Mundher Al-Shabi1, Kelvin Shak2, Maxine Tan2,3. 1. Electrical and Computer Systems Engineering Discipline, School of Engineering, Monash University Malaysia, 47500, Bandar Sunway, Selangor, Malaysia. mundher.al-shabi@monash.edu. 2. Electrical and Computer Systems Engineering Discipline, School of Engineering, Monash University Malaysia, 47500, Bandar Sunway, Selangor, Malaysia. 3. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, 73019, USA.
Abstract
PURPOSE: In recent years, Non-Local-based methods have been successfully applied to lung nodule classification. However, these methods offer 2D attention or limited 3D attention to low-resolution feature maps. Moreover, they still depend on a convenient local filter such as convolution as full 3D attention is expensive to compute and requires a big dataset, which might not be available. METHODS: We propose to use 3D Axial-Attention, which requires a fraction of the computing power of a regular Non-Local network (i.e., self-attention). Unlike a regular Non-Local network, the 3D Axial-Attention network applies the attention operation to each axis separately. Additionally, we solve the invariant position problem of the Non-Local network by proposing to add 3D positional encoding to shared embeddings. RESULTS: We validated the proposed method on 442 benign nodules and 406 malignant nodules, extracted from the public LIDC-IDRI dataset by following a rigorous experimental setup using only nodules annotated by at least three radiologists. Our results show that the 3D Axial-Attention model achieves state-of-the-art performance on all evaluation metrics, including AUC and Accuracy. CONCLUSIONS: The proposed model provides full 3D attention, whereby every element (i.e., pixel) in the 3D volume space attends to every other element in the nodule effectively. Thus, the 3D Axial-Attention network can be used in all layers without the need for local filters. The experimental results show the importance of full 3D attention for classifying lung nodules.
PURPOSE: In recent years, Non-Local-based methods have been successfully applied to lung nodule classification. However, these methods offer 2D attention or limited 3D attention to low-resolution feature maps. Moreover, they still depend on a convenient local filter such as convolution as full 3D attention is expensive to compute and requires a big dataset, which might not be available. METHODS: We propose to use 3D Axial-Attention, which requires a fraction of the computing power of a regular Non-Local network (i.e., self-attention). Unlike a regular Non-Local network, the 3D Axial-Attention network applies the attention operation to each axis separately. Additionally, we solve the invariant position problem of the Non-Local network by proposing to add 3D positional encoding to shared embeddings. RESULTS: We validated the proposed method on 442 benign nodules and 406 malignant nodules, extracted from the public LIDC-IDRI dataset by following a rigorous experimental setup using only nodules annotated by at least three radiologists. Our results show that the 3D Axial-Attention model achieves state-of-the-art performance on all evaluation metrics, including AUC and Accuracy. CONCLUSIONS: The proposed model provides full 3D attention, whereby every element (i.e., pixel) in the 3D volume space attends to every other element in the nodule effectively. Thus, the 3D Axial-Attention network can be used in all layers without the need for local filters. The experimental results show the importance of full 3D attention for classifying lung nodules.
Authors: Denise R Aberle; Amanda M Adams; Christine D Berg; William C Black; Jonathan D Clapp; Richard M Fagerstrom; Ilana F Gareen; Constantine Gatsonis; Pamela M Marcus; JoRean D Sicks Journal: N Engl J Med Date: 2011-06-29 Impact factor: 91.245
Authors: Samuel G Armato; Geoffrey McLennan; Luc Bidaut; Michael F McNitt-Gray; Charles R Meyer; Anthony P Reeves; Binsheng Zhao; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Edwin J R Van Beeke; David Yankelevitz; Alberto M Biancardi; Peyton H Bland; Matthew S Brown; Roger M Engelmann; Gary E Laderach; Daniel Max; Richard C Pais; David P Y Qing; Rachael Y Roberts; Amanda R Smith; Adam Starkey; Poonam Batrah; Philip Caligiuri; Ali Farooqi; Gregory W Gladish; C Matilda Jude; Reginald F Munden; Iva Petkovska; Leslie E Quint; Lawrence H Schwartz; Baskaran Sundaram; Lori E Dodd; Charles Fenimore; David Gur; Nicholas Petrick; John Freymann; Justin Kirby; Brian Hughes; Alessi Vande Casteele; Sangeeta Gupte; Maha Sallamm; Michael D Heath; Michael H Kuhn; Ekta Dharaiya; Richard Burns; David S Fryd; Marcos Salganicoff; Vikram Anand; Uri Shreter; Stephen Vastagh; Barbara Y Croft Journal: Med Phys Date: 2011-02 Impact factor: 4.071