Visually impaired and blind people due to diabetic retinopathy were 2.6 million in 2015 and estimated to be 3.2 million in 2020 globally. Though the incidence of diabetic retinopathy is expected to decrease for high-income countries, detection and treatment of it in the early stages are crucial for low-income and middle-income countries. Due to the recent advancement of deep learning technologies, researchers showed that automated screening and grading of diabetic retinopathy are efficient in saving time and workforce. However, most automatic systems utilize conventional fundus photography, despite ultra-wide-field fundus photography provides up to 82% of the retinal surface. In this study, we present a diabetic retinopathy detection system based on ultra-wide-field fundus photography and deep learning. In experiments, we show that the use of early treatment diabetic retinopathy study 7-standard field image extracted from ultra-wide-field fundus photography outperforms that of the optic disc and macula centered image in a statistical sense.
Stevens-Johnson syndrome (SJS) and its severe variant, toxic epidermal necrolysis (TEN), are acute inflammatory vesiculobullous reactions of the skin and mucous membranes. Cold medicines including non-steroidal anti-inflammatory drugs and multi-ingredient cold medications are reported to be important inciting drugs. Recently, we reported that cold medicine related SJS/TEN (CM-SJS/TEN) with severe mucosal involvement including severe ocular surface complications (SOC) is associated with HLA-A*02:06 and HLA-B*44:03 in the Japanese. In this study, to determine whether HLA-B*44:03 is a common risk factor for CM-SJS/TEN with SOC in different ethnic groups we used samples from Indian, Brazilian, and Korean patients with CM-SJS/TEN with SOC, and investigated the association between CM-SJS/TEN with SOC and HLA-B*44:03 and/or HLA-A*02:06. We found that HLA-B*44:03 was significantly associated with CM-SJS/TEN with SOC in the Indian and Brazilian but not the Korean population, and that HLA-A*02:06 might be weakly associated in the Korean- but not the Indian and Brazilian population.