Automatic Pulmonary Nodule Detection in CT Scans Using Convolutional Neural Networks Based on Maximum Intensity Projection

Abstract

Accurate pulmonary nodule detection is a crucial step in lung cancer screening. Computer-aided detection (CAD) systems are not routinely used by radiologists for pulmonary nodule detection in clinical practice despite their potential benefits. Maximum intensity projection (MIP) images improve the detection of pulmonary nodules in radiological evaluation with computed tomography (CT) scans. Inspired by the clinical methodology of radiologists, we aim to explore the feasibility of applying MIP images to improve the effectiveness of automatic lung nodule detection using convolutional neural networks (CNNs). We propose a CNN-based approach that takes MIP images of different slab thicknesses (5 mm, 10 mm, 15 mm) and 1 mm axial section slices as input. Such an approach augments the two-dimensional (2-D) CT slice images with more representative spatial information that helps discriminate nodules from vessels through their morphologies. Our proposed method achieves sensitivity of 92.7% with 1 false positive per scan and sensitivity of 94.2% with 2 false positives per scan for lung nodule detection on 888 scans in the LIDC-IDRI dataset. The use of thick MIP images helps the detection of small pulmonary nodules (3 mm-10 mm) and results in fewer false positives. Experimental results show that utilizing MIP images can increase the sensitivity and lower the number of false positives, which demonstrates the effectiveness and significance of the proposed MIP-based CNNs framework for automatic pulmonary nodule detection in CT scans. The proposed method also shows the potential that CNNs could gain benefits for nodule detection by combining the clinical procedure.

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

“…[31][32][33] We also improve our performance in detection of nodules smaller than 6 mm, compared to our previous work (sensitivity: 93.4% vs. 90.4%, at 1.0 FP/scan; sensitivity: 95.0% vs. 91.6%, at 2.0 FPs/scan). 30 Another study from Ozdemir et al 24 showed a sensitivity of around 90% with 1FP/scan for nodules smaller than 5 mm, whereas our method achieved a sensitivity of 93.0% with 1FP/scan to detect nodules with the same size. Methods of Dou et al, 21 Xie et al, 22 and Huang et al 26 might need to further improve the discrimination between nodules and wrong findings.…”

“…With projected images as input, convolutional neural networks (CNNs) were employed to identify nodule candidates. 30 Nodule cubes with various sizes were extracted for reduction of false positives. The results showed that using maximum intensity projection can improve the performance of deep learning-based CAD for lung nodule detection.…”

“…The segmentation procedure is described and illustrated in more detail in our previous work. 30 Segmented lung parenchyma in three planes are illustrated in the third row of Fig. 1.…”

Pulmonary Nodule Detection Using V-Net and High-Level Descriptor Based SVM Classifier

“…The 24×24×4 receptive field encompasses small-sized nodules with proper amount of context. In the fusion stage, contour retrieval and an approximation method [27] are combined to extract and refine the predicted candidate information, such as coordinates and size of the bounding box. For candidates with centers are too close to each other, a distance ratio of 1.1 is used to distinguish whether two candidates are actually one finding or two individual findings.…”

Generative augmentation to improve lung nodules detection in resource-limited settings

“…For pulmonary nodes, such a component is the maximum intensity projection (MIP) image. MIP [20,21] is a postprocessing method that projects 3D voxels with maximum intensity to the projection plane. The advantage of MIP is that its formation is a 2D task and therefore requires less computing resources.…”