LUNG CANCER DIAGNOSIS
home    publications    projects

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.

Results

Fig. 2 Qualitative results of high scored nodule detections

Method AUC ROC (%)
Validation set
5-way multi-path cancer predictor 88.7
5-way multi-path cancer predictor + 3D mask subtraction 93.7
Test set (private annotations)
5-way multi-path cancer predictor + 3D mask subtraction
(1st place--ours)
91.3
Mehrtash et al. (2nd place) 89.7

Tab. 1 AUC of the ROC curve obtained on the validation and test set with and without post-processing. Validation set corresponds to the ISBI 2018 Lung Nodule Malignancy Prediction challenge training set with public annotations. Test set corresponds to the ISBI 2018 Lung Nodule Malignancy Prediction challenge test set with private annotations. The test set results are evaluated on the challenge server.



Publications

Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge
Yoganand Balagurunathan, Andrew Beers, Michael McNitt-Gray, Lubomir Hadjiiski, Sandy Napel, Dmitry Goldgof, Gustavo Perez, Pablo Arbelaez, et al.
IEEE Transactions on Medical Imaging, 2021.
IEEE · BibTex

Automated lung cancer diagnosis using three-dimensional convolutional neural networks
Gustavo Perez, Pablo Arbelaez
Medical & Biological Engineering & Computing, 2020.
pdf · project page · springer · BibTex

Automated Detection of Lung Nodules with Three-dimensional Convolutional Neural Networks
Gustavo Perez, Pablo Arbelaez →(oral)
13th International Conference on Medical Information Processing and Analysis, 2017.
pdf · project page · spie · BibTex