The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features using vanilla convolution, it cannot achieve adaptive feature learning. Second, although a Transformer branch can capture the global features, it ignores the channel and cross-dimensional self-attention, resulting in a low segmentation accuracy on complex-content images. To address these challenges, we propose a novel hybrid architecture of convolutional neural networks hand in hand with vision Transformers (CiT-Net) for medical image segmentation. Our network has two advantages. First, we design a dynamic deformable convolution and apply it to the CNNs branch, which overcomes the weak feature extraction ability due to fixed-size convolution kernels and the stiff design of sharing kernel parameters among different inputs. Second, we design a shifted-window adaptive complementary attention module and a compact convolutional projection. We apply them to the Transformer branch to learn the cross-dimensional long-term dependency for medical images. Experimental results show that our CiT-Net provides better medical image segmentation results than popular SOTA methods. Besides, our CiT-Net requires lower parameters and less computational costs and does not rely on pre-training. The code is publicly available at https://github.com/SR0920/CiT-Net.

Popular semi-supervised medical image segmentation networks often suffer from error supervision from unlabeled data since they usually use consistency learning under different data perturbations to regularize model training. These networks ignore the relationship between labeled and unlabeled data, and only compute single pixel-level consistency leading to uncertain prediction results. Besides, these networks often require a large number of parameters since their backbone networks are designed depending on supervised image segmentation tasks. Moreover, these networks often face a high over-fitting risk since a small number of training samples are popular for semi-supervised image segmentation. To address the above problems, in this paper, we propose a novel adversarial self-ensembling network using dynamic convolution (ASE-Net) for semi-supervised medical image segmentation. First, we use an adversarial consistency training strategy (ACTS) that employs two discriminators based on consistency learning to obtain prior relationships between labeled and unlabeled data. The ACTS can simultaneously compute pixel-level and image-level consistency of unlabeled data under different data perturbations to improve the prediction quality of labels. Second, we design a dynamic convolution-based bidirectional attention component (DyBAC) that can be embedded in any segmentation network, aiming at adaptively adjusting the weights of ASE-Net based on the structural information of input samples. This component effectively improves the feature representation ability of ASE-Net and reduces the overfitting risk of the network. The proposed ASE-Net has been extensively tested on three publicly available datasets, and experiments indicate that ASE-Net is superior to state-of-the-art networks, and reduces computational costs and memory overhead. The code is available at: https://github.com/SUST-reynole/ASE-Nethttps://github.com/SUST-reynole/ASE-Net.

A robust computer vision-based approach is developed to estimate the load asymmetry angle defined in the revised NIOSH lifting equation (RNLE). The angle of asymmetry enables the computation of a recommended weight limit for repetitive lifting operations in a workplace to prevent lower back injuries. An open-source package OpenPose is applied to estimate the 2D locations of skeletal joints of the worker from two synchronous videos. Combining these joint location estimates, a computer vision correspondence and depth estimation method is developed to estimate the 3D coordinates of skeletal joints during lifting. The angle of asymmetry is then deduced from a subset of these 3D positions. Error analysis reveals unreliable angle estimates due to occlusions of upper limbs. A robust angle estimation method that mitigates this challenge is developed. We propose a method to flag unreliable angle estimates based on the average confidence level of 2D joint estimates provided by OpenPose. An optimal threshold is derived that balances the percentage variance reduction of the estimation error and the percentage of angle estimates flagged. Tested with 360 lifting instances in a NIOSH-provided dataset, the standard deviation of angle estimation error is reduced from 10.13° to 4.99°. To realize this error variance reduction, 34% of estimated angles are flagged and require further validation.

Performance-cost trade-offs in video object tracking tasks for long video sequences is investigated. A novel frame-subsampled, drift-resilient (FSDR) video object tracking algorithm is presented that would achieve desired tracking accuracy while dramatically reducing computing time by processing only sub-sampled video frames. A new pattern matching score metric is proposed to estimate the probability of drifting. A drift-recovery procedure is developed to enable the algorithm to recover from a drift situation and resume accurate tracking. Compared against state-of-the-art video object tracking algorithms, dramatic performance (accuracy) enhancement and cost (computing time) reduction are observed.

A novel frame-subsampled, drift-resilient (FSDR) video object tracking (VOT) algorithm is proposed. Two design goals are sought: to improve the accuracy and to reduce the processing time. The drifting problem is mitigated with a drift detector and accompanying drift recovery mechanism. When a drift is detected, the recovery mechanism provides an opportunity to put the tracking back on track. To gather context-dependent statistics required for these procedures, an initial short segment of the video sequence will be used as a training sequence. Thus, this algorithm is more suitable for video sequences much longer than several minutes. To reduce computing time, a novel frame-subsampling strategy is proposed to process the VOT on small subset of frames. The trajectory of the tracked object on frames that are skipped will be estimated via interpolation. Compared with state of art VOT algorithms, dramatic improvement of performance (accuracy) and orders of magnitude computing time reduction are observed.