Brain Glioma Segmentation Model based on Multi-scale Information Fusion

Hongwei Zhang; Junshan Chen

doi:10.54691/t1z2rk98

Authors

Hongwei Zhang
Junshan Chen

DOI:

https://doi.org/10.54691/t1z2rk98

Keywords:

Medical Image Segmentation; Adult Diffuse Glioma; MRI; CNN.

Abstract

Predicting histological grading and genetic biomarkers of gliomas using medical imaging and deep learning is a challenging task that is important for personalised treatment and survival prediction. Previous studies require physicians to manually outline the lesion area, which consumes a lot of human resources. Therefore, in this paper, we propose a brain glioma segmentation model based on multi-scale information fusion. Our model is based on the U-Net architecture, which incorporates the use of a multi-scale information fusion module. Compared to the original network model, our approach shows a higher lesion focus and shows strong potential for practical applications.

Downloads

Download data is not yet available.

References

[1] Weller M, Wick W, Aldape K, et al. Glioma[J]. Nature reviews Disease primers, 2015, 1(1): 1-18.

[2] Sahm F, Brandner S, Bertero L, et al. Molecular diagnostic tools for the World Health Organization (WHO) 2021 classification of gliomas, glioneuronal and neuronal tumors; an EANO guideline[J]. Neuro-oncology, 2023, 25(10): 1731-1749.

[3] Zhang S, Yin L, Ma L, et al. Artificial Intelligence Applications in Glioma With 1p/19q Co‐Deletion: A Systematic Review[J]. Journal of Magnetic Resonance Imaging, 2023, 58(5): 1338-1352.

[4] Nicholson A G, Tsao M S, Beasley M B, et al. The 2021 WHO classification of lung tumors: impact of advances since 2015[J]. Journal of Thoracic Oncology, 2022, 17(3): 362-387.

[5] Lu V M, O’Connor K P, Shah A H, et al. The prognostic significance of CDKN2A homozygous deletion in IDH-mutant lower-grade glioma and glioblastoma: a systematic review of the contemporary literature[J]. Journal of neuro-oncology, 2020, 148: 221-229.

[6] Di Bonaventura R, Montano N, Giordano M, et al. Reassessing the role of brain tumor biopsy in the era of advanced surgical, molecular, and imaging techniques—a single-center experience with long-term follow-up[J]. Journal of Personalized Medicine, 2021, 11(9): 909.

[7] Gisina A, Kholodenko I, Kim Y, et al. Glioma stem cells: novel data obtained by single-cell sequencing[J]. International journal of molecular sciences, 2022, 23(22): 14224.

[8] Yogananda C G B, Shah B R, Yu F F, et al. A novel fully automated MRI-based deep-learning method for classification of 1p/19q co-deletion status in brain gliomas[J]. Neuro-oncology advances, 2020, 2(Supplement_4): iv42-iv48.

[9] Wang Y, Wang Y, Guo C, et al. SGPNet: A Three‐Dimensional Multitask Residual Framework for Segmentation and IDH Genotype Prediction of Gliomas[J]. Computational Intelligence and Neuroscience, 2021, 2021(1): 5520281.

[10] Cheng J, Liu J, Kuang H, et al. A fully automated multimodal MRI-based multi-task learning for glioma segmentation and IDH genotyping[J]. IEEE Transactions on Medical Imaging, 2022, 41(6): 1520-1532.

[11] Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository[J]. Journal of digital imaging, 2013, 26: 1045-1057.

[12] Ceccarelli M, Barthel F P, Malta T M, et al. Molecular profiling reveals biologically discrete subsets and pathways of progression in diffuse glioma[J]. Cell, 2016, 164(3): 550-563.

[13] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, 2015: 234-241.