Nowadays, pulmonary Computed Tomography Angiography (CTA) is the main tool for detecting Pulmonary Embolism (PE). However, manual interpretation of CTA volume requires a radiologist, which is time-consuming and error-prone due to the specific conditions of lung tissue, large volume of data, lack of experience, and eye fatigue. Therefore, Computer-Aided Design (CAD) systems are used as a second opinion for the diagnosis of PE. The purpose of this article is to review, evaluate, and compare the performance of deep learning and traditional-based CAD system for diagnosis PE and to help physicians and researchers in this field. In this study, all articles available in databases such as IEEE, ScienceDirect, Wiley, Springer, Nature, and Wolters Kluwer in the field of PE diagnosis were examined using traditional and deep learning methods. From 2002 to 2023, 23 papers were studied to extract the articles with the considered limitations. Each paper presents an automatic PE detection system that we evaluate using criteria such as sensitivity, False Positives (FP), and the number of datasets. This research work includes recent studies, state-of-the-art research works, and a more comprehensive overview compared to previously published review articles in this research area.
Detection of lung mass lesion is widely required in the clinic for diagnosis of different pulmonary defects like lung cancer and pulmonary embolism. Due to severe symptoms of such diseases, real-time detection of the lung mass lesion is significant. In this paper, this problem is addressed by a new image segmentation algorithm. Primarily, a Gabor-based filtering algorithm is employed to remove the intensity nonuniformity of the CT image. Then, the holes and discontinuities of the mass lesion are eliminated through morphological operations. Finally, the lesion objects are extracted by using the thresholding and connected-component-analysis. The experimental results demonstrated significantly short CPU time of the proposed algorithm, as 73 milliseconds for each slice on a typical laptop. Also, the solution quality of our method was considerably high, as 91.6%, 85.4%, and 93.3% in terms of accuracy, sensitivity, and specificity, respectively. We further showed that the proposed method provided better solutions compared to six other counterpart algorithms.