RT Journal Article
SR Electronic
T1 Lymphoma triage from H&E using AI for improved clinical management
JF Journal of Clinical Pathology
JO J Clin Pathol
FD BMJ Publishing Group Ltd and Association of Clinical Pathologists
SP 28
OP 33
DO 10.1136/jcp-2023-209186
VO 78
IS 1
A1 Tsakiroglou, Anna Maria
A1 Bacon, Chris M
A1 Shingleton, Daniel
A1 Slavin, Gabrielle
A1 Vogiatzis, Prokopios
A1 Byers, Richard
A1 Carey, Christopher
A1 Fergie, Martin
YR 2025
UL http://jcp.bmj.com/content/78/1/28.abstract
AB Aims In routine diagnosis of lymphoma, initial non-specialist triage is carried out when the sample is biopsied to determine if referral to specialised haematopathology services is needed. This places a heavy burden on pathology services, causes delays and often results in over-referral of benign cases. We aimed to develop an automated triage system using artificial intelligence (AI) to enable more accurate and rapid referral of cases, thereby addressing these issues.Methods A retrospective dataset of H&E-stained whole slide images (WSI) of lymph nodes was taken from Newcastle University Hospital (302 cases) and Manchester Royal Infirmary Hospital (339 cases) with approximately equal representation of the 3 most prevalent lymphoma subtypes: follicular lymphoma, diffuse large B-cell and classic Hodgkin’s lymphoma, as well as reactive controls. A subset (80%) of the data was used for training, a further validation subset (10%) for model selection and a final non-overlapping test subset (10%) for clinical evaluation.Results AI triage achieved multiclass accuracy of 0.828±0.041 and overall accuracy of 0.932±0.024 when discriminating between reactive and malignant cases. Its ability to detect lymphoma was equivalent to that of two haematopathologists (0.925, 0.950) and higher than a non-specialist pathologist (0.75) repeating the same task. To aid explainability, the AI tool also provides uncertainty estimation and attention heatmaps.Conclusions Automated triage using AI holds great promise in contributing to the accurate and timely diagnosis of lymphoma, ultimately benefiting patient care and outcomes.No data are available. The software used in the current study is Spotlight Pathology proprietary IP and cannot be shared. The Manchester and Newcastle datasets cannot be shared. The CAMELYON 17 dataset is publicly available from https://camelyon17.grand-challenge.org/.