Citations

Background/Objectives: To develop and evaluate a deep learning-based quality control system for Lumbar Spinal Digital Radiographs (LSDR), designed to automate and improve their evaluation and reduce reliance on manual reviews. Methods: This retrospective study utilized a deep learning workflow comprising image segmentation, feature extraction, and a classification model. The dataset, including anteroposterior (AP) and lateral (LAT) X-ray images, was expanded through data augmentation techniques. Four U-Net-based models were assessed: standard U-Net, Swin-UNet, Attention U-Net, and Attention U-Net with the weight map, with the latter selected for its superior performance. Extracted features, such as brightness, contrast, and anatomical positioning, were used in an XGBoost classifier, which was evaluated using mean intersection over union (mIoU), accuracy, sensitivity, specificity, and AUC. Results: The Attention U-Net with weighted attention outperformed the other models, achieving high mIoU scores in both AP and LAT views. The XGBoost classifier achieved the best performance in classifying images as “qualified” or “unqualified,” with an AUC of approximately 0.9, high accuracy, and balanced sensitivity and specificity. This approach effectively addressed class imbalances and improved model accuracy compared to traditional machine learning models such as MLP and SVM. Conclusions: The developed automated quality control system demonstrated potential for enhancing image quality, enhancing diagnostic reliability, and optimizing clinical workflow efficiency.

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 Tumor cells develop various strategies to evade immune surveillance, one of which involves altering the metabolic state of the tumor microenvironment. In response to metabolic stress in the tumor microenvironment, several tumor-infiltrating immune subsets upregulate CD36 to take up lipids. This leads to impaired antitumor immunity, as intratumoral regulatory T cells exhibit increased survival and suppressive activity, whereas CD8+ T cells become more susceptible to ferroptosis and exhaustion. In this study, we develop a humanized anti-CD36 IgG4 antibody, PLT012, against the lipid-binding domain of CD36 with excellent safety and favorable pharmacokinetic features in mice and cynomolgus monkeys. PLT012 alone or in combination with PD-L1 blockade or standard-of-care immunotherapy results in robust antitumor immunity in both immunotherapy-sensitive and -resistant hepatocellular carcinomas (HCC). Notably, PLT012 also reprograms the immune landscape of human HCC ex vivo. Our findings provide proof-of-concept evidence that PLT012 reprograms antitumor immunity in HCC, positioning it as a first-in-class immunotherapy targeting CD36. Significance: Despite the success of cancer immunotherapies, like immune checkpoint inhibitors, many patients still fail to demonstrate significant responses because of metabolic constraints in tumors. PLT012 rejuvenates antitumor immunity by targeting metabolic pathways to reprogram the immune landscape of liver cancer and liver metastasis, with potential to influence future HCC immunotherapy.

Abstract Alpha‐synuclein (αsyn) aggregates are pathological features of several neurodegenerative conditions including Parkinson disease (PD), dementia with Lewy bodies, and multiple system atrophy (MSA). Accumulating evidence suggests that mitochondrial dysfunction and impairments of the autophagic‐lysosomal system can contribute to the deposition of αsyn, which in turn may interfere with health and function of these organelles in a potentially vicious cycle. Here we investigated a potential convergence of αsyn with the PINK1‐PRKN‐mediated mitochondrial autophagy pathway in cell models, αsyn transgenic mice, and human autopsy brain. PINK1 and PRKN identify and selectively label damaged mitochondria with phosphorylated ubiquitin (pS65‐Ub) to mark them for degradation (mitophagy). We found that disease‐causing multiplications of αsyn resulted in accumulation of the ubiquitin ligase PRKN in cells. This effect could be normalized by starvation‐induced autophagy activation and by CRISPR/Cas9‐mediated αsyn knockout. Upon acute mitochondrial damage, the increased levels of PRKN protein contributed to an enhanced pS65‐Ub response. We further confirmed increased pS65‐Ub‐immunopositive signals in mouse brain with αsyn overexpression and in postmortem human disease brain. Of note, increased pS65‐Ub was associated with neuronal Lewy body‐type αsyn pathology, but not glial cytoplasmic inclusions of αsyn as seen in MSA. While our results add another layer of complexity to the crosstalk between αsyn and the PINK1‐PRKN pathway, distinct mechanisms may underlie in cells and brain tissue despite similar outcomes. Notwithstanding, our finding suggests that pS65‐Ub may be useful as a biomarker to discriminate different synucleinopathies and may serve as a potential therapeutic target for Lewy body disease.