Lung cancer is the worldwide leading cause of cancer death and second most common cancer among both men and women. The earlier the stage is diagnosed, the higher the chance of survival. However, only 16% of lung cancer cases are diagnosed at an early stage. Hence, a more accurate and timely diagnosis has been a crucial task yet it remains challenging. We investigate deep learning techniques including the Convolutional Neural Network, U-Net, and Stochastic Gradient Descent models for for categorizing circulating tumor cells from immunofluorescence microscope images of patient blood samples.