At present, artificial intelligence (AI) has been widely used in the diagnosis and treatment of various ophthalmological diseases, but there are still many problems. Due to the lack of standardized test sets, gold standards, and recognized evaluation systems for the accuracy of AI products, it is difficult to compare the results of multiple studies. When it comes to the field of image generation, we hardly have an efficient approach to evaluating research results. In clinical practice, ophthalmological AI research is often out of touch with actual clinical needs. The requirements for the quality and quantity of clinical data put more burden on AI research, limiting the transformation of AI studies. The prediction of systemic diseases based on fundus images is making progressive advancement. However, the lack of interpretability of the research lower the acceptance. Ophthalmology AI research also suffer from ethical controversy due to unconstructed regulations and regulatory mechanisms, concerns on patients’ privacy and data security, and the risk of aggravating the unfairness of medical resources.
Ultra-wide field fundus autofluorescence (FAF) imaging is a new noninvasive technique with an imaging range of about 200 °. It can detect peripheral retinal lesions that cannot be found in previous FAFs and more objectively reflect intracellular content and distribution of lipofuscin in the retinal pigment epithelium (RPE) and RPE cell metabolic status. The ultra-wide field FAF can find the abnormal autofluorescence (AF) in the peripheral retina of the eyes of age-related macular degeneration (AMD), and different AF manifestations may have an impact on the diagnosis and treatment of the different AMD subtypes. It is helpful to evaluate subretinal fluid in the eyes of central serous choroidal retinopathy and can accurately detect the changes in the outer retina of the eyes without subretinal fluid. It can help to determine the type of uveitis and fully display the evolution of the disease. It can also assess the peripheral photoreceptor cell layer and RPE in patients with retinal dystrophy and retinitis pigmentosa, and comprehensively evaluate their retinal function and monitor the progress of disease. It can also assist in the evaluation of the short-term efficacy and RPE cell function after the scleral buckling surgery for patients with rhegmatogenous retinal detachment. In the future, ultra-wide field FAF may change the knowledge and intervention strategy of ocular fundus diseases and promote the clinical and scientific research in this field.
With the rapid development of artificial intelligence (AI), especially deep learning, AI research in the field of ophthalmology has presented a trend of diversification in disease types, generalization in scenarios and deepening in researches. The AI algorithm has showed a good performance in the studies of diabetic retinopathy, age-related macular degeneration, glaucoma and other ocular diseases, yielding up the great potential of ophthalmic AI. However, most studies are still in their infancy, and the application of ophthalmic AI still faces many challenges such as lack of interpretability for results, deficiency of data standardization, and insufficiency of clinical applicability. At the same time, it should also be noted that the development of multi-modal imaging, the innovation of digital technologies (such as 5G and the Internet of Things) and telemedicine, and the new discovery that retina status can reflect systemic diseases have brought new opportunities for the development of ophthalmic AI. Learn the current status of AI research in the field of ophthalmology, grasp the new challenges and opportunities in its development process, successfully realizing the transformation of ophthalmic AI from research to practical application.
【摘要】目的探讨实时超声弹性成像在淋巴结疾病诊断中的应用价值。 方法分析2008年2月4月27例淋巴结疾病患者的65个淋巴结病灶超声弹性图表现,弹性图分级为0~Ⅳ级,弹性图分型为Ⅰ~Ⅲ型。所有淋巴结均经术后病理学或细针抽吸细胞学检查证实,或经随访证实。结果转移性淋巴结弹性分级较高,≥Ⅲ级11/13,占84.62％;淋巴瘤性淋巴结弹性分级较低,≤Ⅱ级16/21,占76.19％。转移性淋巴结中Ⅱ型7/13,占53.85％,转移性淋巴结占全部Ⅱb型的54.55%(6/11);淋巴瘤性淋巴结中Ⅱ型13/21,占61.90％,淋巴瘤性淋巴结占全部Ⅱa型的73.33％(11/15);反应性淋巴结占全部Ⅰa型的68.18％(15/22)。结论实时超声弹性成像能为淋巴结疾病的诊断提供一定信息,弹性图分级对鉴别良恶性淋巴结有统计学意义,分型对于鉴别特定类型淋巴结疾病有一定提示作用。
Optical coherence tomography (OCT) has developed from time-doma in into Fourier-domain OCT (FD-OCT) which indicates clearer details and higher resolution of images. FD-OCT can indicate the structure and pathological changes of each retinal layer, and reveal the retinal external limiting membranes and changes of inner- and outer-segment of visual cells by 3D solid reconstruction. FD-OCT not only provide detailed information of the images for the clinical diagnosis, but also help us investigting the characteristics and pthological mechanisms of ocular fundus diseases, which lead us to a new era of technology of observation on ocualr fundus diseases. In the application, we should pay attention to the significance of different colors of OCT images, and focus on the cohenrence of the position in the image acquistion during the follow-up period. Dynamic observation on the lesions by FD-OCT and aggregated anaylsis of resutls of several imageological examination would be the development direction of imageological examination of ocular fundus diseases.
ObjectiveTo observe the demographic data, disease composition and convenience of remote consultation in ophthalmology. MethodsA retrospective study. From 2015 to 2021, the demographic data, changing trends, disease classification of teleconsultation patients, and hospitals participating in teleconsultation, and the waiting time of patients for teleconsultation was analyzed retrospectively; remote consultation physician level composition and other data was analyzed. ResultsDuring the 7-year period, 1 216 patients with remote consultation were obtained through the platform of the telemedicine center. Among them, there were 680 males and 536 females; the average age was 50.8 years. In 2016 and 2017, the number of patients participating in telemedicine consultations reached a peak of 260 and 221 cases, respectively. Among the ophthalmic diseases, there were 490 cases (40.30%, 490/1 216) of retinal and optic nerve-related diseases, 212 cases (17.43%, 212/1 216) of ocular trauma. 678 cases (56.27%, 678/1 205) of remote consultation waiting time were less than 24 hours, 991 cases (82.24%, 991/1 205) were less than 48 hours. Among the physicians who participated in the remote consultation, there were 733 chief physicians (60.3%, 733/1 216) and 466 deputy chief physicians (38.3%, 466/1 216). ConclusionsDuring the seven-year period from 2015 to 2021, there are relatively few patients with ophthalmology teleconsultation; retinal and optic nerve-related diseases accounted for a high proportion. Remote consultation has high convenience.
Optical imaging technology of ocular fundus, including fundus fluorescein angiography (FFA), optical coherence tomography (OCT) and fundus autofluorescence (FAF), is growing at an unprecedented speed and scale and is integrating into the routine clinical management of ocular fundus diseases, such as diagnosis, treatment, and mechanism study. While FFA allow us to observe the retinal and choroidal blood circulation, OCT and FAF are non-invasive, fast and quantifiable measurement; such techniques show even more unique advantages and are favored tools. All these retinal imaging technologies, together with a variety of retinal function assessments, bring us into the era of big data of ocular fundus diseases. All of these developments are the challenges and opportunities for the operator and user of these fundus optics imaging technologies. In order to improve its clinical applications and allocate resources rationally, we need to understand the optical properties of these retinal imaging technologies, and standardize diagnosis behavior. This is a continuous learning process needs to continue to explore.