A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?

In biomechanics, movement is typically recorded by tracking the trajectories of anatomical landmarks previously marked using passive instrumentation, which entails several inconveniences. To overcome these disadvantages, researchers are exploring different markerless methods, such as pose estimation networks, to capture movement with equivalent accuracy to marker-based photogrammetry. However, pose estimation models usually only provide joint centers, which are incomplete data for calculating joint angles in all anatomical axes. Recently, marker augmentation models based on deep learning have emerged. These models transform pose estimation data into complete anatomical data. Building on this concept, this study presents three marker augmentation models of varying complexity that were compared to a photogrammetry system. The errors in anatomical landmark positions and the derived joint angles were calculated, and a statistical analysis of the errors was performed to identify the factors that most influence their magnitude. The proposed Transformer model improved upon the errors reported in the literature, yielding position errors of less than 1.5 cm for anatomical landmarks and 4.4 degrees for all seven movements evaluated. Anthropometric data did not influence the errors, while anatomical landmarks and movement influenced position errors, and model, rotation axis, and movement influenced joint angle errors.

A Rare Case of Non-IUD-Related Chronic Endometritis caused by Actinomyces Bacteria in a Postmenopausal Woman: A Case Report.

Pelvic actinomycosis is a rare condition, usually associated with intrauterine device (IUD) use. Its clinical presentation may vary from being asymptomatic to the mimicking of pelvic malignancy; it has been described as one of the most misdiagnosed diseases. A 78-year-old woman without a history of IUD use, arrived at our clinic complaining of chronic and intermittent postmenopausal bleeding associated with lower pelvic pain. An endometrial curettage was performed, and endometritis (caused by Actinomyces) identified. Treatment with intravenous piperacillin and tazobactam for 7 days, followed by 6 weeks of oral ampicillin, daily, decreased the bleeding and the pain. Although rare, it is important to consider Actinomyces-related endometritis as a differential diagnosis in cases of elderly woman with postmenopausal bleeding and without a history of IUD use.

Isolated intestinal polyarteritis nodosa in an elderly patient.

Polyarteritis nodosa (PAN) is a necrotising systemic vasculitis involving medium-sized and small-sized vessels. PAN limited to a single organ is rare, particularly in the elderly population. Herein, we present a 73-year-old-woman who developed severe abdominal pain. Mesenteric angiography showed multifocal areas of segmental dilation and narrowing of the superior mesenteric, ileocolic and right colonic arteries. Exploratory laparotomy revealed multiple areas of necrosis of the jejunum for which resection was performed. Histopathological exam disclosed mesenteric vasculitis with fibrinoid necrosis of the arterial wall with leucocytic infiltrates and haemorrhages consistent with PAN. She was started on high-dose corticosteroids with an initial good response. However, 6 months later, she developed intestinal pseudo-obstruction for which oral cyclophosphamide was started. After 5 months of cyclophosphamide therapy, she remained stable without further relapses. Our case suggests that PAN should be considered in elderly patients presenting with abdominal pain even in the absence of systemic involvement.

A Ciliary Motility Index for Activity Measurement in Cell Cultures With Respiratory Syncytial Virus.

BACKGROUND: The respiratory epithelium is frequently infected by the respiratory syncytial virus, resulting in inflammation, a reduction in cilia activity and an increase in the production of mucus. METHODS: In this study, an automatic method has been proposed to characterize the ciliary motility from cell cultures by means of a motility index using a dense optical flow algorithm. This method allows us to determine the ciliary beat frequency (CBF) together with a ciliary motility index of the cells in the cultures. The object of this analysis is to automatically distinguish between normal and infected cells in a culture. RESULTS: The method was applied in 2 stages. It was concluded from the first stage that the CBF is not a good enough indicator to discriminate between the control and infected cultures. However, the ciliary motility index does succeed in discriminating between the control and infected cultures using the t test with a value t = 6.46 and P < .001. In the second stage, it has been shown that the ciliary motility index did not differ significantly between patients, and the analysis of variance test gives α = 0.05, F = 1.61, P = .20. A threshold for this index has been determined using a receiver operating characteristics analysis that gives an area under the curve of 0.93. CONCLUSIONS: We have obtained a ciliary motility index that is able to discriminate between control and infected cultures after the eighth postinfection day. After infection, there is a rapid cilia loss of the cells and the measured CBF corresponds to the remaining noninfected cells. This is why the CBF does not discriminate between the control and the infected cells.

Primary ciliary dyskinesia assessment by means of optical flow analysis of phase-contrast microscopy images.

Primary ciliary dyskinesia implies cilia with defective or total absence of motility, which may result in sinusitis, chronic bronchitis, bronchiectasis and male infertility. Diagnosis can be difficult and is based on an abnormal ciliary beat frequency (CBF) and beat pattern. In this paper, we present a method to determine CBF of isolated cells through the analysis of phase-contrast microscopy images, estimating cilia motion by means of an optical flow algorithm. After having analyzed 28 image sequences (14 with a normal beat pattern and 14 with a dyskinetic pattern), the normal group presented a CBF of 5.2 ± 1.6 Hz, while the dyskinetic patients presented a 1.9 ± 0.9 Hz CBF. The cutoff value to classify a dyskinetic specimen was set to 3.45 Hz (sensitivity 0.86, specificity 0.93). The presented methodology has provided excellent results to objectively diagnose PCD.

Ciliary motility activity measurement using a dense optical flow algorithm.

Persistent respiratory syncytial virus (RSV) infections have been associated with the exacerbation of chronic inflammatory diseases, including chronic obstructive pulmonary disease (COPD). This virus infects the respiratory epithelium, leading to chronic inflammation, and induces the release of mucins and the loss of cilia activity, two factors that determine mucus clearance and the increase in sputum volume. In this study, an automatic method has been established to determine the ciliary motility activity from cell cultures by means of optical flow computation, and has been applied to 136 control cultures and to 144 RSV-infected cultures. The control group presented an average of cell surface with cilia motility per field of 41 ± 15 % (mean ± standard deviation), while the infected group presented a 11 ± 5 %, t-Student p<0.001. The cutoff value to classify a infected specimen was <17.89 % (sensitivity 0.94, specificity 0.93). This methodology has proved to be a robust technique to evaluate cilia motility in cell cultures.