Use of artificial intelligence to enhance detection of nodal metastases

In oncology, the presence of lymph node metastases is one of the most important prognostic factors and its determination is an essential part of tumour staging. 1 Amin MB Greene FL Edge SB et al. The eighth edition AJCC cancer staging manual: continuing to build a bridge from a population-based to a more “personalized” approach to cancer staging. CA Cancer J Clin. 2017; 67: 93-99 Crossref PubMed Scopus (2640) Google Scholar Before treatment, CT, MRI, ultrasound, and PET are the most common non-invasive techniques used for pretreatment cancer staging. However, despite the strengths of these techniques, their sensitivity for evaluation of early or micrometastases in small lymph nodes measuring less than 7–10 mm is low. 2 Compérat E Amin MB Cathomas R et al. Current best practice for bladder cancer: a narrative review of diagnostics and treatments. Lancet. 2022; 400: 1712-1721 Summary Full Text Full Text PDF PubMed Scopus (16) Google Scholar , 3 Woolgar JA Scott J Prediction of cervical lymph node metastasis in squamous cell carcinoma of the tongue/floor of mouth. Head Neck. 1995; 17: 463-472 Crossref PubMed Scopus (212) Google Scholar As a result, for surgically treated diseases, the gold standard consists of pathological evaluation of resected nodal specimens. The final nodal stage is usually determined on the basis of histopathological evaluation of lymph nodes on pathology slides stained with haematoxylin and eosin, increasingly digitised into whole slide images. Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic studyWe developed an AI-based diagnostic model that did well in detecting lymph node metastases, particularly micrometastases. The LNMDM showed substantial potential for clinical applications in improving the accuracy and efficiency of pathologists' work. Full-Text PDF