Reported frequency of post-stroke dysphagia in the literature is highly variable. In view of progress in stroke management, we aimed to assess the current burden of dysphagia in acute ischemic ...stroke.
We studied 570 consecutive patients treated in a tertiary stroke center. Dysphagia was evaluated by using the Gugging Swallowing Screen (GUSS). We investigated the relationship of dysphagia with pneumonia, length of hospital stay and discharge destination and compared rates of favourable clinical outcome and mortality at 3 months between dysphagic patients and those without dysphagia.
Dysphagia was diagnosed in 118 of 570 (20.7%) patients and persisted in 60 (50.9%) at hospital discharge. Thirty-six (30.5%) patients needed nasogastric tube because of severe dysphagia. Stroke severity rather than infarct location was associated with dysphagia. Dysphagic patients suffered more frequently from pneumonia (23.1% vs. 1.1%, p<0.001), stayed longer at monitored stroke unit beds (4.4±2.8 vs. 2.7±2.4 days; p<0.001) and were less often discharged to home (19.5% vs. 63.7%, p = 0.001) as compared to those without dysphagia. At 3 months, dysphagic patients less often had a favourable outcome (35.7% vs. 69.7%; p<0.001), less often lived at home (38.8% vs. 76.5%; p<0.001), and more often had died (13.6% vs. 1.6%; p<0.001). Multivariate analyses identified dysphagia to be an independent predictor of discharge destination and institutionalization at 3 months, while severe dysphagia requiring tube placement was strongly associated with mortality.
Dysphagia still affects a substantial portion of stroke patients and may have a large impact on clinical outcome, mortality and institutionalization.
Injection of soft-tissue fillers into the facial fat compartments is frequently performed to ameliorate the signs of facial aging. This study was designed to investigate the functional anatomy of the ...deep facial fat compartments and to provide information on the effects of injected material in relation to age and gender differences.
Forty fresh frozen cephalic specimens of 17 male and 23 female Caucasian body donors (mean age, 76.9 ± 13.1 years; mean body mass index, 23.6 ± 5.3 kg/m(2)) were investigated. Computed tomographic and magnetic resonance imaging procedures were carried out using colored contrast-enhanced materials with rheologic properties similar to commercially available soft-tissue fillers. Anatomical dissections were performed to guide conclusions.
No statistically significant influences of age or gender were detected in the investigated sample. Increased amounts of injected contrast agent did not correlate with inferior displacement of the material in any of the investigated compartments: deep pyriform, deep medial cheek, deep lateral cheek, deep nasolabial (located within the premaxillary space), and the medial and lateral sub-orbicularis oculi fat.
Increasing volume in the deep midfacial fat compartments did not cause inferior displacement of the injected material. This underscores the role of deep soft-tissue filler injections (i.e., in contact with the bone) in providing support for overlying structures and resulting in anterior projection.
Anatomical knowledge of the facial vasculature is crucial for successful plastic, reconstructive, and minimally invasive procedures of the face. Whereas the majority of previous investigations ...focused on facial arteries, the precise course, variability, and relationship with adjacent structures of the facial vein have been widely neglected.
Seventy-two fresh frozen human cephalic cadavers (32 male and 40 female cadavers; mean age, 75.2 ± 10.9 years; mean body mass index, 24.2 ± 6.6 kg/m; 99 percent Caucasian ethnicity) were investigated by means of layer-by-layer anatomical dissection. In addition, 10 cephalic specimens were investigated using contrast agent-enhanced computed tomographic imaging.
The facial vein displayed a constant course in relation to the adjacent anatomical structures. The vein was identified posterior to the facial artery, anterior to the parotid duct, and deep to the zygomaticus major muscle. The angular vein formed the lateral boundary of the deep medial cheek fat and the premaxillary space, and the medial boundary of the deep lateral cheek fat and the sub-orbicularis oculi fat. The mean distance of the inferior and superior labial veins, of the deep facial vein, and of the angular vein from the inferior orbital margin was 51.6 ± 3.1, 42.6 ± 2.3, 27.4 ± 3.0, and 4.2 ± 0.7 mm, respectively.
This work provides detailed information on the course of the facial vein in relation to neighboring structures. The presented clinically relevant anatomical observations and descriptions of landmarks will serve as helpful information for plastic, reconstructive, and aesthetic surgeons.
Collaterals 2016 (third International Symposium on Collaterals to the Brain) was a multidisciplinary scientific conference focused on collateral circulation in acute ischemic stroke. Decisive ...challenges include generalizability of optimal triage and selection paradigms based on collateral status for definitive treatment of acute ischemic stroke, rapid dissemination of expert methods, and the urgent need to leverage networking opportunities for stroke science related to the hemodynamics of collaterals. The collaterome, or individual capacity to offset ischemia in the brain, and determination of a favorable collateral profile have become pivotal factors in consideration of the precision medicine of stroke decision-making. The conference convened over 50 invited faculty from around the world to connect on-site participants at a state-of-the-art facility with remote audiences in more than 22 countries and regions. The 2½-day program was structured into 40-min sessions devoted to key issues in translating the collaterome in acute stroke therapy across the globe. This unique forum of expertise emphasized the timely impact of collaterals on a monumental scale, encouraging maximal participation, rapid diffusion and added value of a diverse networking resource. The meeting format established a model geographical framework and innovative videoconferencing platform for future scientific conferences.
Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such algorithms is essentially a ...black-box process that renders it difficult for physicians to judge whether the decisions are reliable. The use of explainable artificial intelligence (XAI) is often suggested as a solution to this problem.
We investigate how XAI is used for skin cancer detection: how is it used during the development of new DNNs? What kinds of visualisations are commonly used? Are there systematic evaluations of XAI with dermatologists or dermatopathologists?
Google Scholar, PubMed, IEEE Explore, Science Direct and Scopus were searched for peer-reviewed studies published between January 2017 and October 2021 applying XAI to dermatological images: the search terms histopathological image, whole-slide image, clinical image, dermoscopic image, skin, dermatology, explainable, interpretable and XAI were used in various combinations. Only studies concerned with skin cancer were included.
37 publications fulfilled our inclusion criteria. Most studies (19/37) simply applied existing XAI methods to their classifier to interpret its decision-making. Some studies (4/37) proposed new XAI methods or improved upon existing techniques. 14/37 studies addressed specific questions such as bias detection and impact of XAI on man-machine-interactions. However, only three of them evaluated the performance and confidence of humans using CAD systems with XAI.
XAI is commonly applied during the development of DNNs for skin cancer detection. However, a systematic and rigorous evaluation of its usefulness in this scenario is lacking.
•No evaluation of explainable artificial intelligence (XAI) for skin cancer detection has been conducted to this date.•Overview of 37 studies using XAI on dermatological and dermato histological data.•Analysis of the usage of XAI to inform research on its role as part of computer-aided diagnosis (CAD) systems.
Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses.
We investigated whether a combination of histologic whole slides image (WSI) ...analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone.
We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as ‘uncertain’ (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier.
The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%.
In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low ‘confidence’ improved balanced accuracy.
•Pathologists incorporate patient data in addition to clinical examination.•They put more emphasis on patient data if they are uncertain.•We investigated fusing histologic image/patient data within CNN-based classifiers.•State-of-the-art fusing approaches in general did not yield a performance benefit.•Mimicking humans by fusing patient data only if CNN was uncertain raised accuracy.
Background
Coronavirus disease 2019 (COVID‐19) interferes with the vascular endothelium. It is not known whether COVID‐19 additionally affects arterial stiffness.
Methods
This case–control study ...compared brachial‐ankle pulse wave (baPWV) and carotid‐femoral pulse wave velocities (cfPWV) of acutely ill patients with and without COVID‐19.
Results
Twenty‐two COVID‐19 patients (50% females, 77 67–84 years) were compared with 22 age‐ and sex‐matched controls. In COVID‐19 patients, baPWV (19.9 18.4–21.0 vs. 16.0 14.2–20.4, P = 0.02) and cfPWV (14.3 13.4–16.0 vs. 11.0 9.5–14.6, P = 0.01) were higher than in the controls. In multiple regression analysis, COVID‐19 was independently associated with higher cfPWV (β = 3.164, P = 0.004) and baPWV (β = 3.532, P = 0.003). PWV values were higher in nonsurvivors. In survivors, PWV correlated with length of hospital stay.
Conclusion
COVID‐19 appears to be related to an enhanced PWV reflecting an increase in arterial stiffness. Higher PWV might be related to an increased length of hospital stay and mortality.
One prominent application for deep learning–based classifiers is skin cancer classification on dermoscopic images. However, classifier evaluation is often limited to holdout data which can mask ...common shortcomings such as susceptibility to confounding factors. To increase clinical applicability, it is necessary to thoroughly evaluate such classifiers on out-of-distribution (OOD) data.
The objective of the study was to establish a dermoscopic skin cancer benchmark in which classifier robustness to OOD data can be measured.
Using a proprietary dermoscopic image database and a set of image transformations, we create an OOD robustness benchmark and evaluate the robustness of four different convolutional neural network (CNN) architectures on it.
The benchmark contains three data sets—Skin Archive Munich (SAM), SAM-corrupted (SAM-C) and SAM-perturbed (SAM-P)—and is publicly available for download. To maintain the benchmark's OOD status, ground truth labels are not provided and test results should be sent to us for assessment. The SAM data set contains 319 unmodified and biopsy-verified dermoscopic melanoma (n = 194) and nevus (n = 125) images. SAM-C and SAM-P contain images from SAM which were artificially modified to test a classifier against low-quality inputs and to measure its prediction stability over small image changes, respectively. All four CNNs showed susceptibility to corruptions and perturbations.
This benchmark provides three data sets which allow for OOD testing of binary skin cancer classifiers. Our classifier performance confirms the shortcomings of CNNs and provides a frame of reference. Altogether, this benchmark should facilitate a more thorough evaluation process and thereby enable the development of more robust skin cancer classifiers.
•AI-based skin cancer classifier testing is often limited to holdout data.•However, holdout testing can mask severe susceptibilities and shortcomings.•Therefore, testing on out-of-distribution (OOD) data should become standard practice.•We release a dermoscopic skin cancer image benchmark designed for OOD testing.•This benchmark incorporates various distribution shifts such as corrupted images.