Search

Background: The purpose of this study was to establish a standardized structured workflow to compare findings from high-resolution, optimized reconstructions from post-mortem computed tomography (pmCT) with autopsy results in the detection of fractures of the laryngohyoid complex in strangulation victims. Method: Forty-two strangulation cases were selected, and pmCT scans of the laryngohyoid complex were obtained. Both pmCT scans and autopsy reports were analyzed using a structured template and compared using Cohen’s kappa coefficient (κ) and the McNemar test. The study also compared the prevalence of ossa sesamoidea and non-fusion of the major and minor horns of the hyoid bone between both diagnostic methods. Results: The detection of fractures showed a very good correlation between autopsy and pmCT results (κ = 0.905), with the McNemar test showing no statistically significant difference between the two methods. PmCT identified 28 sesamoid bones, 45 non-fusions of the major horns, and 47 non-fusions of the minor horns of the hyoid bone, compared to four, six, and zero, respectively, identified by autopsy (p < 0.0001). Conclusions: Autopsy and pmCT findings correlate well and can be used in a complementary manner. PmCT is superior to autopsy in identifying dislocations and detecting anatomical variations in the laryngohyoid complex, which can lead to misinterpretations during autopsy. Therefore, we do not advocate replacing autopsy with pmCT but propose using a structured workflow, including our standardized reporting template, for evaluating lesions in the laryngohyoid complex.

Lung lobe segmentation in chest CT is relevant to a wide range of clinical applications. However, existing segmentation pipelines often exhibit vulnerabilities and performance degradations when applied to external datasets. This is usually attributed to the size of the available dataset or model. We show that it is possible to enhance generalizability without huge resources by carefully curating the dataset and combining machine learning with medical expertise. Multiple machine learning techniques (self-supervision (SSL), attention (A), and data augmentation (DA)) are used to train a fast and fully-automated lung lobe segmentation model based on 2D U-Net. Our study involved evaluating these techniques on a diverse dataset collected under the RACOON project, encompassing 100 CT chest scans from patients with bacterial, viral, or SARS-CoV2 infections. We compare our model to a baseline U-Net trained on the same dataset. Our approach significantly improved segmentation accuracy (Dice score of 92.8% vs. 82.3%, p < 0.001). Moreover, our model achieved state-of-the-art performance (Dice score of 92.8% vs. 90.8% for the literature’s state-of-the-art, p = 0.102) with reduced training examples (69 vs. 231 CT Scans). Among the techniques, data augmentation with expert knowledge displayed the most significant impact, enhancing the Dice score by +0.056. Notably, these enhancements are not limited to lobe segmentation but can be seamlessly integrated into various medical imaging segmentation tasks, demonstrating their versatility and potential for broader applications.