We aimed to classify early normal-tension glaucoma (NTG) and glaucoma suspect (GS) using Bruch’s membrane opening-minimum rim width (BMO-MRW), peripapillary retinal nerve fiber layer (RNFL), and the color classification of RNFL based on a deep-learning model. Discriminating early-stage glaucoma and GS is challenging and a deep-learning model may be helpful to clinicians. NTG accounts for an average 77% of open-angle glaucoma in Asians. BMO-MRW is a new structural parameter that has advantages in assessing neuroretinal rim tissue more accurately than conventional parameters. A dataset consisted of 229 eyes out of 277 GS and 168 eyes of 285 patients with early NTG. A deep-learning algorithm was developed to discriminate between GS and early NTG using a training set, and its accuracy was validated in the testing dataset using the area under the curve (AUC) of the receiver operating characteristic curve (ROC). The deep neural network model (DNN) achieved highest diagnostic performance, with an AUC of 0.966 (95%confidence interval 0.929–1.000) in classifying either GS or early NTG, while AUCs of 0.927–0.947 were obtained by other machine-learning models. The performance of the DNN model considering all three OCT-based parameters was the highest (AUC 0.966) compared to the combinations of just two parameters. As a single parameter, BMO-MRW (0.959) performed better than RNFL alone (0.914).

Identifying the lung carcinoma subtype in small biopsy specimens is an important part of determining a suitable treatment plan but is often challenging without the help of special and/or immunohistochemical stains. Pathology image analysis that tackles this issue would be helpful for diagnoses and subtyping of lung carcinoma. In this study, we developed AI models to classify multinomial patterns of lung carcinoma; ADC, LCNEC, SCC, SCLC, and non-neoplastic lung tissue based on convolutional neural networks (CNN or ConvNet). Four CNNs that were pre-trained using transfer learning and one CNN built from scratch were used to classify patch images from pathology whole-slide images (WSIs). We first evaluated the diagnostic performance of each model in the test sets. The Xception model and the CNN built from scratch both achieved the highest performance with a macro average AUC of 0.90. The CNN built from scratch model obtained a macro average AUC of 0.97 on the dataset of four classes excluding LCNEC, and 0.95 on the dataset of three subtypes of lung carcinomas; NSCLC, SCLC, and non-tumor, respectively. Of particular note is that the relatively simple CNN built from scratch may be an approach for pathological image analysis.

PurposeWe aimed to investigate the performance of a deep learning model to discriminate early normal-tension glaucoma (NTG) from glaucoma suspect (GS) eyes using Bruch’s membrane opening (BMO)-based optic disc photography.Methods501 subjects in total were included in this cross-sectional study, including 255 GS eyes and 246 eyes of early NTG patients. BMO-based optic disc photography (BMO overview) was obtained from spectral-domain optical coherence tomography (OCT). The convolutional neural networks (CNN) model built from scratch was used to classify between early NTG and GS. For diagnostic performances of the model, the accuracy and the area under the curve (AUC) of the receiver operating characteristic curve (ROC) were evaluated in the test set.ResultsThe baseline demographics were age, 48.01 ± 13.03 years in GS, 54.48 ± 11.28 years in NTG (p = 0.000); mean deviation, −0.73 ± 2.10 dB in GS, −2.80 ± 2.40 dB in NTG (p = 0.000); and intraocular pressure, 14.92 ± 2.62 mmHg in GS, 14.79 ± 2.61 mmHg in NTG (p = 0.624). Our CNN model showed the mean AUC of 0.94 (0.83–1.00) and the mean accuracy of 0.91 (0.82–0.98) with 10-fold cross validation for discriminating between early NTG and GS.ConclusionThe performance of the CNN model using BMO-based optic disc photography was considerably good in classifying early NTG from GS. This new disc photography of BMO overview can aid in the diagnosis of early glaucoma.

In many small- and medium-sized enterprises (SMEs), defective products are still manually verified in the manufacturing process. Recently, image classification applying deep learning technology has been successful in classifying images of defective and intact products, although there are few cases of utilizing it in practice. SMEs have limited resources; therefore, it is crucial to make careful decisions when applying new methods. We investigated sample size sensitivity to determine the stable performance of deep learning models when applied to the real world. A simple sequential model was constructed, and the dataset was reconstructed into several sizes. For each case, we observed its statistical indicators, such as accuracy, recall, precision, and F1 score, on the same test dataset. Additionally, the loss, accuracy, and AUROC values for the validation dataset were investigated during training. As a result of the conducted research, we were able to confirm that, with 1000 data points or more, the accuracy exceeded 97%. However, more than 5000 cases were required to achieve stability in the model, which had little possibility of overfitting.

No abstract