Yapay Zeka Tabanlı Doğru Bir Anevrizma Tespit Modeli

Öz

Serebral anevrizmalar, yaşamı tehdit eden önemli serebrovasküler hastalıklardır ve erken tanı ve tedavi için Bilgisayarlı Tomografi Anjiyografisi’nin (BTA) doğru yorumlanması kritik öneme sahiptir. Bu çalışma, 1211 BTA görüntüsüne 15 farklı Evrişimli Sinir Ağı (ESA) uygulanarak, derin öğrenmenin radyolog kaynaklı yorumlama hatalarını azaltmadaki etkinliğini değerlendirmektedir. Sınıflandırma öncesinde görüntülere çeşitli önişleme ve filtreleme işlemleri uygulanmış ve karşılaştırmalı performans metrikleri elde edilmiştir. En iyi sonuç, literatürde şimdiye kadar bildirilen en yüksek doğruluk oranı olan %99,72 ile yumuşatma filtresi uygulanmış görüntü veri setinde VGG19 mimarisi kullanılarak elde edilmiştir. VGG19 test setinde model çıktıları 272 gerçek negatif (tn), 1 yanlış negatif (fn), 0 yanlış pozitif (fp) ve 90 gerçek pozitiften (tp) oluşmuştur. Bu bulgular, uygun görüntü önişleme ve filtreleme adımlarının, CNN tabanlı anevrizma tespit performansını anlamlı ölçüde artırdığını ve sınıflandırma doğruluğunu iyileştirmede kritik bir rol oynadığını göstermektedir.

Anahtar Kelimeler

• Beyin Anevrizması
• BTA-Tarama
• Görüntü Filtreleme
• Yapay Zeka

An Accurate Aneurysm Detection Model based on Artificial Intelligence

Öz

Cerebral aneurysms are a major, life threatening cerebrovascular disease, and accurate interpretation of Computed Tomography Angiography (CTA) is critical for early diagnosis and treatment. This study evaluates the effectiveness of deep learning in reducing radiologist related interpretation errors by applying 15 different Convolutional Neural Networks (CNNs) to 1,211 CTA images. Prior to classification, images underwent various preprocessing and filtering operations, and comparative performance metrics were obtained. The best result, representing the highest accuracy reported to date of 99.72%, was achieved with a smoothing filtered image dataset using the VGG19 architecture. In the VGG19 test set, model outputs consisted of 272 true negatives (tn), 1 false negative (fn), 0 false positives (fp), and 90 true positives (tp). These findings demonstrate that appropriate image preprocessing and filtering significantly enhance CNN based aneurysm detection performance and play a crucial role in improving classification accuracy.

Anahtar Kelimeler

• Artificial Intelligence
• Cerebral Aneurysm
• Image Filtering
• CTA-Scan

Kaynakça

1. Kaya V. Anterior Kommunikan Arter Ve Anterior Kommunikan Arter İle İlişkili Anterior Sistem Anevrizmalarında ‘“Morfolojik Ve Hemodinamik Faktörlerin”’ Anevrizma Rüptürü İle İlişkisi. İnönü, 2018.
2. Lawton MT, Vates GE. Subarachnoid Hemorrhage. N Engl J Med 2017;377:257–66. https://doi.org/10.1056/NEJMcp1605827.
3. Jin H, Yin Y, Hu M, Yang G, Qin L. Fully automated unruptured intracranial aneurysm detection and segmentation from digital subtraction angiography series using an end-to-end spatiotemporal deep neural network, 2019. https://doi.org/10.1117/12.2512623.
4. Dai X, Huang L, Qian Y, Xia S, Chong W, Liu J, et al. Deep learning for automated cerebral aneurysm detection on computed tomography images. Int J Comput Assist Radiol Surg 2020. https://doi.org/10.1007/s11548-020-02121-2.
5. Gu F, Wu X, Wu W, Wang Z, Yang X, Chen Z, et al. Performance of deep learning in the detection of intracranial aneurysm: A systematic review and meta-analysis. Eur J Radiol 2022;155:110457. https://doi.org/10.1016/j.ejrad.2022.110457.
6. Heit JJ, Honce JM, Yedavalli VS, Baccin CE, Tatit RT, Copeland K, et al. RAPID Aneurysm: Artificial intelligence for unruptured cerebral aneurysm detection on CT angiography. J Stroke Cerebrovasc Dis 2022;31:106690. https://doi.org/10.1016/j.jstrokecerebrovasdis.2022.106690.
7. Buchlak QD, Milne MR, Seah J, Johnson A, Samarasinghe G, Hachey B, et al. Charting the potential of brain computed tomography deep learning systems. J Clin Neurosci 2022. https://doi.org/10.1016/j.jocn.2022.03.014.
8. Wei X, Jiang J, Cao W, Yu H, Deng H, Chen J, et al. Artificial intelligence assistance improves the accuracy and efficiency of intracranial aneurysm detection with CT angiography. Eur J Radiol 2022;149:110169. https://doi.org/10.1016/j.ejrad.2022.110169.

9. Wang J, Ti L, Sun X, Yang R, Zhang N, Sun K. DSA Image Analysis of Clinical Features and Nursing Care of Cerebral Aneurysm Patients Based on the Deep Learning Algorithm. Scanning 2022;2022:1–6. https://doi.org/10.1155/2022/8485651.
10. Tasci B, Tasci I. Deep feature extraction based brain image classification model using preprocessed images: PDRNet. Biomed Signal Process Control 2022;78:103948. https://doi.org/10.1016/j.bspc.2022.103948.
11. Lehnen NC, Haase R, Schmeel FC, Vatter H, Dorn F, Radbruch A, et al. Automated Detection of Cerebral Aneurysms on TOF-MRA Using a Deep Learning Approach: An External Validation Study. Am J Neuroradiol 2022;43:1700–5. https://doi.org/10.3174/ajnr.A7695.
12. [12] Shi Z, Miao C, Schoepf UJ, Savage RH, Dargis DM, Pan C, et al. A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images. Nat Commun 2020;11:6090. https://doi.org/10.1038/s41467-020-19527-w.
13. Terasaki Y, Yokota H, Tashiro K, Maejima T, Takeuchi T, Kurosawa R, et al. Multidimensional Deep Learning Reduces False-Positives in the Automated Detection of Cerebral Aneurysms on Time-Of-Flight Magnetic Resonance Angiography: A Multi-Center Study. Front Neurol 2022;12. https://doi.org/10.3389/fneur.2021.742126.
14. Chen G, Meng C, Ruoyu D, Dongdong W, Liqin Y, Wei X, et al. 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 2022;225:106998. https://doi.org/10.1016/j.cmpb.2022.106998.
15. Chen G, Yifang B, Jiajun Z, Dongdong W, Zhiyong Z, Ruoyu D, et al. Automated unruptured cerebral aneurysms detection in TOF MR angiography images using dual-channel SE-3D UNet: a multi-center research. Eur Radiol 2023. https://doi.org/10.1007/s00330-022-09385-z.
16. Stember JN, Chang P, Stember DM, Liu M, Grinband J, Filippi CG, et al. Convolutional Neural Networks for the Detection and Measurement of Cerebral Aneurysms on Magnetic Resonance Angiography. J Digit Imaging 2019;32:808–15. https://doi.org/10.1007/s10278-018-0162-z.
17. Di Noto T, Marie G, Tourbier S, Alemán-Gómez Y, Saliou G, Bach Cuadra M, et al. An Anatomically-Informed 3D CNN for Brain Aneurysm Classification with Weak Labels, 2020, p. 56–66. https://doi.org/10.1007/978-3-030-66843-3_6.
18. Tasci B. Automated ischemic acute infarction detection using pre-trained CNN models’ deep features. Biomed Signal Process Control 2023;82:104603. https://doi.org/10.1016/j.bspc.2023.104603.
19. Nakao T, Hanaoka S, Nomura Y, Sato I, Nemoto M, Miki S, et al. Deep neural network‐based computer‐assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging 2018;47:948–53. https://doi.org/10.1002/jmri.25842.
20. Heit JJ, Honce JM, Yedavalli VS, Baccin CE, Tatit RT, Copeland K, et al. RAPID Aneurysm: Artificial intelligence for unruptured cerebral aneurysm detection on CT angiography. J Stroke Cerebrovasc Dis 2022. https://doi.org/10.1016/j.jstrokecerebrovasdis.2022.106690.
21. Suwalska A, Siuda J, Kocot S, Zmuda W, Rudzinska-Bar M, Polanska J. Activation maps of convolutional neural networks as a tool for brain degeneration tracking in early diagnosis of dementia in Parkinson’s disease based on magnetic resonance imaging. Signal, Image Video Process 2023;17:4115–21. https://doi.org/10.1007/s11760-023-02643-7.
22. Kutan F, Aynur Ö. Gürültü Filtreleme Uygulamalarının Medikal Görüntüler Üzerindeki Performanslarının Değerlendirilmesi. Eur J Sci Technol 2020:265–71. https://doi.org/10.31590/ejosat.779957.
23. Meng C, Yang D, Chen D. Cerebral aneurysm image segmentation based on multi-modal convolutional neural network. Comput Methods Programs Biomed 2021;208:106285. https://doi.org/10.1016/j.cmpb.2021.106285.
24. Öziç MÜ, Özşen S. Üç Boyutlu T1 Ağırlıklı Manyetik Rezonans Görüntülerinde Ön İşleme Yöntemleri. Eur J Sci Technol 2020:227–40. https://doi.org/10.31590/ejosat.719062.
25. Shi Z, Miao C, Schoepf UJ, Savage RH, Dargis DM, Pan C, et al. A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images. Nat Commun 2020. https://doi.org/10.1038/s41467-020-19527-w.
26. Qiu J, Tan G, Lin Y, Guan J, Dai Z, Wang F, et al. Automated detection of intracranial artery stenosis and occlusion in magnetic resonance angiography: A preliminary study based on deep learning. Magn Reson Imaging 2022;94:105–11. https://doi.org/10.1016/j.mri.2022.09.006.
27. Liao J, Liu L, Duan H, Huang Y, Zhou L, Chen L, et al. Using a Convolutional Neural Network and Convolutional Long Short-term Memory to Automatically Detect Aneurysms on 2D Digital Subtraction Angiography Images: Framework Development and Validation. JMIR Med Informatics 2022;10:e28880. https://doi.org/10.2196/28880.
28. Vidhya SRS, Arunachalam AR. Automated Detection of False positives and false negatives in Cerebral Aneurysms from MR Angiography Images by Deep Learning Methods. 2021 Int. Conf. Syst. Comput. Autom. Netw., IEEE; 2021, p. 1–4. https://doi.org/10.1109/ICSCAN53069.2021.9526520.
29. Lei X, Yang Y. Deep Learning-Based Magnetic Resonance Imaging in Diagnosis and Treatment of Intracranial Aneurysm. Comput Math Methods Med 2022. https://doi.org/10.1155/2022/1683475.
30. Su R, van der Sluijs M, Cornelissen SAP, Lycklama G, Hofmeijer J, Majoie CBLM, et al. Spatio-temporal deep learning for automatic detection of intracranial vessel perforation in digital subtraction angiography during endovascular thrombectomy. Med Image Anal 2022. https://doi.org/10.1016/j.media.2022.102377.
31. Mei Y jia, Hu R ting, Lin J, Xu H yu, Wu L ya, Li H peng, et al. Diagnosis of Middle Cerebral Artery Stenosis Using Transcranial Doppler Images Based on Convolutional Neural Network. World Neurosurg 2022. https://doi.org/10.1016/j.wneu.2022.01.068.
32. Dai X, Huang L, Qian Y, Xia S, Chong W, Liu J, et al. Deep learning for automated cerebral aneurysm detection on computed tomography images. Int J Comput Assist Radiol Surg 2020;15:715–23. https://doi.org/10.1007/s11548-020-02121-2.
33. Ueda D, Yamamoto A, Nishimori M, Shimono T, Doishita S, Shimazaki A, et al. Deep learning for MR angiography: Automated detection of cerebral aneurysms. Radiology 2019. https://doi.org/10.1148/radiol.2018180901.
34. Rahman AI, Bhuiyan S, Reza ZH, Zaheen J, Khan TAN, Karim DZ. Intracranial Hemorrhage Detection on CT Scan Images using Transfer Learning Approach of Convolutional Neural Network. ACM Int. Conf. Proceeding Ser., 2022. https://doi.org/10.1145/3542954.3542980.
35. Ou C, Qian Y, Chong W, Hou X, Zhang M, Zhang X, et al. A deep learning–based automatic system for intracranial aneurysms diagnosis on three‐dimensional digital subtraction angiographic images. Med Phys 2022. https://doi.org/10.1002/mp.15846.
36. Ivantsits M, Goubergrits L, Kuhnigk JM, Huellebrand M, Bruening J, Kossen T, et al. Detection and analysis of cerebral aneurysms based on X-ray rotational angiography - the CADA 2020 challenge. Med Image Anal 2022. https://doi.org/10.1016/j.media.2021.102333.
37. Sathish Kumar L, Hariharasitaraman S, Narayanasamy K, Thinakaran K, Mahalakshmi J, Pandimurugan V. AlexNet approach for early stage Alzheimer’s disease detection from MRI brain images. Mater. Today Proc., 2021. https://doi.org/10.1016/j.matpr.2021.04.415.
38. Di Noto T, Marie G, Tourbier S, Alemán-Gómez Y, Esteban O, Saliou G, et al. Towards Automated Brain Aneurysm Detection in TOF-MRA: Open Data, Weak Labels, and Anatomical Knowledge. Neuroinformatics 2022. https://doi.org/10.1007/s12021-022-09597-0.
39. Guzmán Ortiz S, Hurtado Ortiz R, Jara Gavilanes A, Ávila Faican R, Parra Zambrano B. A serial image analysis architecture with positron emission tomography using machine learning combined for the detection of lung cancer. Rev Española Med Nucl e Imagen Mol (English Ed 2024;43:500003. https://doi.org/10.1016/j.remnie.2024.500003.
40. Özmen T, Kuzu Ü, Koçyiğit Y, Sarnel H. Early stage diabetes prediction by features selection with metaheuristic methods. Pamukkale Univ J Eng Sci 2023;29:596–606. https://doi.org/10.5505/pajes.2022.82610.
41. Karahan T, Nabiyev V. Plant identification with convolutional neural networks and transfer learning. Pamukkale Univ J Eng Sci 2021;27:638–45. https://doi.org/10.5505/pajes.2020.84042.
42. Alakuş TB, Türkoğlu İ. Prediction of human protein functions with protein mapping techniques and deep learning model. Pamukkale Univ J Eng Sci 2022;28:255–65. https://doi.org/10.5505/pajes.2021.51261.
43. Sez E, Üncü Ya, Yardımcı A. Prematüre Retina Kan Damarlarının Tespitinde Farklı Görüntü İşleme Yöntemlerinin Performanslarının Karşılaştırılması. Süleyman Demirel Üniversitesi Fen Edeb Fakültesi Fen Derg 2023;18:62–75. https://doi.org/10.29233/sdufeffd.1220516.
44. Wu F, Zhu C, Xu J, Bhatt MW, Sharma A. Research on image text recognition based on canny edge detection algorithm and k-means algorithm. Int J Syst Assur Eng Manag 2022;13:72–80. https://doi.org/10.1007/s13198-021-01262-0.
45. Gupta IK, Choubey A, Choubey S. Artifical intelligence with optimal deep learning enabled automated retinal fundus image classification model. Expert Syst 2022;39. https://doi.org/10.1111/exsy.13028.
46. Uzun Y, Boyacıgil M. Raspberry PI Tabanlı Görüntü İşleme Uygulaması Geliştirilmesi. Osmaniye Korkut Ata Üniversitesi Fen Bilim Enstitüsü Derg 2023;6(2):1067–78.
47. A S RA, Gopalan S. Comparative Analysis of Eight Direction Sobel Edge Detection Algorithm for Brain Tumor MRI Images. Procedia Comput Sci 2022;201:487–94. https://doi.org/10.1016/j.procs.2022.03.063.
48. Padlia M, Sharma J. Fractional Sobel Filter Based Brain Tumor Detection and Segmentation Using Statistical Features and SVM, 2019, p. 161–75. https://doi.org/10.1007/978-981-13-0776-8_15.
49. Bilal Macit H, Koyun A. An Active Image Forgery Detection Approach Based on Edge Detection. Comput Mater Contin 2023;75:1603–19. https://doi.org/10.32604/cmc.2023.036216.
50. Gurkan C, Kozalioglu S, Palandoken M. Real Time Mask Detection, Social Distance and Crowd Analysis using Convolutional Neural Networks and YOLO Architecture Designs. Acad Perspect Procedia 2021;4:195–204. https://doi.org/10.33793/acperpro.04.01.29.