Deep convolutional neural networks for multiplanar lung nodule detection: Improvement in small nodule identification

Abstract

Purpose: 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. Methods: The nodule detection system is designed in two stages, multiplanar nodule candidate detection, multiscale false positive (FP) 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 threedimensional multiscale dense convolutional neural network that extracts multiscale contextual information is applied to remove non-nodules. In the public LIDC-IDRI dataset, 888 computed tomography scans with 1186 nodules accepted by at least three of four radiologists are selected to train and evaluate our proposed system via a tenfold cross-validation scheme. The free-response receiver operating characteristic curve is used for performance assessment. Results: The proposed system achieves a sensitivity of 94.2% with 1.0 FP/scan and a sensitivity of 96.0% with 2.0 FPs/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 FP rate of 1.0 (2.0) FPs/scan. At the nodule candidate detection stage, results show that the system with a multiplanar method is capable to detect more nodules compared to using a single plane. Conclusion: 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.

Vocal cord lesions classification based on deep convolutional neural network and transfer learning

“…Empirically, the training process shows no significant improvement in both accuracy and loss after a certain number of epochs, and the optimal epochs can be found via hyperparameter searching experiments. The reference standard for testing is that the system reaches a high sensitivity and a low false‐positive rate 6 when evaluated on a testing set independent of the training set.…”

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

“…Other traditional vision algorithms found successful results in juxtapleural nodules detection [ 89 ]. In the context of this problem, missing a true nodule should be more penalized than predicting too many false suspicions; however, there is an obvious effort in the literature to decrease false positive mistakes, mostly approached by combining different classification networks [ 78 , 90 ], using multi-scaled patches for capturing features at different expression levels [ 80 , 81 , 91 , 92 ], employing other classification algorithms, such as SVM [ 82 , 86 , 87 , 93 , 94 , 95 ], Bayesian networks, and neuro-fuzzy classifiers [ 95 ], or proposing a graph-based image representation with deep point cloud models [ 96 ].…”

Pulmonale Rundherde und Pneumonie

“…Sogenannte CAD(„computer-aided detection“)-Systeme gehören in vielen Kliniken bereits zum Untersuchungsstandard. Neueste Studien haben gezeigt, dass neuronale Netzwerke von Computern mit hoher diagnostischer Genauigkeit pulmonale Noduli erkennen und diese hinsichtlich ihrer Malignitätswahrscheinlichkeit einordnen können [ 29 ]. Zum aktuellen Zeitpunkt dienen diese Systeme jedoch eher der Qualitätskontrolle des radiologischen Befundes und sind noch nicht in den klinischen Alltag integriert.…”