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.

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). 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. 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. 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.

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.

Cutaneous spindle cell (CSC) lesions encompass a spectrum from benign to malignant neoplasms, often posing significant diagnostic challenges. Computer-aided diagnosis systems offer a promising solution to make pathologists’ decisions objective and faster. These systems usually require large-scale datasets with curated labels for effective training; however, manual annotation is time-consuming and expensive. To overcome this challenge, crowdsourcing has emerged as a popular and valuable strategy to scale up the labeling process by distributing the effort among different non-expert annotators. This work introduces AI4SkIN, the first public dataset Whole Slide Images (WSIs) for CSC neoplasms, annotated using an innovative crowdsourcing protocol. AI4SkIN dataset contains 641 Hematoxylin and Eosin stained WSIs with multiclass labels from both expert and trainee pathologists. The dataset improves CSC neoplasm diagnosis using advanced machine learning and crowdsourcing based on Gaussian Processes, showing that models trained on non-expert labels perform comparably to those using expert labels. In conclusion, we illustrate that AI4SkIN provides a good resource for developing and validating methods for multiclass CSC neoplasm classification.

Histological remission (HR) is a key treatment goal in ulcerative colitis (UC), suggesting better disease management and treatment response. Absence of mucosal neutrophils is crucial to defining HR. However, the role of neutrophil quantity and localisation remains unclear. We aimed to develop a novel AI-driven pipeline to automate neutrophil detection, localisation, and quantification, supporting assessment of HR and treatment response. We developed an AI-driven pipeline by integrating and combining the outputs of two deep learning models to segment whole-slide images (WSIs) into epithelium, crypts and lamina propria and detect and quantify neutrophils. Optimal neutrophil density cut-offs to assess disease activity in UC patients from the AMAC phase 2 Mirikizumab trial (NCT02589665; 2015–2019) were identified and validated in the multicentre prospective PICaSSO cohort (2016–2019). Cut-offs to determine treatment response at weeks 12 and 52 were also evaluated. 303 WSIs of UC patients from the multicentre, randomised, double-blind, parallel-arm, placebo-controlled phase 2 clinical trial of Mirikizumab were analysed. The models yielded a 65.0% DICE Sørensen for region segmentation on average and 82.3% precision for neutrophil detection. A density cut-off $\ge$21.7 cells/mm² assessed disease activity with 86% (95% CI: 79%–92%) accuracy, 94% (88%–99%) sensitivity, 74% (54%–89%) specificity, as validated in the PICaSSO cohort. Moreover, a cut-off <21.7 cells/mm² demonstrated 79% (95% CI: 67%–92%) and 85% (95% CI: 70%–96%) accuracy in assessing treatment response at weeks 12 and 52, respectively. This novel AI-based pipeline demonstrates strong potential to detect, localise, and quantify neutrophils to assess histological activity in clinical trials and real-world settings. Furthermore, it effectively stratifies treatment response, offering a reliable and objective framework for personalised UC management. This paper has been supported by research grants from 10.13039/100004312 Eli Lilly and Company .