Scaphoid Fracture Patterns-Part One: Three-Dimensional Computed Tomography Analysis

Pairwise attention-enhanced adversarial model for automatic bone segmentation in CT images

Objective. Bone segmentation is a critical step in screw placement navigation. Although the deep learning methods have promoted the rapid development for bone segmentation, the local bone separation is still challenging due to irregular shapes and similar representational features.Approach. In this paper, we proposed the pairwise attention-enhanced adversarial model (Pair-SegAM) for automatic bone segmentation in computed tomography images, which includes the two parts of the segmentation model and discriminator. Considering that the distributions of the predictions from the segmentation model contains complicated semantics, we improve the discriminator to strengthen the awareness ability of the target region, improving the parsing of semantic information features. The Pair-SegAM has a pairwise structure, which uses two calculation mechanics to set up pairwise attention maps, then we utilize the semantic fusion to filter unstable regions. Therefore, the improved discriminator provides more refinement information to capture the bone outline, thus effectively enhancing the segmentation models for bone segmentation.Main results. To test the Pair-SegAM, we selected the two bone datasets for assessment. We evaluated our method against several bone segmentation models and latest adversarial models on the both datasets. The experimental results prove that our method not only exhibits superior bone segmentation performance, but also states effective generalization.Significance. Our method provides a more efficient segmentation of specific bones and has the potential to be extended to other semantic segmentation domains.

A meta-analysis of union rate after proximal scaphoid fractures: terminology matters

Heterogeneity in the anatomical definition of 'proximal' affects the comparison of outcomes of these scaphoid fractures. This study aims to review published outcomes of all variants to determine both, differences in terminology, and union rate based upon definition. A literature search was conducted to identify articles that reported descriptions and union rate of all acute (<8 weeks of injury) proximal scaphoid fractures in adult patients (>16 years old). Proximal fractures were grouped as reported ('third', 'pole', 'fifth' or 'undefined'). The data were pooled using a fixed-effects method, and a meta-analysis was conducted to compare relative risk (RR) of non-union against non-proximal fractures. Qualitative analysis of 12 articles included three main definitions: 'proximal' (1 article), 'proximal third' (3 articles), and 'proximal pole' (8 articles). Only 6 articles adopted a specific anatomical or ratio description. In a pooled meta-analysis of union rates (15 articles), 'proximal third' and 'proximal pole' fractures demonstrated a relative risk (RR) of non-union of 2.3 and 3.4 in comparison to non-proximal fractures, respectively. Operative management yielded lower non-union rates than non-operative for all fracture types (6% vs. 18%). In conclusion, non-union risk varies depending on definition, with non-standardised classifications adding heterogeneity to reported outcomes. We recommend an approach utilizing fixed anatomical landmarks on plain radiographs (referencing scaphoid length and scapho-capitate joint) to standardise reporting of proximal fracture union in future studies. Abbreviations: CI: confidence intervals; CT: computer tomography; Df: degrees of freedom; DL: dersimonian and laird estimator; MRI: magnetic resonance imaging; NICE: national institute for health and care excellence; OTA: orthopaedic trauma association; PA: posterior-anterior; PRISMA: preferred reporting items for systematic reviews and meta analyses; RCT: randomised controlled trial; RR: relative risk; SNAC: scaphoid non-union advanced collapse; UK: United Kingdom.