Ophthalmic imaging examination is the main basis for early screening, evaluation and diagnosis of eye diseases. In recent years, with the improvement of computer data analysis ability, the deepening of new algorithm research and the popularization of big data platform, artificial intelligence (AI) technology has developed rapidly and become a hot topic in the field of medical assistant diagnosis. The advantage of AI is accurate and efficient, which has great application value in processing image-related data. The application of AI not only helps to promote the development of AI research in ophthalmology, but also helps to establish a new medical service model for ophthalmic diagnosis and promote the process of prevention and treatment of blindness. Future research of ophthalmic AI should use multi-modal imaging data comprehensively to diagnose complex eye diseases, integrate standardized and high-quality data resources, and improve the performance of algorithms.
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.
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 fluorescein angiography (UWFA) can obtain very wide retinal images (up to 200°), and is a very helpful tool to detect peripheral retinal lesions which cannot be found by other imaging methods. Analyzing the characteristics of the UWFA images may improve our understanding, treatment outcomes and management strategies of ocular fundus diseases. However this technology is still in its premature stage, there is still a lot of work to be done to improve its clinical application and study the characteristics and clinical meanings of these peripheral retinal lesions.
The hallmark of the recent latest advances in diagnostic fundus imaging technology is combination of complex hierarchical levels and depths, as well as wide-angle imaging, ultra-wide imaging. The clinical application of wide-angle and ultra-wide imaging, not only can reevaluate the role of the peripheral retina, the classification types and treatment modalities of central retinal vein occlusion, and enhance the reliability of diabetic retinopathy screening, improve the classification and therapeutic decision of diabetic retinopathy, and but also can help guide and improve laser photocoagulation. However we must clearly recognize that the dominant role of ophthalmologists in the diagnosis of ocular fundus diseases cannot be replaced by any advanced fundus imaging technology including wide-angle imaging. We emphasize to use the three factors of cognitive performance (technology, knowledge and thinking) to improve the diagnosis of ocular fundus diseases in China.
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.
Ultra-wide-field fluorescein angiography (UWFA) is a novel breakthrough in ocular fundus imaging technology, which can capture a single, high-resolution, 200° wide image of the ocular fundus that traditional fluorescein angiography cannot reach. This technology has important impacts on the screening, diagnosis, staging, treatment and follow-up of vascular diseases involving peripheral retina (such as diabetic retinopathy, age-related macular degeneration, retinal vein occlusion, uveitis and so on).
Objective To investigate the characteristics of ultrasonogram of eyes with silicon oil tamponade. Methods Forty-seven patients (47 eyes) who had undergone the operation of silicon-oil removing were examined by A-(to determine the length of ocular axis) and B-scan before and after the operation respectively. The length of ocular axis and cubage of vitreous chamber were detected and the characteristics of the ultrasonograms were observed according to the default parameters of ultrasonograph. Results The results of A-scan showed that the preoperative axial length was 1.465 times of the postoperative one in the eyes without lens, and 1.284 times in eyes with lens; after modified the parameter according to the acoustic velocity, the preoperative axial length was (0.78±0.34) mm longer than the postoperative one in the eyes without lens, and (0.56±0.32) mm in eyes with lens. The results of A-scan showed that the cubage of vitreous chamber enlarged obviously in eyes with silicon oil tamponade, and the acoustic features included complete filling and partial filling according to the amount of silicon oil. Several arc echoes at the posterior segment of eye were detected in the silicon-oil-filling eyes with retinal detachment. Conclusion In the silicon-oil-filling eyes with lengthened ocular axis, the characteristics of B-scan images are affected by acoustic velocity through silicon oil, the amount of silicon oil capacity and the emulsification of silicon oil. (Chin J Ocul Fundus Dis，2004，20：349-351)
ObjectiveTo analyze the consistency of diagnostic results using simple and comprehensive reading methods on stereoscopic color fundus photographs of diabetic retinopathy (DR) with diabetic macular edema (DME).
Methods450 sets of 7-field stereoscopic color fundus photographs of DR DME were compared to standard fundus photographs of early treatment and DR study group. The pictures were read by two groups of reader with similar experience. Two strategies were used to make the judgments, including simple reading which based on the color fundus photographs only, and comprehensive reading which based on color fundus photographs, fundus fluorescein angiography (FFA) and optical coherence tomography (OCT). 15 parameters were scored, including micro-aneurysms (MA), intra-retinal hemorrhage (IRH), hard exudates (HE), cotton wood spot (CW), intra-retinal microvascular abnormalities (IRMA), neovascularization on optic disc (NVD), neovascularization elsewhere (NVE), optic fiber proliferation (FPD), fiber proliferation elsewhere (FPE), pre-retinal hemorrhage (PRH), vitreous hemorrhage (VH), retinal elevation (RE), retinal detachment of central macular (RDC), venous beading (VB), Venous leak (VL). The reliability was evaluated using weighted κ(κw) statistic values. According to Fleiss statistical theory, κw≥0.75, consistency is excellent; 0.60≤κw < 0.75, consistency is good; 0.40≤κw < 0.60, consistency is general; κw < 0.40, consistency is poor.
ResultsThe κw values of these 15 parameters were 0.22-1.00, 0.28-1.00 for the simple reading and comprehensive reading respectively. For simple reading, the consistency was poor for 8 parameters (MA, NVD, NVE, FPE, PRH, IRMA, VB, VL), general for 3 parameters (CW, FPD, VH), good for 2 parameters (IRH, HE) and excellent for 2 parameters (RE, RDC). For comprehensive reading, the consistency was poor for 2 parameters (NVE, VB), general for 6 parameters (MA, IRH, CW, FPE, IRMA, VL), good for 2 parameters (NVD, HE), excellent for 5 parameters (FPE, PRH, VH, RE, RDC).
ConclusionThe comprehensive reading has higher consistency to judge the abnormality parameters of the fundus photographs of DR with DME.
Using optical imaging equipment with different wavelength and computer technology, fundus optical imaging diagnostic techniques can record fundus reflected light, auto fluorescence and emitted light after excitation by external light source in order to observe and analyze the structure and pathological process of retina and choroid. Advances in fundus optical image capture technology (including laser, confocal laser, spontaneous auto-fluorescence, multispectral imaging) and storage and analysis technology, promote this field into a high-definition digital imaging era, with features of rapid, non-invasive, wide-angle three-dimensional multi-level integration, dynamic automatic navigation location tracking and combined application of a variety of optical imaging diagnostic techniques. In order to promote clinical and scientific research of ocular fundus diseases, we need to understand the development trend of optical imaging diagnostic technique, interpret the fundus imaging features appropriately, reasonably chose different inspection techniques, establish standardized diagnosis criteria and continue to expand clinical applications.
