Abstract
Objective: To develop a new content-based image retrieval (CBIR) based computer-aided diagnosis (CAD) scheme to discriminate the lung nodules benign or malignant and to perform a preliminary evaluation of this CAD scheme and its robustness.
Methods: Two lung nodule datasets from LIDC-IDRI lung CT database were assembled. Two nodule density related features were computed to represent each nodule. For each queried nodule, a twostep CBIR scheme was applied to retrieve the top ten most similar reference nodules. A classification likelihood value was calculated to predict the malignancy of the lung nodule. To assess the robustness of the CBIR scheme, we first tested this CAD scheme on the second dataset, and then used the second dataset to retrieve the first dataset. To verify the feasibility of the CBIR scheme, classification performance of our scheme was comparied with that of classical classifiers. Results: Through applying a leave-one-out validation method on the first dataset, an area under the ROC curve (AUC) of 0.915 was obtained, and the total classification accuracy was 83.0%. For robustness on the second dataset, the AUC was 0.727, and the total classification accuracy was 66.1%. When we used the second dataset to retrieve the first dataset, the AUC value and the total classification accuracy were 0.751 and 71.3%, respectively. The classification performance of the proposed scheme outperforms that of the classical classifiers. Conclusion: This study demonstrated that (1) a simple and efficient CBIR based CAD scheme applying two nodule density related features achieved high performance for classification of lung nodules and (2) this CAD scheme using CBIR approach also had high robustness performance in the future clinical application.Keywords: Computed tomography, computer-aided diagnosis, content-based image retrieval, heterogeneity, lesion density, lung nodules, robustness.
Graphical Abstract
Call for Papers in Thematic Issues
Intelligent Information Retrieval for Multispectral and Hyperspectral Imaging
Multispectral and hyperspectral imaging is an interdisciplinary research area, widely focuses on spectral, spatial, and temporal data. It offers a plethora of opportunities to efficiently analyze the vast area of the earth's surface. However, there are numerous factors such as dimensionality and size of the hyperspectral data, lesser training samples, ...read more
Machine and Deep Learning in Medical Image Diagnosis
Medical Image Processing regards a set of methodologies that have been developed over recent years with the purpose of improving medical image quality, improving medical data visualization, understanding, and assisting medical diagnosis, and so on. The application of machine and deep learning methods in sensing and imaging can potentially have ...read more
Quantum Machine Learning for Medical Data and Imaging
Quantum computing has promised a significant speedup in certain computationally intensive tasks that are intractable on classical computers. Researchers in quantum machine learning, such as those working in computer vision, image processing, biomedical analysis, and related topics, may play an important role in comprehending and working on complicated medical data, ...read more
12