Development and clinical validation of a deep learning-based knee CT image segmentation method for robotic-assisted total knee arthroplasty.

BACKGROUND: This study aimed to develop a novel deep convolutional neural network called Dual-path Double Attention Transformer (DDA-Transformer) designed to achieve precise and fast knee joint CT image segmentation and to validate it in robotic-assisted total knee arthroplasty (TKA). METHODS: The femoral, tibial, patellar, and fibular segmentation performance and speed were evaluated and the accuracy of component sizing, bone resection and alignment of the robotic-assisted TKA system constructed using this deep learning network was clinically validated. RESULTS: Overall, DDA-Transformer outperformed six other networks in terms of the Dice coefficient, intersection over union, average surface distance, and Hausdorff distance. DDA-Transformer exhibited significantly faster segmentation speeds than nnUnet, TransUnet and 3D-Unet (p < 0.01). Furthermore, the robotic-assisted TKA system outperforms the manual group in surgical accuracy. CONCLUSIONS: DDA-Transformer exhibited significantly improved accuracy and robustness in knee joint segmentation, and this convenient and stable knee joint CT image segmentation network significantly improved the accuracy of the TKA procedure.

Two-Stage Deep Learning Model for Diagnosis of Lumbar Spondylolisthesis Based on Lateral X-Ray Images.

BACKGROUND: Diagnosing early lumbar spondylolisthesis is challenging for many doctors because of the lack of obvious symptoms. Using deep learning (DL) models to improve the accuracy of X-ray diagnoses can effectively reduce missed and misdiagnoses in clinical practice. This study aimed to use a two-stage deep learning model, the Res-SE-Net model with the YOLOv8 algorithm, to facilitate efficient and reliable diagnosis of early lumbar spondylolisthesis based on lateral X-ray image identification. METHODS: A total of 2424 lumbar lateral radiographs of patients treated in the Beijing Tongren Hospital between January 2021 and September 2023 were obtained. The data were labeled and mutually identified by 3 orthopedic surgeons after reshuffling in a random order and divided into a training set, validation set, and test set in a ratio of 7:2:1. We trained 2 models for automatic detection of spondylolisthesis. YOLOv8 model was used to detect the position of lumbar spondylolisthesis, and the Res-SE-Net classification method was designed to classify the clipped area and determine whether it was lumbar spondylolisthesis. The model performance was evaluated using a test set and an external dataset from Beijing Haidian Hospital. Finally, we compared model validation results with professional clinicians' evaluation. RESULTS: The model achieved promising results, with a high diagnostic accuracy of 92.3%, precision of 93.5%, and recall of 93.1% for spondylolisthesis detection on the test set, the area under the curve (AUC) value was 0.934. CONCLUSIONS: Our two-stage deep learning model provides doctors with a reference basis for the better diagnosis and treatment of early lumbar spondylolisthesis.

Digital contact tracing on hypergraphs.

The higher-order interactions emerging in the network topology affect the effectiveness of digital contact tracing (DCT). In this paper, we propose a mathematical model in which we use the hypergraph to describe the gathering events. In our model, the role of DCT is modeled as individuals carrying the app. When the individuals in the hyperedge all carry the app, epidemics cannot spread through this hyperedge. We develop a generalized percolation theory to investigate the epidemic outbreak size and threshold. We find that DCT can effectively suppress the epidemic spreading, i.e., decreasing the outbreak size and enlarging the threshold. DCT limits the spread of the epidemic to larger cardinality of hyperedges. On real-world networks, the inhibitory effect of DCT on the spread of epidemics is evident when the spread of epidemics is small.

Relaxational signal attenuation during soft refocusing pulses.

Quantitative NMR is widely used, but the systematic errors introduced when signals are excited by anything other than a single hard pulse are not always well understood. One important source of error in experiments using soft pulses is the spin relaxation that takes place during pulses, which contains contributions from both spin-spin and spin-lattice relaxation. Here it is shown that relaxation on resonance during shaped soft 180° refocusing pulses in practical experiments can be well represented by biexponential decay, with rate constants R2 and a shape-dependent linear combination of R1 and R2, where R1 and R2 are the inverses of the spin-lattice and spin-spin relaxation times T1 and T2. In principle this would allow correction for relaxational losses in experiments using on-resonance selective refocusing pulses.