the remaining uncharacterized Spanish patients.

High penetrance of acute intermittent porphyria in a Spanish founder mutation population and CYP2D6 genotype as a susceptibility factor.

BACKGROUND: Acute intermittent porphyria (AIP) is a low-penetrant genetic metabolic disease caused by a deficiency of hydroxymethylbilane synthase (HMBS) in the haem biosynthesis. Manifest AIP (MAIP) is considered when carriers develop typical acute neurovisceral attacks with elevation of porphyrin precursors, while the absence of attacks is referred to as latent AIP (LAIP). Attacks are often triggered by drugs, endocrine factors, fasting or stress. Although AIP penetrance is traditionally considered to be around 10-20%, it has been estimated to be below 1% in general population studies and a higher figure has been found in specific AIP populations. Genetic susceptibility factors underlying penetrance are still unknown. Drug-metabolizing cytochrome P450 enzymes (CYP) are polymorphic haem-dependent proteins which play a role in haem demand, so they might modulate the occurrence of AIP attacks. Our aim was to determine the prevalence and penetrance of AIP in our population and analyse the main hepatic CYP genes to assess their association with acute attacks. For this, CYP2C9*2, *3; CYP2C19*2; CYP2D6*4, *5; CYP3A4*1B and CYP3A5*3 defective alleles were genotyped in fifty AIP carriers from the Region of Murcia, a Spanish population with a high frequency of the HMBS founder mutation c.669_698del30. RESULTS: AIP penetrance was 52%, and prevalence was estimated as 17.7 cases/million inhabitants. The frequency of defective CYP2D6 alleles was 3.5 times higher in LAIP than in MAIP. MAIP was less frequent among CYP2D6*4 and *5 carriers (p < 0.05). The urine porphobilinogen (PBG)-to-creatinine ratio was lower in these individuals, although it was associated with a lower prevalence of attacks (p < 0.05) rather than with the CYP2D6 genotype. CONCLUSIONS: AIP prevalence in our region is almost 3 times higher than that estimated for the rest of Spain. The penetrance was high, and similar to other founder mutation AIP populations. This is very relevant for genetic counselling and effective health care. CYP2D6*4 and *5 alleles may be protective factors for acute attacks, and CYP2D6 may constitute a penetrance-modifying gene. Further studies are needed to confirm these findings, which would allow a further progress in clinical risk profile assessment based on the CYP genotype, leading to predictive personalized medicine for each AIP carrier in the future.