综述

人工智能在眼前段疾病的应用

Application of artificial intelligence in anterior segment ophthalmic diseases

:171-177
 
随着人工智能(artificial intelligence,AI)技术的快速发展,基于深度学习(deep learning,DL)和机器学习的AI技术在医学领域上的应用受到了广泛的关注。AI在眼科的应用也逐渐向更全面更深入的层次发展,通过角膜断层扫描、光学相干断层扫描、裂隙灯图像等技术,AI在对角膜病变、结膜病变、白内障、青光眼等眼部疾病的诊断和治疗方面都表现出了良好的性能。然而AI在眼科的应用方面也存在一些诸如结果可解释性的欠缺、数据集标准化的缺乏、数据集质量的不齐、模型适用性的不足和伦理问题等挑战。在5G和远程医疗飞速发展的时代,眼科AI同时也有许多新的机遇。本文综述了AI在前段眼科疾病中的应用、临床实施的潜在挑战和前景,为AI在眼科领域的进一步发展提供参考信息。
With the rapid development of artificial intelligence (AI) technology, the application of AI technology based on deep learning (DL) and machine learning (ML) in the medical field has received widespread attention. The application of AI in ophthalmology is gradually being shifted to a more comprehensive and in-depth level. Trained on corneal tomography, optical coherence tomography (OCT), slit-lamp images, and other techniques. AI can achieve robust performance in the diagnosis and treatment of corneal lesions, conjunctival lesions, cataract, glaucoma and other ophthalmic diseases. However, there are also some challenges in the application of AI in ophthalmology, including the lack of interpretability of results, lack of standardization of data sets, uneven quality of data sets, insufficient applicability of models and ethical issues. In the era of 5G and telemedicine, there are also many new opportunities for ophthalmic AI. In this review, we provided a summary of the state-of-the-art AI application in anterior segment ophthalmic diseases, potential challenges in clinical implementation and its development prospects, and provides reference information for the further development of artificial intelligence in the field of ophthalmology.
综述

人工智能在白内障手术治疗和教学中的应用与展望

Application and prospect of artificial intelligence in the treatment and teaching of cataract surgery

:178-184
 
人工智能(artificial intelligence,AI)在白内障手术中的应用越来越广泛,二者结合对于白内障手术的术前诊断和分级管理、术中人工晶状体选择、位置预测及术后管理(视力预测、并发症预测及随访)、手术培训和教学方面均起到巨大的促进作用。诚然,AI在与白内障手术相关的管理、分析和研究中还面临着许多问题,但其广泛的应用前景不可忽视。现对AI在白内障手术治疗和教学中的应用做以总结,并对其未来的发展做出展望。
Artificial intelligence (AI) has been widely used in cataract surgery. The combination of the two can play a great role in improving preoperative diagnosis, grading management of cataract surgery, intraoperative intraocular lens selection and location prediction, postoperative management (vision prediction, complication prediction and follow-up), surgical training and teaching. It is true that AI still faces many problems in the management, analysis and research related to cataract surgery, but its broad application prospects cannot be ignored. This review summarizes the application of AI in cataract surgery and teaching, and the future prospects of AI.
论著

发生于眶骨的占位性病变CT和病理表现及其相关性

Computed tomography and pathological manifestations of space-occupying lesions of the orbital bone and their relevance

:719-726
 
目的:分析发生于眶骨的占位性病变的CT表现及其与组织病理学之间的关系。方法:回顾性收集15例经临床表现、影像学特征、病理证实为发生于眶骨占位病变患者的临床资料,分析其CT检查、组织病理学切片及其他临床表现。结果:在15例患者中,经病理诊断为骨瘤的患者有4例,骨内血管瘤3例,骨样骨瘤和骨化性纤维瘤各2例,嗜酸性肉芽肿3例,尤文肉瘤1例。骨瘤由成熟板层骨构成,对应在CT上呈现为高密度的骨样结节状隆起;骨内血管瘤病理主要表现为骨小梁间的畸形血管,在CT上表现为典型的“栅栏状”“蜂窝状”特征;骨样骨瘤以骨样组织和结缔组织为主,在CT上为类圆形的高密度影,中央为典型的低密度“瘤巢“影,外周为增生的骨密度影;骨化性纤维瘤由增生的纤维组织及骨样组织构成,CT表现为肿瘤表面常有骨壳包绕,病变多呈圆形或椭圆形;嗜酸性肉芽肿主要由大量朗格汉斯细胞组成,对应CT上的软组织肿块影,可伴溶骨性破坏;尤文肉瘤以低分化的小圆细胞为主,CT表现为虫蚀样骨质破坏,破坏的骨组织间有软组织病变。结论:发生于眶骨的各类病变有其特有的病理组成,不同的病理组成在CT上表现出相应的影像特征。
Objective: To analyze computed tomography (CT) manifestations of space-occupying lesions of the orbital bone and their relationship with histopathology. Methods: The clinical data of 15 patients with orbital bone occupying lesions confirmed by clinical manifestations , imaging features and pathological symptoms features were retrospectively collected, and their CT examination, histopathological sections and other clinical manifestations were analyzed. Results: Among the 15 patients, 4 cases were pathologically diagnosed with osteoma, 3 cases of intraosseous hemangioma, 2 cases of osteoid osteoma and 2 cases of ossifying fibroma, 3 cases of eosinophilic granuloma and 1 case of Ewing’s sarcoma. Osteoma was composed of mature lamellar bones, which corresponded to a high-density osteoid nodular protuberance on CT. The pathological features of intraosseous hemangioma were mainly malformed blood vessels between bone trabeculae and typical “fence” and “honeycomb” features on CT. Osteoid osteoma was mainly composed of bone-like tissue and connective tissue, mainly showing round high-density shadow, typical low-density “tumor nest” shadow in the center, and hypertrophic bone density shadow in the periphery. Ossifying fibroma was composed of proliferative fibrous tissue and bone-like tissue. CT showed that the surface of the tumor was often surrounded by bone shell, and the lesions were mostly round or oval. Eosinophilic granuloma was mainly composed of a large number of Langerhans cells, which corresponded to the soft tissue mass on CT and could be accompanied by osteolytic destruction. Ewing’s sarcoma was mainly composed of poorly differentiated small round cells, and CT manifestations were worm-eaten bone destruction with soft tissue lesions between destroyed bone tissues. Conclusion: Various lesions occurring in the orbital bone have their own special pathological composition. Different pathological components show corresponding imaging features on CT.
论著

应用光学相干断层扫描血管成像评估视网膜血流的可重复性及再现性

Repeatability and reproducibility of quantification of superficial retinal capillaries using optical coherence tomography angiography

:439-448
 
目的:应用Cirrus HD-OCT 5000对正常眼黄斑及视盘血流参数进行血管成像测量,评估其可重复性及再现性。方法:纳入40只正常眼进行前瞻性研究。操作者A于一周内3天的同一时段(T1,T2,T3)对正常受试者的同一眼黄斑及视盘进行3次血管成像扫描,扫描过程中均开启FastTracTM图像跟踪功能,操作者B在T 2时间点再次对受试者同一眼进行相同程序扫描,使用Angio PlexMetrixTM量化软件(版本10.0)自动测量黄斑和视盘的血管长度密度(vessel length density,VD)和血管灌注密度(vascular perfusion density,PD)。应用单因素方差分析或非参数检验比较3次扫描的VD、PD是否有差异。采用组内相关系数(intraclass correlation coefficient,ICC)、变异系数(coefficient of variation,CV)评价操作者A的可重复性,采用一致性相关系数(consistent correlation coefficient,CCC)、重复性系数(repeatability coefficient,CR)、C V评价操作者间的再现性。结果:操作者A对黄斑及视盘各区域3次扫描的V D、P D之间差异无统计学意义(P >0.05)。操作者A对黄斑和视盘V D、PD 3次扫描的ICC值分别为0.260~0.517、0.362~0.898,黄斑及视盘各区域V D、P D的C V值均<8.1%。黄斑和视盘V D、P D的操作者间CCC值分别为0.3130~0.5665、0.5149~0.7801;黄斑VD和PD的CR值分别为3.2212~4.6399、0.0574~0.0832;视盘VD和PD的CR值分别为2.0675~4.0630、0.0447~0.0730。黄斑CV值均<9.0%,视盘CV值均<6.9%。结论:非同日的同一时段视盘浅层血流参数具有较好的重复性及再现性,黄斑浅层血流参数的重复性及再现性相对较差。
Objective: To evaluate the repeatability and reproducibility of quantification of macular and peri-papillary superficial capillaries in normal eyes using Cirrus HD-OCT 5000 angiography. Methods: Forty normal eyes were included in this prospective study. Angiography 3 mm × 3 mm scan protocol centered on the disc or macula of the same eye was repeated 3 times by operator A in the same period on 3 days (T1, T2, T3) within 1 week,and the FastTracTM image tracking function was turned on during the scan. Operator B repeated the same scan independently at T2 after operator A. Angio Plex MetrixTM quantification software (version 10.0) was used to automatically measure the vessel length density (VD) and vascular perfusion density (PD) of macular and peri-papillary superficial capillaries. One-way analysis of variance or nonparametric test was used to compare the VD and PD measurements of the 3 scans. The intraclass correlation coefficient (ICC) and coefficient of variation (CV)were calculated to evaluate the intra-operator repeatability. Consistent correlation coefficient (CCC), repeatability coefficient (CR), and CV were calculated to evaluate the inter-operator reproducibility. Results: There was no statistically significant difference in the measurements of VD and PD between the 3 scans of the macular and peri-papillary superficial capillaries by operator A (P>0.05). The ICC values for the 3 scans of VD and PD of the macular and peri-papillary superficial capillaries by operator A were 0.260–0.517 and 0.362~0.898, respectively.The CV values of the VD and PD of the macular and peri-papillary superficial capillaries were all <8.1%. The inter-operator CCC values of the macular and peri-papillary superficial capillaries were 0.3130–0.5665 and 0.5149~0.7801,respectively; the CR values of the VD and PD of macula were 3.2212–4.6399 and 0.0574–0.0832, respectively; the CR values of the VD and PD of optic disc were 2.0675–4.0630 and 0.0447–0.0730, respectively. The CV values of macular were all <9.0%, and the CV values of optic disc were all <6.9%. Conclusion:The macular and peri-papillary superficial capillaries parameters in the same period on different days have a good repeatability and reproducibility,while the superficial macular blood flow parameters have relatively poor repeatability and reproducibility.
论著

应用光学相干断层扫描血管成像评估视网膜血流的可重复性及再现性

Repeatability and reproducibility of quantification of superficial retinal capillaries using optical coherence tomography angiography

:439-448
 
目的:应用Cirrus HD-OCT 5000对正常眼黄斑及视盘血流参数进行血管成像测量,评估其可重复性及再现性。方法:纳入40只正常眼进行前瞻性研究。操作者A于一周内3天的同一时段(T1,T2,T3)对正常受试者的同一眼黄斑及视盘进行3次血管成像扫描,扫描过程中均开启FastTracTM图像跟踪功能,操作者B在T2时间点再次对受试者同一眼进行相同程序扫描,使用Angio Plex MetrixTM 量化软件(版本10.0)自动测量黄斑和视盘的血管长度密度(vessel length density,VD)和血管灌注密度(vascular perfusion density,PD)。应用单因素方差分析或非参数检验比较3次扫描的VD、PD是否有差异。采用组内相关系数(intraclass correlation coefficient,ICC)、变异系数(coefficient of variation,CV)评价操作者A的可重复性,采用一致性相关系数(consistent correlation coefficient,CCC)、重复性系数(repeatability coefficient,CR)、CV评价操作者间的再现性。结果:操作者A对黄斑及视盘各区域3次扫描的VD、PD之间差异无统计学意义(P>0.05)。操作者A对黄斑和视盘VD、PD 3次扫描的ICC值分别为0.260~0.517、0.362~0.898,黄斑及视盘各区域VD、PD的CV值均<8.1%。黄斑和视盘VD、PD的操作者间CCC值分别为0.3130~0.5665、0.5149~0.7801;黄斑VD和PD的CR值分别为3.2212~4.6399、0.0574~0.0832;视盘VD和PD的CR值分别为2.0675~4.0630、0.0447~0.0730。黄斑CV值均<9.0%,视盘CV值均<6.9%。结论:非同日的同一时段视盘浅层血流参数具有较好的重复性及再现性,黄斑浅层血流参数的重复性及再现性相对较差。
Objective: To evaluate the repeatability and reproducibility of quantification of macular and peri-papillary superficial capillaries in normal eyes using Cirrus HD-OCT 5000 angiography. Methods: Forty normal eyes were included in this prospective study. Angiography 3 mm × 3 mm scan protocol centered on the disc or macula of the same eye was repeated 3 times by operator A in the same period on 3 days (T1, T2, T3) within 1 week, and the FastTracTM image tracking function was turned on during the scan. Operator B repeated the same scan independently at T2 after operator A. Angio Plex MetrixTM quantification software (version 10.0) was used to automatically measure the vessel length density (VD) and vascular perfusion density (PD) of macular and peri-papillary superficial capillaries. One-way analysis of variance or nonparametric test was used to compare the VD and PD measurements of the 3 scans. The intraclass correlation coefficient (ICC) and coefficient of variation (CV) were calculated to evaluate the intra-operator repeatability. Consistent correlation coefficient (CCC), repeatability coefficient (CR), and CV were calculated to evaluate the inter-operator reproducibility. Results: There was no statistically significant difference in the measurements of VD and PD between the 3 scans of the macular and peri-papillary superficial capillaries by operator A (P>0.05). The ICC values for the 3 scans of VD and PD of the macular and peri-papillary superficial capillaries by operator A were 0.260–0.517 and 0.362~0.898, respectively. The CV values of the VD and PD of the macular and peri-papillary superficial capillaries were all <8.1%. The inter-operator CCC values of the macular and peri-papillary superficial capillaries were 0.3130–0.5665 and 0.5149~0.7801, respectively; the CR values of the VD and PD of macula were 3.2212–4.6399 and 0.0574–0.0832, respectively; the CR values of the VD and PD of optic disc were 2.0675–4.0630 and 0.0447–0.0730, respectively. The CV values of macular were all <9.0%, and the CV values of optic disc were all <6.9%. Conclusion: The macular and peri-papillary superficial capillaries parameters in the same period on different days have a good repeatability and reproducibility, while the superficial macular blood flow parameters have relatively poor repeatability and reproducibility.
其他期刊
  • 眼科学报

    主管:中华人民共和国教育部
    主办:中山大学
    承办:中山大学中山眼科中心
    主编:林浩添
    主管:中华人民共和国教育部
    主办:中山大学
    浏览
  • Eye Science

    主管:中华人民共和国教育部
    主办:中山大学
    承办:中山大学中山眼科中心
    主编:林浩添
    主管:中华人民共和国教育部
    主办:中山大学
    浏览
推荐阅读
出版者信息