Automated 3-D lung tumor detection and classification by an active contour model and CNN classifier

作者：

Highlights：

• A model is developed to help lung tumor prognosticate and find centroid displacement.

• The proposed model segment tumor portion and also extract features.

• An enhanced CNN based on AlexNet architecture is proposed.

• Enhanced CNN helps to classify CT images such as benign or malignant tumors.

摘要

•A model is developed to help lung tumor prognosticate and find centroid displacement.•The proposed model segment tumor portion and also extract features.•An enhanced CNN based on AlexNet architecture is proposed.•Enhanced CNN helps to classify CT images such as benign or malignant tumors.

论文关键词：Image segmentation,LIDC-IDRI data set,Active contour model,Inhomogeneity,Multi-scale Gaussian distribution,Enhanced CNN classifier

论文评审过程：Received 19 September 2018, Revised 17 April 2019, Accepted 25 May 2019, Available online 27 May 2019, Version of Record 6 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.05.041