Deep learning in digital pathology for personalized treatment plans of cancer patients

Machine learning evaluation of immune infiltrate through digital tumour score allows prediction of survival outcome in a pooled analysis of three international stage III colon cancer cohorts

BACKGROUND

T-cell immune infiltrates are robust prognostic variables in localised colon cancer. Evaluation of prognosis using artificial intelligence is an emerging field. We evaluated whether machine learning analysis improved prediction of patient outcome in comparison with analysis of T cell infiltrate only or in association with clinical variables.

METHODS

We used data from two phase III clinical trials (Prodige-13 and PETACC08) and one retrospective Italian cohort (HARMONY). Cohorts were split into training (N = 692), internal validation (N = 297) and external validation (N = 672) sets. Tumour slides were stained with CD3mAb. CD3 Machine Learning (CD3ML) score was computed using graphical parameters within the tumour tiles obtained from CD3 slides. CD3 infiltrates in tumour core and invasive margin were automatically detected. Associations of CD3 infiltrates and CD3ML with 5-year Disease-Free Survival (DFS) were examined using univariate and multivariable survival models by Cox regression.

FINDINGS

CD3 density both in the invasive margin and the tumour core were significantly associated with DFS in the different sets. Similarly, CD3ML score was significantly associated with DFS in all sets. CD3 assessment did not provide added value on top of CD3ML assessment (Likelihood Ratio Test (LRT), p = 0.13). In contrast, CD3ML improved prediction of DFS when combined with a clinical risk stage (LRT, p = 0.001). Stratified by clinical risk score (High or Low), patients with low CD3ML score had better DFS.

INTERPRETATION

In all tested sets, machine learning analysis of tumour cells improved prediction of prognosis compared to clinical parameters. Adding tumour-infiltrating lymphocytes assessment did not improve prognostic determination.

FUNDING

This research received no external funding.

Clinical Use of Molecular Biomarkers in Canine and Feline Oncology: Current and Future

Molecular biomarkers are central to personalised medicine for human cancer patients. It is gaining traction as part of standard veterinary clinical practice for dogs and cats with cancer. Molecular biomarkers can be somatic or germline genomic alterations and can be ascertained from tissues or body fluids using various techniques. This review discusses how these genomic alterations can be determined and the findings used in clinical settings as diagnostic, prognostic, predictive, and screening biomarkers. We showcase the somatic and germline genomic alterations currently available to date for testing dogs and cats in a clinical setting, discussing their utility in each biomarker class. We also look at some emerging molecular biomarkers that are promising for clinical use. Finally, we discuss the hurdles that need to be overcome in going 'bench to bedside', i.e., the translation from discovery of genomic alterations to adoption by veterinary clinicians. As we understand more of the genomics underlying canine and feline tumours, molecular biomarkers will undoubtedly become a mainstay in delivering precision veterinary care to dogs and cats with cancer.

Machine learning-based clinical decision support using laboratory data

Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.

The molecular mechanism of actions and clinical utilities of tumor infiltrating lymphocytes in gastrointestinal cancers: a comprehensive review and future prospects toward personalized medicine

Gastrointestinal (GI) cancers remain a significant global health burden, accounting for a substantial number of cases and deaths. Regrettably, the inadequacy of dependable biomarkers hinders the precise forecasting of patient prognosis and the selection of appropriate therapeutic sequencing for individuals with GI cancers, leading to suboptimal outcomes for numerous patients. The intricate interplay between tumor-infiltrating lymphocytes (TILs) and the tumor immune microenvironment (TIME) has been shown to be a pivotal determinant of response to anti-cancer therapy and consequential clinical outcomes across a multitude of cancer types. Therefore, the assessment of TILs has garnered global interest as a promising prognostic biomarker in oncology, with the potential to improve clinical decision-making substantially. Moreover, recent discoveries in immunotherapy have progressively changed the landscape of cancer treatment and significantly prolonged the survival of patients with advanced cancers. Nonetheless, the response rate remains constrained within solid tumor sufferers, even when TIL landscapes appear comparable, which calls for the development of our understanding of cellular and molecular cross-talk between TIME and tumor. Hence, this comprehensive review encapsulates the extant literature elucidating the TILs' underlying molecular pathogenesis, prognostic significance, and their relevance in the realm of immunotherapy for patients afflicted by GI tract cancers. Within this review, we demonstrate that the type, density, and spatial distribution of distinct TIL subpopulations carries pivotal implications for the prediction of anti-cancer treatment responses and patient survival. Furthermore, this review underscores the indispensable role of TILs in modulating therapeutic responses within distinct molecular subtypes, such as those characterized by microsatellite stability or programmed cell death ligand-1 expression in GI tract cancers. The review concludes by outlining future directions in TIL-based personalized medicine, including integrating TIL-based approaches into existing treatment regimens and developing novel therapeutic strategies that exploit the unique properties of TILs and their potential as a promising avenue for personalized cancer treatment.

CADUCEO: A Platform to Support Federated Healthcare Facilities through Artificial Intelligence

Data-driven algorithms have proven to be effective for a variety of medical tasks, including disease categorization and prediction, personalized medicine design, and imaging diagnostics. Although their performance is frequently on par with that of clinicians, their widespread use is constrained by a number of obstacles, including the requirement for high-quality data that are typical of the population, the difficulty of explaining how they operate, and ethical and regulatory concerns. The use of data augmentation and synthetic data generation methodologies, such as federated learning and explainable artificial intelligence ones, could provide a viable solution to the current issues, facilitating the widespread application of artificial intelligence algorithms in the clinical application domain and reducing the time needed for prevention, diagnosis, and prognosis by up to 70%. To this end, a novel AI-based functional framework is conceived and presented in this paper.