Machine learning methods can differentiate malignancy from reactive benign changes due to COVID-19 shot
Spain: Machine learning methods can differentiate between malignant and benign lymph nodes that react as a side effect of COVID-19 vaccination, suggests a recent study in the European Journal of Radiology. These techniques can be used for the non-invasive diagnosis of lymph node status in patients with suspicious reactive nodes. The institutional review board-approved retrospective study...
Spain: Machine learning methods can differentiate between malignant and benign lymph nodes that react as a side effect of COVID-19 vaccination, suggests a recent study in the European Journal of Radiology. These techniques can be used for the non-invasive diagnosis of lymph node status in patients with suspicious reactive nodes.
The institutional review board-approved retrospective study was conducted by David Coronado-Gutiérrez, Hospital Clínic de Barcelona (University of Barcelona) and Hospital Sant Joan de Deu, Barcelona, Spain, and colleagues with the objective to assess the potential of quantitative image analysis and machine learning techniques to differentiate between malignant lymph nodes and benign lymph nodes affected by reactive changes due to COVID-19 vaccination.
The researchers improved their previously published artificial intelligence model by retraining it with newly collected images. They tested the performance on images containing benign lymph nodes affected by COVID-19 vaccination. Specialized breast-imaging radiologists acquired and selected all the images. The nature of each node (benign or malignant) was assessed through a strict clinical protocol using ultrasound-guided biopsies.
The findings of the study were as follows:
· A total of 180 new images from 154 different patients were recruited: 71 images (10 cases and 61 controls) were used to retrain the old model and 109 images (36 cases and 73 controls) were used to evaluate its performance.
· The achieved accuracy of the proposed method was 92.7% with 77.8% sensitivity and 100% specificity at the optimal cut-off point.
· In comparison, the visual node inspection made by radiologists from ultrasound images reached 69.7% accuracy with 41.7% sensitivity and 83.6% specificity.
"Image analysis and machine learning methods can be used to differentiate between malignant lymph nodes affected by metastatic breast cancer and benign lymph nodes affected by reactive changes due to COVID-19 vaccination," wrote the authors.
"These techniques are useful for the non-invasive diagnosis of lymph node status in patients with and without diagnosed breast cancer with suspicious reactive nodes," they concluded. "Larger, multicenter studies are required to confirm and validate the results of our study."
Reference:
Coronado-Gutiérrez D, Ganau S, Bargalló X, Úbeda B, Porta M, Sanfeliu E, Burgos-Artizzu XP. Quantitative ultrasound image analysis of axillary lymph nodes to differentiate malignancy from reactive benign changes due to COVID-19 vaccination. Eur J Radiol. 2022 Sep;154:110438. doi: 10.1016/j.ejrad.2022.110438. Epub 2022 Jul 7. PMCID: PMC9259511.
Disclaimer: This site is primarily intended for healthcare professionals. Any content/information on this website does not replace the advice of medical and/or health professionals and should not be construed as medical/diagnostic advice/endorsement/treatment or prescription. Use of this site is subject to our terms of use, privacy policy, advertisement policy. © 2024 Minerva Medical Treatment Pvt Ltd