To date, for the diagnosis of dentofacial dysmorphosis, we have relied almost entirely on reference points, planes, and angles. This is time consuming, and it is also greatly influenced by the skill level of the practitioner. To solve this problem, we wanted to know if deep neural networks could predict postoperative results of orthognathic surgery without relying on reference points, planes, and angles. We use three-dimensional point cloud data of the skull of 269 patients. The proposed method has two main stages for prediction. In step 1, the skull is divided into six parts through the segmentation network. In step 2, three-dimensional transformation parameters are predicted through the alignment network. The ground truth values of transformation parameters are calculated through the iterative closest points (ICP), which align the preoperative part of skull to the corresponding postoperative part of skull. We compare pointnet, pointnet++ and pointconv for the feature extractor of the alignment network. Moreover, we design a new loss function, which considers the distance error of transformed points for a better accuracy. The accuracy, mean intersection over union (mIoU), and dice coefficient (DC) of the first segmentation network, which divides the upper and lower part of skull, are 0.9998, 0.9994, and 0.9998, respectively. For the second segmentation network, which divides the lower part of skull into 5 parts, they were 0.9949, 0.9900, 0.9949, respectively. The mean absolute error of transverse, anterior–posterior, and vertical distance of part 2 (maxilla) are 0.765 mm, 1.455 mm, and 1.392 mm, respectively. For part 3 (mandible), they were 1.069 mm, 1.831 mm, and 1.375 mm, respectively, and for part 4 (chin), they were 1.913 mm, 2.340 mm, and 1.257 mm, respectively. From this study, postoperative results can now be easily predicted by simply entering the point cloud data of computed tomography.

In this paper, a method using a semantic segmentation method based on edge-region focal loss was proposed to estimate the heading angle of resin in a catheter-extrusion process. The approach leveraged an improved semantic segmentation facilitated by this new loss function and principal component analysis. Accurate heading angle estimation was critical and depended on the precision of segmentation, demanding robust and precise segmentation even in the presence of external disturbances. The edge-region focal loss enhanceed segmentation by heavily weighting areas with ambiguous boundaries, which was particularly important in scenarios with various semantic elements in the background and foreground or near object boundaries. Image data were collected using RGB cameras to validate the effectiveness of this method. The method’s accuracy was affirmed by the mean intersection over union (mIoU) and mean absolute error measurements, achieving mean absolute errors of the angle and mIoU at 0.5002 and 0.8657, respectively. These results demonstrate the method’s suitability for monitoring the extrusion process. Furthermore, compared to traditional loss functions, the edge-region focal loss shows superior performance in segmenting adjacent boundary regions between the background and objects and maintains robustness in noisy environments.

Estimating metric depth for safety-relevant targets from a top-view crane camera is challenging because monocular predictions are scale-ambiguous and target regions of interest (RoIs) mix returns from payloads, personnel, hoisting wires, and the ground. We present a target-focused pipeline in which a detector defines RoIs, a dense metric-depth map is predicted, and one representative depth is extracted per object. A DINOv2–DPT relative-depth network is fixed, while a multiscale adapter, DINO detection branch, and pixel-wise spatial affine calibration head are trained. Ground-truth bounding boxes restrict metric supervision to target-relevant regions but are not inputs to the calibration head. At evaluation, all depth methods use identical predicted RoIs, and a class-aware kernel-density estimation rule extracts representative depths. On 272 hardware-synchronized RGB–LiDAR frames from one operational 150-ton crane, the proposed method achieved a target-level RMSE of 0.564 m and a pixel-level inlier ratio of 0.966 for $\delta <1.25$. One-to-one ground-truth matching yielded a 0.566 m target RMSE with detection precision/recall of 0.960/0.970. AdaBins obtained lower pixel-level MAE and RMSE, whereas the proposed method obtained lower target-level errors. These results demonstrate the feasibility of target-focused metric ranging under the evaluated operational crane conditions.