Design and synthesis of cantharidin derivative DCZ5418 as a TRIP13 inhibitor with anti-multiple myeloma activity in vitro and in vivo.

Natural product cantharidin can inhibit multiple myeloma cell growth in vitro, while serious adverse effects limited its clinical application. Therefore, the structural modification of cantharidin is needed. Herein, inspired by the structural similarity of the aliphatic endocyclic moiety in cantharidin and TRIP13 inhibitor DCZ0415, we designed and synthesized DCZ5418 and its nineteen derivatives. The molecular docking study indicated that DCZ5418 had a similar binding mode to TRIP13 protein as DCZ0415 while with a stronger docking score. Moreover, the bioassay studies of the MM-cells viability inhibition, TRIP13 protein binding affinity and enzyme inhibiting activity showed that DCZ5418 had good anti-MM activity in vitro and definite interaction with TRIP13 protein. The acute toxicity test of DCZ5418 showed less toxicity in vivo than cantharidin. Furthermore, DCZ5418 showed good anti-MM effects in vivo with a lower dose administration than DCZ0415 (15 mg/kg vs 25 mg/kg) on the tumor xenograft models. Thus, we obtained a new TRIP13 inhibitor DCZ5418 with improved safety and good activity in vivo, which provides a new example of lead optimization by using the structural fragments of natural products.

Design, synthesis and biological evaluation of chalcone derivatives as potent and orally active hCYP3A4 inhibitors.

Human cytochrome P450 3A4 (hCYP3A4), one of the most important drug-metabolizing enzymes, catalyze the metabolic clearance of ∼50% therapeutic drugs. CYP3A4 inhibitors have been used for improving the in vivo efficacy of hCYP3A4-substrate drugs. However, most of existing hCYP3A4 inhibitors may trigger serious adverse effects or undesirable effects on endogenous metabolism. This study aimed to discover potent and orally active hCYP3A4 inhibitors from chalcone derivatives and to test their anti-hCYP3A4 effects both in vitro and in vivo. Following three rounds of screening and structural optimization, the isoquinoline chalcones were found with excellently anti-hCYP3A4 effects. SAR studies showed that introducing an isoquinoline ring on the A-ring significantly enhanced anti-CYP3A4 effect, generating A10 (IC50 = 102.10 nM) as a promising lead compound. The 2nd round of SAR studies showed that introducing a substituent group at the para position of the carbonyl group on B-ring strongly improved the anti-CYP3A4 effect. As a result, C6 was identified as the most potent hCYP3A4 inhibitor (IC50 = 43.93 nM) in human liver microsomes (HLMs). C6 also displayed potent anti-hCYP3A4 effect in living cells (IC50 = 153.00 nM), which was superior to the positive inhibitor ketoconazole (IC50 = 251.00 nM). Mechanistic studies revealed that C6 could potently inhibit CYP3A4-catalyzed N-ethyl-1,8-naphthalimide (NEN) hydroxylation in a competitive manner (Ki = 30.00 nM). Moreover, C6 exhibited suitable metabolic stability in HLMs and showed good safety profiles in mice. In vivo tests demonstrated that C6 (100 mg/kg, orally administration) significantly increased the AUC(0-inf) of midazolam by 3.63-fold, and strongly prolonged its half-life by 1.66-fold compared with the vehicle group in mice. Collectively, our findings revealed the SARs of chalcone derivatives as hCYP3A4 inhibitors and offered several potent chalcone-type hCYP3A4 inhibitors, while C6 could serve as a good lead compound for developing novel, orally active CYP3A4 inhibitors with improved druglikeness properties.

Design, synthesis and biological evaluation of salicylanilides as novel allosteric inhibitors of human pancreatic lipase.

Obesity is a growing global health problem and is associated with increased prevalence of many metabolic disorders, including diabetes, hypertension and cardiovascular disease. Pancreatic lipase (PL) has been validated as a key target for developing anti-obesity agents, owing to its crucial role in lipid digestion and absorption. In the past few decades, porcine PL (pPL) is always used as the enzyme source for screening PL inhibitors, which generate numerous pPL inhibitors but the potent inhibitors against human PL (hPL) are rarely reported. Herein, a series of salicylanilide derivatives were designed and synthesized, while their anti-hPL effects were assayed by a fluorescence-based biochemical approach. To investigate the structure-activity relationships of salicylanilide derivatives as hPL inhibitors in detail, structural modifications on three rings (A, B and C) of the salicylanilide skeleton were performed. Among all tested compounds, 2t and 2u were found possessing the most potent anti-PL activity, showing IC50 values of 1.86 µM and 1.63 µM, respectively. Inhibition kinetic analyses suggested that both 2t and 2u could effectively inhibit hPL in a non-competitive manner, with the ki value of 1.67 µM and 1.70 µM, respectively. Fluorescence quenching assays suggested that two inhibitors could quench the fluorescence of hPL via a static quenching procedure. Molecular docking simulations suggested that 2t and 2u could tightly bind on an allosteric site of hPL. Collectively, the structure-activity relationships of salicylanilide derivatives as hPL inhibitors were carefully investigated, while two newly identified reversible hPL inhibitors (2t and 2u) could be used as promising lead compounds to develop novel anti-obesity drugs.

Development of Yin-Yang ligand for cannabinoid receptors.

Cannabinoid receptors (CBs), including CB1 and CB2, are the key components of a lipid signaling endocannabinoid system (ECS). Development of synthetic cannabinoids has been attractive to modulate ECS functions. CB1 and CB2 are structurally closely related subtypes but with distinct functions. While most efforts focus on the development of selective ligands for single subtype to circumvent the undesired off-target effect, Yin-Yang ligands with opposite pharmacological activities simultaneously on two subtypes, offer unique therapeutic potential. Herein we report the development of a new Yin-Yang ligand which functions as an antagonist for CB1 and concurrently an agonist for CB2. We found that in the pyrazole-cored scaffold, the arm of N1-phenyl group could be a switch, modification of which yielded various ligands with distinct activities. As such, the ortho-morpholine substitution exerted the desired Yin-Yang bifunctionality which, based on the docking study and molecular dynamic simulation, was proposed to be resulted from the hydrogen bonding with S173 and S285 in CB1 and CB2, respectively. Our results demonstrated the feasibility of structure guided ligand evolution for challenging Yin-Yang ligand.

Biocement stabilization of an experimental-scale artificial slope and the reformation of iron-rich crusts.

Novel biotechnologies are required to remediate iron ore mines and address the increasing number of tailings (mine waste) dam collapses worldwide. In this study, we aimed to accelerate iron reduction and oxidation to stabilize an artificial slope. An open-air bioreactor was inoculated with a mixed consortium of microorganisms capable of reducing iron. Fluid from the bioreactor was allowed to overflow onto the artificial slope. Carbon sources from the bioreactor fluid promoted the growth of a surface biofilm within the artificial slope, which naturally aggregated the crushed grains. The biofilms provided an organic framework for the nucleation of iron oxide minerals. Iron-rich biocements stabilized the artificial slope and were significantly more resistant to physical deformation compared with the control experiment. These biotechnologies highlight the potential to develop strategies for mine remediation and waste stabilization by accelerating the biogeochemical cycling of iron.

Ensemble Learning with Supervised Methods Based on Large-Scale Protein Language Models for Protein Mutation Effects Prediction.

Machine learning has been increasingly utilized in the field of protein engineering, and research directed at predicting the effects of protein mutations has attracted increasing attention. Among them, so far, the best results have been achieved by related methods based on protein language models, which are trained on a large number of unlabeled protein sequences to capture the generally hidden evolutionary rules in protein sequences, and are therefore able to predict their fitness from protein sequences. Although numerous similar models and methods have been successfully employed in practical protein engineering processes, the majority of the studies have been limited to how to construct more complex language models to capture richer protein sequence feature information and utilize this feature information for unsupervised protein fitness prediction. There remains considerable untapped potential in these developed models, such as whether the prediction performance can be further improved by integrating different models to further improve the accuracy of prediction. Furthermore, how to utilize large-scale models for prediction methods of mutational effects on quantifiable properties of proteins due to the nonlinear relationship between protein fitness and the quantification of specific functionalities has yet to be explored thoroughly. In this study, we propose an ensemble learning approach for predicting mutational effects of proteins integrating protein sequence features extracted from multiple large protein language models, as well as evolutionarily coupled features extracted in homologous sequences, while comparing the differences between linear regression and deep learning models in mapping these features to quantifiable functional changes. We tested our approach on a dataset of 17 protein deep mutation scans and indicated that the integrated approach together with linear regression enables the models to have higher prediction accuracy and generalization. Moreover, we further illustrated the reliability of the integrated approach by exploring the differences in the predictive performance of the models across species and protein sequence lengths, as well as by visualizing clustering of ensemble and non-ensemble features.

Transition-Linker Containing Detergents for Membrane Protein Studies.

It is a pressing need, but still challenging to explore the structure and function of membrane proteins (MPs). One of the main obstacles is the limited availability of matched detergents for the handling of specific MPs. We describe herein the design of new detergents by incorporation of a transition linker between the hydrophilic head and the hydrophobic tail. This design allows a gradual change of hydrophobicity between the outside and inside of micelles, in contrast to the abrupt switch in conventional detergents. Notably, many of these detergents assembled into micelles in while retaining low critical micelle concentrations. Meanwhile, thermal stabilizing evaluation identified superior detergents for representative MPs, including G protein-coupled receptors and a transporter protein. Among them, further improved the NMR study of MPs. We anticipate these that results will encourage future detergent expansion through new remodeling on the traditional detergent scaffold.

Global-local multi-stage temporal convolutional network for cataract surgery phase recognition.

BACKGROUND: Surgical video phase recognition is an essential technique in computer-assisted surgical systems for monitoring surgical procedures, which can assist surgeons in standardizing procedures and enhancing postsurgical assessment and indexing. However, the high similarity between the phases and temporal variations of cataract videos still poses the greatest challenge for video phase recognition. METHODS: In this paper, we introduce a global-local multi-stage temporal convolutional network (GL-MSTCN) to explore the subtle differences between high similarity surgical phases and mitigate the temporal variations of surgical videos. The presented work consists of a triple-stream network (i.e., pupil stream, instrument stream, and video frame stream) and a multi-stage temporal convolutional network. The triple-stream network first detects the pupil and surgical instruments regions in the frame separately and then obtains the fine-grained semantic features of the video frames. The proposed multi-stage temporal convolutional network improves the surgical phase recognition performance by capturing longer time series features through dilated convolutional layers with varying receptive fields. RESULTS: Our method is thoroughly validated on the CSVideo dataset with 32 cataract surgery videos and the public Cataract101 dataset with 101 cataract surgery videos, outperforming state-of-the-art approaches with 95.8% and 96.5% accuracy, respectively. CONCLUSIONS: The experimental results show that the use of global and local feature information can effectively enhance the model to explore fine-grained features and mitigate temporal and spatial variations, thus improving the surgical phase recognition performance of the proposed GL-MSTCN.

Evaluation of Ocular Surface Characteristics in Dry Eye Disease With and Without Soft Contact Lens Wear: A Comparative Study.

OBJECTIVES: To investigate ocular surface alterations and in vivo confocal microscopic characteristics of the cornea in dry eye disease (DED) with contact lens wear (CLW). METHODS: Sixty participants were divided into three groups: DED with CLW (n=20), DED without CLW (n=20), and normal control (n=20). Ocular surface parameters were evaluated. Basal tears and in vivo confocal microscopy images of the cornea were collected. Multiplex bead analysis was used to assess interleukin (IL)-6, IL-1ß, tumor necrosis factor (TNF)-α, nerve growth factor (NGF), and substance P (SP) in tears. Nerve morphology and dendritic cell density in corneal subbasal nerve images were calculated. RESULTS: The DED with CLW group showed significantly higher ocular surface staining scores ( P =0.022) and higher levels of IL-1ß, NGF, and SP in tears ( P =0.014, P =0.004 and P =0.025) than the DED without CLW group. Corneal dendritic cell density in the DED with CLW group was significantly higher than that in the normal controls ( P =0.001) and DED without CLW group ( P =0.043). Tear cytokine levels of IL-1ß, NGF, and SP were correlated with ocular surface parameters in the DED with CLW group. Moreover, the years of CLW were positively correlated with corneal dendritic cell density (r=0.527, P =0.017) and negatively correlated with corneal nerve density (r=-0.511, P =0.021). CONCLUSIONS: Patients with DED with CLW showed greater epithelial damage, elevated inflammatory cytokines and neuromediators in tears, and higher corneal dendritic cell density than patients with DED without CLW. The immune and nervous systems may be involved in contact lens-related DED.

One step stereoselective synthesis of oxazoline-fused saccharides and their conversion into the corresponding 1,2-cis glycosylamines bearing various protected groups.

Herein we disclosed a straightforward synthesis of oxazoline-fused saccharides (oxazolinoses) from peracetylated saccharides and benzonitriles under acidic conditions with stoichiometric amounts of water. The density functional theory (DFT) calculations have revealed the origin of the stereoselectivity and the key role of water in promoting the departure of the acetyl group at C-2. The resulting oxazolinoses can be concisely converted into the corresponding 1,2-cis glycosylamines bearing various protected groups, allowing the access to schisandrin derivatives.

Weighing features of lung and heart regions for thoracic disease classification.

BACKGROUND: Chest X-rays are the most commonly available and affordable radiological examination for screening thoracic diseases. According to the domain knowledge of screening chest X-rays, the pathological information usually lay on the lung and heart regions. However, it is costly to acquire region-level annotation in practice, and model training mainly relies on image-level class labels in a weakly supervised manner, which is highly challenging for computer-aided chest X-ray screening. To address this issue, some methods have been proposed recently to identify local regions containing pathological information, which is vital for thoracic disease classification. Inspired by this, we propose a novel deep learning framework to explore discriminative information from lung and heart regions. RESULT: We design a feature extractor equipped with a multi-scale attention module to learn global attention maps from global images. To exploit disease-specific cues effectively, we locate lung and heart regions containing pathological information by a well-trained pixel-wise segmentation model to generate binarization masks. By introducing element-wise logical AND operator on the learned global attention maps and the binarization masks, we obtain local attention maps in which pixels are are 1 for lung and heart region and 0 for other regions. By zeroing features of non-lung and heart regions in attention maps, we can effectively exploit their disease-specific cues in lung and heart regions. Compared to existing methods fusing global and local features, we adopt feature weighting to avoid weakening visual cues unique to lung and heart regions. Our method with pixel-wise segmentation can help overcome the deviation of locating local regions. Evaluated by the benchmark split on the publicly available chest X-ray14 dataset, the comprehensive experiments show that our method achieves superior performance compared to the state-of-the-art methods. CONCLUSION: We propose a novel deep framework for the multi-label classification of thoracic diseases in chest X-ray images. The proposed network aims to effectively exploit pathological regions containing the main cues for chest X-ray screening. Our proposed network has been used in clinic screening to assist the radiologists. Chest X-ray accounts for a significant proportion of radiological examinations. It is valuable to explore more methods for improving performance.

Construction of a rAAV-SaCas9 system expressing eGFP and its application to improve muscle mass.

An ideal rAAV gene editing system not only effectively edits genes at specific site, but also prevents the spread of the virus from occurring off-target or carcinogenic risks. This is important for gene editing research at specific site in vivo. We report a single rAAV containing SaCas9 and guide RNAs under the control of subtle EF1a and tRNA promoters. The capacity of rAAV was compressed, and the editing efficiency was similar to that of the classical Cas9 system in vitro and in vivo. And we inserted the sequence of the green fluorescent protein eGFP into rAAV. The number of cells infected with the rAAV and the region in which the rAAV spreads were known by the fluorescent expression of eGFP in cells. In addition, we demonstrated that myostatin gene in the thigh muscles of C57BL/10 mice was knocked out by the rAAV9-SaCas9 system to make muscle mass increased obviously. The protein eGFP into rAAV has significant implications for our indirect analysis of the editing efficiency of SaCas9 in the genome of the target tissue and reduces the harm caused by off-target editing and prevents other tissue mutations. The rAAV system has substantial potential in improving muscle mass and preventing muscle atrophy.

An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study.

AIMS/HYPOTHESIS: Corneal confocal microscopy is a rapid non-invasive ophthalmic imaging technique that identifies peripheral and central neurodegenerative disease. Quantification of corneal sub-basal nerve plexus morphology, however, requires either time-consuming manual annotation or a less-sensitive automated image analysis approach. We aimed to develop and validate an artificial intelligence-based, deep learning algorithm for the quantification of nerve fibre properties relevant to the diagnosis of diabetic neuropathy and to compare it with a validated automated analysis program, ACCMetrics. METHODS: Our deep learning algorithm, which employs a convolutional neural network with data augmentation, was developed for the automated quantification of the corneal sub-basal nerve plexus for the diagnosis of diabetic neuropathy. The algorithm was trained using a high-end graphics processor unit on 1698 corneal confocal microscopy images; for external validation, it was further tested on 2137 images. The algorithm was developed to identify total nerve fibre length, branch points, tail points, number and length of nerve segments, and fractal numbers. Sensitivity analyses were undertaken to determine the AUC for ACCMetrics and our algorithm for the diagnosis of diabetic neuropathy. RESULTS: The intraclass correlation coefficients for our algorithm were superior to those for ACCMetrics for total corneal nerve fibre length (0.933 vs 0.825), mean length per segment (0.656 vs 0.325), number of branch points (0.891 vs 0.570), number of tail points (0.623 vs 0.257), number of nerve segments (0.878 vs 0.504) and fractals (0.927 vs 0.758). In addition, our proposed algorithm achieved an AUC of 0.83, specificity of 0.87 and sensitivity of 0.68 for the classification of participants without (n = 90) and with (n = 132) neuropathy (defined by the Toronto criteria). CONCLUSIONS/INTERPRETATION: These results demonstrated that our deep learning algorithm provides rapid and excellent localisation performance for the quantification of corneal nerve biomarkers. This model has potential for adoption into clinical screening programmes for diabetic neuropathy. DATA AVAILABILITY: The publicly shared cornea nerve dataset (dataset 1) is available at http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Tortuosity%20Data%20Set.htm and http://bioimlab.dei.unipd.it/Corneal%20Nerve%20Data%20Set.htm.

Geometrical force constraint method for vessel and x-ray angiogram simulation.

This study proposes a novel geometrical force constraint method for 3-D vasculature modeling and angiographic image simulation. For this method, space filling force, gravitational force, and topological preserving force are proposed and combined for the optimization of the topology of the vascular structure. The surface covering force and surface adhesion force are constructed to drive the growth of the vasculature on any surface. According to the combination effects of the topological and surface adhering forces, a realistic vasculature can be effectively simulated on any surface. The image projection of the generated 3-D vascular structures is simulated according to the perspective projection and energy attenuation principles of X-rays. Finally, the simulated projection vasculature is fused with a predefined angiographic mask image to generate a realistic angiogram. The proposed method is evaluated on a CT image and three generally utilized surfaces. The results fully demonstrate the effectiveness and robustness of the proposed method.

Choroidal Layer Analysis in OCT images via Ambiguous Boundary-aware Attention.

Optical Coherence Tomography (OCT) is a commonly used retina imaging technique, and it is capable of revealing the morphology of the choroid. However, the segmentation and quantitative analysis of the sublayers and vessels in choroid are rarely explored, primarily due to the indistinct boundaries of choroidal sublayers, and imbalanced distribution of vessels observed in OCT imagery. In this paper, we propose a novel two-stage architecture called Choroidal Layer Analysis network (CLA), that may be considered the first attempt in this research community for joint segmentation of choroidal sublayers and choroidal vessels in OCT images. CLA employs the encoder-decoder network with the residual U-shape module as the backbone. In order to empower the ability of the segmentation model to identify the inconspicuous boundaries of choroidal sublayers, we introduce an Ambiguous Boundary Attention block (ABA) into the bottleneck of the encoder-decoder network in the first stage. For more accurate segmentation of large choroidal vessels with ambiguous contours and imbalanced spatial distribution, the second stage introduces an active contour-based loss to refine the contours of choroidal vessels simultaneously with precise identification of each vessel via contextual modeling. To train, test and validate the proposed model, we conducted a choroidal segmentation dataset containing 800 OCT images, with their sublayers and large choroidal vessels manually annotated. Experimental results demonstrate the superiority of the proposed approach compared with other state-of-the-art segmentation networks in large margins. It is worth noting that we also reconstructed the large choroidal vessels in three-dimensional (3D) based on the segmentation results, and multiple 3D morphological parameters were calculated. The statistical analysis of these parameters demonstrates significant differences between the healthy control and high myopia group, and this further confirms the proposed work may facilitate subsequent disease understanding and clinical decision-making.

Integration of smartphone technology and artificial intelligence for advanced ophthalmic care: A systematic review.

Background: The convergence of smartphone technology and artificial intelligence (AI) has revolutionized the landscape of ophthalmic care, offering unprecedented opportunities for diagnosis, monitoring, and management of ocular conditions. Nevertheless, there is a lack of systematic studies on discussing the integration of smartphone and AI in this field. Main text: This review includes 52 studies, and explores the integration of smartphones and AI in ophthalmology, delineating its collective impact on screening methodologies, disease detection, telemedicine initiatives, and patient management. The collective findings from the curated studies indicate promising performance of the smartphone-based AI screening for various ocular diseases which encompass major retinal diseases, glaucoma, cataract, visual impairment in children and ocular surface diseases. Moreover, the utilization of smartphone-based imaging modalities, coupled with AI algorithms, is able to provide timely, efficient and cost-effective screening for ocular pathologies. This modality can also facilitate patient self-monitoring, remote patient monitoring and enhancing accessibility to eye care services, particularly in underserved regions. Challenges involving data privacy, algorithm validation, regulatory frameworks and issues of trust are still need to be addressed. Furthermore, evaluation on real-world implementation is imperative as well, and real-world prospective studies are currently lacking. Conclusions: Smartphone ocular imaging merged with AI enables earlier, precise diagnoses, personalized treatments, and enhanced service accessibility in eye care. Collaboration is crucial to navigate ethical and data security challenges while responsibly leveraging these innovations, promising a potential revolution in care access and global eye health equity.

Cross-modality transfer learning with knowledge infusion for diabetic retinopathy grading.

Background: Ultra-wide-field (UWF) fundus photography represents an emerging retinal imaging technique offering a broader field of view, thus enhancing its utility in screening and diagnosing various eye diseases, notably diabetic retinopathy (DR). However, the application of computer-aided diagnosis for DR using UWF images confronts two major challenges. The first challenge arises from the limited availability of labeled UWF data, making it daunting to train diagnostic models due to the high cost associated with manual annotation of medical images. Secondly, existing models' performance requires enhancement due to the absence of prior knowledge to guide the learning process. Purpose: By leveraging extensively annotated datasets within the field, which encompass large-scale, high-quality color fundus image datasets annotated at either image-level or pixel-level, our objective is to transfer knowledge from these datasets to our target domain through unsupervised domain adaptation. Methods: Our approach presents a robust model for assessing the severity of diabetic retinopathy (DR) by leveraging unsupervised lesion-aware domain adaptation in ultra-wide-field (UWF) images. Furthermore, to harness the wealth of detailed annotations in publicly available color fundus image datasets, we integrate an adversarial lesion map generator. This generator supplements the grading model by incorporating auxiliary lesion information, drawing inspiration from the clinical methodology of evaluating DR severity by identifying and quantifying associated lesions. Results: We conducted both quantitative and qualitative evaluations of our proposed method. In particular, among the six representative DR grading methods, our approach achieved an accuracy (ACC) of 68.18% and a precision (pre) of 67.43%. Additionally, we conducted extensive experiments in ablation studies to validate the effectiveness of each component of our proposed method. Conclusion: In conclusion, our method not only improves the accuracy of DR grading, but also enhances the interpretability of the results, providing clinicians with a reliable DR grading scheme.

Multi-granularity learning of explicit geometric constraint and contrast for label-efficient medical image segmentation and differentiable clinical function assessment.

Automated segmentation is a challenging task in medical image analysis that usually requires a large amount of manually labeled data. However, most current supervised learning based algorithms suffer from insufficient manual annotations, posing a significant difficulty for accurate and robust segmentation. In addition, most current semi-supervised methods lack explicit representations of geometric structure and semantic information, restricting segmentation accuracy. In this work, we propose a hybrid framework to learn polygon vertices, region masks, and their boundaries in a weakly/semi-supervised manner that significantly advances geometric and semantic representations. Firstly, we propose multi-granularity learning of explicit geometric structure constraints via polygon vertices (PolyV) and pixel-wise region (PixelR) segmentation masks in a semi-supervised manner. Secondly, we propose eliminating boundary ambiguity by using an explicit contrastive objective to learn a discriminative feature space of boundary contours at the pixel level with limited annotations. Thirdly, we exploit the task-specific clinical domain knowledge to differentiate the clinical function assessment end-to-end. The ground truth of clinical function assessment, on the other hand, can serve as auxiliary weak supervision for PolyV and PixelR learning. We evaluate the proposed framework on two tasks, including optic disc (OD) and cup (OC) segmentation along with vertical cup-to-disc ratio (vCDR) estimation in fundus images; left ventricle (LV) segmentation at end-diastolic and end-systolic frames along with ejection fraction (LVEF) estimation in two-dimensional echocardiography images. Experiments on nine large-scale datasets of the two tasks under different label settings demonstrate our model's superior performance on segmentation and clinical function assessment.

Deep segmentation of OCTA for evaluation and association of changes of retinal microvasculature with Alzheimer's disease and mild cognitive impairment.

BACKGROUND: Optical coherence tomography angiography (OCTA) enables fast and non-invasive high-resolution imaging of retinal microvasculature and is suggested as a potential tool in the early detection of retinal microvascular changes in Alzheimer's Disease (AD). We developed a standardised OCTA analysis framework and compared their extracted parameters among controls and AD/mild cognitive impairment (MCI) in a cross-section study. METHODS: We defined and extracted geometrical parameters of retinal microvasculature at different retinal layers and in the foveal avascular zone (FAZ) from segmented OCTA images obtained using well-validated state-of-the-art deep learning models. We studied these parameters in 158 subjects (62 healthy control, 55 AD and 41 MCI) using logistic regression to determine their potential in predicting the status of our subjects. RESULTS: In the AD group, there was a significant decrease in vessel area and length densities in the inner vascular complexes (IVC) compared with controls. The number of vascular bifurcations in AD is also significantly lower than that of healthy people. The MCI group demonstrated a decrease in vascular area, length densities, vascular fractal dimension and the number of bifurcations in both the superficial vascular complexes (SVC) and the IVC compared with controls. A larger vascular tortuosity in the IVC, and a larger roundness of FAZ in the SVC, can also be observed in MCI compared with controls. CONCLUSION: Our study demonstrates the applicability of OCTA for the diagnosis of AD and MCI, and provides a standard tool for future clinical service and research. Biomarkers from retinal OCTA images can provide useful information for clinical decision-making and diagnosis of AD and MCI.

Adversarial-based latent space alignment network for left atrial appendage segmentation in transesophageal echocardiography images.

Left atrial appendage (LAA) is a leading cause of atrial fibrillation and thrombosis in cardiovascular disease. Clinicians can rely on LAA occlusion (LAAO) to effectively prevent and treat ischaemic strokes attributed to the LAA. The correct selection of the LAAO is one of the most critical stages in the successful surgical process, which relies on the quantification of the anatomical structure of the LAA for successful intervention in LAAO. In this paper, we propose an adversarial-based latent space alignment framework for LAA segmentation in transesophageal echocardiography (TEE) images by introducing prior knowledge from the label. The proposed method consists of an LAA segmentation network, a label reconstruction network, and a latent space alignment loss. To be specific, we first employ ConvNeXt as the backbone of the segmentation and reconstruction network to enhance the feature extraction capability of the encoder. The label reconstruction network then encodes the prior shape features from the LAA labels to the latent space. The latent space alignment loss consists of the adversarial-based alignment and the contrast learning losses. It can motivate the segmentation network to learn the prior shape features of the labels, thus improving the accuracy of LAA edge segmentation. The proposed method was evaluated on a TEE dataset including 1,783 images and the experimental results showed that the proposed method outperformed other state-of-the-art LAA segmentation methods with Dice coefficient, AUC, ACC, G-mean, and Kappa of 0.831, 0.917, 0.989, 0.911, and 0.825, respectively.