
浏览全部资源
扫码关注微信
重庆师范大学计算机与信息科学学院,重庆
崔少国,博士,教授,博士生导师。美国威斯康星大学访问学者,博望学者领军人才。重庆市人工智能及创新应用研究生导师团队负责人,重庆市电子信息专业硕士校企联合培养实践基地负责人,人工智能与智慧医疗创新研究团队负责人。中国计算机学会教育专委会执行委员,中国计算机学会数字医学专委会执行委员,中国人工智能学会终身会员,国际一般系统论研究会中国分会医学信息系统专业委员会常务委员,中华医学会医学信息学分会医学信息学教育专业学组成员。主持和参与国家自然科学基金、国家社会科学基金、教育部人文社科项目等30余项;在国内外重要专业学术期刊上发表SCI/EI等科研论文30余篇;申请并授权国际发明专利2项,国家发明专利12项,软件著作权4项。主要从事人工智能与医学影像智能分析方面的研究。E-mail: csg@cqnu.edu.cn
收稿日期:2024-09-26,
修回日期:2025-03-07,
纸质出版日期:2025-07-30
移动端阅览
崔少国,陈俊杉.深度学习和磁共振图像辅助脑胶质瘤基因分型的研究进展[J].陆军军医大学学报,2025,47(14):1557-1567.DOI:10.16016/j.2097-0927.202409134.
CUI S G,CHEN J S.Advances in deep learning and MRI co-assisted genotyping of brain gliomas[J].J Army Med Univ,2025,47(14):1557-1567.DOI:10.16016/j.2097-0927.202409134.
脑胶质瘤的基因型状态是评估患者预后和生存周期的重要指标,其基因分型具有显著的临床价值。虽然生物分子标志物是脑胶质瘤分型的重要依据,但依然存在检测成本高、效率低的问题。近年来,人工智能技术的快速发展为脑胶质瘤的自动分型提供了新的解决方案,其中基于磁共振图像(MRI)和深度学习技术的基因状态预测已成为研究热点。目前的研究通过整合多模态MRI数据,构建了从监督学习到非监督学习的技术体系,通过多任务联合优化和迁移学习,在单基因分型中取得了较高的预测精度。同时,多基因联合分析作为新兴方向,已取得了初步探索成果。未来,开发多基因同步预测模型、基于生成数据增强提高小样本泛化能力、采用多源异构数据和大模型提升预测精度,以及引入可视化技术提升可解释性等,将成为脑胶质瘤基因分型研究的关键突破方向。
The genotypic status of gliomas is a critical indicator for assessing patient prognosis and survival duration
with its genetic classification holding significant clinical value. Although biomolecular markers serve as essential criteria for glioma classification
challenges such as high detection costs and low efficiency persist. In recent years
the rapid advancement of artificial intelligence (AI) has provided novel solutions for the automated classification of gliomas
with MRI-based deep learning techniques for genetic status prediction emerging as a research hotspot. Current studies have established a technical framework ranging from supervised to unsupervised learning by integrating multimodal MRI data
achieving high predictive accuracy in single-gene classification through multi-task joint optimization and transfer learning. Meanwhile
multi-gene joint analysis
as an emerging direction
has yielded preliminary exploratory results. In the future
key breakthroughs in glioma genetic classification research will include the development of multi-gene synchronous prediction models
enhancing generalization capabilities for small samples through generative data augmentation
improving prediction accuracy using multi-source heterogeneous data and large models
and introducing visualization techniques to enhance interpretability.
WELLER M , WICK W , ALDAPE K , et al . Glioma [J]. Nat Rev Dis Primers , 2015 , 1 : 15017 . DOI: 10.1038/nrdp. 2015.17 http://dx.doi.org/10.1038/nrdp.2015.17 .
LI D P , CHEN Z P . Current statue and advances of treatment for gliomas [J]. J Pract Med , 2021 , 37 ( 18 ): 2312 - 2316 . DOI: 10. 3969/j. issn. 1006-5725. 2021. 18. 002 http://dx.doi.org/10.3969/j.issn.1006-5725.2021.18.002 .
李洁 , 刘光耀 , 樊凤仙 , 等 . 深度学习和影像组学在脑胶质瘤中的研究进展 [J]. 磁共振成像 , 2022 , 13 ( 4 ): 158 - 161 . DOI: 10.12015/issn.1674-8034.2022.04.035 http://dx.doi.org/10.12015/issn.1674-8034.2022.04.035 .
LI J , LIU G Y , FAN F X , et al . Research progress of deep learning and radiomics in glioma [J]. Chin J Magn Reson Imag , 2022 , 13 ( 4 ): 158 - 161 . DOI: 10. 12015/issn. 1674- 8034. 2022. 04. 035 http://dx.doi.org/10.12015/issn.1674-8034.2022.04.035 .
YUILE A , SATGUNASEELAN L , WEI J Q , et al . CDKN2A/B homozygous deletions in astrocytomas: a literature review [J]. Curr Issues Mol Biol , 2023 , 45 ( 7 ): 5276 - 5292 . DOI: 10.3390/cimb45070335 http://dx.doi.org/10.3390/cimb45070335 .
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 Oncol , 2023 , 25 ( 10 ): 1731 - 1749 . DOI: 10.1093/neuonc/noad100 http://dx.doi.org/10.1093/neuonc/noad100 .
ZHANG S M , YIN L J , MA L , et al . Artificial intelligence applications in glioma with 1p/19q co-deletion: a systematic review [J]. J Magn Reson Imaging , 2023 , 58 ( 5 ): 1338 - 1352 . DOI: 10.1002/jmri.28737 http://dx.doi.org/10.1002/jmri.28737 .
OLYMPIOS N , GILARD V , MARGUET F , et al . TERT promoter alterations in glioblastoma: a systematic review [J]. Cancers (Basel) , 2021 , 13 ( 5 ): 1147 . DOI: 10.3390/cancers13051147 http://dx.doi.org/10.3390/cancers13051147 .
ERIC HUANG L . Impact of CDKN2A/B homozygous deletion on the prognosis and biology of IDH-mutant glioma [J]. Biomedicines , 2022 , 10 ( 2 ): 246 . DOI: 10.3390/biomedicines10020246 http://dx.doi.org/10.3390/biomedicines10020246 .
MAGAKI S , HOJAT S A , WEI B , et al . An introduction to the performance of immunohistochemistry [M]. New York : Springer , 2019 . DOI: 10. 1007/978-1-4939-8935-5_25 http://dx.doi.org/10.1007/978-1-4939-8935-5_25 .
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]. J Pers Med , 2021 , 11 ( 9 ): 909 . DOI: 10.3390/jpm11090909 http://dx.doi.org/10.3390/jpm11090909 .
GISINA A , KHOLODENKO I , KIM Y , et al . Glioma stem cells: novel data obtained by single-cell sequencing [J]. Int J Mol Sci , 2022 , 23 ( 22 ): 14224 . DOI: 10.3390/ijms 232214224 http://dx.doi.org/10.3390/ijms232214224 .
CAO Y J , YAO X H . Preoperative MRI enhancement grade for adult diffuse glioma affects IDH mutation and WHO grade [J]. J Amry Med Univ , 2024 , 46 ( 12 ): 1441 - 1446 . DOI: 10. 16016/j. 2097 0927. 202403016 http://dx.doi.org/10.16016/j.20970927.202403016 .
HU L S , NING S L , ESCHBACHER J M , et al . Radiogenomics to characterize regional genetic heterogeneity in glioblastoma [J]. Neuro Oncol , 2017 , 19 ( 1 ): 128 - 137 . DOI: 10.1093/neuonc/now135 http://dx.doi.org/10.1093/neuonc/now135 .
LECUN Y , BENGIO Y , HINTON G . Deep learning [J]. Nature , 2015 , 521 ( 7553 ): 436 - 444 . DOI: 10.1038/nature14539 http://dx.doi.org/10.1038/nature14539 .
LU Z Y , BAI Y Z , CHEN Y , et al . The classification of gliomas based on a Pyramid dilated convolution resnet model [J]. Pattern Recognit Lett , 2020 , 133 : 173 - 179 . DOI: 10.1016/j.patrec.2020.03.007 http://dx.doi.org/10.1016/j.patrec.2020.03.007 .
LIANG S , ZHANG R G , LIANG D Y , et al . Multimodal 3D DenseNet for IDH genotype prediction in gliomas [J]. Genes (Basel) , 2018 , 9 ( 8 ): 382 . DOI: 10.3390/genes9080382 http://dx.doi.org/10.3390/genes9080382 .
LIU Z , LIN Y T , CAO Y , et al . Swin transformer: hierarchical vision transformer using shifted windows [C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . IEEE , 2021 : 9992 - 10002 . DOI: 10.1109/ICCV48922.2021.00986 http://dx.doi.org/10.1109/ICCV48922.2021.00986 .
WU J F , XU Q , SHEN Y Q , et al . Swin transformer improves the IDH mutation status prediction of gliomas free of MRI-based tumor segmentation [J]. J Clin Med , 2022 , 11 ( 15 ): 4625 . DOI: 10.3390/jcm11154625 http://dx.doi.org/10.3390/jcm11154625 .
BANGALORE YOGANANDA C G , WAGNER B C , TRUONG N C D , et al . MRI-based deep learning method for classification of IDH mutation status [J]. Bioengineering (Basel) , 2023 , 10 ( 9 ): 1045 . DOI: 10.3390/bioengineering 10091045 http://dx.doi.org/10.3390/bioengineering10091045 .
ZHANG L Q , WANG R , GAO J N , et al . A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma [J]. Eur Radiol , 2024 , 34 ( 1 ): 391 - 399 . DOI: 10.1007/s00330-023-09944-y http://dx.doi.org/10.1007/s00330-023-09944-y .
CHEN Q J , WANG L H , XING Z Y , et al . Deep wavelet scattering orthogonal fusion network for glioma IDH mutation status prediction [J]. Comput Biol Med , 2023 , 166 : 107493 . DOI: 10.1016/j.compbiomed.2023.107493 http://dx.doi.org/10.1016/j.compbiomed.2023.107493 .
VAN ENGELEN J E , HOOS H H . A survey on semi-supervised learning [J]. Mach Learn , 2020 , 109 ( 2 ): 373 - 440 . DOI: 10.1007/s10994-019-05855-6 http://dx.doi.org/10.1007/s10994-019-05855-6 .
GE C J , GU I Y , JAKOLA A S , et al . Deep semi-supervised learning for brain tumor classification [J]. BMC Med Imaging , 2020 , 20 ( 1 ): 87 . DOI: 10.1186/s12880-020-00485-0 http://dx.doi.org/10.1186/s12880-020-00485-0 .
CHEN L , BENTLEY P , MORI K , et al . Self-supervised learning for medical image analysis using image context restoration [J]. Med Image Anal , 2019 , 58 : 101539 . DOI: 10.1016/j.media.2019.101539 http://dx.doi.org/10.1016/j.media.2019.101539 .
LIU X , ZHANG F J , HOU Z Y , et al . Self-supervised learning: generative or contrastive [J]. IEEE Trans Knowl Data Eng , 2021 , 35 ( 1 ): 857 - 876 . DOI: 10.1109/TKDE. 2021.3090866 http://dx.doi.org/10.1109/TKDE.2021.3090866 .
HAN L X , XIAO S , LI Z M , et al . Enhanced self- supervised learning for multi-modality MRI segmentation and classification: A novel approach avoiding model collapse [EB/OL]. ( 2025-01-16 ). https://arxiv.org/abs/ 2407.10377 https://arxiv.org/abs/2407.10377 .
NAEEM S , ALI A , ANAM S , et al . An unsupervised machine learning algorithms: comprehensive review [J]. Int J Comput Digit Syst , 2023 , 13 ( 1 ): 911 - 921 . DOI: 10.12785/ijcds/130172 http://dx.doi.org/10.12785/ijcds/130172 .
GE C J , GU I Y , STORE JAKOLA A , et al . Cross-modality augmentation of brain mr images using a novel pairwise generative adversarial network for enhanced glioma classification [C]// 2019 IEEE International Conference on Image Processing (ICIP) . IEEE , 2019 : 559 - 563 . DOI: 10.1109/ICIP.2019.8803808 http://dx.doi.org/10.1109/ICIP.2019.8803808 .
SUN X M , PANDA R , FERIS R , et al . AdaShare: learning what to share for efficient deep multi-task learning [EB/OL]. ( 2020-11-18 ). https://arxiv.org/abs/1911.12423v2 https://arxiv.org/abs/1911.12423v2 .
YU T H , KUMAR S , GUPTA A , et al . Gradient surgery for multi-task learning [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems . ACM , 2020 : 5824 - 5836 . DOI: 10.5555/3495724.3496213 http://dx.doi.org/10.5555/3495724.3496213 .
MATSUI Y , MARUYAMA T , NITTA M , et al . Prediction of lower-grade glioma molecular subtypes using deep learning [J]. J Neurooncol , 2020 , 146 ( 2 ): 321 - 327 . DOI: 10.1007/s11060-019-03376-9 http://dx.doi.org/10.1007/s11060-019-03376-9 .
PASQUINI L , NAPOLITANO A , TAGLIENTE E , et al . Deep learning can differentiate IDH-mutant from IDH-wild GBM [J]. J Pers Med , 2021 , 11 ( 4 ): 290 . DOI: 10.3390/jpm11040290 http://dx.doi.org/10.3390/jpm11040290 .
DECUYPER M , BONTE S , DEBLAERE K , et al . Automated MRI based pipeline for segmentation and prediction of grade, IDH mutation and 1p19q co-deletion in glioma [J]. Comput Med Imaging Graph , 2021 , 88 : 101831 . DOI: 10.1016/j.compmedimag.2020.101831 http://dx.doi.org/10.1016/j.compmedimag.2020.101831 .
CHOI Y S , BAE S , CHANG J H , et al . Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics [J]. Neuro Oncol , 2021 , 23 ( 2 ): 304 - 313 . DOI: 10.1093/neuonc/noaa177 http://dx.doi.org/10.1093/neuonc/noaa177 .
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]. Neurooncol Adv , 2020 , 2 ( 1 ): vdaa066 . DOI: 10.1093/noajnl/vdaa066 http://dx.doi.org/10.1093/noajnl/vdaa066 .
WANG Y , WANG Y , GUO C J , et al . SGPNet: a three-dimensional multitask residual framework for segmentation and IDH genotype prediction of gliomas [J]. Comput Intell Neurosci , 2021 , 2021 ( 1 ): 5520281 . DOI: 10.1155/2021/5520281 http://dx.doi.org/10.1155/2021/5520281 .
YAO J X , LIU J , CHENG J H , et al . M3CI-net: multi-modal MRI-based characteristics inspired network for IDH genotyping [C]// 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) . IEEE , 2023 : 1649 - 1654 . DOI: 10.1109/BIBM58861.2023.10385313 http://dx.doi.org/10.1109/BIBM58861.2023.10385313 .
CHENG J H , LIU J , KUANG H L , et al . A fully automated multimodal MRI-based multi-task learning for glioma segmentation and IDH genotyping [J]. IEEE Trans Med Imaging , 2022 , 41 ( 6 ): 1520 - 1532 . DOI: 10.1109/TMI.2022.3142321 http://dx.doi.org/10.1109/TMI.2022.3142321 .
ALI M B , GU I Y , BERGER M S , et al . Domain mapping and deep learning from multiple MRI clinical datasets for prediction of molecular subtypes in low grade gliomas [J]. Brain Sci , 2020 , 10 ( 7 ): 463 . DOI: 10.3390/brainsci10070463 http://dx.doi.org/10.3390/brainsci10070463 .
VAN DER VOORT S R , INCEKARA F , WIJNENGA M M J , et al . Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning [J]. Neuro Oncol , 2023 , 25 ( 2 ): 279 - 289 . DOI: 10.1093/neuonc/noac166 http://dx.doi.org/10.1093/neuonc/noac166 .
CHAKRABARTY S , LAMONTAGNE P , SHIMONY J , et al . MRI-based classification of IDH mutation and 1p/19q codeletion status of gliomas using a 2.5D hybrid multi-task convolutional neural network [J]. Neurooncol Adv , 2023 , 5 ( 1 ): vdad023 . DOI: 10.1093/noajnl/vdad023 http://dx.doi.org/10.1093/noajnl/vdad023 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621