Multi-Label Chest X-Ray Image Classification with Single Positive Labels.

Deep learning approaches for multi-label Chest X-ray (CXR) images classification usually require large-scale datasets. However, acquiring such datasets with full annotations is costly, time-consuming, and prone to noisy labels. Therefore, we introduce a weakly supervised learning problem called Single Positive Multi-label Learning (SPML) into CXR images classification (abbreviated as SPML-CXR), in which only one positive label is annotated per image. A simple solution to SPML-CXR problem is to assume that all the unannotated pathological labels are negative, however, it might introduce false negative labels and decrease the model performance. To this end, we present a Multi-level Pseudo-label Consistency (MPC) framework for SPML-CXR. First, inspired by the pseudo-labeling and consistency regularization in semi-supervised learning, we construct a weak-to-strong consistency framework, where the model prediction on weakly-augmented image is treated as the pseudo label for supervising the model prediction on a strongly-augmented version of the same image, and define an Image-level Perturbation-based Consistency (IPC) regularization to recover the potential mislabeled positive labels. Besides, we incorporate Random Elastic Deformation (RED) as an additional strong augmentation to enhance the perturbation. Second, aiming to expand the perturbation space, we design a perturbation stream to the consistency framework at the feature-level and introduce a Feature-level Perturbation-based Consistency (FPC) regularization as a supplement. Third, we design a Transformer-based encoder module to explore the sample relationship within each mini-batch by a Batch-level Transformer-based Correlation (BTC) regularization. Extensive experiments on the CheXpert and MIMIC-CXR datasets have shown the effectiveness of our MPC framework for solving the SPML-CXR problem.

SSM-Net: Semi-supervised multi-task network for joint lesion segmentation and classification from pancreatic EUS images.

Pancreatic cancer does not show specific symptoms, which makes the diagnosis of early stages difficult with established image-based screening methods and therefore has the worst prognosis among all cancers. Although endoscopic ultrasonography (EUS) has a key role in diagnostic algorithms for pancreatic diseases, B-mode imaging of the pancreas can be affected by confounders such as chronic pancreatitis, which can make both pancreatic lesion segmentation and classification laborious and highly specialized. To address these challenges, this work proposes a semi-supervised multi-task network (SSM-Net) to leverage unlabeled and labeled EUS images for joint pancreatic lesion classification and segmentation. Specifically, we first devise a saliency-aware representation learning module (SRLM) on a large number of unlabeled images to train a feature extraction encoder network for labeled images by computing a contrastive loss with a semantic saliency map, which is obtained by our spectral residual module (SRM). Moreover, for labeled EUS images, we devise channel attention blocks (CABs) to refine the features extracted from the pre-trained encoder on unlabeled images for segmenting lesions, and then devise a merged global attention module (MGAM) and a feature similarity loss (FSL) for obtaining a lesion classification result. We collect a large-scale EUS-based pancreas image dataset (LS-EUSPI) consisting of 9,555 pathologically proven labeled EUS images (499 patients from four categories) and 15,500 unlabeled EUS images. Experimental results on the LS-EUSPI dataset and a public thyroid gland lesion dataset show that our SSM-Net clearly outperforms state-of-the-art methods.

[Intraoperative slide rail CT assistance in percutaneous sacroiliac joint screws for the treatment of pelvic posterior ring injury].

OBJECTIVE: To compare the clinical efficacy of intraoperative slide rail CT combined with C-arm X-ray assistance and just C-arm for percutaneous screw in the treatment of pelvic posterior ring injury. METHODS: A retrospective analysis was performed on the patient data of 76 patients with posterior pelvic ring injury admitted to the Department of Orthopedic Trauma from December 2018 to February 2022. Among them, 39 patients in the CT group were treated with C-arm combined with slide rail CT-assisted inline fixation including 23 males and 16 females with an average age of (44.98±7.33) years old;and the other 37 patients in the C-arm group were treated with intraline fixation treatment under only C-arm fluoroscopy including 24 males and 13 females with an average age of (44.37±10.82) years old. Among them, 42 patients with anterior ring fractures were treated with percutaneous inferior iliac spines with internal fixation (INFIX) or suprapubic support screws to fix the anterior pelvic ring. Postoperative follow-up time, operation time, complications of the two groups were compared. Results of Matta reduction criteria, Majed efficacy evaluation, the CT grading and the rate of secondary surgical revision were compared. RESULTS: The nailing time of (32.63±7.33) min in CT group was shorter than that of (52.95±10.64) min in C-arm group (t=-9.739, P<0.05). The follow-up time between CT group (11.97±1.86) months and C-arm group (12.03±1.71) months were not statistically significant(P>0.05). The postoperative complication rates between two groups were not statistically significant (χ2=0.159, P>0.05). Results of Matta reduction criteria (Z=2.79, P<0.05), Majeed efficacy evaluation(Z=2.79, P<0.05), CT grading (Z=2.83, P<0.05) in CT group were better than those in C-arm group(P<0.05); the secondary surgical revision rate in the CT group was significantly lower than that in the C-arm group (χ2=5.641, P<0.05). CONCLUSION: Compared with traditional C-arm fluoroscopy, intraoperative slide rail CT combined with C-arm assisted percutaneous sacroiliac joint screw placement surgery has the characteristics of short operation time, high accuracy and safety, and significant decrease in postoperative secondary revision rate, and is one of the effective methods for re-establishing the stability of the posterior ring of pelvic fracture.

A Highly Sensitive Strain Sensor with Wide Linear Sensing Range Prepared on a Hybrid-Structured CNT/Ecoflex Film via Local Regulation of Strain Distribution.

With the development of information technology, high-performance wearable strain sensors with high sensitivity and stretchability have played a significant role in motion detection. However, many high-sensitivity and outstanding-stretchability strain sensors possess a limited linear sensing range, which limits the enhancement of the flexible strain sensors' performance. Herein, we develop a hybrid-structured carbon nanotube (CNT)/Ecoflex strain sensor with laser-engraved grooves along with punched circular holes in a composite CNT/Ecoflex film by vacuum filtration and permeation. By optimizing the distribution of grooves and circular holes, the strain in the sensing layer can be locally regulated, which alters the morphology of cracks under strain and allows the hybrid-structured CNT/Ecoflex strain sensor to simultaneously exhibit high sensitivity (GF = 43.8) as well as a wide linear sensing range (200%). On the basis of excellent performance, the hybrid-structured CNT/Ecoflex strain sensor is capable of detecting movements in various parts of the human body, including movements of larynx and joint bending.

Linear Capacitive Pressure Sensor with Gradient Architecture through Laser Ablation on MWCNT/Ecoflex Film.

The practical application of flexible pressure sensors, including electronic skins, wearable devices, human-machine interaction, etc., has attracted widespread attention. However, the linear response range of pressure sensors remains an issue. Ecoflex, as a silicone rubber, is a common material for flexible pressure sensors. Herein, we have innovatively designed and fabricated a pressure sensor with a gradient micro-cone architecture generated by CO2 laser ablation of MWCNT/Ecoflex dielectric layer film. In cooperation with the gradient micro-cone architecture and a dielectric layer of MWCNT/Ecoflex with a variable high dielectric constant under pressure, the pressure sensor exhibits linearity (R2 = 0.990) within the pressure range of 0-60 kPa, boasting a sensitivity of 0.75 kPa-1. Secondly, the sensor exhibits a rapid response time of 95 ms, a recovery time of 129 ms, hysteresis of 6.6%, and stability over 500 cycles. Moreover, the sensor effectively exhibited comprehensive detection of physiological signals, airflow detection, and Morse code communication, thereby demonstrating the potential for various applications.

Early postoperative interventions in the prevention and management of thyroidectomy scars.

Thyroidectomy scars, located on the exposed site, can cause distress in patients. Owing to the cosmetic importance of thyroidectomy scars, many studies have been conducted on its prevention and treatment. Scar formation factors mainly include inflammatory cell infiltration, angiogenesis, fibroblast proliferation, secretion of cytokines such as transforming growth factor (TGF)-ß1, and mechanical tension on the wound edges. Anti-scar methods including topical anti-scar agents, skin tension-bearing devices, and local injections of botulinum toxin, as well as lasers and phototherapies, that target these scar formation factors have been developed. However, current studies remain fragmented, and there is a lack of a comprehensive evaluation of the impacts of these anti-scar methods on treating thyroidectomy scars. Early intervention is a crucial but often neglected key to control hyperplastic thyroidectomy scars. Therefore, we review the currently adopted early postoperative strategies for thyroidectomy scar reduction, aiming to illustrate the mechanism of these anti-scar methods and provide flexible and comprehensive treatment selections for clinical physicians to deal with thyroidectomy scars.

DRAC 2022: A public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images.

We described a challenge named "DRAC - Diabetic Retinopathy Analysis Challenge" in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022). Within this challenge, we provided the DRAC datset, an ultra-wide optical coherence tomography angiography (UW-OCTA) dataset (1,103 images), addressing three primary clinical tasks: diabetic retinopathy (DR) lesion segmentation, image quality assessment, and DR grading. The scientific community responded positively to the challenge, with 11, 12, and 13 teams submitting different solutions for these three tasks, respectively. This paper presents a concise summary and analysis of the top-performing solutions and results across all challenge tasks. These solutions could provide practical guidance for developing accurate classification and segmentation models for image quality assessment and DR diagnosis using UW-OCTA images, potentially improving the diagnostic capabilities of healthcare professionals. The dataset has been released to support the development of computer-aided diagnostic systems for DR evaluation.

Resistant starch intake facilitates weight loss in humans by reshaping the gut microbiota.

Emerging evidence suggests that modulation of gut microbiota by dietary fibre may offer solutions for metabolic disorders. In a randomized placebo-controlled crossover design trial (ChiCTR-TTRCC-13003333) in 37 participants with overweight or obesity, we test whether resistant starch (RS) as a dietary supplement influences obesity-related outcomes. Here, we show that RS supplementation for 8 weeks can help to achieve weight loss (mean -2.8 kg) and improve insulin resistance in individuals with excess body weight. The benefits of RS are associated with changes in gut microbiota composition. Supplementation with Bifidobacterium adolescentis, a species that is markedly associated with the alleviation of obesity in the study participants, protects male mice from diet-induced obesity. Mechanistically, the RS-induced changes in the gut microbiota alter the bile acid profile, reduce inflammation by restoring the intestinal barrier and inhibit lipid absorption. We demonstrate that RS can facilitate weight loss at least partially through B. adolescentis and that the gut microbiota is essential for the action of RS.

Dual Branch Multi-Level Semantic Learning for Few-Shot Segmentation.

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Although progress has been made recently by combining prototype-based metric learning, existing methods still face two main challenges. First, various intra-class objects between the support and query images or semantically similar inter-class objects can seriously harm the segmentation performance due to their poor feature representations. Second, the latent novel classes are treated as the background in most methods, leading to a learning bias, whereby these novel classes are difficult to correctly segment as foreground. To solve these problems, we propose a dual-branch learning method. The class-specific branch encourages representations of objects to be more distinguishable by increasing the inter-class distance while decreasing the intra-class distance. In parallel, the class-agnostic branch focuses on minimizing the foreground class feature distribution and maximizing the features between the foreground and background, thus increasing the generalizability to novel classes in the test stage. Furthermore, to obtain more representative features, pixel-level and prototype-level semantic learning are both involved in the two branches. The method is evaluated on PASCAL- 5i 1 -shot, PASCAL- 5i 5 -shot, COCO- 20i 1 -shot, and COCO- 20i 5 -shot, and extensive experiments show that our approach is effective for few-shot semantic segmentation despite its simplicity.

Improvements to a GLCM-based machine-learning approach for quantifying posterior capsule opacification.

BACKGROUND: Posterior capsular opacification (PCO) is a common complication following cataract surgery that leads to visual disturbances and decreased quality of vision. The aim of our study was to employ a machine-learning methodology to characterize and validate enhancements applied to the grey-level co-occurrence matrix (GLCM) while assessing its validity in comparison to clinical evaluations for evaluating PCO. METHODS: One hundred patients diagnosed with age-related cataracts who were scheduled for phacoemulsification surgery were included in the study. Following mydriasis, anterior segment photographs were captured using a high-resolution photographic system. The GLCM was utilized as the feature extractor, and a supported vector machine as the regressor. Three variations, namely, GLCM, GLCM+C (+axial information), and GLCM+V (+regional voting), were analyzed. The reference value for regression was determined by averaging clinical scores obtained through subjective analysis. The relationships between the predicted PCO outcome scores and the ground truth were assessed using Pearson correlation analysis and a Bland-Altman plot, while agreement between them was assessed through the Bland-Altman plot. RESULTS: Relative to the ground truth, the GLCM, GLCM+C, and GLCM+V methods exhibited correlation coefficients of 0.706, 0.768, and 0.829, respectively. The relationship between the PCO score predicted by the GLCM+V method and the ground truth was statistically significant (p < 0.001). Furthermore, the GLCM+V method demonstrated competitive performance comparable to that of two experienced clinicians (r = 0.825, 0.843) and superior to that of two junior clinicians (r = 0.786, 0.756). Notably, a high level of agreement was observed between predictions and the ground truth, without significant evidence of proportional bias (p > 0.05). CONCLUSIONS: Overall, our findings suggest that a machine-learning approach incorporating the GLCM, specifically the GLCM+V method, holds promise as an objective and reliable tool for assessing PCO progression. Further studies in larger patient cohorts are warranted to validate these findings and explore their potential clinical applications.

A deep learning system for predicting time to progression of diabetic retinopathy.

Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. The risk of DR progression is highly variable among different individuals, making it difficult to predict risk and personalize screening intervals. We developed and validated a deep learning system (DeepDR Plus) to predict time to DR progression within 5 years solely from fundus images. First, we used 717,308 fundus images from 179,327 participants with diabetes to pretrain the system. Subsequently, we trained and validated the system with a multiethnic dataset comprising 118,868 images from 29,868 participants with diabetes. For predicting time to DR progression, the system achieved concordance indexes of 0.754-0.846 and integrated Brier scores of 0.153-0.241 for all times up to 5 years. Furthermore, we validated the system in real-world cohorts of participants with diabetes. The integration with clinical workflow could potentially extend the mean screening interval from 12 months to 31.97 months, and the percentage of participants recommended to be screened at 1-5 years was 30.62%, 20.00%, 19.63%, 11.85% and 17.89%, respectively, while delayed detection of progression to vision-threatening DR was 0.18%. Altogether, the DeepDR Plus system could predict individualized risk and time to DR progression over 5 years, potentially allowing personalized screening intervals.

DSMT-Net: Dual Self-Supervised Multi-Operator Transformation for Multi-Source Endoscopic Ultrasound Diagnosis.

Pancreatic cancer has the worst prognosis of all cancers. The clinical application of endoscopic ultrasound (EUS) for the assessment of pancreatic cancer risk and of deep learning for the classification of EUS images have been hindered by inter-grader variability and labeling capability. One of the key reasons for these difficulties is that EUS images are obtained from multiple sources with varying resolutions, effective regions, and interference signals, making the distribution of the data highly variable and negatively impacting the performance of deep learning models. Additionally, manual labeling of images is time-consuming and requires significant effort, leading to the desire to effectively utilize a large amount of unlabeled data for network training. To address these challenges, this study proposes the Dual Self-supervised Multi-Operator Transformation Network (DSMT-Net) for multi-source EUS diagnosis. The DSMT-Net includes a multi-operator transformation approach to standardize the extraction of regions of interest in EUS images and eliminate irrelevant pixels. Furthermore, a transformer-based dual self-supervised network is designed to integrate unlabeled EUS images for pre-training the representation model, which can be transferred to supervised tasks such as classification, detection, and segmentation. A large-scale EUS-based pancreas image dataset (LEPset) has been collected, including 3,500 pathologically proven labeled EUS images (from pancreatic and non-pancreatic cancers) and 8,000 unlabeled EUS images for model development. The self-supervised method has also been applied to breast cancer diagnosis and was compared to state-of-the-art deep learning models on both datasets. The results demonstrate that the DSMT-Net significantly improves the accuracy of pancreatic and breast cancer diagnosis.

Menaquinone-4 attenuates ferroptosis by upregulating DHODH through activation of SIRT1 after subarachnoid hemorrhage.

BACKGROUND: Menaquinone-4(MK-4), the isoform of vitamin K2 in the brain, exerts neuroprotective effects against a variety of central nervous system disorders. This study aimed to demonstrate the anti-ferroptosis effects of MK-4 in neurons after SAH. METHODS: A subarachnoid hemorrhage (SAH) model was prepared by endovascular perforation in mice. In vitro hemoglobin stimulation of primary cortical neurons mimicked SAH. MK-4, Brequinar (BQR, DHODH inhibitor), and Selisistat (SEL, SIRT1 inhibitor) were administered, respectively. Subsequently, WB, immunofluorescence was used to determine protein expression and localization, and transmission electron microscopy was used to observe neuronal mitochondrial structure while other indicators of ferroptosis were measured. RESULTS: MK-4 treatment significantly upregulated the protein levels of DHODH; decreased GSH, PTGS2, NOX1, ROS, and restored mitochondrial membrane potential. Meanwhile, MK-4 upregulated the expression of SIRT1 and promoted its entry into the nucleus. BQR or SEL partially abolished the protective effect of MK-4 on, neurologic function, and ferroptosis. CONCLUSIONS: Taken together, our results suggest that MK-4 attenuates ferroptosis after SAH by upregulating DHODH through the activation of SIRT1.

AI-integrated ocular imaging for predicting cardiovascular disease: advancements and future outlook.

Cardiovascular disease (CVD) remains the leading cause of death worldwide. Assessing of CVD risk plays an essential role in identifying individuals at higher risk and enables the implementation of targeted intervention strategies, leading to improved CVD prevalence reduction and patient survival rates. The ocular vasculature, particularly the retinal vasculature, has emerged as a potential means for CVD risk stratification due to its anatomical similarities and physiological characteristics shared with other vital organs, such as the brain and heart. The integration of artificial intelligence (AI) into ocular imaging has the potential to overcome limitations associated with traditional semi-automated image analysis, including inefficiency and manual measurement errors. Furthermore, AI techniques may uncover novel and subtle features that contribute to the identification of ocular biomarkers associated with CVD. This review provides a comprehensive overview of advancements made in AI-based ocular image analysis for predicting CVD, including the prediction of CVD risk factors, the replacement of traditional CVD biomarkers (e.g., CT-scan measured coronary artery calcium score), and the prediction of symptomatic CVD events. The review covers a range of ocular imaging modalities, including colour fundus photography, optical coherence tomography, and optical coherence tomography angiography, and other types of images like external eye images. Additionally, the review addresses the current limitations of AI research in this field and discusses the challenges associated with translating AI algorithms into clinical practice.