Leveraging Pretrained Transformers for Efficient Segmentation and Lesion Detection in Cone-Beam Computed Tomography Scans.

INTRODUCTION: Cone-beam computed tomography (CBCT) is widely used to detect jaw lesions, although CBCT interpretation is time-consuming and challenging. Artificial intelligence for CBCT segmentation may improve lesion detection accuracy. However, consistent automated lesion detection remains difficult, especially with limited training data. This study aimed to assess the applicability of pretrained transformer-based architectures for semantic segmentation of CBCT volumes when applied to periapical lesion detection. METHODS: CBCT volumes (n = 138) were collected and annotated by expert clinicians using 5 labels - "lesion," "restorative material," "bone," "tooth structure," and "background." U-Net (convolutional neural network-based) and Swin-UNETR (transformer-based) models, pretrained (Swin-UNETR-PRETRAIN), and from scratch (Swin-UNETR-SCRATCH), were trained with subsets of the annotated CBCTs. These models were then evaluated for semantic segmentation performance using the Sørensen-Dice coefficient (DICE), lesion detection performance using sensitivity and specificity, and training sample size requirements by comparing models trained with 20, 40, 60, or 103 samples. RESULTS: Trained with 103 samples, Swin-UNETR-PRETRAIN achieved a DICE of 0.8512 for "lesion," 0.8282 for "restorative materials," 0.9178 for "bone," 0.9029 for "tooth structure," and 0.9901 for "background." "Lesion" DICE was statistically similar between Swin-UNETR-PRETRAIN trained with 103 and 60 images (P > .05), with the latter achieving 1.00 sensitivity and 0.94 specificity in lesion detection. With small training sets, Swin-UNETR-PRETRAIN outperformed Swin-UNETR-SCRATCH in DICE over all labels (P < .001 [n = 20], P < .001 [n = 40]), and U-Net in lesion detection specificity (P = .006 [n = 20], P = .031 [n = 40]). CONCLUSIONS: Transformer-based Swin-UNETR architectures allowed for excellent semantic segmentation and periapical lesion detection. Pretrained, it may provide an alternative with smaller training datasets compared to classic U-Net architectures.

Naoxintong capsule for treating cardiovascular and cerebrovascular diseases: from bench to bedside.

Naoxintong Capsule (NXT), a renowned traditional Chinese medicine (TCM) formulation, has been broadly applied in China for more than 30 years. Over decades, accumulating evidences have proven satisfactory efficacy and safety of NXT in treating cardiovascular and cerebrovascular diseases (CCVD). Studies have been conducted unceasingly, while this growing latest knowledge of NXT has not yet been interpreted properly and summarized comprehensively. Hence, we systematically review the advancements in NXT research, from its chemical constituents, quality control, pharmacokinetics, to its profound pharmacological activities as well as its clinical applications in CCVD. Moreover, we further propose specific challenges for its future perspectives: 1) to precisely clarify bioactivities of single compound in complicated mixtures; 2) to evaluate the pharmacokinetic behaviors of NXT feature components in clinical studies, especially drug-drug interactions in CCVD patients; 3) to explore and validate its multi-target mechanisms by integrating multi-omics technologies; 4) to re-evaluate the safety and efficacy of NXT by carrying out large-scale, multicenter randomized controlled trials. In brief, this review aims to straighten out a paradigm for TCM modernization, which help to contribute NXT as a piece of Chinese Wisdom into the advanced intervention strategy for CCVD therapy.

Interfacing data science with cell therapy manufacturing: where we are and where we need to be.

Although several cell-based therapies have received FDA approval, and others are showing promising results, scalable, and quality-driven reproducible manufacturing of therapeutic cells at a lower cost remains challenging. Challenges include starting material and patient variability, limited understanding of manufacturing process parameter effects on quality, complex supply chain logistics, and lack of predictive, well-understood product quality attributes. These issues can manifest as increased production costs, longer production times, greater batch-to-batch variability, and lower overall yield of viable, high-quality cells. The lack of data-driven insights and decision-making in cell manufacturing and delivery is an underlying commonality behind all these problems. Data collection and analytics from discovery, preclinical and clinical research, process development, and product manufacturing have not been sufficiently utilized to develop a "systems" understanding and identify actionable controls. Experience from other industries shows that data science and analytics can drive technological innovations and manufacturing optimization, leading to improved consistency, reduced risk, and lower cost. The cell therapy manufacturing industry will benefit from implementing data science tools, such as data-driven modeling, data management and mining, AI, and machine learning. The integration of data-driven predictive capabilities into cell therapy manufacturing, such as predicting product quality and clinical outcomes based on manufacturing data, or ensuring robustness and reliability using data-driven supply-chain modeling could enable more precise and efficient production processes and lead to better patient access and outcomes. In this review, we introduce some of the relevant computational and data science tools and how they are being or can be implemented in the cell therapy manufacturing workflow. We also identify areas where innovative approaches are required to address challenges and opportunities specific to the cell therapy industry. We conclude that interfacing data science throughout a cell therapy product lifecycle, developing data-driven manufacturing workflow, designing better data collection tools and algorithms, using data analytics and AI-based methods to better understand critical quality attributes and critical-process parameters, and training the appropriate workforce will be critical for overcoming current industry and regulatory barriers and accelerating clinical translation.

Choline Dehydrogenase Contributes to Salt Tolerance in Dunaliella through Betaine Synthesis.

In Dunaliella tertiolecta, a microalga renowned for its extraordinary tolerance to high salinity levels up to 4.5 M NaCl, the mechanisms underlying its stress response have largely remained a mystery. In a groundbreaking discovery, this study identifies a choline dehydrogenase enzyme, termed DtCHDH, capable of converting choline to betaine aldehyde. Remarkably, this is the first identification of such an enzyme not just in D. tertiolecta but across the entire Chlorophyta. A 3D model of DtCHDH was constructed, and molecular docking with choline was performed, revealing a potential binding site for the substrate. The enzyme was heterologously expressed in E. coli Rosetta (DE3) and subsequently purified, achieving enzyme activity of 672.2 U/mg. To elucidate the role of DtCHDH in the salt tolerance of D. tertiolecta, RNAi was employed to knock down DtCHDH gene expression. The results indicated that the Ri-12 strain exhibited compromised growth under both high and low salt conditions, along with consistent levels of DtCHDH gene expression and betaine content. Additionally, fatty acid analysis indicated that DtCHDH might also be a FAPs enzyme, catalyzing reactions with decarboxylase activity. This study not only illuminates the role of choline metabolism in D. tertiolecta's adaptation to high salinity but also identifies a novel target for enhancing the NaCl tolerance of microalgae in biotechnological applications.

Three coordination polymers based on 4,4'-bis(2-methylimidazol-1-yl)diphenyl ether: Synthesis, structure and selective fluorescent sensing properties.

Three CPs [Zn2(PDA)2(BMIOPE)2·3H2O]n (1), [Co(Br-BDC)(BMIOPE)]n (2) and [Co(MIP)(BMIOPE)]n (3) were synthesized by solvothermal method based on dual-ligand strategy (H2PDA, Br-H2BDC, BMIOPE and H2MIP are 1,3-phenylenediacetic acid, 5-bromo-isophthalic acid, 4,4'-bis(2-methylimidazol-1-yl)diphenyl ether and 5-methylisophthalic acid, respectively). Complexes 1 and 3 exhibit twofold parallel interwoven sql nets. Complex 2 is 2D layer structure. The luminescence property investigations showed that complexes 1-3 could act as multi-responsive fluorescent sensors to detect UO22+, Cr2O72- and CrO42- and nitrofurantoin (NFT) through fluorescence turn-off process, presenting excellent sensitivity and selectivity. Finally, the possible fluorescent quenching mechanisms of complexes 1-3 toward the above pollutants are also further investigated by employing spectroscopic methods and quantum chemical calculations. The fluorescence lifetime measurements manifest the mechanism of fluorescence quenching is static quenching process.