The present study measured 25 dimensions of the ear including the concha and ear canal for ergonomic design of ear products and compared with existing ear measurement studies. Scanning and casting methods were employed to produce 3D ear images for 230 Koreans and 96 Caucasians and measurements of the ear dimensions were obtained by identifying 21 landmarks on individual ear scan image. The Korean ear measurements were found significantly larger (mean difference $\overline{d}$ = 0.4–3.7 mm) and more varied (ratio of SDs =1.01–1.55) than those of Caucasians in most of ear dimensions. The average ear length and ear breadth of male were significantly longer ( $\overline{d}$ = 1.3–7.0 mm) and wider ( $\overline{d}$ = 0.8–3.0 mm) than those of female. Use of gender- and ethnicity-composite ear data is recommended in product design due to the much larger intra-population variations (7.5–22.2 mm) than the corresponding inter-population variations. Practitioner Summary: The 3D ear measurements of Koreans and Caucasians were collected and compared with those of different ethnic populations. The distinct ear features of the populations identified in this study are applicable to ergonomic design of ear products with better fit and comfort. Abbreviations: CCW: cavum concha width; CV: coefficient of variation; EB: ear breadth; EL: ear length; SD: standard deviation; SE: sampling error; 3D: 3 dimensional

The purpose of this study is to propose a framework for accurate and efficient vehicle distance estimation from a monocular camera. The proposed framework consists of a transformer-based object detector, a transformer-based depth estimator, and a distance predictor. The object detector detects various objects that are mostly symmetrical from an image captured by the monocular camera and provides the type of each object and the coordinate information of a bounding box around each object. The depth estimator generates a depth map for the image. Then, the bounding boxes are overlapped with the depth map to extract the depth features of each object, such as the mean depth, minimum depth, and maximum depth of each object. The present study then trained three models—eXtreme Gradient Boosting, Random Forest, and Long Short-Term Memory—to predict the actual distance between the object and the camera based on the type of the object, the bounding box of the object (including its coordinates and size), and the extracted depth features. The present study proposes including the trimmed mean depth of an object to predict the actual distance by excluding the background pixels around an object but within the bounding box of the object. The evaluation results show that the proposed framework outperformed existing studies.

Background/Objectives: Vision Transformers (ViTs) and convolutional neural networks (CNNs) have demonstrated remarkable performances in image classification, especially in the domain of medical imaging analysis. However, ViTs struggle to capture high-frequency components of images, which are critical in identifying fine-grained patterns, while CNNs have difficulties in capturing long-range dependencies due to their local receptive fields, which makes it difficult to fully capture the spatial relationship across lung regions. Methods: In this paper, we proposed a hybrid architecture that integrates ViTs and CNNs within a modular component block(s) to leverage both local feature extraction and global context capture. In each component block, the CNN is used to extract the local features, which are then passed through the ViT to capture the global dependencies. We implemented a gated attention mechanism that combines the channel-, spatial-, and element-wise attention to selectively emphasize the important features, thereby enhancing overall feature representation. Furthermore, we incorporated a multi-scale fusion module (MSFM) in the proposed framework to fuse the features at different scales for more comprehensive feature representation. Results: Our proposed model achieved an accuracy of 99.50% in the classification of four pulmonary conditions. Conclusions: Through extensive experiments and ablation studies, we demonstrated the effectiveness of our approach in improving the medical image classification performance, while achieving good calibration results. This hybrid approach offers a promising framework for reliable and accurate disease diagnosis in medical imaging.

Existing swallowing evaluation methods using X-ray or endoscopy are qualitative. The present study develops a swallowing monitoring and assessment system (SMAS) that is nonintrusive and quantitative. The SMAS comprises an ultrasonic Doppler sensor array, a microphone, and an inertial measurement unit to measure ultrasound signals originating only from swallowing activities. Ultrasound measurements were collected for combinations of two viscosity conditions (water and yogurt) and two volume conditions (3 mL and 9 mL) from 24 healthy participants (14 males and 10 females; age = 30.5 ± 7.6 years) with no history of swallowing disorders and were quantified for 1st peak amplitude, 2nd peak amplitude, peak-to-peak (PP) time interval, duration, energy, and proportion of two or more peaks. The peak amplitudes and energy significantly decreased by viscosity and the PP time interval and duration increased by volume. The correlation between the time measures were higher (r = 0.78) than that of the amplitude measures (r = 0.30), and the energy highly correlated with the 1st peak amplitude (r = 0.86). The proportion of two or more peaks varied from 76.8% to 87.9% by viscosity and volume. Further research is needed to examine the concurrent validity and generalizability of the ultrasonic Doppler sensor-based SMAS.

Accurate liver segmentation from computed tomography (CT) scans is essential for liver cancer diagnosis and liver surgery planning. Convolutional neural network (CNN)-based models have limited segmentation performance due to their localized receptive fields. Hybrid models incorporating CNNs and transformers that can capture long-range dependencies have shown promising performance in liver segmentation with the cost of high model complexity. Therefore, a new network architecture named G-UNETR++ is proposed to improve accuracy in liver segmentation with moderate model complexity. Two gradient-based encoders that take the second-order partial derivatives (the first two elements from the last column of the Hessian matrix of a CT scan) as inputs are proposed to learn the 3D geometric features such as the boundaries between different organs and tissues. In addition, a hybrid loss function that combines dice loss, cross-entropy loss, and Hausdorff distance loss is designed to address class imbalance and improve segmentation performance in challenging cases. The proposed method was evaluated on three public datasets, the Liver Tumor Segmentation (LiTS) dataset, the 3D Image Reconstruction for Comparison of Algorithms Database (3D-IRCADb), and the Segmentation of the Liver Competition 2007 (Sliver07) dataset, and achieved 97.38%, 97.50%, and 97.32% in terms of the dice similarity coefficient for liver segmentation on the three datasets, respectively. The proposed method outperformed the other state-of-the-art models on the three datasets, which demonstrated the strong effectiveness, robustness, and generalizability of the proposed method in liver segmentation.