Detection of intracranial aneurysms using deep learning-based CAD system: usefulness of the scores of CNN’s final layer for distinguishing between aneurysm and infundibular dilatation

Abstract

Purpose We evaluated the diagnostic performance of a clinically available deep learning-based computer-assisted diagnosis software for detecting unruptured aneurysms (UANs) using magnetic resonance angiography and assessed the functionality of the convolutional neural network (CNN) final layer score for distinguishing between UAN and infundibular dilatation (ID). Materials and methods EIRL brain aneurysm (EIRL_BA) was used in this study. The subjects were 117 UAN and/or ID cases including 100 UAN lesions (average sizes of 2.56 ± 1.45 mm) and 40 ID lesions (average sizes of 1.75 ± 0.41 mm) in any of internal carotid artery, middle cerebral artery, and anterior communicating artery, and 123 normal controls. The sensitivity, specificity, and accuracy of EIRL_BA were determined for UAN and ID or UAN only. Furthermore, the relationship between the lesion category and score was examined using a linear regression analysis model, and the receiver operating characteristic (ROC) analysis was used to assess whether the scores represent UAN-like characteristics. Results EIRL_BA showed a total of 203 candidates (an average of 1.73/case) in UAN and/or ID cases and 98 candidates (an average of 0.80/case) in normal controls. For diagnosing either UAN/ID, EIRL_BA showed an overall sensitivity of 80%, specificity of 84.2%, and accuracy of 83.7%, resulting in the positive likelihood ratio of 5.0. For diagnosing UAN only, the overall sensitivity of 89.0, specificity of 82.6%, and accuracy of 83.2% resulting in the positive likelihood ratio of 5.1. In a linear regression analysis, the scores significantly increased in the candidates’ first and second ranks in UAN (p < 0.05) but not in ID. An ROC analysis using the score for diagnosing UAN showed an area under the curve of 0.836. Conclusion EIRL_BA is applicable for detecting small UAN, and the CNN’s final layer scores may be an effective index for discriminating UAN and ID and representing the likelihood of UAN.

Clinical Utility of Breast Ultrasound Images Synthesized by a Generative Adversarial Network

“…The effective utilization of AI by radiologists is expected to not only improve diagnostic performance in the future but also to significantly reduce radiologists' workload and contribute to healthcare cost savings. AI's potential to streamline diagnostic processes and enhance accuracy promises both operational efficiency and reduced strain on healthcare systems, making it a valuable tool in modern medical practice [9,[33][34][35]. GAN is one of the most remarkable methods and has been applied to medical imaging and proven useful in various areas, such as image enhancement, registration, generation, reconstruction, and transformation between images.…”

The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI

“…The inception of Deep Learning (DL) has catalyzed a significant progression in artificial intelligence (AI) [1], unlocking numerous possibilities, especially in diagnostic radiology-an arena pivotal for accurate imaging data interpretation. This progression is attributed mainly to the emergence of Convolutional Neural Networks (CNNs) [2,3], which have markedly enhanced image recognition, segmentation, analysis, and improvement of image quality [1,[4][5][6][7][8][9][10][11][12][13][14][15]. This represents a foundational shift in automated feature extraction from imaging data, consequently reducing the time and expertise required for interpreting medical images.…”

Opportunities and challenges of computer aided diagnosis in new millennium: A bibliometric analysis from 2000 to 2023

“…Statistical data show that CAD was used in approximately 92% of screening mammograms in 2016 in the U.S. [ 8 ] Not only in the field of mammography, but CAD is also used in combination with computer tomography (CT) and magnetic resonance imaging (MRI) for lung nodule, [ 9 ] colorectal cancer, [ 10 ] and intracranial aneurysms screening. [ 11 ] The rapid development of CAD makes it difficult to identify research hotspots and directions for development.…”