Background Visual inspection, lesion detection, and differentiation between malignant and benign features are key aspects of an endoscopist’s role. The use of machine learning for the recognition and differentiation of images has been increasingly adopted in clinical practice. This study aimed to establish convolutional neural network (CNN) models to automatically classify gastric neoplasms based on endoscopic images. Methods Endoscopic white-light images of pathologically confirmed gastric lesions were collected and classified into five categories: advanced gastric cancer, early gastric cancer, high grade dysplasia, low grade dysplasia, and non-neoplasm. Three pretrained CNN models were fine-tuned using a training dataset. The classifying performance of the models was evaluated using a test dataset and a prospective validation dataset. Results A total of 5017 images were collected from 1269 patients, among which 812 images from 212 patients were used as the test dataset. An additional 200 images from 200 patients were collected and used for prospective validation. For the five-category classification, the weighted average accuracy of the Inception-Resnet-v2 model reached 84.6 %. The mean area under the curve (AUC) of the model for differentiating gastric cancer and neoplasm was 0.877 and 0.927, respectively. In prospective validation, the Inception-Resnet-v2 model showed lower performance compared with the endoscopist with the best performance (five-category accuracy 76.4 % vs. 87.6 %; cancer 76.0 % vs. 97.5 %; neoplasm 73.5 % vs. 96.5 %; P < 0.001). However, there was no statistical difference between the Inception-Resnet-v2 model and the endoscopist with the worst performance in the differentiation of gastric cancer (accuracy 76.0 % vs. 82.0 %) and neoplasm (AUC 0.776 vs. 0.865). Conclusion The evaluated deep-learning models have the potential for clinical application in classifying gastric cancer or neoplasm on endoscopic white-light images.

Mammography plays an important role in screening breast cancer among females, and artificial intelligence has enabled the automated detection of diseases on medical images. This study aimed to develop a deep learning model detecting breast cancer in digital mammograms of various densities and to evaluate the model performance compared to previous studies. From 1501 subjects who underwent digital mammography between February 2007 and May 2015, craniocaudal and mediolateral view mammograms were included and concatenated for each breast, ultimately producing 3002 merged images. Two convolutional neural networks were trained to detect any malignant lesion on the merged images. The performances were tested using 301 merged images from 284 subjects and compared to a meta-analysis including 12 previous deep learning studies. The mean area under the receiver-operating characteristic curve (AUC) for detecting breast cancer in each merged mammogram was 0.952 ± 0.005 by DenseNet-169 and 0.954 ± 0.020 by EfficientNet-B5, respectively. The performance for malignancy detection decreased as breast density increased (density A, mean AUC = 0.984 vs. density D, mean AUC = 0.902 by DenseNet-169). When patients’ age was used as a covariate for malignancy detection, the performance showed little change (mean AUC, 0.953 ± 0.005). The mean sensitivity and specificity of the DenseNet-169 (87 and 88%, respectively) surpassed the mean values (81 and 82%, respectively) obtained in a meta-analysis. Deep learning would work efficiently in screening breast cancer in digital mammograms of various densities, which could be maximized in breasts with lower parenchyma density.

Colposcopy is widely used to detect cervical cancers, but experienced physicians who are needed for an accurate diagnosis are lacking in developing countries. Artificial intelligence (AI) has been recently used in computer-aided diagnosis showing remarkable promise. In this study, we developed and validated deep learning models to automatically classify cervical neoplasms on colposcopic photographs. Pre-trained convolutional neural networks were fine-tuned for two grading systems: the cervical intraepithelial neoplasia (CIN) system and the lower anogenital squamous terminology (LAST) system. The multi-class classification accuracies of the networks for the CIN system in the test dataset were 48.6 ± 1.3% by Inception-Resnet-v2 and 51.7 ± 5.2% by Resnet-152. The accuracies for the LAST system were 71.8 ± 1.8% and 74.7 ± 1.8%, respectively. The area under the curve (AUC) for discriminating high-risk lesions from low-risk lesions by Resnet-152 was 0.781 ± 0.020 for the CIN system and 0.708 ± 0.024 for the LAST system. The lesions requiring biopsy were also detected efficiently (AUC, 0.947 ± 0.030 by Resnet-152), and presented meaningfully on attention maps. These results may indicate the potential of the application of AI for automated reading of colposcopic photographs.

Pathologic myopia (PM) is one of the leading causes of visual impairment worldwide. The pathophysiology of PM is not fully understood, but the axial elongation of the eye followed by chorioretinal thinning is suggested as a key mechanism. Pathologic myopia may lead to many complications such as chorioretinal atrophy, foveoschisis, choroidal neovascularization, rhegmatogenous retinal detachment, cataract, and glaucoma. Some complications affect visual acuity significantly, showing poor visual prognosis. This article aims to review the types, pathophysiology, treatment, and visual outcome of the complications of PM.

Purpose.: To investigate the prevalence and risk factors of age-related macular degeneration (AMD) in the general Korean adult population. Methods.: The study involved a nationally representative Korean population from the 2010 to 2011 Korea National Health and Nutrition Examination Survey. A total of 7899 subjects ≥40 years old participated in health interviews, physical examinations, and ophthalmologic assessment including fundus photography. Results.: The overall prevalence of early AMD was estimated at 6.7% (95% confidence interval [CI], 6.1–7.4), and that of late AMD was estimated at 0.7% (95% CI, 0.5–0.9), which included 0.5% prevalence of neovascular AMD and 0.2% prevalence of geographic atrophy. The prevalence rates of early and late AMD among participants aged ≥65 years were 16.9% and 1.8%, respectively. Hyperopia was positively associated with the presence of any AMD type (odds ratio [OR], 1.08 for every 1 diopter increase). In multivariate analyses, significant risk factors for the presence of any AMD type were age, serum high-density lipoprotein (HDL) level, serum gamma-glutamyl transferase (GGT) level, and hepatitis B surface antigen (HBsAg) serum positivity (OR, 2.26). The risk factors for late AMD included age, ever-smoking history (OR, 2.18), serum GGT level, and systolic blood pressure. Conclusions.: The prevalence of AMD in Korea was similar to the prevalence of pooled Asian and Western populations. Age and serum GGT level were strongly associated with both the presence of any AMD and late AMD. Additionally, serum HDL level, HBsAg serum positivity, ever-smoking history, and systolic blood pressure were identified as risk factors for AMD.

Purpose: To investigate the effect of vitreous management on surgical outcomes after scleral fixation of posterior chamber intraocular lenses. Methods: The medical records of 83 eyes from 83 patients, who underwent scleral fixation of posterior chamber intraocular lenses without any preexisting vitreoretinal complication and were followed up for ≥6 months, were reviewed retrospectively. Subjects were divided according to the strategy used for vitreous management into a pars plana vitrectomy (PPV) group (47 eyes) and an anterior vitrectomy (AV) group (36 eyes). Surgical outcomes were compared between the groups. Results: Both groups were comparable regarding demographics, follow-up period, and underlying ocular disease. The degree of visual improvement was similar in both groups (P = 0.911). Postoperatively, each group developed a myopic shift, which was greater in the PPV group than in the AV group (P = 0.040). Intraocular pressure elevations ≥25 mmHg occurred in 50% of eyes in the AV group and in 11% of eyes in the PPV group (P < 0.001). Intraocular lenses dislocated more frequently in the AV group (28%) than in the PPV group (9%; P = 0.036). Intraocular lens capture was more common in the PPV group (23%) than in the AV group (3%; P = 0.010). There was no significant difference in the rate of postoperative vitreoretinal complications. Conclusion: In eyes that received scleral fixation of posterior chamber intraocular lenses, PPV decreased the chances of postoperative intraocular pressure elevation and intraocular lens dislocation but increased the likelihood of intraocular lens capture and the magnitude of postoperative myopic shift.