{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T21:06:08Z","timestamp":1791666368334,"version":"4.3.4"},"reference-count":36,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T00:00:00Z","timestamp":1764460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Background: Accurate detection of intracranial aneurysms, especially those smaller than 3 mm, remains a critical challenge in neurovascular imaging due to their subtle morphology and low contrast in Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) scans. This study presents a Mask R-CNN-based deep learning framework designed to automatically detect and segment intracranial aneurysms, with specific architectural modifications aimed at improving sensitivity to small lesions. Method: A dataset of 447 TOF-MRA volumes (161 aneurysmal, 286 healthy) was used, with patient-level deduplication and 5-fold cross-validation to ensure robust evaluation. Bayesian hyperparameter optimization was applied using Optuna, and two key innovations were introduced: a Small Object Aware ROI Head to better capture micro-aneurysms and customized anchor configurations to improve region proposal quality. Healthy scans were incorporated as negative samples to enhance background modeling, and targeted data augmentation increased model generalization. Results: The proposed model achieved a Dice coefficient of 0.8832, precision of 0.9404, and sensitivity (recall) of 0.8677, with consistent performance across aneurysm sizes. Conclusions: These results demonstrate that the integration of architectural innovations, automated optimization, and negative-sample modeling enables a clinically viable deep learning tool that could serve as a reliable second-reader system for assisting radiologists in intracranial aneurysm detection.<\/jats:p>","DOI":"10.3390\/brainsci15121295","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T09:34:37Z","timestamp":1764581677000},"page":"1295","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Mask R-CNN-Based Approach for Brain Aneurysm Detection and Segmentation from TOF-MRA Data"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5329-0131","authenticated-orcid":false,"given":"Emre","family":"Ayka\u00e7","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Graduate School of Natural and Applied Sciences, Erciyes University, 38039 Kayseri, T\u00fcrkiye"},{"name":"Vocational School of Health Services, Yozgat Bozok University, 66100 Yozgat, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9424-664X","authenticated-orcid":false,"given":"G\u00fcrol","family":"G\u00f6ksungur","sequence":"additional","affiliation":[{"name":"Department of Radiology, Yozgat City Hospital, 66100 Yozgat, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-8303","authenticated-orcid":false,"given":"G\u00fcne\u015f Seda","family":"Albayrak","sequence":"additional","affiliation":[{"name":"Department of Neurology, Yozgat Bozok University, 66100 Yozgat, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8167-096X","authenticated-orcid":false,"given":"Mehmet Emin","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Faculty of Engineering, Erciyes University, 38039 Kayseri, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1056\/NEJMcp1605827","article-title":"Subarachnoid hemorrhage","volume":"377","author":"Lawton","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/S1474-4422(14)70015-8","article-title":"Unruptured intracranial aneurysms: Epidemiology, natural history, management options, and familial screening","volume":"13","author":"Brown","year":"2014","journal-title":"Lancet Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1007\/s00401-011-0939-3","article-title":"Saccular intracranial aneurysm: Pathology and mechanisms","volume":"123","author":"Tulamo","year":"2012","journal-title":"Acta Neuropathol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/S1474-4422(13)70263-1","article-title":"Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: A pooled analysis of six prospective cohort studies","volume":"13","author":"Greving","year":"2014","journal-title":"Lancet Neurol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1016\/S0140-6736(05)67214-5","article-title":"International subarachnoid aneurysm trial (ISAT) of neurosurgical clipping versus endovascular coiling in 2143 patients with ruptured intracranial aneurysms: A randomised comparison","volume":"366","author":"Molyneux","year":"2005","journal-title":"Lancet"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e10771","DOI":"10.1097\/MD.0000000000010771","article-title":"Meta-analysis of computed tomography angiography versus magnetic resonance angiography for intracranial aneurysm","volume":"97","author":"Chen","year":"2018","journal-title":"Medicine"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1016\/j.acra.2004.07.011","article-title":"Automated computerized scheme for detection of unruptured intracranial aneurysms in three-dimensional magnetic resonance angiography","volume":"11","author":"Arimura","year":"2004","journal-title":"Acad. Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1002\/jmri.25842","article-title":"Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography","volume":"47","author":"Nakao","year":"2018","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_10","unstructured":"Bengio, Y., Goodfellow, I., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_11","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings of the 4th International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1007\/s11548-020-02121-2","article-title":"Deep learning for automated cerebral aneurysm detection on computed tomography images","volume":"15","author":"Dai","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hwang, B., Kim, J., Lee, S., Kim, E., Kim, J., Jung, Y., and Hwang, H. (2022). Automatic detection and segmentation of thrombi in abdominal aortic aneurysms using a Mask R-CNN with optimized loss functions. Sensors, 22.","DOI":"10.3390\/s22103643"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1148\/radiol.2018180901","article-title":"Deep learning for MR angiography: Automated detection of cerebral aneurysms","volume":"290","author":"Ueda","year":"2019","journal-title":"Radiology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1007\/s10278-018-0162-z","article-title":"Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography","volume":"32","author":"Stember","year":"2019","journal-title":"J. Digit. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3174\/ajnr.A5911","article-title":"Deep learning\u2013based detection of intracranial aneurysms in 3D TOF-MRA","volume":"40","author":"Sichtermann","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5785","DOI":"10.1007\/s00330-020-06966-8","article-title":"A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance","volume":"30","author":"Joo","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.3349\/ymj.2021.62.11.1052","article-title":"A deep learning model with high standalone performance for diagnosis of unruptured intracranial aneurysm","volume":"62","author":"Joo","year":"2021","journal-title":"Yonsei Med. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.3174\/ajnr.A7242","article-title":"Deep learning\u2013based software improves clinicians\u2019 detection sensitivity of aneurysms on brain TOF-MRA","volume":"42","author":"Sohn","year":"2021","journal-title":"Am. J. Neuroradiol."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Terasaki, Y., Yokota, H., Tashiro, K., Maejima, T., Takeuchi, T., Kurosawa, R., Yamauchi, S., Takada, A., Mukai, H., and Ohira, K. (2022). Multidimensional deep learning reduces false positives in the automated detection of cerebral aneurysms on TOF-MRA: A multi-center study. Front. Neurol., 12.","DOI":"10.3389\/fneur.2021.742126"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s12021-022-09597-0","article-title":"Towards automated brain aneurysm detection in TOF-MRA: Open data, weak labels, and anatomical knowledge","volume":"21","author":"Marie","year":"2023","journal-title":"Neuroinformatics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e195600","DOI":"10.1001\/jamanetworkopen.2019.5600","article-title":"Deep learning\u2013assisted diagnosis of cerebral aneurysms using the HeadXNet model","volume":"2","author":"Park","year":"2019","journal-title":"JAMA Netw. Open"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6090","DOI":"10.1038\/s41467-020-19527-w","article-title":"A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images","volume":"11","author":"Shi","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1136\/jnis-2023-020905","article-title":"Deep geometric learning for intracranial aneurysm detection: Towards expert rater performance","volume":"16","author":"Bizjak","year":"2024","journal-title":"J. Neurointerv. Surg."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chen, G., Meng, C., Ruoyu, D., Dongdong, W., Liqin, Y., Wei, X., Yuxin, L., and Daoying, G. (2022). An automatic detection method of cerebral aneurysms in time-of-flight magnetic resonance angiography images based on attention 3D U-Net. Comput. Methods Programs Biomed., 225.","DOI":"10.1016\/j.cmpb.2022.106998"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1177\/15910199211000956","article-title":"Deep neural network-based detection and segmentation of intracranial aneurysms on 3D rotational DSA","volume":"27","author":"Liu","year":"2021","journal-title":"Interv. Neuroradiol."},{"key":"ref_31","unstructured":"Hayat, M., Aramvith, S., Bhattacharjee, S., and Ahmad, N. (2025). Attention GhostUNet++: Enhanced Segmentation of Adipose Tissue and Liver in CT Images. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Qiao, L., Veltrup, M., and Mayer, B. (2025). Comparison of Mask R-CNN and YOLOv8-Seg for Improved Monitoring of the PCB Surface during Laser Cleaning. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-02131-7"},{"key":"ref_33","unstructured":"Di Noto, T., Marie, G., Tourbier, S., Alem\u00e1n-G\u00f3mez, Y., Esteban, O., Saliou, G., Cuadra, M.B., Hagmann, P., and Richiardi, J. (2022). Lausanne_TOF-MRA_Aneurysm_Cohort [dataset]. OpenNeuro."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"74","DOI":"10.3390\/neurolint16010005","article-title":"The Management of Intracranial Aneurysms: Current Trends and Future Directions","volume":"16","author":"Deshmukh","year":"2024","journal-title":"Neurol. Int."},{"key":"ref_35","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., and Girshick, R. (2024, September 01). Detectron2. Facebook AI Research. Available online: https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1007\/s10278-024-01018-9","article-title":"A Data Augmentation Methodology to Reduce the Class Imbalance in Histopathology Images","volume":"37","author":"Carvalho","year":"2024","journal-title":"J. Imaging Inform. Med."}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/15\/12\/1295\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T10:11:46Z","timestamp":1764583906000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/15\/12\/1295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,30]]},"references-count":36,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["brainsci15121295"],"URL":"https:\/\/doi.org\/10.3390\/brainsci15121295","relation":{},"ISSN":["2076-3425"],"issn-type":[{"value":"2076-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,30]]}}}