专家述评
ENGLISH ABSTRACT
重视人工智能在葡萄膜恶性黑色素瘤中的应用和挑战
丁运刚
李永平
作者及单位信息
·
DOI: 10.3760/cma.j.cn115989-20240722-00206
Focusing on the application and challenges of artificial intelligence in uveal malignant melanoma
Ding Yungang
Li Yongping
Authors Info & Affiliations
Ding Yungang
Affiliated Eye Hospital of Shandong University of Traditional Chinese Medicine, Jinan 250002, China
Li Yongping
Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou 510060, China
·
DOI: 10.3760/cma.j.cn115989-20240722-00206
269
24
0
2
1
4
PDF下载
APP内阅读
摘要

葡萄膜恶性黑色素瘤是成人常见的原发性眼内恶性肿瘤,具有高度隐匿性和转移性,具有高致盲和致死风险。随着机器学习和深度学习技术的发展,人工智能(AI)在葡萄膜恶性黑色素瘤的诊断、治疗和预后评估中展现出相当的应用潜力,能够深入挖掘临床影像、病理及基因组等多维数据,辅助临床医师进行诊断和治疗决策。AI可以分析眼部照相和放射学图像数据,辅助鉴别诊断;预测放射治疗不良反应和效果,辅助优化治疗方案;基于临床特征和数字病理图像,构建精准的预后预测模型,其准确率可以媲美基因表达谱分析。尽管AI在葡萄膜恶性黑色素瘤的临床应用面临数据、技术和人机协作等挑战,但是随着对葡萄膜恶性黑色素瘤研究的深入和AI技术的发展,AI有望更精准、高效地助力葡萄膜恶性黑色素瘤患者的诊疗和预后评估,最终改善患者预后。

葡萄膜;黑色素瘤;人工智能;机器学习;诊断;治疗;预后评估
ABSTRACT

Uveal malignant melanoma is one of the common primary intraocular malignancies in adults.Its high concealment and significant metastatic potential lead to a high risk of blindness and mortality.With advances in machine learning and deep learning techniques, artificial intelligence (AI) has shown increasing promise for application in the diagnosis, management, and prognosis evaluation of uveal malignant melanoma.AI can thoroughly analyze the multi-modal data, such as clinical images, pathological images, and genetic data, and assist clinicians in diagnosis and treatment planning.AI analyzes ophthalmic photography and radiological image to assist in differential diagnosis, and predicts side effects and outcomes of radiotherapy to optimize treatments.AI constructs the models for accurate prognosis based on clinical features and digital pathology images, and its accuracy is comparable to that of gene expression profiling tests.The clinical application of AI in uveal malignant melanoma faces the challenges of data availability, technology limitations, and effective human-machine collaboration.However, with ongoing research in both uveal malignant melanoma and AI, AI is expected to improve the accuracy and efficiency of diagnosis, management, and prognosis assessment, ultimately improving patient outcomes.

Uvea;Melanoma;Artificial intelligence;Machine learning;Diagnosis;Treatment;Prognosis evaluation
Li Yongping, Email: mocdef.nabuyila1691ilgnipgnoy
引用本文

丁运刚,李永平. 重视人工智能在葡萄膜恶性黑色素瘤中的应用和挑战[J]. 中华实验眼科杂志,2024,42(12):1084-1089.

DOI:10.3760/cma.j.cn115989-20240722-00206

PERMISSIONS

Request permissions for this article from CCC.

评价本文
*以上评分为匿名评价
本文评分
5 [累计1个]
葡萄膜恶性黑色素瘤(uveal malignant melanoma,UM)是一种成人常见的原发性眼内恶性肿瘤,起源于眼内的葡萄膜组织,该肿瘤约90%发生在脉络膜,6%发生在睫状体,4%发生在虹膜 [ 1 ]。UM具有高度隐匿性、鉴别诊断困难、易转移和致死率高的特点,给患者带来了较大的致盲和致死风险 [ 2 , 3 ]。近年来,随着机器学习(machine learning,ML)和深度学习(deep learning,DL)技术的快速发展,人工智能(artificial intelligence,AI)在UM诊断、治疗和预后评估中的应用研究也取得了相当的进展 [ 4 ]。AI可以深入挖掘肿瘤检查数据集中的隐藏关系,涵盖临床、影像、检验、病理、基因组学、转录组学和多模态数据等多种数据类型 [ 5 , 6 ]。随着AI技术的发展,其对眼科临床数据进行自动化分析的研究报道日益增多,相关的伦理规范也在不断完善 [ 7 ]。因此,重视AI在UM诊疗中的应用,并积极面对相关挑战,将有助于推动UM诊疗进展,提高患者生存质量和生活水平。
试读结束,您可以通过登录机构账户或个人账户后获取全文阅读权限。
参考文献
[1]
Shields CL Furuta M Thangappan A et al. Metastasis of uveal melanoma millimeter-by-millimeter in 8033 consecutive eyes[J]. Arch Ophthalmol 2009127(8)∶989998. DOI: 10.1001/archophthalmol.2009.208 .
返回引文位置Google Scholar
百度学术
万方数据
[2]
Jager MJ Shields CL Cebulla CM et al. Uveal melanoma[J/OL]. Nat Rev Dis Primers 20206(1)∶24[2024-07-10]. https://pubmed.ncbi.nlm.nih.gov/32273508/. DOI: 10.1038/s41572-020-0158-0 .
返回引文位置Google Scholar
百度学术
万方数据
[3]
Carvajal RD Sacco JJ Jager MJ et al. Advances in the clinical management of uveal melanoma[J]. Nat Rev Clin Oncol 202320(2)∶99115. DOI: 10.1038/s41571-022-00714-1 .
返回引文位置Google Scholar
百度学术
万方数据
[4]
Koseoglu ND Corrêa ZM Liu T Artificial intelligence for ocular oncology[J]. Curr Opin Ophthalmol 202334(5)∶437440. DOI: 10.1097/ICU.0000000000000982 .
返回引文位置Google Scholar
百度学术
万方数据
[5]
赵汉卿罗婧婷李洋单细胞转录组测序在葡萄膜黑色素瘤中应用的研究进展[J]. 中华眼底病杂志 202238(3)∶248252. DOI: 10.3760/cma.j.cn511434-20220130-00063 .
返回引文位置Google Scholar
百度学术
万方数据
Zhao HQ Luo JT Li Y et al. Research progress of single-cell transcriptome sequencing in uveal melanoma[J]. Chin J Ocul Fundus Dis 202238(3)∶248252. DOI: 10.3760/cma.j.cn511434-20220130-00063 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[6]
Eisenstein M AI assistance for planning cancer treatment[J]. Nature 2024629(8014)∶S14S16. DOI: 10.1038/d41586-024-01431-8 .
返回引文位置Google Scholar
百度学术
万方数据
[7]
《眼科人工智能临床应用伦理专家共识(2023)》专家组中国医药教育协会数字影像与智能医疗分会中国医药教育协会智能医学专业委员会眼科人工智能临床应用伦理专家共识(2023)[J]. 中华实验眼科杂志 202341(1)∶17. DOI: 10.3760/cma.j.cn115989-20220905-00414 .
返回引文位置Google Scholar
百度学术
万方数据
Expert Workgroup of Expert consensus for ethics of clinical application of artificial intelligence in ophthalmology (2023)Digital Imaging and Intelligent Medicine Branch of China Medical Education AssociationIntelligent Medicine Special Committee of China Medical Education Association. Expert consensus for ethics of clinical application of artificial intelligence in ophthalmology (2023)[J]. Chin J Exp Ophthalmol 202341(1)∶17. DOI: 10.3760/cma.j.cn115989-20220905-00414 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[8]
林浩添吴晓航加快基于眼科图像数据库的眼病人工智能辅助诊断平台建设[J]. 中华实验眼科杂志 201836(8)∶577580. DOI: 10.3760/cma.j.issn.2095-0160.2018.08.001 .
返回引文位置Google Scholar
百度学术
万方数据
Lin HT Wu XH . Accelerating the construction of artificial intelligence diagnostic platform based on ophthalmic imaging database[J]. Chin J Exp Ophthalmol 201836(8)∶577580. DOI: 10.3760/cma.j.issn.2095-0160.2018.08.001 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[9]
Yu KH Healey E Leong TY et al. Medical artificial intelligence and human values[J]. N Engl J Med 2024390(20)∶18951904. DOI: 10.1056/NEJMra2214183 .
返回引文位置Google Scholar
百度学术
万方数据
[10]
Zabor EC Raval V Luo S et al. A prediction model to discriminate small choroidal melanoma from choroidal nevus[J]. Ocul Oncol Pathol 20228(1)∶7178. DOI: 10.1159/000521541 .
返回引文位置Google Scholar
百度学术
万方数据
[11]
Luo J Chen Y Yang Y et al. Prognosis prediction of uveal melanoma after plaque brachytherapy based on ultrasound with machine learning[J/OL]. Front Med (Lausanne) 20218777142[2024-07-10]. https://pubmed.ncbi.nlm.nih.gov/35127747/. DOI: 10.3389/fmed.2021.777142 .
返回引文位置Google Scholar
百度学术
万方数据
[12]
Chen YN Wang YN Chen MX et al. Machine learning models for outcome prediction of Chinese uveal melanoma patients:a 15-year follow-up study[J]. Cancer Commun (Lond) 202242(3)∶273276. DOI: 10.1002/cac2.12253 .
返回引文位置Google Scholar
百度学术
万方数据
[13]
Indini A Di Guardo L Cimminiello C et al. Artificial intelligence estimates the importance of baseline factors in predicting response to anti-PD1 in metastatic melanoma[J]. Am J Clin Oncol 201942(8)∶643648. DOI: 10.1097/COC.0000000000000566 .
返回引文位置Google Scholar
百度学术
万方数据
[14]
Sun M Zhou W Qi X et al. Prediction of BAP1 expression in uveal melanoma using densely-connected deep classification networks[J/OL]. Cancers (Basel) 201911(10)∶1579[2024-07-10]. https://pubmed.ncbi.nlm.nih.gov/31623293/. DOI: 10.3390/cancers11101579 .
返回引文位置Google Scholar
百度学术
万方数据
[15]
Sabazade S Lumia Michalski MA Bartoszek J et al. Development and validation of a deep learning algorithm for differentiation of choroidal nevi from small melanoma in fundus photographs[J/OL]. Ophthalmol Sci 20245(1)∶100613[2024-11-12]. https://pubmed.ncbi.nlm.nih.gov/39421390/. DOI: 10.1016/j.xops.2024.100613 .
返回引文位置Google Scholar
百度学术
万方数据
[16]
Zhang H Kalirai H Acha-Sagredo A et al. Piloting a deep learning model for predicting nuclear BAP1 immunohistochemical expression of uveal melanoma from hematoxylin-and-eosin sections[J/OL]. Transl Vis Sci Technol 20209(2)∶50[2024-07-11]. https:// pubmed.ncbi.nlm.nih.gov/32953248/ . DOI: 10.1167/tvst.9.2.50 .
返回引文位置Google Scholar
百度学术
万方数据
[17]
Bera K Braman N Gupta A et al. Predicting cancer outcomes with radiomics and artificial intelligence in radiology[J]. Nat Rev Clin Oncol 202219(2)∶132146. DOI: 10.1038/s41571-021-00560-7 .
返回引文位置Google Scholar
百度学术
万方数据
[18]
于颖彦人工智能在病理学研究与应用的进展[J]. 中华病理学杂志 202049(5)∶393396. DOI: 10.3760/cma.j.cn112151-20190924-00525 .
返回引文位置Google Scholar
百度学术
万方数据
Yu YY . Progress of artificial intelligence on pathological research and u tilization [J]. Chin J Pathol 202049(5)∶393396. DOI: 10.3760/cma.j.cn112151-20190924-00525 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[19]
Rantala ES Hernberg MM Piperno-Neumann S et al. Metastatic uveal melanoma:the final frontier[J/OL]. Prog Retin Eye Res 202290101041[2024-07-11]. https://pubmed.ncbi.nlm.nih.gov/34999237/. DOI: 10.1016/j.preteyeres.2022.101041 .
返回引文位置Google Scholar
百度学术
万方数据
[20]
Su Y Xu X Zuo P et al. Value of MR-based radiomics in differentiating uveal melanoma from other intraocular masses in adults[J/OL]. Eur J Radiol 2020131109268[2024-07-11]. https://pubmed.ncbi.nlm.nih.gov/32947090/. DOI: 10.1016/j.ejrad.2020.109268 .
返回引文位置Google Scholar
百度学术
万方数据
[21]
Fionda B Pagliara MM Chyrek AJ et al. Ocular brachytherapy (interventional radiotherapy):preserving the vision[J/OL]. Clin Oncol (R Coll Radiol) 202335(8)∶e445e452[2024-07-11]. https://pubmed.ncbi.nlm.nih.gov/36792447/. DOI: 10.1016/j.clon.2023.01.021 .
返回引文位置Google Scholar
百度学术
万方数据
[22]
Li Y Shi J Yang J et al. Uveal melanoma:progress in molecular biology and therapeutics[J/OL]. Ther Adv Med Oncol 202012 1758835920 965852 [2024-07-12]. https://pubmed.ncbi.nlm.nih.gov/33149769/. DOI: 10.1177/1758835920965852 .
返回引文位置Google Scholar
百度学术
万方数据
[23]
Fu Y Xiao W Mao Y Recent advances and challenges in uveal melanoma immunotherapy[J/OL]. Cancers (Basel) 202214(13)∶3094[2024-07-12]. https://pubmed.ncbi.nlm.nih.gov/35804863/. DOI: 10.3390/cancers14133094 .
返回引文位置Google Scholar
百度学术
万方数据
[24]
Zhou X Meng F Xu B et al. STING promotes invasion and migration of uveal melanoma through p38-MAPK signaling[J/OL]. Oncol Rep 202451(2)∶23[2024-07-12]. https://pubmed.ncbi.nlm.nih.gov/38099424/. DOI: 10.3892/or.2023.8682 .
返回引文位置Google Scholar
百度学术
万方数据
[25]
Chi H Peng G Yang J et al. Machine learning to construct sphingolipid metabolism genes signature to characterize the immune landscape and prognosis of patients with uveal melanoma[J/OL]. Front Endocrinol (Lausanne) 2022131056310[2024-07-12]. https://pubmed.ncbi.nlm.nih.gov/36568076/. DOI: 10.3389/fendo.2022.1056310 .
返回引文位置Google Scholar
百度学术
万方数据
[26]
Kaliki S Shields CL Shields JA . Uveal melanoma:estimating prognosis[J]. Indian J Ophthalmol 201563(2)∶93102. DOI: 10.4103/0301-4738.154367 .
返回引文位置Google Scholar
百度学术
万方数据
[27]
Berus T Markiewicz A Biecek P et al. Clinical significance of nucleoli cytomorphology assessment in patients with uveal melanoma[J]. Anticancer Res 202040(6)∶35053512. DOI: 10.21873/anticanres.14338 .
返回引文位置Google Scholar
百度学术
万方数据
[28]
Figueiredo CR Kalirai H Sacco JJ et al. Loss of BAP1 expression is associated with an immunosuppressive microenvironment in uveal melanoma,with implications for immunotherapy development[J]. J Pathol 2020250(4)∶420439. DOI: 10.1002/path.5384 .
返回引文位置Google Scholar
百度学术
万方数据
[29]
Donizy P Krzyzinski M Markiewicz A et al. Machine learning models demonstrate that clinicopathologic variables are comparable to gene expression prognostic signature in predicting survival in uveal melanoma[J]. Eur J Cancer 2022174251260. DOI: 10.1016/j.ejca.2022.07.031 .
返回引文位置Google Scholar
百度学术
万方数据
[30]
李彬张旭重视对葡萄膜黑色素瘤侵袭转移机制的研究[J]. 中华实验眼科杂志 201230(9)∶769773. DOI: 10.3760/cma.j.issn.2095-0160.2012.09.001 .
返回引文位置Google Scholar
百度学术
万方数据
Li B Zhang X Attach importance to the study on mechanism of invasion and metastasis of uveal melanoma[J]. Chin J Exp Ophthalmol 201230(9)∶769773. DOI: 10.3760/cma.j.issn.2095-0160.2012.09.001 .
Goto CitationGoogle Scholar
Baidu Scholar
Wanfang Data
[31]
Vaquero-Garcia J Lalonde E Ewens KG et al. PRiMeUM:a model for predicting risk of metastasis in uveal melanoma[J]. Invest Ophthalmol Vis Sci 201758(10)∶40964105. DOI: 10.1167/iovs.17-22255 .
返回引文位置Google Scholar
百度学术
万方数据
[32]
Onken MD Worley LA Char DH et al. Collaborative Ocular Oncology Group report number 1:prospective validation of a multi-gene prognostic assay in uveal melanoma[J]. Ophthalmology 2012119(8)∶15961603. DOI: 10.1016/j.ophtha.2012.02.017 .
返回引文位置Google Scholar
百度学术
万方数据
[33]
Liu T Chen H Gomez C et al. Direct gene expression profile prediction for uveal melanoma from digital cytopathology images via deep learning and salient image region identification[J/OL]. Ophthalmol Sci 20233(1)∶100240[2024-07-13]. https://pubmed.ncbi.nlm.nih.gov/36561353/. DOI: 10.1016/j.xops.2022.100240 .
返回引文位置Google Scholar
百度学术
万方数据
[34]
Negretti GS Bayasi F Goldstein S et al. Association of Fitzpatrick Skin Type with metastatic risk from uveal melanoma in 854 consecutive patients at a single center[J]. Eye (Lond) 202438(3)∶565571. DOI: 10.1038/s41433-023-02735-1 .
返回引文位置Google Scholar
百度学术
万方数据
[35]
Luo J Zhang C Yang Y et al. Characteristics,treatments,and survival of uveal melanoma:a comparison between Chinese and American cohorts[J/OL]. Cancers (Basel) 202214(16)∶3960[2024-07-13]. https://pubmed.ncbi.nlm.nih.gov/36010953/. DOI: 10.3390/cancers14163960 .
返回引文位置Google Scholar
百度学术
万方数据
[36]
Oakden-Rayner L Dunnmon J Carneiro G et al. Hidden stratification causes clinically meaningful failures in machine learning for medical imaging[J]. Proc ACM Conf Health Inference Learn (2020) 20202020151159. DOI: 10.1145/3368555.3384468 .
返回引文位置Google Scholar
百度学术
万方数据
[37]
Neupane R Gaudana R Boddu S Imaging techniques in the diagnosis and management of ocular tumors:prospects and challenges[J/OL]. AAPS J 201820(6)∶97[2024-07-13]. https://pubmed.ncbi.nlm.nih.gov/30187172/. DOI: 10.1208/s12248-018-0259-9 .
返回引文位置Google Scholar
百度学术
万方数据
[38]
Shields CL Lim LS Dalvin LA et al. Small choroidal melanoma:detection with multimodal imaging and management with plaque radiotherapy or AU-011 nanoparticle therapy[J]. Curr Opin Ophthalmol 201930(3)∶206214. DOI: 10.1097/ICU.0000000000000560 .
返回引文位置Google Scholar
百度学术
万方数据
[39]
Gunasekeran DV Zheng F Lim G et al. Acceptance and perception of artificial intelligence usability in eye care (APPRAISE) for ophthalmologists:a multinational perspective[J/OL]. Front Med (Lausanne) 20229875242[2024-07-14]. https://pubmed.ncbi.nlm.nih.gov/36314006/. DOI: 10.3389/fmed.2022.875242 .
返回引文位置Google Scholar
百度学术
万方数据
[40]
Cioffi GM Pinilla-Echeverri N Sheth T et al. Does artificial intelligence enhance physician interpretation of optical coherence tomography:insights from eye tracking[J/OL]. Front Cardiovasc Med 2023101283338[2024-07-14]. https://pubmed.ncbi.nlm.nih.gov/38144364/. DOI: 10.3389/fcvm.2023.1283338 .
返回引文位置Google Scholar
百度学术
万方数据
[41]
Pettit RW Fullem R Cheng C et al. Artificial intelligence,machine learning,and deep learning for clinical outcome prediction[J]. Emerg Top Life Sci 20215(6)∶729745. DOI: 10.1042/ETLS20210246 .
返回引文位置Google Scholar
百度学术
万方数据
[42]
Gallée L Kniesel H Ropinski T et al. Artificial intelligence in radiology - beyond the black box[J]. Rofo 2023195(9)∶797803. DOI: 10.1055/a-2076-6736 .
返回引文位置Google Scholar
百度学术
万方数据
[43]
Tan TF Thirunavukarasu AJ Jin L et al. Artificial intelligence and digital health in global eye health:opportunities and challenges[J/OL]. Lancet Glob Health 202311(9)∶e1432e1443[2024-07-14]. https://pubmed.ncbi.nlm.nih.gov/37591589/. DOI: 10.1016/S2214-109X(23)00323-6 .
返回引文位置Google Scholar
百度学术
万方数据
备注信息
A
李永平,Email: mocdef.nabuyila1691ilgnipgnoy
B
所有作者均声明不存在利益冲突
评论 (0条)
注册
登录
时间排序
暂无评论,发表第一条评论抢沙发
MedAI助手(体验版)
文档即答
智问智答
机器翻译
回答内容由人工智能生成,我社无法保证其准确性和完整性,该生成内容不代表我们的态度或观点,仅供参考。
生成快照
文献快照

你好,我可以帮助您更好的了解本文,请向我提问您关注的问题。

0/2000

《中华医学会杂志社用户协议》 | 《隐私政策》

《SparkDesk 用户协议》 | 《SparkDesk 隐私政策》

网信算备340104764864601230055号 | 网信算备340104726288401230013号

技术支持:

历史对话
本文全部
还没有聊天记录
设置
模式
纯净模式沉浸模式
字号