New artificial intelligence (AI) software that can help to spot prostate cancer is being trialled by researchers at Oxford University Hospitals (OUH) NHS Foundation Trust.Researchers and clinicians in Oxford have begun an evaluation of artificial intelligence software that could help pathologists diagnose prostate cancer.Testing of the technology in a clinical setting, which is under way at Oxford University Hospitals (OUH) NHS Foundation Trust, is a key milestone in the University of Oxford-led ARTICULATE PRO study.This two-year project, funded by an AI in Health and Care Award from the NHS AI Lab in partnership with the Accelerated Access Collaborative, aims to investigate the deployment of AI in the prostate cancer pathway by using Paige Prostate, computer-assisted diagnostic system that aims to help pathologists detect, grade and measure tumours in prostate biopsies, or tissue samples.OUH pathologists are using the AI applications to help read prostate biopsy slides as part of their routine work. The technology should flag suspicious areas to pathologists immediately by identifying the hallmarks of malignant cells captured by previous training in large datasets of biopsies. It also assesses the amount of tumour present and how aggressive it appears.The project is led by OUH Cellular Pathology Consultant and Nuffield Department of Surgical Sciences Associate Professor Clare Verrill, an expert urological histopathologist. She leads a multi-disciplinary team of clinical and non-clinical colleagues, including three patient representatives.Professor Verrill said: ‘One of our key aims in the health service is to diagnose cancers accurately and at an earlier stage so that treatment can be delivered more quickly and, ultimately, outcomes for patients improve. If we can harness this diagnostic technology to achieve this, it will be great news for patients.‘That’s why this evaluation – one of the first of its kind – is an important step. We will be looking not only at how well this software performs in a busy clinical setting and whether diagnostic accuracy and efficiency improves, but also assessing the experience of clinicians and patients, and looking at the impact on workflow.’She added: ‘In 2020, OUH’s histopathology laboratory was one of the first in the UK to achieve the milestone of scanning 100 percent of its surgical histology workload. Our digital pathology experience makes us an ideal setting to test AI technologies such as Paige Prostate Suite in a real-world clinical setting.’Some 46,000 new prostate cancer cases are reported in the UK each year, which represents a 12 percent increase in the past 10 years.The ARTICULATE PRO team have previously published a survey of Prostate Cancer UK supporters on the use of digital pathology and AI technologies in diagnostic practice.Two other NHS trusts – University Hospital Coventry and Warwickshire and North Bristol NHS Trust – will also assess the Paige Prostate Suite software.Margaret Horton, Vice President of Clinical Partnerships and Evidence Generation at Paige, said: ‘With patients in focus as the beneficiaries of Paige’s prostate AI in routine use, we look forward to completing our health economics study assessing the impacts of using AI in routine service.‘We are excited to be evaluating the potential health economic benefits of deploying the Paige Prostate Suite in a large and diverse real-world clinical setting together with our advisors and partners at the York Health Economic Consortium.’SOURCE: Oxford University Hospitals

Colorectal cancer, the second most lethal cancer worldwide, exhibits varying behaviour even among individuals with similar disease profiles who undergo the same treatment. Now, a new artificial intelligence (AI) model may now offer valuable insight to doctors making prognoses and determining treatments for patients with colorectal cancer. Researchers at Harvard Medical School (Boston, MA, USA) and National Cheng Kung University (Tainan, Taiwan) have developed a tool called MOMA (Multi-omics Multi-cohort Assessment) that accurately predicts colorectal tumor aggressiveness, patient survival rates with and without disease recurrence, and the most effective therapy by analyzing tumor sample images alone. Unlike many existing AI tools that primarily replicate or optimize human expertise, MOMA identifies and interprets visual patterns on microscopy images that are undetectable to the human eye. The tool is freely available to researchers and clinicians. The model was trained using data from approximately 2,000 colorectal cancer patients from diverse national patient cohorts, totaling over 450,000 participants. During training, researchers provided the model with information about patients' age, sex, cancer stage, and outcomes, as well as genomic, epigenetic, protein, and metabolic profiles of the tumors. The model was then tasked with identifying visual markers related to tumor types, genetic mutations, epigenetic changes, disease progression, and patient survival using pathology images of tumor samples. The model's performance was assessed using a set of previously unseen tumor sample images from different patients, comparing its predictions to actual patient outcomes and other clinical data. MOMA accurately predicted overall survival following diagnosis and the number of cancer-free years for patients. It also correctly anticipated individual patient responses to various therapies based on the presence of specific genetic mutations influencing cancer progression or spread. In both areas, the tool outperformed human pathologists and current AI models. The researchers recommend testing the model in a prospective, randomized trial evaluating its performance in real patients over time after initial diagnosis before deploying it in clinics and hospitals. Such a study would directly compare MOMA's real-life performance using only images with human clinicians who utilize additional knowledge and test results unavailable to the model, providing the gold-standard demonstration of its capabilities. “Our model performs tasks that human pathologists cannot do based on image viewing alone,” said study co-senior author Kun-Hsing Yu, assistant professor of biomedical informatics in the Blavatnik Institute at Harvard Medical School, who led an international team of pathologists, oncologists, biomedical informaticians, and computer scientists. “What we anticipate is not a replacement of human pathology expertise, but augmentation of what human pathologists can do. We fully expect that this approach will augment the current clinical practice of cancer management.” Related Links:Harvard Medical SchoolNational Cheng Kung University

The use of machine learning algorithms to analyze whole slide images (WSIs) is set to transform various processes of clinical practice. More recently, machine learning-based computational frameworks have been developed to aid in the assessment of Alzheimer’s disease and other neurological conditions. However, advances in the use of machine learning frameworks to diagnose neurological diseases lag far behind the diagnostic applications of digital pathology in oncology.