AI-Assisted MRI for Brain Tumor Segmentation: A Cross-Sectional Diagnostic Accuracy Study
Article Sidebar
Main Article Content
Abstract
Background: Brain tumor segmentation on MRI is essential for diagnosis, treatment planning, radiotherapy guidance, and follow-up assessment, but manual delineation is time-consuming and subject to reader variability. Artificial intelligence may improve segmentation consistency, although local validation is required before clinical use. Objective: To evaluate the diagnostic accuracy and segmentation agreement of AI-assisted MRI for brain tumor delineation compared with expert radiologist consensus assessment. Methods: This prospective cross-sectional diagnostic accuracy study included 124 adult patients undergoing MRI brain for suspected or diagnosed intracranial tumor in Lahore, Pakistan. MRI sequences included routine brain tumor imaging sequences, with contrast-enhanced assessment used where clinically indicated. AI-generated tumor masks were compared with expert radiologist consensus segmentation as the reference standard. Sensitivity, specificity, positive predictive value, negative predictive value, overall accuracy, Dice similarity coefficient, and absolute tumor volume difference were calculated. Results: AI-assisted MRI demonstrated sensitivity of 91.8%, specificity of 88.6%, positive predictive value of 90.4%, negative predictive value of 89.9%, and overall accuracy of 90.2%. The mean Dice similarity coefficient for whole tumor segmentation was 0.84 ± 0.09, with highest agreement in enhancing tumors (0.89 ± 0.06) and lowest agreement in post-treatment lesions (0.73 ± 0.11). The mean absolute AI-expert tumor volume difference was 5.9 ± 4.7 cm³. Conclusion: AI-assisted MRI showed promising segmentation accuracy and may support radiologists by providing an initial tumor outline, particularly in enhancing lesions. Expert review remains necessary in non-enhancing and post-treatment cases, and multicenter validation is required before routine clinical adoption
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
1. Pakistan Brain Tumour Consortium, Enam SA, Shah MM, Bajwa MH, Khalid MU, Bakhshi SK, et al. The Pakistan Brain Tumour Epidemiology Study. J Pak Med Assoc. 2022;72(11 Suppl 4). doi:10.47391/JPMA.11-S4-AKUB01.
2. Danish F, Salam H, Qureshi MA, Nouman M. Comparative clinical and epidemiological study of central nervous system tumours in Pakistan and global database. Interdiscip Neurosurg. 2021;25:101239. doi:10.1016/j.inat.2021.101239.
3. Bajwa MH, Khalid MU, Shah MM, Shamim MS, Laghari AA, Akhunzada NZ, et al. Treatment patterns of glioma in Pakistan: an epidemiological perspective. J Pak Med Assoc. 2022;72(11 Suppl 4). doi:10.47391/JPMA.11-S4-AKUB05.
4. Abdullah UE, Laghari AA, Khalid MU, Rashid HB, Jabbar AA, Mubarak F, et al. Current management of glioma in Pakistan. Glioma. 2019;2(4):139-144. doi:10.4103/glioma.glioma_15_19.
5. Louis DN, Perry A, Wesseling P, Brat DJ, Cree IA, Figarella-Branger D, et al. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary. Neuro Oncol. 2021;23(8):1231-1251. doi:10.1093/neuonc/noab106.
6. Wen PY, Macdonald DR, Reardon DA, Cloughesy TF, Sorensen AG, Galanis E, et al. Updated response assessment criteria for high-grade gliomas: Response Assessment in Neuro-Oncology Working Group. J Clin Oncol. 2010;28(11):1963-1972. doi:10.1200/JCO.2009.26.3541.
7. Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging. 2015;34(10):1993-2024. doi:10.1109/TMI.2014.2377694.
8. Bakas S, Akbari H, Sotiras A, Bilello M, Rozycki M, Kirby JS, et al. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data. 2017;4:170117. doi:10.1038/sdata.2017.117.
9. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF, editors. Medical Image Computing and Computer-Assisted Intervention — MICCAI 2015. Cham: Springer; 2015. p. 234-241. doi:10.1007/978-3-319-24574-4_28.
10. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W, editors. Medical Image Computing and Computer-Assisted Intervention — MICCAI 2016. Cham: Springer; 2016. p. 424-432. doi:10.1007/978-3-319-46723-8_49.
11. Milletari F, Navab N, Ahmadi SA. V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision. Stanford: IEEE; 2016. p. 565-571. doi:10.1109/3DV.2016.79.
12. Kamnitsas K, Ledig C, Newcombe VFJ, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61-78. doi:10.1016/j.media.2016.10.004.
13. Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging. 2016;35(5):1240-1251. doi:10.1109/TMI.2016.2538465.
14. Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, et al. Brain tumor segmentation with deep neural networks. Med Image Anal. 2017;35:18-31. doi:10.1016/j.media.2016.05.004.
15. Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203-211. doi:10.1038/s41592-020-01008-z.
16. Kofler F, Berger C, Waldmannstetter D, Lipkova J, Ezhov I, Tetteh G, et al. BraTS Toolkit: translating BraTS brain tumor segmentation algorithms into clinical and scientific practice. Front Neurosci. 2020;14:125. doi:10.3389/fnins.2020.00125.
17. Wang TW, Shiao YC, Hong JS, Lee WK, Hsu MS, Cheng HM, et al. Artificial Intelligence Detection and Segmentation Models: a systematic review and meta-analysis of brain tumors in magnetic resonance imaging. Mayo Clin Proc Digit Health. 2024;2(1):75-91. doi:10.1016/j.mcpdig.2024.01.002.
18. Di Ieva A, Russo C, Liu S, Jian A, Bai MY, Qian Y, et al. Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario. Neuroradiology. 2021;63(8):1253-1262. doi:10.1007/s00234-021-02649-3.
19. Kickingereder P, Isensee F, Tursunova I, Petersen J, Neuberger U, Bonekamp D, et al. Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study. Lancet Oncol. 2019;20(5):728-740. doi:10.1016/S1470-2045(19)30098-1.
20. Hoebel KV, Patel JB, Beers AL, Chang K, Singh P, Brown JM, et al. Expert-centered evaluation of deep learning algorithms for brain tumor segmentation. Radiol Artif Intell. 2024;6(1). doi:10.1148/ryai.220231.
21. Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, Moher D, et al. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ. 2015;351:h5527. doi:10.1136/bmj.h5527.
22. Mongan J, Moy L, Kahn CE Jr. Checklist for Artificial Intelligence in Medical Imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell. 2020;2(2):e200029. doi:10.1148/ryai.2020200029.