Progress of machine learning based on magnetic resonance imaging for orbital tumor research

Share this content in WeChat

• Review •

WANG Yan WU Xusha HU Wenzhong LI Yan XI Yibin YIN Hong

Cite this article as: WANG Y, WU X S, HU W Z, et al. Progress of machine learning based on magnetic resonance imaging for orbital tumor research[J]. Chin J Magn Reson Imaging, 2024, 15(8): 212-217. DOI:10.12015/issn.1674-8034.2024.08.034.

Abstract

[Abstract] Orbital tumors vary in location and histopathological differences, presenting diagnostic challenges. Although advances in imaging technology have improved this problem, its classification and identification remains a challenge. As a key branch of artificial intelligence, machine learning has achieved certain results in the medical field, especially its combination with imaging and ophthalmology has greatly promoted the precision treatment of orbital tumors, and it has shown great potential and broad application prospects in tumor identification, lesion segmentation and image reconstruction, which is expected to improve the diagnosis level of orbital tumors and reduce the cost of clinical practice. This article reviews the application of MRI-based machine learning technology in orbital tumors, aiming to provide clinicians and radiologists with ideas for the diagnosis, treatment and prognosis of orbital tumors, and to further promote the application and popularization of machine learning in this field.

[Keywords] orbital tumors；magnetic resonance imaging；machine learning；differential diagnosis；efficacy prediction；prognosis

Contributor Information

WANG Yan¹ WU Xusha² HU Wenzhong² LI Yan² XI Yibin² YIN Hong^{1,
2*}

¹ College of Life Science, Northwestern University, Xi'an 710068, China

² Department of Medical Imaging, Xi'an People's Hospital, Xi'an 710100, China

Corresponding author: YIN H, E-mail: yinnhong@163.com

Conflicts of interest None.

Publication Information

Received 2024-05-15

Accepted 2024-07-14

DOI: 10.12015/issn.1674-8034.2024.08.034

Text

References

[1]

MILMAN T, GROSSNIKLAUS H E, GOLDMAN-LEVY G, et al. The 5th edition of the World Health Organization classification of tumours of the eye and orbit[J]. Ocul Oncol Pathol, 2023, 9(3/4): 71-95. DOI: 10.1159/000530730.

[2]

MOMBAERTS I, RAMBERG I, COUPLAND S E, et al. Diagnosis of orbital mass lesions: clinical, radiological, and pathological recommendations[J]. Surv Ophthalmol, 2019, 64(6): 741-756. DOI: 10.1016/j.survophthal.2019.06.006.

[3]

HE Z Y, MAO Y T, LU S H, et al. Machine learning-based radiomics for histological classification of parotid tumors using morphological MRI: a comparative study[J]. Eur Radiol, 2022, 32(12): 8099-8110. DOI: 10.1007/s00330-022-08943-9.

[4]

SAEEDI S, REZAYI S, KESHAVARZ H, et al. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques[J/OL]. BMC Med Inform Decis Mak, 2023, 23(1): 16 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36691030/. DOI: 10.1186/s12911-023-02114-6.

[5]

HAN Q H, DU L Z, MO Y, et al. Machine learning based non-enhanced CT radiomics for the identification of orbital cavernous venous malformations: an innovative tool[J]. J Craniofac Surg, 2022, 33(3): 814-820. DOI: 10.1097/SCS.0000000000008446.

[6]

LIN L Y, ZHOU P, SHI M, et al. A deep learning model for screening computed tomography imaging for thyroid eye disease and compressive optic neuropathy[J/OL]. Ophthalmol Sci, 2024, 4(1): 100412 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/38046559/. DOI: 10.1016/j.xops.2023.100412.

[7]

BAO X L, SUN Y J, ZHAN X, et al. Orbital and eyelid diseases: the next breakthrough in artificial intelligence?[J/OL]. Front Cell Dev Biol, 2022, 10: 1069248 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36467418/. DOI: 10.3389/fcell.2022.1069248.

[8]

WIEDERHOLD G, MCCARTHY J. Arthur Samuel: pioneer in machine learning[J]. IBM J Res Dev, 1992, 36(3): 329-331. DOI: 10.1147/rd.363.0329.

[9]

GUPTA S, PAUDEL A, THAPA M, et al. Optimal sampling-based neural networks for uncertainty quantification and stochastic optimization[J/OL]. Aerosp Sci Technol, 2023, 133: 108109 [2024-05-14]. https://www.sciencedirect.com/science/article/abs/pii/S1270963823000068?via%3Dihub. DOI: 10.1016/j.ast.2023.108109.

[10]

CHANDRABHATLA A S, HORGAN T M, COTTON C C, et al. Clinical applications of machine learning in the management of intraocular cancers: a narrative review[J/OL]. Invest Ophthalmol Vis Sci, 2023, 64(10): 29 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/37477930/. DOI: 10.1167/iovs.64.10.29.

[11]

RAO Y J, WU D, HAN M N, et al. AT-GAN: a generative adversarial network with attention and transition for infrared and visible image fusion[J/OL]. Inf Fusion, 2023, 92: 336-349 [2024-05-14]. https://www.sciencedirect.com/science/article/abs/pii/S156625352200255X?via%3Dihub. DOI: 10.1016/j.inffus.2022.12.007.

[12]

LI Z W, LIU F, YANG W J, et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Trans Neural Netw Learn Syst, 2022, 33(12): 6999-7019. DOI: 10.1109/TNNLS.2021.3084827.

[13]

LIU X, CHEN H Y, YAO C, et al. BTMF-GAN: a multi-modal MRI fusion generative adversarial network for brain tumors[J/OL]. Comput Biol Med, 2023, 157: 106769 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36947904/. DOI: 10.1016/j.compbiomed.2023.106769.

[14]

HINDARTO D, SANTOSO H. Performance comparison of supervised learning using non-neural network and neural network[J/OL]. J Nas Pendidik Teknik Inform, 2022, 11(1): 49 [2024-05-14]. https://doi.org/10.23887/janapati.v11i1.40768. DOI: 10.23887/janapati.v11i1.40768.

[15]

BANI HANI S H, AHMAD M M. Machine-learning algorithms for ischemic heart disease prediction: a systematic review[J/OL]. Curr Cardiol Rev, 2023, 19(1): e090622205797 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/35692135/. DOI: 10.2174/1573403X18666220609123053.

[16]

DOĞDU C, KESSLER T, SCHNEIDER D, et al. A comparison of machine learning algorithms and feature sets for automatic vocal emotion recognition in speech[J/OL]. Sensors, 2022, 22(19): 7561 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36236658/. DOI: 10.3390/s22197561.

[17]

SMITI A. When machine learning meets medical world: current status and future challenges[J/OL]. Comput Sci Rev, 2020, 37: 100280 [2024-05-14]. https://doi.org/10.1016/j.cosrev.2020.100280. DOI: 10.1016/j.cosrev.2020.100280.

[18]

SHARMA T, SHAH M. A comprehensive review of machine learning techniques on diabetes detection[J/OL]. Vis Comput Ind Biomed Art, 2021, 4(1): 30 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/34862560/. DOI: 10.1186/s42492-021-00097-7.

[19]

SUDHARSAN M, THAILAMBAL G. Alzheimer's disease prediction using machine learning techniques and principal component analysis (PCA)[J/OL]. Mater Today Proc, 2023, 81: 182-190 [2024-05-14]. https://doi.org/10.1016/j.matpr.2021.03.061. DOI: 10.1016/j.matpr.2021.03.061.

[20]

BENNING L, PEINTNER A, PEINTNER L. Advances in and the applicability of machine learning-based screening and early detection approaches for cancer: a primer[J/OL]. Cancers, 2022, 14(3): 623 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/35158890/. DOI: 10.3390/cancers14030623.

[21]

ALHARBI F, VAKANSKI A. Machine learning methods for cancer classification using gene expression data: a review[J/OL]. Bioengineering, 2023, 10(2): 173 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36829667/. DOI: 10.3390/bioengineering10020173.

[22]

MAHMOUD A, TOUIL H, HANN F, et al. Case Report: an unusual orbital tumor[J/OL]. F1000Research, 2023, 12: 700 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/38726301/. DOI: 10.12688/f1000research.130056.2.

[23]

ELBAZE S, DURON L, MAMBOUR N, et al. A signature of structural MRI features at 3 Tesla allows an accurate characterization of orbital cavernous venous malformation[J]. Eur Radiol, 2023, 33(3): 2149-2159. DOI: 10.1007/s00330-022-09163-x.

[24]

COHEN L M, YOON M K. Update on current aspects of orbital imaging: CT, MRI, and ultrasonography[J]. Int Ophthalmol Clin, 2019, 59(4): 69-79. DOI: 10.1097/IIO.0000000000000288.

[25]

CHEN L, SHEN Y, HUANG X, et al. MRI-based radiomics for differentiating orbital cavernous hemangioma and orbital schwannoma[J/OL]. Front Med, 2021, 8: 795038 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/34977096/. DOI: 10.3389/fmed.2021.795038.

[26]

SHAO Y C, CHEN Y Q, CHEN S N, et al. Radiomics analysis of T1WI and T2WI magnetic resonance images to differentiate between IgG4-related ophthalmic disease and orbital MALT lymphoma[J/OL]. BMC Ophthalmol, 2023, 23(1): 288 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/37353736/. DOI: 10.1186/s12886-023-03036-7.

[27]

O'SHAUGHNESSY E, COSSEC C L, MAMBOUR N, et al. Diagnostic performance of dynamic contrast-enhanced 3T MR imaging for characterization of orbital lesions: validation in a large prospective study[J]. AJNR Am J Neuroradiol, 2024, 45(3): 342-350. DOI: 10.3174/ajnr.A8131.

[28]

ANG T, JUNIAT V, PATEL S, et al. Evaluation of orbital lesions with DCE-MRI: a literature review[J]. Orbit, 2024, 43(3): 408-416. DOI: 10.1080/01676830.2022.2149819.

[29]

RUSSO C, STRIANESE D, PERROTTA M, et al. Multi-parametric magnetic resonance imaging characterization of orbital lesions: a triple blind study[J]. Semin Ophthalmol, 2020, 35(2): 95-102. DOI: 10.1080/08820538.2020.1742358.

[30]

LI F, LIU K, SUN G L. The value of conventional MRI combined with apparent diffusion coefficient in differential diagnosis of orbital tumors[J]. Chin J Magn Reson Imag, 2020, 11(12): 1163-1166. DOI: 10.12015/issn.1674-8034.2020.12.018.

[31]

PRADEEP T, RAVIPATI A, MELACHURI S, et al. Utility of diffusion-weighted imaging to differentiate benign and malignant solid orbital tumours[J]. Can J Ophthalmol, 2023, 58(5): 455-460. DOI: 10.1016/j.jcjo.2022.04.008.

[32]

MORAES G, FU D J, WILSON M, et al. Quantitative analysis of OCT for neovascular age-related macular degeneration using deep learning[J]. Ophthalmology, 2021, 128(5): 693-705. DOI: 10.1016/j.ophtha.2020.09.025.

[33]

O'SHAUGHNESSY E, SENICOURT L, MAMBOUR N, et al. Toward precision diagnosis: machine learning in identifying malignant orbital tumors with multiparametric 3 T MRI[J/OL]. Invest Radiol, 2024 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/38597586/. DOI: 10.1097/RLI.0000000000001076.

[34]

LI T, BO W, HU C Y, et al. Applications of deep learning in fundus images: a review[J/OL]. Med Image Anal, 2021, 69: 101971 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/33524824/. DOI: 10.1016/j.media.2021.101971.

[35]

VAN ELST S, DE BLOEME C M, NOTEBOOM S, et al. Automatic segmentation and quantification of the optic nerve on MRI using a 3D U-Net[J/OL]. J Med Imaging, 2023, 10(3): 034501 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/37197374/. DOI: 10.1117/1.JMI.10.3.034501.

[36]

NGUYEN H G, PICA A, MAEDER P, et al. Ocular structures segmentation from multi-sequences MRI using 3D unet with fully connected CRFs[C]//International Workshop on Ophthalmic Medical Image Analysis, International Workshop on Computational Pathology. Cham: Springer, 2018: 167-175. DOI: 10.1007/978-3-030-00949-6_20.

[37]

STRIJBIS V I J, DE BLOEME C M, JANSEN R W, et al. Multi-view convolutional neural networks for automated ocular structure and tumor segmentation in retinoblastoma[J/OL]. Sci Rep, 2021, 11(1): 14590 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/34272413/. DOI: 10.1038/s41598-021-93905-2.

[38]

EGGER E, SCHALENBOURG A, ZOGRAFOS L, et al. Maximizing local tumor control and survival after proton beam radiotherapy of uveal melanoma[J]. Int J Radiat Oncol Biol Phys, 2001, 51(1): 138-147. DOI: 10.1016/s0360-3016(01)01560-7.

[39]

HASSAN M K, FLEURY E, SHAMONIN D, et al. An automatic framework to create patient-specific eye models from 3D magnetic resonance images for treatment selection in patients with uveal melanoma[J/OL]. Adv Radiat Oncol, 2021, 6(6): 100697 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/34660938/. DOI: 10.1016/j.adro.2021.100697.

[40]

PAL A, RATHI Y. A review and experimental evaluation of deep learning methods for MRI reconstruction[J/OL]. J Mach Learn Biomed Imaging, 2022, 1: 001 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/35722657/. DOI: 10.1109/TMI.2018.2865356.

[41]

MONTALT-TORDERA J, MUTHURANGU V, HAUPTMANN A, et al. Machine learning in Magnetic Resonance Imaging: image reconstruction[J/OL]. Phys Med, 2021, 83: 79-87 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/33721701/. DOI: 10.1016/j.ejmp.2021.02.020.

[42]

HAMMERNIK K, KLATZER T, KOBLER E, et al. Learning a variational network for reconstruction of accelerated MRI data[J]. Magn Reson Med, 2018, 79(6): 3055-3071. DOI: 10.1002/mrm.26977.

[43]

SCHLEMPER J, CABALLERO J, HAJNAL J V, et al. A deep cascade of convolutional neural networks for dynamic MR image reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(2): 491-503. DOI: 10.1109/TMI.2017.2760978.

[44]

BENFENATI A, BOLZI D, CAUSIN P, et al. A deep learning generative model approach for image synthesis of plant leaves[J/OL]. PLoS One, 2022, 17(11): e0276972 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/36399435/. DOI: 10.1371/journal.pone.0276972.

[45]

ESTLER A, ZERWECK L, BRUNNÉE M, et al. Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality[J]. J Neuroimaging, 2024, 34(2): 232-240. DOI: 10.1111/jon.13187.

[46]

YEN M T, BILYK J R, WLADIS E J, et al. Treatments for ocular adnexal lymphoma: a report by the American academy of ophthalmology[J]. Ophthalmology, 2018, 125(1): 127-136. DOI: 10.1016/j.ophtha.2017.05.037.

[47]

WICKWAR S, MCBAIN H, EZRA D G, et al. The psychosocial and clinical outcomes of orbital decompression surgery for thyroid eye disease and predictors of change in quality of life[J/OL]. Ophthalmology, 2015, 122(12): 2568-2576.e1 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/26421706/. DOI: 10.1016/j.ophtha.2015.08.030.

[48]

NIWA M, ISHIKURA S, TATEKAWA K, et al. Radiotherapy alone for stage IE ocular adnexal mucosa-associated lymphoid tissue lymphomas: long-term results[J/OL]. Radiat Oncol, 2020, 15(1): 25 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/32000814/. DOI: 10.1186/s13014-020-1477-8.

[49]

REHN S, ELSAYAD K, OERTEL M, et al. Radiotherapy dose and volume de-escalation in ocular adnexal lymphoma[J]. Anticancer Res, 2020, 40(7): 4041-4046. DOI: 10.21873/anticanres.14400.

[50]

HSU C R, CHEN Y Y, YAO M, et al. Orbital and ocular adnexal lymphoma: a review of epidemiology and prognostic factors in Taiwan[J]. Eye, 2021, 35(7): 1946-1953. DOI: 10.1038/s41433-020-01198-y.

[51]

ZHOU M, WANG J Q, SHI J H, et al. Prediction model of radiotherapy outcome for Ocular Adnexal Lymphoma using informative features selected by chemometric algorithms[J/OL]. Comput Biol Med, 2024, 170: 108067 [2024-05-14]. https://pubmed.ncbi.nlm.nih.gov/38301513/. DOI: 10.1016/j.compbiomed.2024.108067.

[52]

SHAIN A H, BAGGER M M, YU R, et al. The genetic evolution of metastatic uveal melanoma[J]. Nat Genet, 2019, 51(7): 1123-1130. DOI: 10.1038/s41588-019-0440-9.

[53]

DOGRUSÖZ M, BAGGER M, VAN DUINEN S G, et al. The prognostic value of AJCC staging in uveal melanoma is enhanced by adding chromosome 3 and 8q status[J]. Invest Ophthalmol Vis Sci, 2017, 58(2): 833-842. DOI: 10.1167/iovs.16-20212.

[54]

VAQUERO-GARCIA J, LALONDE E, EWENS K G, et al. PRiMeUM: a model for predicting risk of metastasis in uveal melanoma[J]. Invest Ophthalmol Vis Sci, 2017, 58(10): 4096-4105. DOI: 10.1167/iovs.17-22255.

PREV Advances in differentiating intracranial isolated fibromas from different grades of meningiomas based on diffusion-weighted imaging

NEXT Research progress of conventional MRI characteristics in prognostic prediction of nasopharyngeal carcinoma

LINK

Tel & Fax: +8610-67113815 E-mail: editor@cjmri.cn