Camp, Jon

Abstract Background/Purpose Diagnosing wrist ligament injuries is challenging; early detection and treatment are important to prevent osteoarthritis progression. Interosseous proximity maps, a proxy measure for joint space, can be generated from volumetric imaging data and may provide important information about wrist health. Artificial intelligence (AI) could enhance accuracy of noninvasive diagnosis based on imaging-derived metrics. This work demonstrates feasibility of AI training using synthetic proximity map data generated from finite element models (FEMs). Methods Personalized wrist FEMs for two asymptomatic participants were created from four-dimensional computed tomography-derived anatomic and kinematic data. Monte Carlo sampling varied 22 ligament material properties and simulated 7,500 unique injury scenarios generating 9,000,000 labeled red, green, and blue (RGB) images of interosseous proximity vector fields from FEM-derived motions. Images were associated with 17 descriptive metrics, including gross wrist angles and bone surface pairs, and used to develop mixed-input convolutional neural networks (CNNs). Model performance was evaluated for identifying specific ligament injuries. Results Average area under receiver operating characteristic curve (AUROC) for CNNs was 0.757 across all injury types and kinematics. In a subset with clinically-relevant functional angles, the average AUROC was 0.824. Best-performing individual ligament AUROCs ranged from 0.807 to 0.999. Sensitivities and specificities exceeded 0.99 for some ligament injury simulations under specific wrist angles and bone surface pairs. Conclusion This study demonstrates the feasibility of using synthetic data from FEMs to train AI models for classifying wrist ligament injuries. Proximity-based RGB images may be a relevant biomarker of ligamentous injury.

Abstract Senescent cells accumulate with age and contribute to tissue dysfunction, yet their identification in tissues is challenging due to low abundance, heterogeneous phenotypes, and the lack of specific markers. Senescence-associated features span multiple subcellular compartments, including nuclear DNA damage foci, cytosolic protein changes, and perinuclear alterations, each requiring tailored detection strategies. To overcome these challenges, we developed SenoQuant ( https://github.com/HaamsRee/senoquant ), a versatile software designed for comprehensive, accurate, and unbiased spatial quantification and prediction of senescence markers across diverse tissue contexts. Utilizing AI models, SenoQuant enables precise nuclear and cytoplasmic segmentation and detection of senescence markers across low- and high-plex imaging modalities, applicable to cultured cells and tissue sections from mice and humans. The platform also supports custom AI models; for example, we built SenCeption, a proof-of-concept predictor of single-cell p21 status from DAPI-stained nuclei in human skin. Available as a free napari plugin, SenoQuant is widely accessible to researchers. By providing a unified approach to senescence analysis and prediction, SenoQuant opens new opportunities for exploring the complex biology of senescence and its impacts on aging and disease.

Kidney stones are a common urologic condition with a high amount of recurrence. Recurrence depends on a multitude of factors the incidence of precursors to kidney stones, plugs, and plaques. One method of characterising the stone precursors is endoscopic assessment, though it is manual and time‐consuming. Deep learning has become a popular technique for semantic segmentation because of the high accuracy that has been demonstrated. The present Letter examined the efficacy of deep learning to segment the renal papilla, plaque, and plugs. A U‐Net model with ResNet‐34 encoder was tested; the Letter examined dropout (to avoid overtraining) and two different loss functions (to address the class imbalance problem. The models were then trained in 1666 images and tested on 185 images. The Jaccard‐cross‐entropy loss function was more effective than the focal loss function. The model with the dropout rate 0.4 was found to be more effective due to its generalisability. The model was largely successful at delineating the papilla. The model was able to correctly detect the plaques and plugs; however, small plaques were challenging. Deep learning was found to be applicable for segmentation of an endoscopic image for the papilla, plaque, and plug, with room for improvement.