Gastric cancer is a significant health concern, particularly in Korea, and its accurate detection is crucial for effective treatment. However, a gastroscopic biopsy can be time-consuming and may, thus, delay diagnosis and treatment. Thus, this study proposed a gastric cancer diagnostic method, CADx, to facilitate a more efficient image analysis. Owing to the challenges in collecting medical image data, small datasets are often used in this field. To overcome this limitation, we used AutoAugment’s ImageNet policy and applied cut-and-paste techniques using a sliding window algorithm to further increase the size of the dataset. The results showed an accuracy of 0.8317 for T-stage 1 and T-stage 4 image classification and an accuracy of 0.8417 for early gastric cancer and normal image classification, indicating improvements of 7 and 9%, respectively. Furthermore, through the application of test-time augmentation to the early gastric cancer and normal image datasets, the image classification accuracy was improved by 5.8% to 0.9000. Overall, the results of this study demonstrate the effectiveness of the proposed augmentation methods for enhancing gastric cancer classification performance.

Accurate pregnancy diagnosis is important for reproductive management in pig farming. This study evaluated a computer-aided diagnosis workflow using portable low-frequency ultrasound videos from 1895 sows at two sites. Xception frame predictions were aggregated into video-level decisions. Original, Preprocessing (wavelet denoising and contrast-limited adaptive histogram equalization), Mixup, and their combination (Combined) were compared across ten repeated sow-level splits. Combined achieved mean accuracies of 84.5% and 85.3% in Datasets A and B, respectively, with pregnant-sow videos restricted to days 18–25 post-insemination. Compared with Original, mean specificity increased by 1.3 and 2.4 percentage points and Youden’s index by 1.7 and 2.3 points, while mean sensitivity was numerically similar. Paired 95% confidence intervals for specificity and Youden’s index differences excluded zero only in Dataset B, without adjustment for multiple comparisons. Paired comparisons of the area under the curve (AUC) did not establish improved discrimination. Mixup yielded the highest mean specificity and AUC, whereas Combined yielded higher mean sensitivity than Mixup. This trade-off varied across partition subsets. Cross-site and leave-one-session-out evaluations showed performance variability across acquisition settings, with no consistently best condition. These comparisons identify configuration-dependent trade-offs requiring further evaluation for diagnostic support.