Establishment and evaluation of an automatic multi‑sequence MRI segmentation model of primary central nervous system lymphoma based on the nnU‑Net deep learning network method

Wang,Tao; Tang,Xingru; Du,Jun; Jia,Yongqian; Mou,Weiwei; Lu,Guang

doi:10.3892/ol.2025.15080

Establishment and evaluation of an automatic multi‑sequence MRI segmentation model of primary central nervous system lymphoma based on the nnU‑Net deep learning network method

Authors:
- Tao Wang
- Xingru Tang
- Jun Du
- Yongqian Jia
- Weiwei Mou
- Guang Lu
View Affiliations

Affiliations: Department of Hematology, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, P.R. China, Department of Clinical Medicine, Shanghai Jiao Tong University, Shanghai 200030, P.R. China, Department of Hematology, Shanghai Jiao Tong University School of Medicine Affiliated Renji Hospital, Shanghai 200001, P.R. China, Department of Pediatrics, Shengli Oilfield Central Hospital, Dongying, Shandong 257099, P.R. China, Department of Hematology, Shandong Second Provincial General Hospital, Jinan, Shandong 250022, P.R. China
Published online on: May 9, 2025 https://doi.org/10.3892/ol.2025.15080
Article Number: 334
Copyright: © Wang et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Accurate quantitative assessment using gadolinium‑contrast magnetic resonance imaging (MRI) is crucial in therapy planning, surveillance and prognostic assessment of primary central nervous system lymphoma (PCNSL). The present study aimed to develop a multimodal artificial intelligence deep learning segmentation model to address the challenges associated with traditional 2D measurements and manual volume assessments in MRI. Data from 49 pathologically‑confirmed patients with PCNSL from six Chinese medical centers were analyzed, and regions of interest were manually segmented on contrast‑enhanced T1‑weighted and T2‑weighted MRI scans for each patient, followed by fully automated voxel‑wise segmentation of tumor components using a 3‑dimenstional convolutional deep neural network. Furthermore, the efficiency of the model was evaluated using practical indicators and its consistency and accuracy was compared with traditional methods. The performance of the models were assessed using the Dice similarity coefficient (DSC). The Mann‑Whitney U test was used to compare continuous clinical variables and the χ² test was used for comparisons between categorical clinical variables. T1WI sequences exhibited the optimal performance (training dice: 0.923, testing dice: 0.830, outer validation dice: 0.801), while T2WI showed a relatively poor performance (training dice of 0.761, a testing dice of 0.647, and an outer validation dice of 0.643. In conclusion, the automatic multi‑sequences MRI segmentation model for PCNSL in the present study displayed high spatial overlap ratio and similar tumor volume with routine manual segmentation, indicating its significant potential.

View Figures

View References

1	Villano JL, Shaikh H, Dolecek TA and McCarthy BJ: Age, gender, and racial differences in incidence and survival in primary CNS lymphoma. Br J Cancer. 105:1414–1418. 2011. View Article : Google Scholar : PubMed/NCBI
2	Chukwueke U, Grommes C and Nayak L: Primary central nervous system lymphomas. Hematol Oncol Clin North Am. 36:147–159. 2022. View Article : Google Scholar : PubMed/NCBI
3	Morales-Martinez A, Nichelli L, Hernandez-Verdin I, Houillier C, Alentorn A and Hoang-Xuan K: Prognostic factors in primary central nervous system lymphoma. Curr Opin Oncol. 34:676–684. 2022. View Article : Google Scholar : PubMed/NCBI
4	Schaff LR and Grommes C: Primary central nervous system lymphoma. Blood. 140:971–979. 2022. View Article : Google Scholar : PubMed/NCBI
5	Lukas RV, Stupp R, Gondi V and Raizer JJ: Primary central nervous system Lymphoma-PART 1: Epidemiology, diagnosis, staging, and prognosis. Oncology (Williston Park). 32:17–22. 2018.PubMed/NCBI
6	Sangeetha SKB, Muthukumaran V, Deeba K, Rajadurai H, Maheshwari V and Dalu GT: Multiconvolutional transfer learning for 3D brain tumor magnetic resonance images. Comput Intell Neurosci. 2022:87224762022. View Article : Google Scholar : PubMed/NCBI
7	Sadad T, Rehman A, Munir A, Saba T, Tariq U, Ayesha N and Abbasi R: Brain tumor detection and multi-classification using advanced deep learning techniques. Microsc Res Tech. 84:1296–1308. 2021. View Article : Google Scholar : PubMed/NCBI
8	Abd-Ellah MK, Awad AI, Khalaf AAM and Hamed HFA: A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned. Magn Reson Imaging. 61:300–318. 2019. View Article : Google Scholar : PubMed/NCBI
9	Lu G, Zhang Y, Wang W, Miao L and Mou W: Machine learning and deep learning CT-based models for predicting the primary central nervous system lymphoma and glioma types: A multicenter retrospective study. Front Neurol. 13:9052272022. View Article : Google Scholar : PubMed/NCBI
10	Xia W, Hu B, Li H, Shi W, Tang Y, Yu Y, Geng C, Wu Q, Yang L, Yu Z, et al: Deep learning for automatic differential diagnosis of primary central nervous system lymphoma and glioblastoma: Multi-parametric magnetic resonance imaging based convolutional neural network model. J Magn Reson Imaging. 54:880–887. 2021. View Article : Google Scholar : PubMed/NCBI
11	Pennig L, Hoyer UCI, Goertz L, Shahzad R, Persigehl T, Thiele F, Perkuhn M, Ruge MI, Kabbasch C, Borggrefe J, et al: Primary central nervous system lymphoma: Clinical evaluation of automated segmentation on multiparametric MRI using deep learning. J Magn Reson Imaging. 53:259–268. 2021. View Article : Google Scholar : PubMed/NCBI
12	Ramadan S, Radice T, Ismail A, Fiori S and Tarella C: Advances in therapeutic strategies for primary CNS B-cell lymphomas. Expert Rev Hematol. 15:295–304. 2022. View Article : Google Scholar : PubMed/NCBI
13	Batchelor TT: Primary central nervous system lymphoma. Hematology Am Soc Hematol Educ Program. 2016:379–385. 2016. View Article : Google Scholar : PubMed/NCBI
14	Bonm AV, Ritterbusch R, Throckmorton P and Graber JJ: Clinical imaging for diagnostic challenges in the management of gliomas: A review. J Neuroimaging. 30:139–145. 2020. View Article : Google Scholar : PubMed/NCBI
15	Huang RY, Bi WL, Griffith B, Kaufmann TJ, la Fougère C, Schmidt NO, Tonn JC, Vogelbaum MA, Wen PY, Aldape K, et al: Imaging and diagnostic advances for intracranial meningiomas. Neuro Oncol. 21:i44–i61. 2019. View Article : Google Scholar : PubMed/NCBI
16	Yadav AS, Kumar S, Karetla GR, Cotrina-Aliaga JC, Arias-Gonzáles JL, Kumar V, Srivastava S, Gupta R, Ibrahim S, Paul R, et al: A feature extraction using probabilistic neural network and BTFSC-Net model with deep learning for brain tumor classification. J Imaging. 9:102022. View Article : Google Scholar : PubMed/NCBI
17	ZainEldin H, Gamel SA, El-Kenawy EM, Alharbi AH, Khafaga DS, Ibrahim A and Talaat FM: Brain tumor detection and classification using deep learning and Sine-cosine fitness grey wolf optimization. Bioengineering (Basel). 10:182022. View Article : Google Scholar : PubMed/NCBI
18	Taher F, Shoaib MR, Emara HM, Abdelwahab KM, Abd El-Samie FE and Haweel MT: Efficient framework for brain tumor detection using different deep learning techniques. Front Public Health. 10:9596672022. View Article : Google Scholar : PubMed/NCBI
19	Hwang K, Park J, Kwon YJ, Cho SJ, Choi BS, Kim J, Kim E, Jang J, Ahn KS, Kim S and Kim CY: Fully automated segmentation models of supratentorial meningiomas assisted by inclusion of normal brain images. J Imaging. 8:3272022. View Article : Google Scholar : PubMed/NCBI
20	Dang K, Vo T, Ngo L and Ha H: A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification. IBRO Neurosci Rep. 13:523–532. 2022. View Article : Google Scholar : PubMed/NCBI
21	Lin YY, Guo WY, Lu CF, Peng SJ, Wu YT and Lee CC: Application of artificial intelligence to stereotactic radiosurgery for intracranial lesions: Detection, segmentation, and outcome prediction. J Neurooncol. 161:441–450. 2023. View Article : Google Scholar : PubMed/NCBI
22	Laukamp KR, Pennig L, Thiele F, Reimer R, Görtz L, Shakirin G, Zopfs D, Timmer M, Perkuhn M and Borggrefe J: Automated meningioma segmentation in multiparametric MRI: comparable effectiveness of a deep learning model and manual segmentation. Clin Neuroradiol. 31:357–366. 2021. View Article : Google Scholar : PubMed/NCBI
23	Chang K, Beers AL, Bai HX, Brown JM, Ly KI, Li X, Senders JT, Kavouridis VK, Boaro A, Su C, et al: Automatic assessment of glioma burden: A deep learning algorithm for fully automated volumetric and bidimensional measurement. Neuro Oncol. 21:1412–1422. 2019. View Article : Google Scholar : PubMed/NCBI
24	Peng J, Luo H, Zhao G, Lin C, Yi X and Chen S: A Review of medical image segmentation algorithms based on deep learning. Computer Engineering Appl. 57:44–57. 2021.(In Chinese).
25	Latif G: DeepTumor: Framework for brain MR image classification, segmentation and tumor detection. Diagnostics (Basel). 12:28882022. View Article : Google Scholar : PubMed/NCBI
26	Kickingereder P, Isensee F, Tursunova I, Petersen J, Neuberger U, Bonekamp D, Brugnara G, Schell M, Kessler T, Foltyn M, et al: Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: A multicentre, retrospective study. Lancet Oncol. 20:728–740. 2019. View Article : Google Scholar : PubMed/NCBI
27	Isensee F, Jaeger PF, Kohl SAA, Petersen J and Maier-Hein KH: nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 18:203–211. 2021. View Article : Google Scholar : PubMed/NCBI
28	Pemberton HG, Wu J, Kommers I, Müller DMJ, Hu Y, Goodkin O, Vos SB, Bisdas S, Robe PA, Ardon H, et al: Multi-class glioma segmentation on real-world data with missing MRI sequences: Comparison of three deep learning algorithms. Sci Rep. 13:189112023. View Article : Google Scholar : PubMed/NCBI
29	Ganesan P, Feng R, Deb B, Tjong FVY, Rogers AJ, Ruipérez-Campillo S, Somani S, Clopton P, Baykaner T, Rodrigo M, et al: Novel domain Knowledge-encoding algorithm enables Label-efficient deep learning for cardiac CT segmentation to guide atrial fibrillation treatment in a pilot dataset. Diagnostics (Basel). 14:15382024. View Article : Google Scholar : PubMed/NCBI
30	Fazekas F, Chawluk JB, Alavi A, Hurtig HI and Zimmerman RA: MR signal abnormalities at 1.5 T in Alzheimer's dementia and normal aging. AJR Am J Roentgenol. 149:351–356. 1987. View Article : Google Scholar : PubMed/NCBI
31	Isensee F, Petersen J, Klein A, Zimmerer D, Jaeger PF, Kohl S, Wasserthal J, Koehler G, Norajitra T, Wirkert S and Maier-Hein KH: nnU-Net: Self-adapting framework for U-Net-based medical image segmentation. ArXiv. abs/1809.10486. 2018.
32	Perkuhn M, Stavrinou P, Thiele F, Shakirin G, Mohan M, Garmpis D, Kabbasch C and Borggrefe J: Clinical evaluation of a multiparametric deep learning model for glioblastoma segmentation using heterogeneous magnetic resonance imaging data from clinical routine. Invest Radiol. 53:647–654. 2018. View Article : Google Scholar : PubMed/NCBI
33	Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, Burren Y, Porz N, Slotboom J, Wiest R, et al: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging. 34:1993–2024. 2015. View Article : Google Scholar : PubMed/NCBI
34	Bousabarah K, Letzen B, Tefera J, Savic L, Schobert I, Schlachter T, Staib LH, Kocher M, Chapiro J and Lin M: Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning. Abdom Radiol (NY). 46:216–225. 2021. View Article : Google Scholar : PubMed/NCBI
35	Naser PV, Maurer MC, Fischer M, Karimian-Jazi K, Ben-Salah C, Bajwa AA, Jakobs M, Jungk C, Jesser J, Bendszus M, et al: Deep learning aided preoperative diagnosis of primary central nervous system lymphoma. iScience. 27:1090232024. View Article : Google Scholar : PubMed/NCBI
36	Cassinelli Petersen GI, Shatalov J, Verma T, Brim WR, Subramanian H, Brackett A, Bahar RC, Merkaj S, Zeevi T, Staib LH, et al: Machine learning in differentiating gliomas from primary CNS lymphomas: A systematic review, reporting quality, and risk of bias assessment. AJNR Am J Neuroradiol. 43:526–533. 2022. View Article : Google Scholar : PubMed/NCBI
37	Ferreri AJM, Calimeri T, Cwynarski K, Dietrich J, Grommes C, Hoang-Xuan K, Hu LS, Illerhaus G, Nayak L, Ponzoni M and Batchelor TT: Primary central nervous system lymphoma. Nat Rev Dis Primers. 9:292023. View Article : Google Scholar : PubMed/NCBI
38	Gill CM, Loewenstern J, Rutland JW, Arib H, Pain M, Umphlett M, Kinoshita Y, McBride RB, Bederson J, Donovan M, et al: Peritumoral edema correlates with mutational burden in meningiomas. Neuroradiology. 63:73–80. 2021. View Article : Google Scholar : PubMed/NCBI
39	Reszec J, Hermanowicz A, Rutkowski R, Turek G, Mariak Z and Chyczewski L: Expression of MMP-9 and VEGF in meningiomas and their correlation with peritumoral brain edema. Biomed Res Int. 2015:6468532015. View Article : Google Scholar : PubMed/NCBI