Advances in radiomics and deep learning for precision management of intracranial benign lesions treated with gamma knife radiosurgery

Share this content in WeChat

[Chinese] [PDF] 31 1

• Review •

ZHENG Zhisong MEI Nan YIN Bo YANG Chuanbo LIU Chengcheng REN Rui JIANG Xingyue

Cite this article as ZHENG Z S, MEI N, YIN B, et al. Advances in radiomics and deep learning for precision management of intracranial benign lesions treated with gamma knife radiosurgery[J]. Chin J Magn Reson Imaging, 2026, 17(6): 188-197. DOI:10.12015/issn.1674-8034.2026.06.024.

Abstract

[Abstract] Gamma Knife radiosurgery (GKRS), with its high spatial precision and favorable normal-tissue sparing, has become an important modality for the management of intracranial benign lesions. As a precision radiotherapy technique, however, target delineation, dose planning, and treatment response assessment in GKRS remain constrained by interpatient heterogeneity and clinically occult imaging information. In addition, conventional response evaluation, which relies predominantly on post-treatment follow-up, is inherently limited by temporal delay, resulting in substantial variability in clinical outcomes among patients and underscoring the need for more individualized management strategies. In this context, radiomics and deep learning (DL), as emerging research hotspots in GKRS, provide novel technical approaches for the noninvasive evaluation and personalized management of intracranial benign lesions. However, current evidence remains fragmented, with limited clinical translation. Most studies have focused on a single disease entity or an isolated stage of the GKRS management workflow, while existing reviews have insufficiently covered certain benign intracranial lesions and have not fully clarified the interconnections and disease-specific differences across the GKRS management process. Accordingly, this review centers on the precision-management workflow of GKRS and summarizes the current advances in radiomics and DL for intracranial benign lesions from three perspectives: pre-treatment risk stratification, target delineation and treatment planning, and post-treatment response monitoring and complication surveillance. It further discusses the major methodological challenges and future directions in this field, with the aim of providing imaging-based evidence and clinical insights for the development of individualized therapeutic strategies.

[Keywords] gamma knife radiosurgery；intracranial benign lesions；radiomics；deep learning；magnetic resonance imaging；prognostic evaluation；image segmentation

Contributor Information

ZHENG Zhisong¹ MEI Nan² YIN Bo² YANG Chuanbo¹ LIU Chengcheng¹ REN Rui¹ JIANG Xingyue^1*

¹ Department of Radiology, Binzhou Medical University Hospital, Binzhou 256603, China

² Department of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, China

Corresponding author: JIANG X Y, E-mail: xyjiang188@sina.com

Conflicts of interest None.

Publication Information

Received 2026-03-30

Accepted 2026-05-14

DOI: 10.12015/issn.1674-8034.2026.06.024

Text

References

[1]

EHRET F, ROGERS C L, FONTANESI J, et al. Radiation therapy for non-malignant central nervous system tumors, disorders, and illnesses - current applications and future directions[J/OL]. Semin Radiat Oncol, 2026, 36: 77-94 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/41391900/. DOI: 10.1016/j.semradonc.2025.08.005.

[2]

TZIKOULIS V, GKANTAIFI A, ALONGI F, et al. Benign intracranial lesions - radiotherapy: an overview of treatment options, indications and therapeutic results[J]. Rev Recent Clin Trials, 2020, 15(2): 93-121. DOI: 10.2174/1574887114666191111100635.

[3]

QUINTIN K, JOSSET S, LATORZEFF I, et al. Radiotherapy of benign intracranial tumours: 2025 update[J/OL]. Cancer/Radiothérapie, 2025, 29(7/8): 104775 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/41273886/. DOI: 10.1016/j.canrad.2025.104775.

[4]

CHINA M, VASTANI A, HILL C S, et al. Gamma Knife radiosurgery for cerebral arteriovenous malformations: a systematic review and meta-analysis[J]. Neurosurg Rev, 2022, 45(3): 1987-2004. DOI: 10.1007/s10143-022-01751-1.

[5]

FONTOURA GALVÃO G DA, VERLY G, BESSA M D, et al. Gamma knife stereotactic radiosurgery for cerebral cavernous malformations: meta-analysis of reconstructed time-to-event data[J]. Cerebrovasc Dis, 2025, 54(2): 196-207. DOI: 10.1159/000539079.

[6]

KHABOUSHAN A S, MAROUFI S F, JARRAH N, et al. Comparison of stereotactic radiosurgery and rhizotomy for trigeminal neuralgia: a systematic review and Meta-Analysis[J/OL]. Neurosurg Rev, 2025, 48(1): 613 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40833460/. DOI: 10.1007/s10143-025-03763-z.

[7]

GANZ J C. Gamma knife evolving instrumentation[J]. Prog Brain Res, 2022, 268(1): 49-63. DOI: 10.1016/bs.pbr.2021.10.025.

[8]

YU J X, ZENG J M, HU G Y, et al. Post-operative gamma knife radiosurgery for WHO grade I intracranial meningiomas: a single-center, retrospective study[J/OL]. Front Neurol, 2023, 14: 1094032 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/36860575/. DOI: 10.3389/fneur.2023.1094032.

[9]

GUIOT J, VAIDYANATHAN A, DEPREZ L, et al. A review in radiomics: Making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-440. DOI: 10.1002/med.21846.

[10]

NERNEKLI K, PERSAD A R, HORI Y S, et al. Automatic segmentation of vestibular schwannomas: a systematic review[J/OL]. World Neurosurg, 2024, 188: 35-44 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/38685346/. DOI: 10.1016/j.wneu.2024.04.145.

[11]

HAJIKARIMLOO B, NAZARI M A, HABIBI M A, et al. Machine learning-based models in prediction of the radiological outcomes of vestibular schwannoma following stereotactic radiosurgery: a systematic review and meta-analysis[J/OL]. BMC Neurol, 2025, 25(1): 385 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/41013393/. DOI: 10.1186/s12883-025-04093-9.

[12]

ALHOSANIE T N, HAMMO B, KLAIB A F, et al. Integrating artificial intelligence with Gamma Knife radiosurgery in treating meningiomas and schwannomas: a review[J/OL]. Neurosurg Rev, 2025, 48(1): 655 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40965768/. DOI: 10.1007/s10143-025-03820-7.

[13]

LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.

[14]

MARIOTTI F, AGOSTINI A, BORGHERESI A, et al. Insights into radiomics: a comprehensive review for beginners[J]. Clin Transl Oncol, 2025, 27(11): 4091-4102. DOI: 10.1007/s12094-025-03939-5.

[15]

MAJUMDER S, KATZ S, KONTOS D, et al. State of the art: radiomics and radiomics-related artificial intelligence on the road to clinical translation[J/OL]. BJR|Open, 2023, 6: tzad004 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/38352179/. DOI: 10.1093/bjro/tzad004.

[16]

ZHANG H, SONG L T, CAO D Z, et al. Research status of imageology in radiotherapy[J]. J Clin Radiol, 2025, 44(4): 767-773. DOI: 10.13437/j.cnki.jcr.2025.04.016.

[17]

KOGA T, SHIN M, SAITO N. Role of γ knife radiosurgery in neurosurgery: past and future perspectives[J]. Neurol Med Chir, 2010, 50(9): 737-748. DOI: 10.2176/nmc.50.737.

[18]

MORELLI I, BANINI M, GRETO D, et al. Integrating radiomics and artificial intelligence (AI) in stereotactic body radiotherapy (SBRT)/stereotactic radiosurgery (SRS): predictive tools for tailored cancer care[J/OL]. Cancers, 2025, 17(17): 2906 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40941003/. DOI: 10.3390/cancers17172906.

[19]

SOLTYS S G, MILANO M T, XUE J Y, et al. Stereotactic radiosurgery for vestibular schwannomas: tumor control probability analyses and recommended reporting standards[J]. Int J Radiat Oncol, 2021, 110(1): 100-111. DOI: 10.1016/j.ijrobp.2020.11.019.

[20]

LANGENHUIZEN P P J H, SEBREGTS S H P, ZINGER S, et al. Prediction of transient tumor enlargement using MRI tumor texture after radiosurgery on vestibular schwannoma[J]. Med Phys, 2020, 47(4): 1692-1701. DOI: 10.1002/mp.14042.

[21]

GEORGE-JONES N A, WANG K, WANG J, et al. Prediction of vestibular schwannoma enlargement after radiosurgery using tumor shape and MRI texture features[J/OL]. Otol Neurotol, 2021, 42(3): e348-e354 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/33065598/. DOI: 10.1097/mao.0000000000002938.

[22]

LANGENHUIZEN P P J H, ZINGER S, LEENSTRA S, et al. Radiomics-based prediction of long-term treatment response of vestibular schwannomas following stereotactic radiosurgery[J/OL]. Otol Neurotol, 2020, 41(10): e1321-e1327 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/33492808/. DOI: 10.1097/mao.0000000000002886.

[23]

YANG H C, WU C C, LEE C C, et al. Prediction of pseudoprogression and long-term outcome of vestibular schwannoma after Gamma Knife radiosurgery based on preradiosurgical MR radiomics[J/OL]. Radiother Oncol, 2021, 155: 123-130 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/33161011/. DOI: 10.1016/j.radonc.2020.10.041.

[24]

HUANG C Y, PENG S J, WU H M, et al. Quantification of tumor response of cystic vestibular schwannoma to Gamma Knife radiosurgery by using artificial intelligence[J]. J Neurosurg, 2022, 136(5): 1298-1306. DOI: 10.3171/2021.4.JNS203700.

[25]

HUANG C Y, PENG S J, YANG H C, et al. Association between pseudoprogression of vestibular schwannoma after radiosurgery and radiological features of solid and cystic components[J]. Neurosurgery, 2023, 93(6): 1383-1392. DOI: 10.1227/neu.0000000000002599.

[26]

PRICE M, BALLARD C A P, BENEDETTI J R, et al. CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2018–2022[J/OL]. Neuro Oncol, 2025, 27(Supplement_4): iv1-iv66 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/41092086/. DOI: 10.1093/neuonc/noaf194.

[27]

GOLDBRUNNER R, STAVRINOU P, JENKINSON M D, et al. EANO guideline on the diagnosis and management of meningiomas[J]. Neuro Oncol, 2021, 23(11): 1821-1834. DOI: 10.1093/neuonc/noab150.

[28]

SPECKTER H, RADULOVIC M, TRIVODALIEV K, et al. MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery[J]. J Neurooncol, 2022, 159(2): 281-291. DOI: 10.1007/s11060-022-04063-y.

[29]

SPECKTER H, RADULOVIC M, LAZO E, et al. Prediction of pituitary adenoma's volumetric response to gamma knife radiosurgery using machine learning-supported MRI radiomics[J/OL]. J Clin Med, 2025, 14(9): 2896 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40363927/. DOI: 10.3390/jcm14092896.

[30]

GAO D Z, MENG X Y, JIN H W, et al. Assessment of gamma knife radiosurgery for unruptured cerebral arterioveneus malformations based on multi-parameter radiomics of MRI[J/OL]. Magn Reson Imaging, 2022, 92: 251-259 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/35870722/. DOI: 10.1016/j.mri.2022.07.008.

[31]

WU D J, KOLLITZ M, WARD M, et al. Prediction of obliteration after the gamma knife radiosurgery of arteriovenous malformations using hand-crafted radiomics and deep-learning methods[J/OL]. Cureus, 2024, 16(4): e58835 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/38784357/. DOI: 10.7759/cureus.58835.

[32]

JABAL M S, MOHAMMED M A, NESVICK C L, et al. DSA quantitative analysis and predictive modeling of obliteration in cerebral AVM following stereotactic radiosurgery[J]. AJNR Am J Neuroradiol, 2024, 45(10): 1521-1527. DOI: 10.3174/ajnr.A8351.

[33]

MENG X Y, GAO D Z, JIN H W, et al. Factors affecting volume reduction velocity for arteriovenous malformations after treatment with dose-stage stereotactic radiosurgery[J/OL]. Front Oncol, 2021, 11: 769533 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/34988014/. DOI: 10.3389/fonc.2021.769533.

[34]

MENG X Y, GAO D Z, HE H W, et al. A machine learning model predicts the outcome of SRS for residual arteriovenous malformations after partial embolization: a real-world clinical obstacle[J/OL]. World Neurosurg, 2022, 163: e73-e82 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/35276397/. DOI: 10.1016/j.wneu.2022.03.007.

[35]

MULFORD K L, MOEN S L, GRANDE A W, et al. Identifying symptomatic trigeminal nerves from MRI in a cohort of trigeminal neuralgia patients using radiomics[J]. Neuroradiology, 2022, 64(3): 603-609. DOI: 10.1007/s00234-022-02900-5.

[36]

HUNG P S, NOORANI A, ZHANG J Y, et al. Regional brain morphology predicts pain relief in trigeminal neuralgia[J/OL]. NeuroImage Clin, 2021, 31: 102706 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/34087549/. DOI: 10.1016/j.nicl.2021.102706.

[37]

KIM K H, JUNG S, LEE H J, et al. A deep neural network-based model predicting peritumoral edema after radiosurgery for meningioma[J/OL]. World Neurosurg, 2022, 164: e280-e289 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/35526813/. DOI: 10.1016/j.wneu.2022.04.125.

[38]

LI X X, LU Y P, LIU L, et al. Predicting peritumoral edema development after gamma knife radiosurgery of meningiomas using machine learning methods: a multicenter study[J]. Eur Radiol, 2023, 33(12): 8912-8924. DOI: 10.1007/s00330-023-09955-9.

[39]

ZHAO W, YIN C Y, MA L, et al. Predictive value of MRI for identifying symptomatic neurovascular compressions in classical trigeminal neuralgia: a PRISMA-compliant meta-analysis[J/OL]. BMC Neurol, 2024, 24(1): 466 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/39614218/. DOI: 10.1186/s12883-024-03977-6.

[40]

LEE W K, YANG H C, LEE C C, et al. Lesion delineation framework for vestibular schwannoma, meningioma and brain metastasis for gamma knife radiosurgery using stereotactic magnetic resonance images[J/OL]. Comput Methods Programs Biomed, 2023, 229: 107311 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/36577161/. DOI: 10.1016/j.cmpb.2022.107311.

[41]

YANG H C, PENG T C, CHEN Z H, et al. Deep learning for automated segmentation of brain edema in meningioma after radiosurgery[J/OL]. BMC Med Imaging, 2025, 25(1): 130 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40264119/. DOI: 10.1186/s12880-025-01660-x.

[42]

SHAPEY J, WANG G T, DORENT R, et al. An artificial intelligence framework for automatic segmentation and volumetry of vestibular schwannomas from contrast-enhanced T1-weighted and high-resolution T2-weighted MRI[J]. J Neurosurg, 2021, 134(1): 171-179. DOI: 10.3171/2019.9.JNS191949.

[43]

LEE W K, WU C C, LEE C C, et al. Combining analysis of multi-parametric MR images into a convolutional neural network: Precise target delineation for vestibular schwannoma treatment planning[J/OL]. Artif Intell Med, 2020, 107: 101911 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/32828450/. DOI: 10.1016/j.artmed.2020.101911.

[44]

LEE C C, LEE W K, WU C C, et al. Applying artificial intelligence to longitudinal imaging analysis of vestibular schwannoma following radiosurgery[J/OL]. Sci Rep, 2021, 11: 3106 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/33542422/. DOI: 10.1038/s41598-021-82665-8.

[45]

ČERNÝ M, MAY J, HAMÁČKOVÁ L, et al. Utility of artificial intelligence in radiosurgery for pituitary adenoma: a deep learning-based automated segmentation model and evaluation of its clinical applicability[J]. J Neurosurg, 2025, 143(2): 413-422. DOI: 10.3171/2024.12.JNS242167.

[46]

HANCEVIC M, NEMIR J, MARASANOV S, et al. Gamma Knife radiosurgery for brain arteriovenous malformations-a single-center experience[J/OL]. Acta Neurochir, 2025, 167(1): 121 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40272578/. DOI: 10.1007/s00701-025-06523-6.

[47]

KOO J H, HWANG E H, SONG J H, et al. Feasibility of gamma knife radiosurgery for brain arteriovenous malformations according to Nidus Type[J]. J Korean Neurosurg Soc, 2024, 67(4): 431-441. DOI: 10.3340/jkns.2023.0177.

[48]

SIMON A B, HURT B, KARUNAMUNI R, et al. Automated segmentation of multiparametric magnetic resonance images for cerebral AVM radiosurgery planning: a deep learning approach[J/OL]. Sci Rep, 2022, 12: 786 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/35039538/. DOI: 10.1038/s41598-021-04466-3.

[49]

HONG J S, YOU W C, SUN M H, et al. Deep learning detection and segmentation of brain arteriovenous malformation on magnetic resonance angiography[J]. J Magn Reson Imaging, 2024, 59(2): 587-598. DOI: 10.1002/jmri.28795.

[50]

ZENG C, LI Y H, YAN W, et al. A study of the correlation between the compression location and the painful region in classical trigeminal neuralgia by MRN[J]. Chin J Magn Reson Imaging, 2022, 13(7): 103-106. DOI: 10.12015/issn.1674-8034.2022.07.018.

[51]

SEMENOV D, BELOUSOVA O, GOLANOV A, et al. Gamma-knife radiosurgery for intracranial cavernous malformations: a single center experience[J/OL]. J Clin Neurosci, 2025, 139: 111456 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40618543/. DOI: 10.1016/j.jocn.2025.111456.

[52]

CHOU C J, YANG H C, LEE C C, et al. Auto-segmentation of cerebral cavernous malformations using a convolutional neural network[J/OL]. BMC Med Imaging, 2025, 25(1): 190 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40420000/. DOI: 10.1186/s12880-025-01738-6.

[53]

WANG H S, QU T X, BERNSTEIN K, et al. Automatic segmentation of vestibular schwannomas from T1-weighted MRI with a deep neural network[J/OL]. Radiat Oncol, 2023, 18(1): 78 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/37158968/. DOI: 10.1186/s13014-023-02263-y.

[54]

KUJAWA A, DORENT R, CONNOR S, et al. Deep learning for automatic segmentation of vestibular schwannoma: a retrospective study from multi-center routine MRI[J/OL]. Front Comput Neurosci, 2024, 18: 1365727 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/38784680/. DOI: 10.3389/fncom.2024.1365727.

[55]

LEE W K, HONG J S, LIN Y H, et al. Federated learning: a cross-institutional feasibility study of deep learning based intracranial tumor delineation framework for stereotactic radiosurgery[J]. J Magn Reson Imaging, 2024, 59(6): 1967-1975. DOI: 10.1002/jmri.28950.

[56]

HWANG J H, PARK C K, KANG S B, et al. Deep learning super-resolution technique based on magnetic resonance imaging for application of image-guided diagnosis and surgery of trigeminal neuralgia[J/OL]. Life (Basel), 2024, 14(3): 355 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/38541680/. DOI: 10.3390/life14030355.

[57]

CORNELISSEN S, SCHOUTEN S M, LANGENHUIZEN P P J H, et al. Towards clinical implementation of automated segmentation of vestibular schwannomas: a reliability study comparing AI and human performance[J]. Neuroradiology, 2025, 67(4): 1049-1059. DOI: 10.1007/s00234-025-03611-3.

[58]

WANG T H, LEI Y, TIAN S B, et al. Learning-based automatic segmentation of arteriovenous malformations on contrast CT images in brain stereotactic radiosurgery[J]. Med Phys, 2019, 46(7): 3133-3141. DOI: 10.1002/mp.13560.

[59]

HO H H, YANG H C, YANG W X, et al. Deep learning for automated segmentation of radiation-induced changes in cerebral arteriovenous malformations following radiosurgery[J/OL]. BMC Med Imaging, 2025, 25(1): 218 [2025-03-29]. https://pubmed.ncbi.nlm.nih.gov/40597846/. DOI: 10.1186/s12880-025-01796-w.

[60]

KUO P H, LEE C C, LU C F. Radiomics-based prediction of re-hemorrhage in cerebral cavernous malformation after gamma knife radiosurgery[C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). November 1-5, 2021, Mexico. IEEE, 2021: 3668-3671. DOI: 10.1109/EMBC46164.2021.9629762.

PREV Advances of intracranial high-resolution magnetic resonance-vessel wall imaging for precise assessment and prognostic prediction in cerebrovascular disease endovascular interventions

NEXT Advances in spinal cord diffusion tensor imaging and its clinical applications

LINK

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