Lung Tumor Location and Identification with AlexNet and a Custom CNN

Allison M Rossetto, Wenjin Zhou

Abstract: Lung cancer is the leading cause of cancer deaths in the world and early detection is a crucial part of increasing patient survival. Deep learning techniques provide us with a method of automated analysis of patient scans. In this work, we compare AlexNet, a multi-layered and highly flexible architecture, with a custom CNN to determine if lung nodules with patient scans are benign or cancerous. We have found our CNN architecture to be highly accurate (99.79%) and fast while maintaining low False Positive and False Negative rates (< 0.01% and 0.15% respectively). This is important as high false positive rates are a serious issue with lung cancer diagnosis. We have found that AlexNet is not well suited to the problem of nodule identification, though it is a good baseline comparison because of its flexibility.

Data: [LUNA](https://paperswithcode.com/dataset/luna)