Automated Lung Cancer Diagnosis Using Three-dimensional Convolutional Neural Networks

Gustavo Perez, Pablo Arbelaez

Github code repository  

Ranked 1st place at the ISBI 2018 - Lung Nodule Malignancy Prediction Challenge  

Lung cancer is the deadliest cancer worldwide. It has been shown that early detection using low-dose computer tomography (LDCT) scans can reduce deaths caused by this disease. We present a general framework for the detection of lung cancer in chest LDCT images. Our method consists of a nodule detector trained on the LIDC-IDRI dataset followed by a cancer predictor trained on the Kaggle DSB 2017 dataset and evaluated on the IEEE International Symposium on Biomedical Imaging (ISBI) 2018 Lung Nodule Malignancy Prediction test set. Our candidate extraction approach is effective to produce accurate candidates with a recall of 99.6%. In addition, our false positive reduction stage classifies successfully the candidates and increases precision by a factor of 2000. Our cancer predictor obtained a ROC AUC of 0.913 and was ranked 1st place at the ISBI 2018 Lung Nodule Malignancy Prediction challenge.

Fig. 1 Proposed method: pre-processing for noise reduction and lung extraction with a mask, candidate generation using morphological operations, nodule classification with a three-dimensional convolutional neural network to reduce false positives and increase precision, and a 5-way convolutional neural network to obtain a final cancer probability for each subject.