Deep convolutional neural networks for multi-planar lung nodule detection: improvement in small nodule identification

Sunyi Zheng, Ludo J Cornelissen, Xiaonan Cui, Xueping Jing, Raymond N J Veldhuis, Matthijs Oudkerk, Peter M A van Ooijen
2020 Medical Physics (Lancaster)  
Early detection of lung cancer is of importance since it can increase patients' chances of survival. To detect nodules accurately during screening, radiologists would commonly take the axial, coronal and sagittal planes into account, rather than solely the axial plane in clinical evaluation. Inspired by clinical work, the paper aims to develop an accurate deep learning framework for nodule detection by a combination of multiple planes. The nodule detection system is designed in two stages,
more » ... -planar nodule candidate detection, multi-scale false positive reduction. At the first stage, a deeply-supervised encoder-decoder network is trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are merged. To further refine results, a 3-D multi-scale dense convolutional neural network that extracts multi-scale contextual information is applied to remove non-nodules. In the public LIDC-IDRI dataset, 888 CT scans with 1186 nodules accepted by at least three out of four radiologists are selected to train and evaluate our proposed system via a ten-fold cross-validation scheme. The free-response receiver operating characteristic curve is used for performance assessment. The proposed system achieves a sensitivity of 94.2% with 1.0 false positive/scan and a sensitivity of 96.0% with 2.0 false positives/scan. Although it is difficult to detect small nodules (i.e. < 6 mm), our designed CAD system reaches a sensitivity of 93.4% (95.0%) of these small nodules at an overall false positive rate of 1.0 (2.0) false positives/scan. At the nodule candidate detection stage, results show that the system with a multi-planar method is capable to detect more nodules compared to using a single plane. Our approach achieves good performance not only for small nodules, but also for large lesions on this dataset. This demonstrates the effectiveness of our developed CAD system for lung nodule detection.
doi:10.1002/mp.14648 pmid:33300162 fatcat:jbotre3gwbdpvh7svj2fun74ea