Artificial intelligence for automated detection and measurements of carpal instability signs on conventional radiographs.

OBJECTIVES: To develop and validate an artificial intelligence (AI) system for measuring and detecting signs of carpal instability on conventional radiographs. MATERIALS AND METHODS: Two case-control datasets of hand and wrist radiographs were retrospectively acquired at three hospitals (hospitals A, B, and C). Dataset 1 (2178 radiographs from 1993 patients, hospitals A and B, 2018-2019) was used for developing an AI system for measuring scapholunate (SL) joint distances, SL and capitolunate (CL) angles, and carpal arc interruptions. Dataset 2 (481 radiographs from 217 patients, hospital C, 2017-2021) was used for testing, and with a subsample (174 radiographs from 87 patients), an observer study was conducted to compare its performance to five clinicians. Evaluation metrics included mean absolute error (MAE), sensitivity, and specificity. RESULTS: Dataset 2 included 258 SL distances, 189 SL angles, 191 CL angles, and 217 carpal arc labels obtained from 217 patients (mean age, 51 years ± 23 [standard deviation]; 133 women). The MAE in measuring SL distances, SL angles, and CL angles was respectively 0.65 mm (95%CI: 0.59, 0.72), 7.9 degrees (95%CI: 7.0, 8.9), and 5.9 degrees (95%CI: 5.2, 6.6). The sensitivity and specificity for detecting arc interruptions were 83% (95%CI: 74, 91) and 64% (95%CI: 56, 71). The measurements were largely comparable to those of the clinicians, while arc interruption detections were more accurate than those of most clinicians. CONCLUSION: This study demonstrates that a newly developed automated AI system accurately measures and detects signs of carpal instability on conventional radiographs. CLINICAL RELEVANCE STATEMENT: This system has the potential to improve detections of carpal arc interruptions and could be a promising tool for supporting clinicians in detecting carpal instability.

Musculoskeletal radiologist-level performance by using deep learning for detection of scaphoid fractures on conventional multi-view radiographs of hand and wrist.

OBJECTIVES: To assess how an artificial intelligence (AI) algorithm performs against five experienced musculoskeletal radiologists in diagnosing scaphoid fractures and whether it aids their diagnosis on conventional multi-view radiographs. METHODS: Four datasets of conventional hand, wrist, and scaphoid radiographs were retrospectively acquired at two hospitals (hospitals A and B). Dataset 1 (12,990 radiographs from 3353 patients, hospital A) and dataset 2 (1117 radiographs from 394 patients, hospital B) were used for training and testing a scaphoid localization and laterality classification component. Dataset 3 (4316 radiographs from 840 patients, hospital A) and dataset 4 (688 radiographs from 209 patients, hospital B) were used for training and testing the fracture detector. The algorithm was compared with the radiologists in an observer study. Evaluation metrics included sensitivity, specificity, positive predictive value (PPV), area under the characteristic operating curve (AUC), Cohen's kappa coefficient (κ), fracture localization precision, and reading time. RESULTS: The algorithm detected scaphoid fractures with a sensitivity of 72%, specificity of 93%, PPV of 81%, and AUC of 0.88. The AUC of the algorithm did not differ from each radiologist (0.87 [radiologists' mean], p ≥ .05). AI assistance improved five out of ten pairs of inter-observer Cohen's κ agreements (p < .05) and reduced reading time in four radiologists (p < .001), but did not improve other metrics in the majority of radiologists (p ≥ .05). CONCLUSIONS: The AI algorithm detects scaphoid fractures on conventional multi-view radiographs at the level of five experienced musculoskeletal radiologists and could significantly shorten their reading time. KEY POINTS: • An artificial intelligence algorithm automatically detects scaphoid fractures on conventional multi-view radiographs at the same level of five experienced musculoskeletal radiologists. • There is preliminary evidence that automated scaphoid fracture detection can significantly shorten the reading time of musculoskeletal radiologists.

Predicting vasovagal reactions to a virtual blood donation using facial image analysis.

BACKGROUND: People with needle fear experience not only anxiety and stress but also vasovagal reactions (VVR), including nausea, dizziness, sweating, pallor changes, or even fainting. However, the mechanism behind needle fear and the VVR response are not yet well understood. The aim of our study was to explore whether fluctuations in facial temperature in several facial regions are related to the level of experienced vasovagal reactions, in a simulated blood donation. STUDY DESIGN AND METHODS: We recruited 45 students at Tilburg University and filmed them throughout a virtual blood donation procedure using an Infrared Thermal Imaging (ITI) camera. Participants reported their fear of needles and level of experienced vasovagal reactions. ITI data pre-processing was completed on each video frame by detecting facial landmarks and image alignment before extracting the mean temperature from the six regions of interest. RESULTS: Temperatures of the chin and left and right cheek areas increased during the virtual blood donation. Mixed-effects linear regression showed a significant association between self-reported vasovagal reactions and temperature fluctuations in the area below the nose. DISCUSSION: Our results suggest that the area below the nose may be an interesting target for measuring vasovagal reactions using video imaging techniques. This is the first in a line of studies, which assess whether it is possible to automatically detect levels of fear and vasovagal reactions using facial imaging, from which the development of e-health solutions and interventions can benefit.

Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering.

Cell migration is a key feature for living organisms. Image analysis tools are useful in studying cell migration in three-dimensional (3-D) in vitro environments. We consider angiogenic vessels formed in 3-D microfluidic devices (MFDs) and develop an image analysis system to extract cell behaviors from experimental phase-contrast microscopy image sequences. The proposed system initializes tracks with the end-point confocal nuclei coordinates. We apply convolutional neural networks to detect cell candidates and combine backward Kalman filtering with multiple hypothesis tracking to link the cell candidates at each time step. These hypotheses incorporate prior knowledge on vessel formation and cell proliferation rates. The association accuracy reaches 86.4% for the proposed algorithm, indicating that the proposed system is able to associate cells more accurately than existing approaches. Cell culture experiments in 3-D MFDs have shown considerable promise for improving biology research. The proposed system is expected to be a useful quantitative tool for potential microscopy problems of MFDs.

Automated tracking and quantification of angiogenic vessel formation in 3D microfluidic devices.

Angiogenesis, the growth of new blood vessels from pre-existing vessels, is a critical step in cancer invasion. Better understanding of the angiogenic mechanisms is required to develop effective antiangiogenic therapies for cancer treatment. We culture angiogenic vessels in 3D microfluidic devices under different Sphingosin-1-phosphate (S1P) conditions and develop an automated vessel formation tracking system (AVFTS) to track the angiogenic vessel formation and extract quantitative vessel information from the experimental time-lapse phase contrast images. The proposed AVFTS first preprocesses the experimental images, then applies a distance transform and an augmented fast marching method in skeletonization, and finally implements the Hungarian method in branch tracking. When applying the AVFTS to our experimental data, we achieve 97.3% precision and 93.9% recall by comparing with the ground truth obtained from manual tracking by visual inspection. This system enables biologists to quantitatively compare the influence of different growth factors. Specifically, we conclude that the positive S1P gradient increases cell migration and vessel elongation, leading to a higher probability for branching to occur. The AVFTS is also applicable to distinguish tip and stalk cells by considering the relative cell locations in a branch. Moreover, we generate a novel type of cell lineage plot, which not only provides cell migration and proliferation histories but also demonstrates cell phenotypic changes and branch information.

Dll4-containing exosomes induce capillary sprout retraction in a 3D microenvironment.

Delta-like 4 (Dll4), a membrane-bound Notch ligand, plays a fundamental role in vascular development and angiogenesis. Dll4 is highly expressed in capillary endothelial tip cells and is involved in suppressing neighboring stalk cells to become tip cells during angiogenesis. Dll4-Notch signaling is mediated either by direct cell-cell contact or by Dll4-containing exosomes from a distance. However, whether Dll4-containing exosomes influence tip cells of existing capillaries is unknown. Using a 3D microfluidic device and time-lapse confocal microscopy, we show here for the first time that Dll4-containing exosomes causes tip cells to lose their filopodia and trigger capillary sprout retraction in collagen matrix. We demonstrate that Dll4 exosomes can freely travel through 3D collagen matrix and transfer Dll4 protein to distant tip cells. Upon reaching endothelial sprout, it causes filopodia and tip cell retraction. Continuous application of Dll4 exosomes from a distance lead to significant reduction of sprout formation. This effect correlates with Notch signaling activation upon Dll4-containing exosome interaction with recipient endothelial cells. Furthermore, we show that Dll4-containing exosomes increase endothelial cell motility while suppressing their proliferation. These data revealed novel functions of Dll4 in angiogenesis through exosomes.

2D data-driven stalk cell prediction model based on tip-stalk cell interaction in angiogenesis.

Angiogenesis is the growth process of blood vessels from existing vessels. During angiogenesis, endothelial cells (ECs), which line the vessel, specialize into tip and stalk cells. Tip cells respond to angiogenic signals, burrow into the extracellular matrix (ECM) and form conduits. Stalk cells follow the tip cells along the conduits, and form solid sprouts or lumen vessels. Interactions between stalk cells and tip cells are important for creating functional vessels. The goal of this work is to predict stalk cells migration trajectories from known tip cell trajectories. Four factors influence the position and velocity of cell migration in ECM: cell-cell interaction, drag force, chemotactic signal and cell-ECM interaction. As chemotactic signal and cell-ECM interactions have little effect on stalk cell movement, the proposed model includes the influence of cell-cell interactions and drag force only. The unknown parameters in the model are inferred by Maximum Likelihood Estimation (MLE) from experimental time-lapse cell migration data. Numerical results suggest that the proposed model can accurately predict stalk cell trajectories. The proposed model may be useful for the study of angiogenesis, a critical process for cancer tumor growth.