A volumetric multi-head attention strategy for lung nodule classification in CT

Alejandra Moreno; Andrea Rueda; Fabio Martinez

doi:10.1117/12.2654256

7 April 2023 A volumetric multi-head attention strategy for lung nodule classification in CT

Alejandra Moreno, Andrea Rueda, Fabio Martinez

Proceedings Volume 12465, Medical Imaging 2023: Computer-Aided Diagnosis; 124652N (2023) https://doi.org/10.1117/12.2654256
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Pulmonary nodules are the principal lung cancer indicator, whose malignancy is mainly related to their size, morphological and textural features. Computational deep representations are today the most common tool to characterize lung nodules but remain limited to capturing nodule variability. In consequence, nodule malignancy classification from CT observations remains an open problem. This work introduces a multi-head attention network that takes advantage of volumetric nodule observations and robustly represents textural and geometrical patterns, learned from a discriminative task. The proposed approach starts by computing 3D convolutions, exploiting textural patterns of volumetric nodules. Such convolutional representation is enriched from a multi-scale projection using receptive field blocks, followed by multiple volumetric attentions that exploit non-local nodule relationships. These attentions are fused to enhance the representation and achieve more robust malignancy discrimination. The proposed approach was validated on the public LIDC-IDRI dataset, achieving a 91.82% in F1-score, 91.19% in sensitivity, and 92.43% in AUC for binary classification. The reported results outperform the state-of-the-art strategy with 3D nodule representations.

Citation Download Citation

Alejandra Moreno, Andrea Rueda, and Fabio Martinez "A volumetric multi-head attention strategy for lung nodule classification in CT", Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 124652N (7 April 2023); https://doi.org/10.1117/12.2654256

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available