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.

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.

Background/Objectives: This study aimed to develop a fully automatic method for liver tumor segmentation based on our previously developed gradient-enhanced network G-UNETR++. Methods: The proposed method consists of segmentation of the full liver region from computed tomography (CT) images using G-UNETR++, masking the CT images with the extracted liver region to exclude non-liver regions, and liver tumor segmentation from the masked CT images, also using G-UNETR++. To train and evaluate the model, a total of 131 CT scans (97 for training, 20 for validation, and 20 for testing) from the publicly available LiTS dataset were used. Furthermore, another public dataset, the 3DIRCADb dataset consisting of 20 CT scans was used for cross-validation of the effectiveness and generalizability of our method. Results: Experimental results showed that our method outperformed state-of-the-art models over both the LiTS dataset and the 3DIRCADb dataset, with an average dice score of 0.844 and 0.832 over the two datasets, respectively. Conclusions: The proposed method is effective in clinical application to help physicians with liver tumor diagnosis and treatment.

The success of deep learning requires large datasets and extensive training, which can create significant computational challenges. To address these challenges, pseudo-coresets, small learnable datasets that mimic the entire data, have been proposed. Bayesian Neural Networks, which offer predictive uncertainty and probabilistic interpretation for deep neural networks, also face issues with large-scale datasets due to their high-dimensional parameter space. Prior works on Bayesian Pseudo-Coresets (BPC) attempt to reduce the computational load for computing weight posterior distribution by a small number of pseudo-coresets but suffer from memory inefficiency during BPC training and sub-optimal results. To overcome these limitations, we propose Variational Bayesian Pseudo-Coreset (VBPC), a novel approach that utilizes variational inference to efficiently approximate the posterior distribution, reducing memory usage and computational costs while improving performance across benchmark datasets.