Multi-scale Convolutional Neural Networks for Lung Nodule Classification

• Published in: Information Processing in Medical Imaging Vol. 24; pp. 588 - 599
• Main Authors: Shen, Wei, Zhou, Mu, Yang, Feng, Yang, Caiyun, Tian, Jie
• Format: Book Chapter Journal Article
• Language: English
• Published: Cham Springer International Publishing 2015
• Series: Lecture Notes in Computer Science
• Subjects: Algorithms; Computed Tomography (CT) Imaging; Computer-Aided Diagnoses (CAD); Convolutional Neural Networks; Humans; Lung Neoplasms - diagnostic imaging; Lung nodule classification; Neural Networks (Computer); Pattern Recognition, Automated - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Radiography, Thoracic - methods; Reproducibility of Results; Sensitivity and Specificity; Solitary Pulmonary Nodule - diagnostic imaging; Tomography, X-Ray Computed - methods
• ISBN: 9783319199917; 3319199919
• ISSN: 0302-9743; 1011-2499; 1611-3349
• DOI: 10.1007/978-3-319-19992-4_46

We investigate the problem of diagnostic lung nodule classification using thoracic Computed Tomography (CT) screening. Unlike traditional studies primarily relying on nodule segmentation for regional analysis, we tackle a more challenging problem on directly modelling raw nodule patches without any prior definition of nodule morphology. We propose a hierarchical learning framework—Multi-scale Convolutional Neural Networks (MCNN)—to capture nodule heterogeneity by extracting discriminative features from alternatingly stacked layers. In particular, to sufficiently quantify nodule characteristics, our framework utilizes multi-scale nodule patches to learn a set of class-specific features simultaneously by concatenating response neuron activations obtained at the last layer from each input scale. We evaluate the proposed method on CT images from Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), where both lung nodule screening and nodule annotations are provided. Experimental results demonstrate the effectiveness of our method on classifying malignant and benign nodules without nodule segmentation.