Here we demonstrate a CAD system for lung cancer classification
of CT scans with unmarked nodules, a dataset
from the Kaggle Data Science Bowl 2017. Thresholding
was used as an initial segmentation approach to to segment
out lung tissue from the rest of the CT scan. Thresholding
produced the next best lung segmentation. The initial
approach was to directly feed in the segmented CT scans
into 3D CNNs for classification, but this proved to be inadequate.
Instead, a modified U-Net trained on LUNA16
data (CT scans with labeled nodules) was used to first detect
nodule candidates in the Kaggle CT scans. The U-Net
nodule detection produced many false positives, so regions
of CTs with segmented lungs where the most likely nodule
candidates were located as determined by the U-Net output
were fed into 3D Convolutional Neural Networks (a
vanilla 3D CNN and a Googlenet-based 3D CNN) to ultimately
classify the CT scan as positive or negative for
lung cancer. The vanilla 3D CNN produced a test set AUC
of ??? and the Googlenet-based 3D CNN produced a test
set AUC of ???. While performance of our CAD system is
not state-of-the-art, current CAD systems in literature have
several training and testing phases that each requires a lot
of labeled data, while our CAD system has only three major
phases (segmentation, nodule candidate detection, and
malignancy classification), allowing more efficient training
and detection and more generalizability to other cancers.
- Introduction
Lung cancer is one of the most common cancers, accounting
for over 225,000 cases, 150,000 deaths, and $12
billion in health care costs yearly in the U.S. [1]. It is also
one of the deadliest cancers; overall, only 17% of people in