A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images

A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images Muntakim Mahmud Khan Department of Biomedical Physics and Technology, University of Dhaka, Dhaka 1000, Bangladesh http://orcid.org/0009-0008-8207-0227 Muhammad E. H. Chowdhury Department of Electrical Engineering, Qatar University, Doha 2713, Qatar http://orcid.org/0000-0003-0744-8206 A. S. M. Shamsul Arefin Department of Biomedical Physics and Technology, University of Dhaka, Dhaka 1000, Bangladesh Kanchon Kanti Podder Department of Biomedical Physics and Technology, University of Dhaka, Dhaka 1000, Bangladesh Md. Sakib Abrar Hossain Department of Biomedical Physics and Technology, University of Dhaka, Dhaka 1000, Bangladesh Abdulrahman Alqahtani Department of Medical Equipment Technology, College of Applied, Medical Science, Majmaah University, Majmaah City 11952, Saudi Arabia Department of Biomedical Technology, College of Applied Medical Sciences in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia M. Murugappan Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha 13133, Kuwait Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Sciences, Technology, and Advanced Studies, Chennai 600117, India Center of Excellence for Unmanned Aerial Systems (CoEUAS), Universiti Malaysia Perlis, Perlis 02600, Malaysia http://orcid.org/0000-0002-5839-4589 Amith Khandakar Department of Electrical Engineering, Qatar University, Doha 2713, Qatar http://orcid.org/0000-0001-7068-9112 Adam Mushtak Clinical Imaging Department, Hamad Medical Corporation, Doha 3050, Qatar Md. Nahiduzzaman Department of Electrical Engineering, Qatar University, Doha 2713, Qatar Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth.
07 31 2023 2537 diagnostics13152537 Qatar University student grant http://dx.doi.org/10.13039/ QUST-1-CENG-2023-796 Prince Sattam Bin Abdulaziz University http://dx.doi.org/10.13039/100009392 PSAU/2023/R/1444 https://creativecommons.org/licenses/by/4.0/ 10.3390/diagnostics13152537 https://www.mdpi.com/2075-4418/13/15/2537 https://www.mdpi.com/2075-4418/13/15/2537/pdf 10.1109/CAIPT.2017.8320684 Pak, M., and Kim, S. (2017, January 8–10). A review of deep learning in image recognition. Proceedings of the 2017 IEEE 4th International Conference on Computer Applications and Information Processing Technology (CAIPT), Kuta Bali, Indonesia. Li Deep learning for hemorrhagic lesion detection and segmentation on brain CT images IEEE J. Biomed. Health Inform. 2020 10.1109/JBHI.2020.3028243 25 1646 Tahir Deep learning for reliable classification of COVID-19, MERS, and SARS from chest X-ray images Cogn. Comput. 2022 10.1007/s12559-021-09955-1 14 1752 10.1109/ICIP46576.2022.9897412 Degerli, A., Kiranyaz, S., Chowdhury, M.E., and Gabbouj, M. (2022, January 16–19). Osegnet: Operational segmentation network for Covid-19 detection using chest X-ray images. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France. Gul Deep learning techniques for liver and liver tumor segmentation: A review Comput. Biol. Med. 2022 10.1016/j.compbiomed.2022.105620 147 105620 10.3390/diagnostics11050893 Qiblawey, Y., Tahir, A., Chowdhury, M.E., Khandakar, A., Kiranyaz, S., Rahman, T., Ibtehaz, N., Mahmud, S., Maadeed, S.A., and Musharavati, F. (2021). Detection and severity classification of COVID-19 in CT images using deep learning. Diagnostics, 11. Parizel Intracranial hemorrhage: Principles of CT and MRI interpretation Eur. Radiol. 2001 10.1007/s003300000800 11 1770 Zhu Application of Deep Learning to Ischemic and Hemorrhagic Stroke Computed Tomography and Magnetic Resonance Imaging Seminars in Ultrasound, CT and MRI 2022 10.1053/j.sult.2022.02.004 Volume 43 147 10.1109/ICSESS47205.2019.9040733 Qiu, Y., Chang, C.S., Yan, J.L., Ko, L., and Chang, T.S. (2019, January 18–20). Semantic segmentation of intracranial hemorrhages in head CT scans. Proceedings of the 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS), Beijing, China. Goncharov CT-Based COVID-19 triage: Deep multitask learning improves joint identification and severity quantification Med. Image Anal. 2021 10.1016/j.media.2021.102054 71 102054 10.1007/978-3-030-32248-9_94 Kwon, D., Ahn, J., Kim, J., Choi, I., Jeong, S., Lee, Y.-S., Park, J., and Lee, M. (2019, January 13–17). Siamese U-Net with healthy template for accurate segmentation of intracranial hemorrhage. Proceedings of the Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China. Anupama Synergic deep learning model–based automated detection and classification of brain intracranial hemorrhage images in wearable networks Pers. Ubiquitous Comput. 2022 10.1007/s00779-020-01492-2 26 1 Vamsi Early Detection of Hemorrhagic Stroke Using a Lightweight Deep Learning Neural Network Model Trait. Du Signal 2021 10.18280/ts.380616 38 1727 10.3390/app10093297 Wang, J.L., Farooq, H., Zhuang, H., and Ibrahim, A.K. (2020). Segmentation of intracranial hemorrhage using semi-supervised multi-task attention-based U-net. Appl. Sci., 10. Gautam, A., and Raman, B. (2019). Machine Intelligence and Signal Analysis, Springer. Balwant A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods, Datasets, Libraries, and Future Directions IRBM 2022 10.1016/j.irbm.2022.05.002 43 521 10.3390/diagnostics11020169 Rehman, M.U., Cho, S., Kim, J., and Chong, K.T. (2021). Brainseg-net: Brain tumor mr image segmentation via enhanced encoder–decoder network. Diagnostics, 11. Rehman RAAGR2-Net: A brain tumor segmentation network using parallel processing of multiple spatial frames Comput. Biol. Med. 2023 10.1016/j.compbiomed.2022.106426 152 106426 Wu MR brain segmentation based on DE-ResUnet combining texture features and background knowledge Biomed. Signal Process. Control 2022 10.1016/j.bspc.2022.103541 75 103541 Zhao Automated 3D fetal brain segmentation using an optimized deep learning approach Am. J. Neuroradiol. 2022 10.3174/ajnr.A7419 43 448 10.3390/diagnostics12102405 Salman Khan, M., Ullah, A., Khan, K.N., Riaz, H., Yousafzai, Y.M., Rahman, T., Chowdhury, M.E., and Abul Kashem, S.B. (2022). Deep Learning Assisted Automated Assessment of Thalassaemia from Haemoglobin Electrophoresis Images. Diagnostics, 12. Hssayeni Computed tomography images for intracranial hemorrhage detection and segmentation Intracranial Hemorrhage Segm. Using A Deep. Convolutional Model Data 2020 5 14 Murphy, A., and Baba, Y. (2023, May 17). Windowing (CT). Reference Article, Radiopaedia. org. ed. Available online: https://radiopaedia.org/articles/windowing-ct?lang=us. Davidson Protocol for measurement of liver fat by computed tomography J. Appl. Physiol. 2006 10.1152/japplphysiol.00986.2005 100 864 Najm Automated brain extraction from head CT and CTA images using convex optimization with shape propagation Comput. Methods Programs Biomed. 2019 10.1016/j.cmpb.2019.04.030 176 1 Srinivasan An efficient implementation of artificial neural networks with K-fold cross-validation for process optimization J. Internet Technol. 2019 20 1213 Chowdhury Classification of viral, bacterial, and COVID-19 pneumonia using deep learning framework from chest X-ray images Comput. Sci. Inf. Technol. 2022 12 1 10.3390/s22114249 Khandakar, A., Chowdhury, M.E.H., Reaz, M.B.I., Ali, S.H.M., Kiranyaz, S., Rahman, T., Chowdhury, M.H., Ayari, M.A., Alfkey, R., and Bakar, A.A.A. (2022). A Novel Machine Learning Approach for Severity Classification of Diabetic Foot Complications Using Thermogram Images. Sensors, 22. Rahman HipXNet: Deep Learning Approaches to Detect Aseptic Loos-Ening of Hip Implants Using X-ray Images IEEE Access 2022 10.1109/ACCESS.2022.3173424 10 53359 Weng Nas-unet: Neural architecture search for medical image segmentation IEEE Access 2019 10.1109/ACCESS.2019.2908991 7 44247 10.3390/healthcare9010054 Tran, S.-T., Cheng, C.-H., Nguyen, T.-T., Le, M.-H., and Liu, D.-G. (2021). TMD-Unet: Triple-Unet with multi-scale input features and dense skip connection for medical image segmentation. Healthcare, 9. Peeples Jointly optimized spatial histogram UNET architecture (JOSHUA) for adipose tissue segmentation BME Front. 2022 10.34133/2022/9854084 2022 9854084 Rahman BIO-CXRNET: A robust multimodal stacking machine learning technique for mortality risk prediction of COVID-19 patients using chest X-ray images and clinical data Neural Comput. Appl. 2023 10.1007/s00521-023-08606-w 35 17461 Zhou Unet++: Redesigning skip connections to exploit multiscale features in image segmentation IEEE Trans. Med. Imaging 2019 10.1109/TMI.2019.2959609 39 1856 10.1109/CVPR.2017.106 Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 10.1109/CVPR.2009.5206848 Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F. (2009, January 20–25). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA. Xu Multi-loss regularized deep neural network IEEE Trans. Circuits Syst. Video Technol. 2015 10.1109/TCSVT.2015.2477937 26 2273 Tahir COVID-19 infection localization and severity grading from chest X-ray images Comput. Biol. Med. 2021 10.1016/j.compbiomed.2021.105002 139 105002 Yi-de, M., Qing, L., and Zhi-Bai, Q. (2004, January 20–22). Automated image segmentation using improved PCNN model based on cross-entropy. Proceedings of the 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong, China. 10.1109/CIBCB48159.2020.9277638 Jadon, S. (2020, January 27–29). A survey of loss functions for semantic segmentation. Proceedings of the 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Vina del Mar, Chile. Kumar 3D reconstruction of face from 2D CT scan images Procedia Eng. 2012 10.1016/j.proeng.2012.01.952 30 970 Ram Image processing with ImageJ Biophotonics Int. 2004 11 36 Bernstein Effect of windowing and zero-filled reconstruction of MRI data on spatial resolution and acquisition strategy J. Magn. Reson. Imaging Off. J. Int. Soc. Magn. Reson. Med. 2001 14 270 Shi Review of CT image reconstruction open source toolkits J. X-ray Sci. Technol. 2020 28 619 Makela A review of cardiac image registration methods IEEE Trans. Med. Imaging 2002 10.1109/TMI.2002.804441 21 1011 Bockisch Positron emission tomography/computed tomography–imaging protocols, artifacts, and pitfalls Mol. Imaging Biol. 2004 10.1016/j.mibio.2004.04.006 6 188 Bhadauria Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging Signal Image Video Process. 2014 10.1007/s11760-012-0298-0 8 357