A multiscale 3D network for lung nodule detection using flexible nodule modeling

Abstract

AbstractBackgroundLung cancer is the most common type of cancer. Detection of lung cancer at an early stage can reduce mortality rates. Pulmonary nodules may represent early cancer and can be identified through computed tomography (CT) scans. Malignant risk can be estimated based on attributes like size, shape, location, and density.PurposeDeep learning algorithms have achieved remarkable advancements in this domain compared to traditional machine learning methods. Nevertheless, many existing anchor‐based deep learning algorithms exhibit sensitivity to predefined anchor‐box configurations, necessitating manual adjustments to obtain optimal outcomes. Conversely, current anchor‐free deep learning‐based nodule detection methods normally adopt fixed‐size nodule models like cubes or spheres.MethodsTo address these technical challenges, we propose a multiscale 3D anchor‐free deep learning network (M3N) for pulmonary nodule detection, leveraging adjustable nodule modeling (ANM). Within this framework, ANM empowers the representation of target objects in an anisotropic manner, with a novel point selection strategy (PSS) devised to accelerate the learning process of anisotropic representation. We further incorporate a composite loss function that combines the conventional L2 loss and cosine similarity loss, facilitating M3N to learn nodules’ intensity distribution in three dimensions.ResultsExperiment results show that the M3N achieves 90.6% competitive performance metrics (CPM) with seven predefined false positives per scan on the LUNA 16 dataset. This performance appears to exceed that of other state‐of‐the‐art deep learning‐based networks reported in their respective publications. Individual test results also demonstrate that M3N excels in providing more accurate, adaptive bounding boxes surrounding the contours of target nodules.ConclusionsThe newly developed nodule detection system reduces reliance on prior knowledge, such as the general size of objects in the dataset, thus it should enhance overall robustness and versatility. Distinct from traditional nodule modeling techniques, the ANM approach aligns more closely with the morphological characteristics of nodules. Time consumption and detection results demonstrate promising efficiency and accuracy which should be validated in clinical settings.