Efficient convolutional neural networks for multi-planar lung nodule detection: improvement on small nodule identification
share
We propose a multi-planar pulmonary nodule detection system using convolutional neural networks. The 2-D convolutional neural network model, U-net++, was trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are combined. For false positive reduction, we apply 3-D multi-scale dense convolutional neural networks to efficiently remove false positive candidates. We use the public LIDC-IDRI dataset which includes 888 CT scans with 1186 nodules annotated by four radiologists. After ten-fold cross-validation, our proposed system achieves a sensitivity of 95.3 and a sensitivity of 96.2 difficult to detect small nodules (i.e. nodules with a diameter < 6 mm), our designed CAD system reaches a sensitivity of 93.8 nodules at an overall false positive rate of 0.5 (1.0) false positives/scan. At the nodule candidate detection stage, the proposed system detected 98.1 nodules after merging the predictions from all three planes. Using only the 1 mm axial slices resulted in the detection of 91.1 than that of utilizing solely the coronal or sagittal slices. The results show that a multi-planar method is capable to detect more nodules compared to using a single plane. Our approach achieves state-of-the-art performance on this dataset, which demonstrates the effectiveness and efficiency of our developed CAD system for lung nodule detection.
READ FULL TEXT
