Intracranial aneurysm detection: an object detection perspective

• Published in: International journal for computer assisted radiology and surgery Vol. 19; no. 9; pp. 1667 - 1675
• Main Authors: Assis, Youssef, Liao, Liang, Pierre, Fabien, Anxionnat, René, Kerrien, Erwan
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2024; Springer Nature B.V; Springer Verlag
• Subjects: Algorithms; Aneurysms; Angiography; Annotations; Artificial Intelligence; Computer Imaging; Computer Science; Computer Vision and Pattern Recognition; Data sampling; Health Informatics; Humans; Image Interpretation, Computer-Assisted - methods; Image segmentation; Imaging; Imaging, Three-Dimensional - methods; Intracranial Aneurysm - diagnosis; Intracranial Aneurysm - diagnostic imaging; Magnetic resonance; Magnetic Resonance Angiography - methods; Medical Imaging; Medicine; Medicine & Public Health; Methods; Neural and Evolutionary Computing; Neural networks; Object recognition; Pattern Recognition and Graphics; Performance evaluation; Radiology; Review Article; Sensitivity and Specificity; State-of-the-art reviews; Surgery; Vision; Deep learning; Intracranial aneurysms; Computer-aided detection; Magnetic resonance angiography; deep learning; intracranial aneurysm; magnetic resonance angiography
• ISSN: 1861-6429; 1861-6410; 1861-6429
• DOI: 10.1007/s11548-024-03132-z

Purpose Intracranial aneurysm detection from 3D Time-Of-Flight Magnetic Resonance Angiography images is a problem of increasing clinical importance. Recently, a streak of methods have shown promising performance by using segmentation neural networks. However, these methods may be less relevant in a clinical settings where diagnostic decisions rely on detecting objects rather than their segmentation. Methods We introduce a 3D single-stage object detection method tailored for small object detection such as aneurysms. Our anchor-free method incorporates fast data annotation, adapted data sampling and generation to address class imbalance problem, and spherical representations for improved detection. Results A comprehensive evaluation was conducted, comparing our method with the state-of-the-art SCPM-Net, nnDetection and nnUNet baselines, using two datasets comprising 402 subjects. The evaluation used adapted object detection metrics. Our method exhibited comparable or superior performance, with an average precision of 78.96%, sensitivity of 86.78%, and 0.53 false positives per case. Conclusion Our method significantly reduces the detection complexity compared to existing methods and highlights the advantages of object detection over segmentation-based approaches for aneurysm detection. It also holds potential for application to other small object detection problems.