Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances

Tuğrul Hakan Gençtürk; Fidan Kaya Gülağız; İsmail Kaya

doi:10.21541/apjess.1771865

Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances

Abstract

The brain is one of the body's most critical structures, governing or controlling all organs. Therefore, damage to the brain can have life-threatening effects. Midline shift (MLS), on the other hand, is a serious condition that results from the migration of brain compartments from one to the other for various reasons, leading to various neurological symptoms such as increased cranial pressure, impaired consciousness, paralysis, and even brain death. Therefore, early diagnosis is crucial in cases of MLS. The first step in diagnosing MLS is identifying the ventricles, one of the structures that define the midline in the brain. The ventricles can be visualized in different ways depending on the case, increasing the risk of physicians making errors in the initial diagnosis. The aim of this study is to create an artificial intelligence (AI)-powered ventricle detection architecture that will assist physicians in minimizing this error. For this purpose, Faster Region Based Convolutional Networks (Faster R-CNN), You Only Look Once X (YOLOX), Cascade Region Based Convolutional Neural Network (Cascade R-CNN), Efficient Detection (EfficientDet), enhanced YOLO versions (YOLOv8n, YOLO11n) and current transformer-based deep learning (DL) architecture Shifted Window Transformer (Swin Transformer) were tested. The study was conducted on the mainly CQ500 dataset and results were validated with a subset of tests obtained from the RSNA brain hemorrhage dataset. Both datasets are open and marked with a bounding box technique. Comparisons of current DL models reveal which models are more advantageous in which situations. Furthermore, the inclusion of an open dataset provides a basis for future research.

Keywords

References

M. S. Greenberg, Handbook of Neurosurgery, 7th ed. Thieme, pp 84-122, 2010.
M. S. Greenberg, Handbook of Neurosurgery, 7th ed. Thieme, pp 850-930, 2010.
J. Motuel, I. Biette, C. Cognard, O. Fourcade, and T. Geeraerts, "Brain midline shift assessment using sonography in neurocritical care patients," Critical Care, vol. 15, suppl. 1, P343, 2011, doi: 10.1186/cc9763.
F. Xiao, I.-J. Chiang, J.-M. Wong, Y.-H. Tsai, K.-C. Huang, and C.-C. Liao, "Automatic measurement of midline shift on deformed brains using Multiresolution Binary Level Set method and Hough Transform," Computer Biology and Medicine, vol. 41, no. 9, pp. 756–762, 2011, doi: 10.1016/j.compbiomed.2011.06.011.
S. Cha and A. E. George, "How much asymmetry should be considered normal variation or within normal range in asymmetrical frontal horns of the lateral ventricles noted during CT brain scans without evidence of midline shift or any other significant lesion?," AJR American Journal of Roentgenology, vol. 178, no. 1, 240, 2002, doi: 10.2214/ajr.178.1.1780240a.
W.-S. Yang, Q. Li, R. Li, Q.-J. Liu, X.-C. Wang, L.-B. Zhao, and P. Xie, "Defining the optimal midline shift threshold to predict poor outcome in patients with supratentorial spontaneous intracerebral hemorrhage," Neurocritical Care, vol. 28, pp. 314–321, 2018, doi: 10.1007/s12028-017-0483-7.
Y. Zhu, X. Jin, L. Xu, P. Han, S. Lin, and Z. Lu, "Establishment and validation of prognosis model for patients with cerebral contusion," BMC Neurology, vol. 21, 463, 2021, doi: 10.1186/s12883-021-02482-4.
R. A. G. Oliveira, M. de Oliveira Lima, W. S. Paiva, L. M. de Sá Malbouisson, M. J. Teixeira, and E. Bor-Seng-Shu, "Comparison between brain computed tomography scan and transcranial sonography to evaluate third ventricle width, peri-mesencephalic cistern, and sylvian fissure in traumatic brain-injured patients," Frontiers in Neurology, vol. 8, 44, 2017, doi: 10.3389/fneur.2017.00044.

R. Liu, S. Li, B. Su, C.-L. Tan, T.-Y. Leong, B.-C. Pang, C.-C.T. Lim, and C.-K. Lee, "Automatic detection and quantification of brain midline shift using anatomical marker model," Computerized Medical Imaging and Graphics, vol. 38, no. 1, pp. 1–14, 2014, doi: 10.1016/j.compmedimag.2013.11.001.
C.-C. Liao et al., "Automatic recognition of midline shift on brain CT images," Computers in Biology and Medicine, vol. 40, no. 3, pp. 331–339, 2010, doi: 10.1016/j.compbiomed.2010.01.004.
W. Chen, A. Belle, C. Cockrell, K. R. Ward, and K. Najarian, "Automated midline shift and intracranial pressure estimation based on brain CT images," Journal of Visualized Experiments, no. 74, e3871, 2013, doi: 10.3791/3871.
R. Liu, S. Li, C.-L. Tan, B.-C. Pang, C.-T. Lim, C.-K. Lee, and Z. Zhang, "From hemorrhage to midline shift: A new method of tracing the deformed midline in traumatic brain injury CT images," in Proceedings of the 2009 16th IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, pp. 2637–2640, 2009, doi: 10.1109/ICIP.2009.5414092.
E. L. Yuh, A. D. Gean, G. T. Manley, A. L. Callen, and M. Wintermark, "Computer-aided assessment of head computed tomography (CT) studies in patients with suspected traumatic brain injury," Journal of Neurotrauma, vol. 25, no. 10, pp. 1163–1172, 2008, doi: 10.1089/neu.2008.0590.
D. Agrawal, J. Sharwari, and P. Latha, "Automated midline shift detection and quantification in traumatic brain injury: A comprehensive review," Indian Journal of Neurotrauma, vol. 21, no. 1, pp. 6–12, 2024, doi: 10.1055/s-0043-1777676.
S. Chilamkurthy, R. Ghosh, S. Tanamala et al., "Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study," The Lancet, vol. 392, no. 10162, pp. 2388–2396, 2018, doi: 10.1016/S0140-6736(18)31645-3.
N. P. Nguyen, Y. Yoo, A. Chekkoury et al., "Brain midline shift detection and quantification by a cascaded deep network pipeline on non-contrast computed tomography scans," in Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada, pp. 487–495, 2021, doi: 10.1109/ICCVW54120.2021.00059.
H.-C. Wang, S.-H. Ho, F. Xiao, and J.-H. Chou, "A simple, fast and fully automated approach for midline shift measurement on brain computed tomography," arXiv preprint arXiv:1703.00797, 2017. [Online]. Available: https://arxiv.org/abs/1703.00797
S. Jain, T. V. Vyvere, V. Terzopoulos, D. M. Sima, E. Roura, A. Maas, G. Wilms, and J. Verheyden, "Automatic quantification of computed tomography features in acute traumatic brain injury," Journal of Neurotrauma, vol. 36, no. 11, pp. 1794–1803, 2019, doi: 10.1089/neu.2018.6183.
J.-L. Yan, Y.-L. Chen, M.-Y. Chen, B.-A. Chen, J.-X. Chang, C.-C. Kao, M.-C. Hsieh, Y.-T. Peng, K.-C. Huang, and P.-Y. Chen, "A robust, fully automatic detection method and calculation technique of midline shift in intracranial hemorrhage and its clinical application," Diagnostics, vol. 12, no. 3, 693, 2022, doi: 10.3390/diagnostics12030693.
M. Hooshmand, S. M. R. Soroushmehr, C. Williamson, J. Gryak, and K. Najarian, "Automatic midline shift detection in traumatic brain injury," in Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, pp. 131–134, 2018, doi: 10.1109/EMBC.2018.8512243.
H. Wei, X. Tang, M. Zhang et al., "The delineation of largely deformed brain midline using regression-based line detection network," Medical Physics, vol. 47, no. 11, pp. 5531–5542, 2020, doi: 10.1002/mp.14302.
D. Wu, H. Li, J. Chang, C. Qin, Y. Chen, Y. Liu, Q. Zhang, B. Huang, M. Feng, R. Wang, and J. Yao, “Automatic brain midline surface delineation on 3D CT images with intracranial hemorrhage,” IEEE Trans. Med. Imaging, vol. 41, no. 9, pp. 2217–2227, 2022, doi: 10.1109/TMI.2022.3160184.
M.K. Nag, A. Gupta, A.S. Hariharasudhan, A.K. Sadhu, A. Das, and N. Ghosh, “Quantitative analysis of brain herniation from non-contrast CT images using deep learning,” J. Neurosci. Methods, vol. 349, no. 109033, 2021, doi: 10.1016/j.jneumeth.2020.109033.
X. Xia, X. Zhang, Z. Huang, Q. Ren, H. Li, Y. Li, K. Liang, H. Wang, K. Han, and X. Meng, “Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks,” Am. J. Trans. Res,. vol. 13, no. 10, pp. 11513–11521, 2021, PMID: 34786077, PMCID: PMC8581948.
D. Agrawal, S. Joshi, V. Bahel, L. Poonamallee, and A. Agrawal, “Three-dimensional convolutional neural network-based automated detection of midline shift in traumatic brain injury cases from head computed tomography scans,” J. Neurosci. Rural Pract., vol. 15, no. 2, pp. 293–299, 2024, doi: 10.25259/JNRP_490_2023.
A.R. Wu, S.Y. Hsieh, H.H. Chou, C.S. Lai, J.Y. Hung, B. Wang, and Y.S. Tsai, “Deep learning-based prediction of mortality using brain midline shift and clinical information,” Heliyon, vol. 11, no. 2, 2025, doi: 10.1016/j.heliyon.2024.e41271.
M. K. Nag, A. K. Sadhu, C. Kumar, and S. Choudhary, "Efficient automated quantification of midline shift in intracerebral hemorrhage using a binarized deep learning model on non-contrast head CT," Neuroradiology, PMID: 41204958, 2025, doi: 10.1007/s00234-025-03835-3.
A.E. Flanders, L.M. Prevedello, G. Shih, S.S. Halabi, J. Kalpathy-Cramer, … and J. Nath, “Construction of a machine learning dataset through collaboration: the RSNA 2019 brain CT hemorrhage challenge,” Radiol.: Artif. Intell. vol. 2, no. 3, 190211, 2020, doi: 10.1148/ryai.2020190211.
S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.
Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, "YOLOX: Exceeding YOLO series in 2021," arXiv preprint arXiv:2107.08430, 2021. [Online]. Available: https://arxiv.org/abs/2107.08430
Z. Cai and N. Vasconcelos, "Cascade R-CNN: Delving into high quality object detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp. 6154–6162, 2018, doi: 10.1109/CVPR.2018.00644.
M. Tan, R. Pang, and Q. V. Le, "EfficientDet: Scalable and efficient object detection," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 10778-10787, 2020, doi: 10.1109/CVPR42600.2020.01079.
G. Jocher, J. Qiu, and A. Chaurasia, "Ultralytics YOLO (Version 8.0.0)," Ultralytics, 2023. Accessed: 06.11.2025. [Computer software]. Available: https://github.com/ultralytics/ultralytics
Z. Liu et al., "Swin transformer: Hierarchical vision transformer using shifted windows," in Proc. IEEE/CVF Int. Conf. Comput. Vis., pp. 9992–10002, 2021, doi: 10.1109/ICCV48922.2021.00986.
T. H. Gençtürk, F. Kaya Gülağız, and İ. Kaya, "Derin Öğrenme yöntemleri kullanılarak BT taramalarında beyin kanaması teşhisinin karşılaştırmalı bir analizi," Journal of Intelligent Systems: Theory and Applications, vol. 6, no. 1, pp. 75–84, 2023, doi: 10.38016/jista.1215025.
T. H. Gençtürk, İ. Kaya, and F. Kaya Gülağız, "A comparative study on subdural brain hemorrhage segmentation," in Proceedings of the International Conference on Computing, Intelligence and Data Analytics, Kocaeli, Turkey, pp. 304–318, Cham: Springer International Publishing, 2022, doi: 10.1007/978-3-031-27099-4_24.
L. Han, C. Ma, Y. Liu, J. Jia, and J. Sun, "SC-YOLOv8: A security check model for the inspection of prohibited items in X-ray images," Electronics, vol. 12, no. 20, 4208, 2023, doi: 10.3390/electronics12204208.
C. Shen, C. Ma, and W. Gao, "Multiple attention mechanism enhanced YOLOX for remote sensing object detection," Sensors, vol. 23, no. 3, 1261, 2023, doi: 10.3390/s23031261.
J. Bai, W. Zhu, Z. Nie, X. Yang, Q. Xu, and D. Li, “HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets,” Computers, vol. 14, no. 5, 195, 2025, doi: 10.3390/computers14050195.
T. H. Gençtürk, F. Kaya Gülağız, and İ. Kaya, "Detection and segmentation of subdural hemorrhage on head CT images," IEEE Access, vol. 12, pp. 82235–82246, 2024, doi: 10.1109/ACCESS.2024.3411932.

Details

Primary Language

English

Subjects

Deep Learning, Machine Vision

Journal Section

Research Article

Authors

Tuğrul Hakan Gençtürk
0000-0002-2736-271X
Türkiye

Fidan Kaya Gülağız ^*
0000-0003-3519-9278
Türkiye

İsmail Kaya
0000-0002-4128-5845
Türkiye

Publication Date

January 31, 2026

Submission Date

August 25, 2025

Acceptance Date

December 24, 2025

Published in Issue

Year 2026 Volume: 14 Number: 1

DOI

https://doi.org/10.21541/apjess.1771865

IZ

https://izlik.org/JA66ER56XX

Cite

RIS / Bibtex

APA

Gençtürk, T. H., Kaya Gülağız, F., & Kaya, İ. (2026). Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances. Academic Platform Journal of Engineering and Smart Systems, 14(1), 66-75. https://doi.org/10.21541/apjess.1771865

AMA

1.Gençtürk TH, Kaya Gülağız F, Kaya İ. Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances. APJESS. 2026;14(1):66-75. doi:10.21541/apjess.1771865

Chicago

Gençtürk, Tuğrul Hakan, Fidan Kaya Gülağız, and İsmail Kaya. 2026. “Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances”. Academic Platform Journal of Engineering and Smart Systems 14 (1): 66-75. https://doi.org/10.21541/apjess.1771865.

EndNote

Gençtürk TH, Kaya Gülağız F, Kaya İ (January 1, 2026) Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances. Academic Platform Journal of Engineering and Smart Systems 14 1 66–75.

IEEE

[1]T. H. Gençtürk, F. Kaya Gülağız, and İ. Kaya, “Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances”, APJESS, vol. 14, no. 1, pp. 66–75, Jan. 2026, doi: 10.21541/apjess.1771865.

ISNAD

Gençtürk, Tuğrul Hakan - Kaya Gülağız, Fidan - Kaya, İsmail. “Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances”. Academic Platform Journal of Engineering and Smart Systems 14/1 (January 1, 2026): 66-75. https://doi.org/10.21541/apjess.1771865.

JAMA

1.Gençtürk TH, Kaya Gülağız F, Kaya İ. Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances. APJESS. 2026;14:66–75.

MLA

Gençtürk, Tuğrul Hakan, et al. “Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances”. Academic Platform Journal of Engineering and Smart Systems, vol. 14, no. 1, Jan. 2026, pp. 66-75, doi:10.21541/apjess.1771865.

Vancouver

1.Tuğrul Hakan Gençtürk, Fidan Kaya Gülağız, İsmail Kaya. Ventricle Detection Case Study: Comparison of Current Deep Learning Architecture Performances. APJESS. 2026 Jan. 1;14(1):66-75. doi:10.21541/apjess.1771865