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.

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.

The aim of this study was to predict Bruch’s membrane opening-minimum rim Width (BMO-MRW), a relatively new parameter using conventional optical coherence tomography (OCT) parameter, using retinal nerve fibre layer (RNFL) thickness and visual field (VF) global indexes (MD, PSD, and VFI). We developed an interpretable machine learning model that integrates structural and functional parameters to predict BMO-MRW. The model achieved the highest predictive accuracy in the inferotemporal sector (R² = 0.68), followed by the global region (R² = 0.67) and the superotemporal sector (R² = 0.64). Through SHAP (SHapley Additive exPlanations) analysis, we demonstrated that RNFL parameters were significant contributing parameters to the prediction of various BMO-MRW parameters, with age and PSD also identified as critical factors. Our machine learning model could provide useful clinical information about the management of glaucoma when BMO-MRW is not available. Our machine learning model has the potential to be highly beneficial in clinical practice for glaucoma diagnosis and the monitoring of disease progression.

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 (adenocarcinoma, squamous cell carcinoma, small cell carcinoma, large cell neuroendocrine carcinoma) 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 evaluated the diagnostic performance of each model in the test sets. The Xception model achieved the highest performance among pre-trained CNNs with an accuracy of 0.86 and an area under the curve (AUC) of 0.97. The built from scratch CNN model obtained an accuracy of 0.92 and an AUC ranging from 0.99 to 1.00 for subtyping lung carcinoma tasks. These results demonstrate how promising CNN models are for developing improved diagnostic workflow systems for diagnosis and subtyping of lung carcinoma. Of particular note is the fact that the built from scratch CNN described in this paper achieves prompt and consistent results so has the potential to be applied in working hospitals for pathological diagnoses.