Localization of contrast-enhanced breast lesions in ultrafast screening MRI using deep convolutional neural networks.

Autor: Jing X; Department of Radiation Oncology, and Data Science Center in Health (DASH), Machine Learning Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands. x.jing@umcg.nl., Dorrius MD; Department of Radiology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Zheng S; School of Engineering, Artificial Intelligence and Biomedical Image Analysis Lab, Westlake University, No.18 Shilongshan, Road Cloud Town, Xihu District, Hangzhou, 310024, Zhejiang, China., Wielema M; Department of Radiology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., Oudkerk M; Faculty of Medical Sciences, University of Groningen, and Institute of Diagnostic Accuracy, Wiersmastraat 5, 9713 GH, Groningen, The Netherlands., Sijens PE; Department of Radiology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands., van Ooijen PMA; Department of Radiation Oncology, and Data Science Center in Health (DASH), Machine Learning Lab, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9713 GZ, Groningen, The Netherlands.
Jazyk: angličtina
Zdroj: European radiology [Eur Radiol] 2024 Mar; Vol. 34 (3), pp. 2084-2092. Date of Electronic Publication: 2023 Sep 02.
DOI: 10.1007/s00330-023-10184-3
Abstrakt: Objectives: To develop a deep learning-based method for contrast-enhanced breast lesion detection in ultrafast screening MRI.
Materials and Methods: A total of 837 breast MRI exams of 488 consecutive patients were included. Lesion's location was independently annotated in the maximum intensity projection (MIP) image of the last time-resolved angiography with stochastic trajectories (TWIST) sequence for each individual breast, resulting in 265 lesions (190 benign, 75 malignant) in 163 breasts (133 women). YOLOv5 models were fine-tuned using training sets containing the same number of MIP images with and without lesions. A long short-term memory (LSTM) network was employed to help reduce false positive predictions. The integrated system was then evaluated on test sets containing enriched uninvolved breasts during cross-validation to mimic the performance in a screening scenario.
Results: In five-fold cross-validation, the YOLOv5x model showed a sensitivity of 0.95, 0.97, 0.98, and 0.99, with 0.125, 0.25, 0.5, and 1 false positive per breast, respectively. The LSTM network reduced 15.5% of the false positive prediction from the YOLO model, and the positive predictive value was increased from 0.22 to 0.25.
Conclusions: A fine-tuned YOLOv5x model can detect breast lesions on ultrafast MRI with high sensitivity in a screening population, and the output of the model could be further refined by an LSTM network to reduce the amount of false positive predictions.
Clinical Relevance Statement: The proposed integrated system would make the ultrafast MRI screening process more effective by assisting radiologists in prioritizing suspicious examinations and supporting the diagnostic workup.
Key Points: • Deep convolutional neural networks could be utilized to automatically pinpoint breast lesions in screening MRI with high sensitivity. • False positive predictions significantly increased when the detection models were tested on highly unbalanced test sets with more normal scans. • Dynamic enhancement patterns of breast lesions during contrast inflow learned by the long short-term memory networks helped to reduce false positive predictions.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: