(1) Background: Spondylolisthesis, a common disease among older individuals, involves the displacement of vertebrae. The condition may gradually manifest with age, allowing for potential prevention by the research of predictive algorithms. However, one key issue that hinders research in spondylolisthesis prediction algorithms is the need for publicly available spondylolisthesis datasets. (2) Purpose: This paper introduces BUU-LSPINE, a new dataset for the lumbar spine. It includes 3600 patients’ plain film images annotated with vertebral position, spondylolisthesis diagnosis, and lumbosacral transitional vertebrae (LSTV) ground truth. (4) Methods: We established an annotation pipeline to create the BUU-SPINE dataset and evaluated it in three experiments as follows: (1) lumbar vertebrae detection, (2) vertebral corner points extraction, and (3) spondylolisthesis prediction. (5) Results: Lumbar vertebrae detection achieved the highest precision rates of 81.93% on the AP view and 83.45% on the LA view using YOLOv5; vertebral corner point extraction achieved the lowest average error distance of 4.63 mm on the AP view using ResNet152V2 and 4.91 mm on the LA view using DenseNet201. Spondylolisthesis prediction reached the highest accuracy of 95.14% on the AP view and 92.26% on the LA view of a testing set using Support Vector Machine (SVM). (6) Discussions: The results of the three experiments highlight the potential of BUU-LSPINE in developing and evaluating algorithms for lumbar vertebrae detection and spondylolisthesis prediction. These steps are crucial in advancing the creation of a clinical decision support system (CDSS). Additionally, the findings demonstrate the impact of Lumbosacral transitional vertebrae (LSTV) conditions on lumbar detection algorithms.

Explainable artificial intelligence (XAI) techniques are used to understand the rationale behind the decision-making of machine learning models. In addition to the need for model explainability, the demand for an ever-growing number of multimodal features has dramatically increased model complexity. This underscores the importance of precise feature selection to ensure high model accuracy. Using our Approximate Inverse Model Explanations (AIME) technique, which currently presents the best XAI capability in the field, this study incorporated a novel backward and forward deletion process. This pre-assesses global feature importance by calculating and ordering their AIME-reported global importance. Through the backward deletion process, it assesses model accuracy by progressively eliminating less important features, resulting in a feature set configuration that guarantees the highest model accuracy. Then, the forward deletion process further refines the feature set by discarding the least important features until the he model’s accuracy declines, which reduces the computational burden and ensures optimal performance. We applied our method to the detailed and expansive Multimodal Emotion Line dataset and leveraged 4,870 facial, voice, and spoken language features in the Google Colab Pro+ environment to demonstrate AIME’s efficacy in enabling researchers to maximize both model explainability and performance: the holy grail of XAI.

Wearing a facial mask is indispensable in the COVID-19 pandemic; however, it has tremendous effects on the performance of existing facial emotion recognition approaches. In this paper, we propose a feature vector technique comprising three main steps to recognize emotions from facial mask images. First, a synthetic mask is used to cover the facial input image. With only the upper part of the image showing, and including only the eyes, eyebrows, a portion of the bridge of the nose, and the forehead, the boundary and regional representation technique is applied. Second, a feature extraction technique based on our proposed rapid landmark detection method employing the infinity shape is utilized to flexibly extract a set of feature vectors that can effectively indicate the characteristics of the partially occluded masked face. Finally, those features, including the location of the detected landmarks and the Histograms of the Oriented Gradients, are brought into the classification process by adopting CNN and LSTM; the experimental results are then evaluated using images from the CK+ and RAF-DB data sets. As the result, our proposed method outperforms existing cutting-edge approaches and demonstrates better performance, achieving 99.30% and 95.58% accuracy on CK+ and RAF-DB, respectively.

Depth estimation is a crucial step toward 3D scene understanding. Most traditional systems rely on direct sensing of this information by means of photogrammetry or on stereo imaging. As the scenes getting more complex, these modalities were impeded by, for instances, occlusion and imperfect lighting condition, etc. As a consequence, reconstructed surfaces are normally left with voids, due to missing data. Therefore, surface regularization is often required as post-processing. With the recent advances in deep learning, depth inference from a monocular image has attracted considerable interests. Many convolutional architectures have been proposed to infer depth information from a monocular image, with promising results. Thus far, visual cues learned and generalized by these networks may be ambiguous, resulting in inaccurate estimation. To address these issues, this paper presents an effective method for fusing point clouds extracted from depth values, directly measured by an infrared camera and estimated by a modified ResNet-50 from an RGB image, of the same scene. To ensure robustness and efficiency of finding the correspondence between and aligning these point clouds, an information theoretic alignment strategy, called CEICP, was proposed. The experimental results on a public dataset demonstrated that the proposed method outperformed its counterparts, while producing good quality surface renditions of the underlying scene.

The explainability of AI and machine learning models has become crucial, drawing significant attention to explainable AI (XAI) technologies. Global feature importance extraction is key to understanding the behavior of these models. However, existing XAI techniques often overlook the effects of multicollinearity in data, limiting their accuracy. We propose a method that combines approximate inverse model explanations (AIME) with hidden Markov models (HMMs). The HMMs are used to extract hidden states, and the local feature importance for each state is calculated. These values are then used to generate heuristics that adjust the importance of global features. We evaluated our method using the Wine Quality, Census Income, Gas Sensor Array Drift at Different Concentrations, and Breast Cancer Wisconsin datasets. The results showed that our method effectively handles strong multicollinearity and provides approximately 20% more accurate feature importance assessments than previous methods depending on the dataset. Therefore, our approach can better represent XAI contributions using algorithmic or human-supplied heuristics. Our study confirms that this approach is valid for XAI and enables the integration of algorithmic or human-supplied heuristics to realize XAI, which can significantly benefit various fields by enhancing model interpretability and decision-making processes.

Plain film X-ray scanners are indispensable for medical diagnostics and clinical procedures. This type of device typically produces two radiographic images of the human spine, including the anteroposterior and lateral views. However, these two photographs presented perspectives that were distinct. The proposed procedure consists of three fundamental steps. For automated cropping, the grayscale lumbar input image was initially projected vertically using its vertical pattern. Then, Delaunay triangulation was performed with the SURF features serving as the triangle nodes. The posture area of the vertebrae was calculated by utilizing the edge density of each node. The proposed method provided an automated estimation of the position of the human lumbar vertebrae, thereby decreasing the radiologist’s workload, computing time, and complexity in a variety of bone-clinical applications. Numerous applications can be supported by the results of the proposed method, including the segmentation of lumbar vertebrae pose, bone mineral density examination, and vertebral pose deformation. The proposed method can estimate the vertebral position with an accuracy of 80.32 percent, a recall rate of 85.37 percent, a precision rate of 82.36%, and a false-negative rate of 15.42 percent.