Weakly supervised segmentation models as explainable radiological classifiers for lung tumour detection on CT images.

Robert J O'SheaThubeena ManickavasagarCarolyn HorstDaniel HughesJames CusackSophia TsokaGary CookVicky Goh

Published in: Insights into imaging (2023)

• Explainability and interpretability are essential for reliable medical image classifiers. • This study applies weakly supervised segmentation to generate explainable image classifiers. • The weakly supervised Unet inherently explains its image-level predictions at voxel level.

Keyphrases

deep learning
machine learning
convolutional neural network
healthcare
computed tomography
magnetic resonance imaging
contrast enhanced
dual energy
label free
positron emission tomography
sensitive detection