Lung Cancer Prediction

Lung cancer is the deadliest cancer worldwide. It has been shown that early detection using computer tomography (CT) scans can reduce deaths caused by this disease. We present a general framework for the detection of lung cancer in chest CT 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 ISBI 2018 Lung Nodule Malignancy Prediction test set. Our candidate extraction approach is effective to produce precise candidates with a recall of 99.6%. In addition, false positive reduction stage manages to successfully classify candidates and increases precision by a factor of 7.000. Our cancer predictor obtained a ROC AUC of 0.913 and was ranked 1st place at theISBI 2018 Lung Nodule Malignancy Prediction challenge.
Figure 1. Qualitative results of lung cancer predictions.

Method

Results

Table 1. Average precision obtained with different false positive reduction methods of the nodule detector.

Method

  • No FP reduction method
  • HOG + SVM
  • CNN 2D
  • CNN 2.5D
  • CNN 3D

    • AP (%)

  • 0.0062
  • 0.021
  • 8.9
  • 36.7
  • 44.8
    • Table 2. AUC of the ROC curve obtained on the validation and test set with and without post-processing.

    Method

  • Validation set
  • 5-way Siamese cancer predictor
  • + 3D mask subtraction (X = 0.82)
  • Test set
  • 5-way Siamese cancer predictor
  • + 3D mask subtraction (X = 0.82)

    • AUC ROC (%)

  •  
  • 91.5
  •  
  •  
  • 91.3*
    • * ISBI 2018 lung cancer challenge results can be found here.
    Figure 2. Comparison between false positive reduction methods. HOG+SVM and best networks using convolutions in 2D, 2.5D (2D convolutions over 3D candidates) and 3D.

    Downloads

    • Paper
    • Project code
    • Pretrained models

    Citation

    BACK TO LUNG CANCER DIAGNOSIS
    BACK TO RESEARCH
    • Address:
      Cra. 1 E No. 19A - 40. 111711, Bogotá, Colombia - Mario Laserna Building - School of Engineering - Universidad de Los Andes
    • Phone:
      [571] 332 4327, 332 4328, 332 4329