Deep learning-based segmentation of diffuse large B-cell lymphoma in 18-FDG PET images
DOI:
https://doi.org/10.22399/ijbimes.4Keywords:
DLBCL,, 18-FDG,, PET,, Deep learning,, segmentationAbstract
Diffuse large B-cell lymphoma (DLBCL) is a common and aggressive subtype of non-Hodgkin lymphoma. This study aimed to evaluate the effectiveness of deep learning for automatically segmenting DLBCL lesions in positron emission tomography (PET) images, which is crucial for treatment planning and monitoring. A 2D U-Net convolutional neural network was trained on a dataset of FDG-PET scans from 150 DLBCL patients. The model's performance was evaluated using two key metrics: the Dice similarity coefficient (DSC) and the Jaccard index. The results showed a mean DSC of 0.71 and a mean Jaccard index of 0.62, indicating accurate identification of lymphoma lesions. These findings suggest that deep learning-based automated segmentation holds great potential for accurately detecting and delineating DLBCL lesions, thereby improving the precision and effectiveness of treatment planning and monitoring for affected individuals.
References
[1] M. Martelli, A. J. Ferreri, C. Agostinelli, A. Di Rocco, M. Pfreundschuh, and S. A. Pileri, "Diffuse large B-cell lymphoma," Critical reviews in oncology/hematology, vol. 87, no. 2, pp. 146-171, 2013.
[2] S. Li, K. H. Young, and L. J. Medeiros, "Diffuse large B-cell lymphoma," Pathology, vol. 50, no. 1, pp. 74-87, 2018.
[3] Y. Liu and S. K. Barta, "Diffuse large B‐cell lymphoma: 2019 update on diagnosis, risk stratification, and treatment," American journal of hematology, vol. 94, no. 5, pp. 604-616, 2019.
[4] J. Yuan, Y. Zhang, and X. Wang, "Application of machine learning in the management of lymphoma: Current practice and future prospects," Digital Health, vol. 10, p. 20552076241247963, 2024.
[5] P. Blanc-Durand et al., "Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network," European Journal of Nuclear Medicine and Molecular Imaging, vol. 48, no. 5, pp. 1362-1370, 2021/05/01 2021.
[6] K. Keijzer et al., "Semi-automated 18F-FDG PET segmentation methods for tumor volume determination in Non-Hodgkin lymphoma patients: a literature review, implementation and multi-threshold evaluation," Computational and Structural Biotechnology Journal, vol. 21, pp. 1102-1114, 2023/01/01/ 2023.
[7] F. Yousefirizi et al., "TMTV-Net: fully automated total metabolic tumor volume segmentation in lymphoma PET/CT images — a multi-center generalizability analysis," European Journal of Nuclear Medicine and Molecular Imaging, 2024/02/08 2024.
[8] A. Viswanathan et al., "Deep learning-based classifier of diffuse large B-cell lymphoma cell-of-origin with clinical outcome," Briefings in Functional Genomics, vol. 22, no. 1, pp. 42-48, 2023.
[9] R. A. Kuker et al., "A deep learning-aided automated method for calculating metabolic tumor volume in diffuse large B-cell lymphoma," Cancers, vol. 14, no. 21, p. 5221, 2022.
[10] H. El Achi et al., "Automated diagnosis of lymphoma with digital pathology images using deep learning," Annals of Clinical & Laboratory Science, vol. 49, no. 2, pp. 153-160, 2019.
[11] S. Basu, R. Agarwal, and V. Srivastava, "Deep discriminative learning model with calibrated attention map for the automated diagnosis of diffuse large B-cell lymphoma," Biomedical Signal Processing and Control, vol. 76, p. 103728, 2022.
[12] L. Huang, S. Ruan, P. Decazes, and T. Denœux, "Lymphoma segmentation from 3D PET-CT images using a deep evidential network," International Journal of Approximate Reasoning, vol. 149, pp. 39-60, 2022.
[13] M. Wang et al., "PSR-Nets: Deep neural networks with prior shift regularization for PET/CT based automatic, accurate, and calibrated whole-body lymphoma segmentation," Computers in Biology and Medicine, vol. 151, p. 106215, 2022.
[14] M. Karimdjee et al., "Evaluation of a convolution neural network for baseline total tumor metabolic volume on [18F] FDG PET in diffuse large B cell lymphoma," European Radiology, vol. 33, no. 5, pp. 3386-3395, 2023.
[15] X.-X. Yin, L. Sun, Y. Fu, R. Lu, and Y. Zhang, "U-Net-Based medical image segmentation," Journal of healthcare engineering, vol. 2022, 2022.
[16] C. Jiang et al., "Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images," European Radiology, vol. 32, no. 7, pp. 4801-4812, 2022.
[17] F. Yousefirizi et al., "Semi-supervised learning towards automated segmentation of PET images with limited annotations: application to lymphoma patients," Physical and Engineering Sciences in Medicine, vol. 47, no. 3, pp. 833-849, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Sajad Keshavarz, Elham Saeedzadeh, Elnaz Jenabi, Dariush Sardari, Hossein Arabi
This work is licensed under a Creative Commons Attribution 4.0 International License.
