Author(s)

Zhao Lu

Affiliation(s)

Fifth Clinical Medical College,Capital Medical University, Beijing 100070, China.

Corresponding Author

Zhao Lu

ABSTRACT

This study introduces a multi-path Convolutional Neural Network (CNN) for MRI-based brain tumor segmentation and classification, marking a significant stride in medical imaging. The model adeptly segments meningioma and pituitary tumors, as evidenced by robust performance metrics. Challenges persist in glioma segmentation, with a need for enhanced precision. The model's ability to discern glioma regions, despite these obstacles, is promising. The research underscores the necessity for meticulous dataset curation and anatomical knowledge integration to refine specificity and minimize false positives. The findings suggest potential clinical applications in aiding preliminary diagnoses and call for further model refinement. Advanced techniques like 3D convolutional networks and positional encoding are discussed as future enhancements. Overall, the paper contributes to medical imaging advancements, emphasizing the role of innovative deep learning approaches in improving clinical decision-making.

KEYWORDS

Deep Learning; Convolutional Neural Networks (CNN); Brain Tumor Segmentation; MRI Data Analysis

CITE THIS PAPER

Zhao Lu. A novel deep learning approach for brain tumor segmentation and classification using MRI data. Bioinformatics and Computational Medicine. 2025, 2(1): 1-6. DOI: https://doi.org/10.61784/bcm3002.

REFERENCES

[1] Bhowmik P, Udgata G, Trivedi S. Risk assessment in construction industry using a fuzzy logic. Recent Developments in Sustainable Infrastructure (ICRDSI-2020)—Structure and Construction Management: Conference Proceedings from ICRDSI-2020. Singapore: Springer Nature Singapore, 2022: 517–526.

[2] Biratu ES, Schwenker F, Ayano YM, et al. A survey of brain tumor segmentation and classification algorithms. Journal of Imaging, 2021, 7(9): 179.

[3] Biswas TK, Zaman K. A fuzzy-based risk assessment methodology for construction projects under epistemic uncertainty. International Journal of Fuzzy Systems, 2019, 21(4): 1221–1240.

[4] Devunooru S, Alsadoon A, Chandana PWC, et al. Deep learning neural networks for medical image segmentation of brain tumours for diagnosis: a recent review and taxonomy. Journal of Ambient Intelligence and Humanized Computing, 2021, 12: 455–483.

[5] Di Ieva A, Russo C, Liu S, 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: 1253–1262.

[6] Díaz-Pernas FJ, Martínez-Zarzuela M, Antón-Rodríguez M, et al. A deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network. Healthcare, 2021, 9(2): 153.

[7] Gunasekara SR, Kaldera HNTK, Dissanayake MB. A systematic approach for MRI brain tumor localization and segmentation using deep learning and active contouring. Journal of Healthcare Engineering, 2021, 2021: 1–13.

[8] Gupta S, Gupta M. Deep learning for brain tumor segmentation using magnetic resonance images. In: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE, 2021: 1–6.

[9] Isensee F, Jager PF, Full PM, et al. nnU-Net for brain tumor segmentation. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, Revised Selected Papers, Part II. Springer International Publishing, 2021: 118–132.