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

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

Abstract Purpose Interpretability is essential for reliable convolutional neural network (CNN) image classifiers in radiological applications. We describe a weakly supervised segmentation model that learns to delineate the target object, trained with only image-level labels (“image contains object”...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Robert O’Shea, Thubeena Manickavasagar, Carolyn Horst, Daniel Hughes, James Cusack, Sophia Tsoka, Gary Cook, Vicky Goh
Materyal Türü: Makale
Dil:English
Baskı/Yayın Bilgisi: SpringerOpen 2023-11-01
Seri Bilgileri:Insights into Imaging
Konular:
Explainable artificial intelligence
Model interpretation
Weakly supervised learning
Lung neoplasms
Tumour segmentation
Online Erişim:https://doi.org/10.1186/s13244-023-01542-2

Internet

https://doi.org/10.1186/s13244-023-01542-2

Benzer Materyaller