The integration of artificial intelligence (AI) into histopathology has emerged as a transformative force in disease diagnosis and treatment, particularly in oncology. This poster looks into the potential of AI to complement or replace traditional pathology practices. AI applications in histopathology include tumour detection and grading, prognosis prediction, and algorithmic analysis of demographic and clinical data (Cui & Zhang, 2021). Machine learning, especially convolutional neural networks (CNNs), has demonstrated improved sensitivity in detecting cancer metastases (Liu et al., 2017) and higher accuracy in grading systems (Chang et al., 2019). Notably, AI has outperformed pathologists in certain diagnostic metrics, such as a 28% increase in area under the curve (AUC) for cervical cancer screening (Hu et al., 2019). However, the integration of AI and pathologists results in increased diagnostic specificity and efficiency. This was evidenced when AI was combined with pathologists and resulted in enhanced diagnostic specificity by 1.6% in breast cancer mammogram screenings (Schaffter et al., 2020).

Despite its advantages, AI faces challenges, including image processing limitations, storage and computational demands, and patients and practitioners do not have complete trust in the technology at its current stage. Additionally, variability in image quality and the need for robust validation hinder widespread adoption. The evidence underscores that while AI cannot currently replace pathologists, it serves as a valuable tool to enhance accuracy, reduce workloads, and enable personalized treatment approaches.

Future directions highlight the integration of genomics, proteomics, and informatics with whole slide imaging to create data-rich pathomics (analysing digital pathology images to retrieve quantitative data that can be used to make a diagnosis) platforms. This progression is expected to revolutionise histopathology, making advanced diagnostic capabilities accessible to healthcare systems globally and optimise clinical workflows (Mobadersany et al., 2018). AI’s successful implementation hinges on addressing technological constraints and fostering trust among healthcare providers and patients

Mr. Taanish Unhale is a British medical student in the final year of their MBChB at Anglia Ruskin University in the UK. Based in Chelmsford, they possess significant research experience, which has contributed to their academic and professional growth. Taanish is focused on pursuing a career in medicine with a strong foundation in clinical and research skills.