
浏览全部资源
扫码关注微信
陆军军医大学附属新桥医院血液病医学中心,重庆 400037
刘思恒,Email:26656379@qq.com, 研究方向:血液肿瘤诊断。
张 诚,Email:chzhang2014@163.com。
收稿:2022-01-11,
纸质出版:2022-08-28
移动端阅览
刘思恒,李佳,彭贤贵,等.探索Morphogo在多发性骨髓瘤MRD检测中的应用[J].重庆医科大学学报,2022,47(8):948-952.
Liu Siheng,Li Jia,Peng Xiangui,et al.Application of Morphogo in the detection of minimal residual disease in multiple myeloma[J].Journal of Chongqing Medical University,2022,47(8):948-952.
刘思恒,李佳,彭贤贵,等.探索Morphogo在多发性骨髓瘤MRD检测中的应用[J].重庆医科大学学报,2022,47(8):948-952. DOI: 10.13406/j.cnki.cyxb.003089.
Liu Siheng,Li Jia,Peng Xiangui,et al.Application of Morphogo in the detection of minimal residual disease in multiple myeloma[J].Journal of Chongqing Medical University,2022,47(8):948-952. DOI: 10.13406/j.cnki.cyxb.003089.
目的
2
探索人工智能骨髓细胞识别系统Morphogo应用于多发性骨髓瘤微小残留病(minimal residual disease,MRD)检测的临床价值及面临问题。
方法
2
收集已经由流式细胞术(multiparameter flow cytometry,MFC)检查后明确微小残留病结果的病例65例,调取其留存的骨髓瑞氏染色涂片,通过基于人工智能(artificial intelligence,AI)平台的分析系统Morphogo对所有骨髓涂片进行全自动扫描及细胞分类。AI及细胞形态学多发性骨髓瘤MRD阳性阈值设为浆细胞比例大于4.4%。按AI自动识别细胞数量将病例分为I 500组、I 1000组、I 2000组,每组病例的人工智能微小残留病(AI-MRD)、细胞形态学(morphology)微小残留病(M-MRD)和流式细胞术微小残留病(MFC-MRD)结果两两行Kappa一致性检验,并计算各组敏感度、特异度、准确度。分别以MFC-MRD和M-MRD结果为金标准绘制AI-MRD的受试者工作特征(receiver operating characteristic,ROC)曲线并计算其曲线下面积(area under the curve,AUC)。
结果
2
分组后AI-MRD vs. MFC-MRD 和AI-MRD vs. M-MRD的Kappa值、敏感度、特异度、准确度、AUC均随识别细胞数量的增加而增高,其中I 2000组AI-MRD vs. MFC-MRD的Kappa一致性检验结果为Kappa=0.500(
P
=0.013),敏感度为71%,特异度为80%,准确度为75%;AI-MRD vs. M-MRD的Kappa一致性检验结果为Kappa=0.667(
P
=0.001),敏感度为100%,特异度为75%,准确度为83%。以MFC-MRD结果为标准,I 2000组AI-MRD的ROC AUC=0.800(
P
=0.002,95%CI=0.588~0.934),M-MRD的ROC AUC=0.779(
P
=0.005,95%CI=0.564~0.921)。
结论
2
人工智能骨髓细胞识别系统Morphogo检测多发性骨髓瘤MRD具有细胞识别准确度高、速度快、成本低等特点,后续开发中应加入细胞组化染色、细胞免疫等技术提高人工智能多发性骨髓瘤微小残留病诊断的准确率。
Objective
2
To explore the application prospects and problems of artificial intelligence bone marrow cell recognition system,Morphogo,in the detection of minimal residual disease(MRD) of multiple myeloma.
Methods
2
A total of 65 cases of MRD of multiple myeloma confirmed by multiparameter flow cytometry(MFC) were collected,and their bone marrow Wright's staining smears were obtained. All bone marrow smears were automatically scanned and classified by Morphogo based on artificial intelligence platform. The positive threshold of MRD of AI and cytomorphology in multiple myeloma was set as the proportion of plasma cells,which was greater than 4.4%. The cases were divided into I 500 group,I 1000 group and I 2000 group according to the number of AI automatically recognized cells. The results of AI-MRD,morphological-MRD(M-MRD) and MFC-MRD in each group were tested by Kappa consistency test,and the sensitivity,specificity and accuracy of each group were calculated. Taking MFC-MRD and M-MRD results as the gold standard,the receiver operating characteristic (ROC) curve of AI-MRD was drawn and its area under the curve (AUC) value was calculated.
Results
2
After grouping,with the increase of the number of recognized cells,the Kappa value,sensitivity,specificity,accuracy and AUC of AI-MRD vs. MFC-MRD and AI-MRD vs. M-MRD increased. The Kappa consistency test of AI-MRD vs. MFC-MRD in I 2000 group showed that the Kappa value was 0.500(
P
=0.013),sensitivity was 71%,specificity was 80%,and accuracy was 75%. The Kappa consistency test results of AI-MRD vs. M-MRD showed that the Kappa value was 0.667(
P
=0.001),sensitivity was 100%,specificity was 75%,and accuracy was 83%. When MFC-MRD results were taken as the diagnostic criteria,the AUC of AI-MRD in I 2000 group was 0.800(
P
=0.002,95%CI=0.588-0.934),and the AUC of M-MRD was 0.779(
P
=0.005,95%CI=0.564-0.921).
Conclusion
2
The detection of MRD of multiple myeloma by Morphogo has the characteristics of high accuracy,high speed and low cost. In the follow-up development,it should be considered to develop technologies such as cell histochemical staining and cellular immunity,so as to improve the diagnostic accuracy of MRD of artificial intelligence multiple myeloma.
杨珮钰 , 刘蒙蒙 , 樊红琼 , 等 . 105例初诊多发性骨髓瘤患者微小残留病的动态监测及其预后价值 [J ] . 中华血液学杂志 , 2019 , 40 ( 7 ): 584 - 588 .
Yang PY , Liu MM , Fan HQ , et al . The prognostic significance of dynamic monitoring of minimal residual disease(MRD)status in patients with newly-diagnosed multiple myeloma [J ] . Chin J Hematol , 2019 , 40 ( 7 ): 584 - 588 .
Kumar S , Paiva B , Anderson KC , et al . International Myeloma Working Group consensus criteria for response and minimal residual disease assessment in multiple myeloma [J ] . Lancet Oncol , 2016 , 17 ( 8 ): e328 - e346 .
Ramesh AN , Kambhampati C , Monson JRT , et al . Artificial intelligence in medicine [J ] . Ann R Coll Surg Engl , 2004 , 86 ( 5 ): 334 - 338 .
Thrall JH , Li X , Li QZ , et al . Artificial intelligence and machine learning in radiology:opportunities,challenges,pitfalls,and criteria for success [J ] . J Am Coll Radiol JACR , 2018 , 15 ( 3 Pt B ): 504 - 508 .
Salto-Tellez M , Maxwell P , Hamilton P . Artificial intelligence-the third revolution in pathology [J ] . Histopathology , 2019 , 74 ( 3 ): 372 - 376 .
Fu XY , Fu M , Li Q , et al . Morphogo:an automatic bone marrow cell classification system on digital images analyzed by artificial intelligence [J ] . Acta Cytol , 2020 , 64 ( 6 ): 588 - 596 .
Girodon F , Favre B , Carli PM , et al . Minor dysplastic changes are frequently observed in the bone marrow aspirate in elderly patients without haematological disease [J ] . Clin Lab Haematol , 2001 , 23 ( 5 ): 297 - 300 .
Mateos MV , Cavo M , Blade J , et al . Overall survival with daratumumab,bortezomib,melphalan,and prednisone in newly diagnosed multiple myeloma(ALCYONE):a randomised,open-label,phase 3 trial [J ] . Lancet , 2020 , 395 ( 10218 ): 132 - 141 .
中国医师协会血液科医师分会 , 中华医学会血液学分会 , 中国医师协会多发性骨髓瘤专业委员会 . 中国多发性骨髓瘤诊治指南(2020年修订) [J ] . 中华内科杂志 , 2020 , 59 ( 5 ): 341 - 346 .
Chinese Hematology Association , Chinese Society of Hematology , Chinese Myeloma Committee-Chinese Hematology Association . The guidelines for the diagnosis and management of multiple myeloma in China(2020 revision) [J ] . Chin J Intern Med , 2020 , 59 ( 5 ): 341 - 346 .
常 亮 , 邓小明 , 周明全 , 等 . 图像理解中的卷积神经网络 [J ] . 自动化学报 , 2016 , 42 ( 9 ): 1300 - 1312 .
Chang L , Deng XM , Zhou MQ , et al . Convolutional neural networks in image understanding [J ] . Acta Autom Sin , 2016 , 42 ( 9 ): 1300 - 1312 .
杜忠华 , 张福明 , 吴 波 , 等 . 人工智能技术Morphogo系统在骨髓细胞形态学检查的临床应用 [J ] . 中国实验诊断学 , 2021 , 25 ( 7 ): 958 - 961 .
Du ZH , Zhang FM , Wu B , et al . Clinical application of artificial intelligence technology Morphogo system in morphological examination of bone marrow cells [J ] . Chin J Lab Diagn , 2021 , 25 ( 7 ): 958 - 961 .
唐 万 , 胡 俊 , 张 晖 , 等 . Kappa系数:一种衡量评估者间一致性的常用方法 [J ] . 上海精神医学 , 2015 , 27 ( 1 ): 62 - 67 .
Tang W , Hu J , Zhang H , et al . Kappa coefficient:a popular measure of rater agreement [J ] . Shanghai Arch Psychiatry , 2015 , 27 ( 1 ): 62 - 67 .
Krizhevsky A , Sutskever I , Hinton GE . ImageNet classification with deep convolutional neural networks [J ] . Commun ACM , 2017 , 60 ( 6 ): 84 - 90 .
Lin DJ , Johnson PM , Knoll F , et al . Artificial intelligence for MR image reconstruction:an overview for clinicians [J ] . J Magn Reson Imaging , 2021 , 53 ( 4 ): 1015 - 1028 .
Pantanowitz L , Farahani N , Parwani A . Whole slide imaging in pathology:advantages,limitations,and emerging perspectives [J ] . Pathol Lab Med Int , 2015 ( 7 ): 23 - 33 .
0
浏览量
3
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621