Long-term outcomes of newly diagnosed POEMS syndrome patients who received first-line lenalidomide-based therapy.

Not available.

SBCNet: Scale and Boundary Context Attention Dual-Branch Network for Liver Tumor Segmentation.

Automated segmentation of liver tumors in CT scans is pivotal for diagnosing and treating liver cancer, offering a valuable alternative to labor-intensive manual processes and ensuring the provision of accurate and reliable clinical assessment. However, the inherent variability of liver tumors, coupled with the challenges posed by blurred boundaries in imaging characteristics, presents a substantial obstacle to achieving their precise segmentation. In this paper, we propose a novel dual-branch liver tumor segmentation model, SBCNet, to address these challenges effectively. Specifically, our proposed method introduces a contextual encoding module, which enables a better identification of tumor variability using an advanced multi-scale adaptive kernel. Moreover, a boundary enhancement module is designed for the counterpart branch to enhance the perception of boundaries by incorporating contour learning with the Sobel operator. Finally, we propose a hybrid multi-task loss function, concurrently concerning tumors' scale and boundary features, to foster interaction across different tasks of dual branches, further improving tumor segmentation. Experimental validation on the publicly available LiTS dataset demonstrates the practical efficacy of each module, with SBCNet yielding competitive results compared to other state-of-the-art methods for liver tumor segmentation.

Ankle-brachial index associates with arteriovenous fistula stenosis.

BACKGROUND: Arteriovenous fistula (AVF) stenosis is associated with pre-existing arterial atherosclerosis of AVF and results in significant morbidity and hospitalization for hemodialysis patients. The ankle brachial index (ABI) is a noninvasive method of assessing atherosclerosis. This study was to examine whether ABI is a significant predictor for AVF stenosis. METHODS: This was a retrospective, longitudinal cohort study. Patients with hemodialysis between 1 January 2016 and 31 December 2022 were reviewed. ABI was assessed in January 2016. AVF stenosis was diagnosed by fistulography. RESULTS: A total of 82 patients were included. Forty-two patients experienced AVF stenosis. The univariate logistic regression analysis showed that AVF stenosis was associated with age (OR: 1.045, p = 0.033), DM status (OR: 5.529, p = 0.013), 7-year averaged cholesterol level (OR: 1.018, p = 0.034), 7-year averaged triglyceride level (OR: 1.007, p = 0.017), and ABI (OR: 0.011, p < 0.001). In multivariate logistic regression analysis, ABI was a strong predictor for AVF stenosis (OR: 0.036, p = 0.023). Then, a cut-off point of ABI with optimal sensitivity and specificity for AVF stenosis was 1.01. An analysis of time to events with adjustment for other variables showed that patients with ABI < 1.01 were significantly associated with AVF stenosis (HR: 3.859, p < 0.001). CONCLUSIONS: ABI below 1.01 was associated with AVF stenosis. This finding may be useful in tailoring surveillance programs for monitoring AVF function.

Long-Term Outcomes of Autologous Stem Cell Transplantation in Patients with Newly Diagnosed POEMS Syndrome.

POEMS (polyneuropathy, organomegaly, endocrinopathy, monoclonal gammopathy, and skin changes) syndrome is a rare form of plasma cell dyscrasia often treated with high-dose chemotherapy and autologous stem cell transplantation (ASCT). ASCT has resulted in satisfactory and sustained therapeutic outcomes. However, a substantial number of patients eventually experience disease progression, requiring second-line treatment. Therefore, it would be of further benefit to identify patients who will acquire the best long-term survival after ASCT. The aim of this study was to fully reveal the outcomes of patients undergoing ASCT in a large series with long-term follow-up. Long-term outcomes of 239 patients with newly diagnosed POEMS syndrome undergoing ASCT at a single center were evaluated retrospectively. Rates of hematologic complete response (CRH) and vascular endothelial growth factor (VEGF) complete response (CRV) were 57.3% and 68.6%, respectively, with 90.5% of patients achieving an overall clinical response. At a median follow-up of 94 months, the 5-year overall survival (OS) rate was 92.8%, and the 5-year time to next-line treatment (TTNT) rate was 72.2% (median TTNT, 96 months). Patients achieving CRH (5-year TTNT rate, 82.5% versus 60.7%; P < .0001) or CRV (5-year TTNT rate 83.7% versus 54.2%; P < .0001) had better survival outcomes compared to non-CR group patients. Dual hematologic and VEGF complete responses carry further benefit for survival (median TTNT, 129 months versus 68 months; P < .0001). Seven cases of second primary malignancy were recorded, all of which were solid tumors. Front-line ASCT resulted in excellent long-term survival in patients with POEMS syndrome, with the best survival observed in those achieving dual hematologic and VEGF CRs.

SC-SSL: Self-Correcting Collaborative and Contrastive Co-Training Model for Semi-Supervised Medical Image Segmentation.

Image segmentation achieves significant improvements with deep neural networks at the premise of a large scale of labeled training data, which is laborious to assure in medical image tasks. Recently, semi-supervised learning (SSL) has shown great potential in medical image segmentation. However, the influence of the learning target quality for unlabeled data is usually neglected in these SSL methods. Therefore, this study proposes a novel self-correcting co-training scheme to learn a better target that is more similar to ground-truth labels from collaborative network outputs. Our work has three-fold highlights. First, we advance the learning target generation as a learning task, improving the learning confidence for unannotated data with a self-correcting module. Second, we impose a structure constraint to encourage the shape similarity further between the improved learning target and the collaborative network outputs. Finally, we propose an innovative pixel-wise contrastive learning loss to boost the representation capacity under the guidance of an improved learning target, thus exploring unlabeled data more efficiently with the awareness of semantic context. We have extensively evaluated our method with the state-of-the-art semi-supervised approaches on four public-available datasets, including the ACDC dataset, M&Ms dataset, Pancreas-CT dataset, and Task_07 CT dataset. The experimental results with different labeled-data ratios show our proposed method's superiority over other existing methods, demonstrating its effectiveness in semi-supervised medical image segmentation.

An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease.

BACKGROUND: Corneal fluorescein staining is a key biomarker in evaluating dry eye disease. However, subjective scales of corneal fluorescein staining are lacking in consistency and increase the difficulties of an accurate diagnosis for clinicians. This study aimed to propose an automatic machine learning-based method for corneal fluorescein staining evaluation by utilizing prior information about the spatial connection and distribution of the staining region. METHODS: We proposed an end-to-end automatic machine learning-based classification model that consists of staining region identification, feature signature construction, and machine learning-based classification, which fully scrutinizes the multiscale topological features together with conventional texture and morphological features. The proposed model was evaluated using retrospective data from Beijing Tongren Hospital. Two masked ophthalmologists scored images independently using the Sjögren's International Collaborative Clinical Alliance Ocular Staining Score scale. RESULTS: A total of 382 images were enrolled in the study. A signature with six topological features, two textural features, and two morphological features was constructed after feature extraction and selection. Support vector machines showed the best classification performance (accuracy: 82.67%, area under the curve: 96.59%) with the designed signature. Meanwhile, topological features contributed more to the classification, compared with other features. According to the distribution and correlation with features and scores, topological features performed better than others. CONCLUSIONS: An automatic machine learning-based method was advanced for corneal fluorescein staining evaluation. The topological features in presenting the spatial connectivity and distribution of staining regions are essential for an efficient corneal fluorescein staining evaluation. This result implies the clinical application of topological features in dry-eye diagnosis and therapeutic effect evaluation.

A white-light-emitting sensor array based on cucurbit[8]uril for quantitative detection of multicomponent nitroaniline isomers.

A white-light-emitting supramolecular complex through supramolecular interactions has been assembled; the white luminescent supramolecular complex exhibits two emission spectra. Based on this, a dual-channel white-light array sensor was constructed. The results show that it can quickly identify and detect nitroaniline isomer pollutants (p-nitroaniline, m-nitroaniline, o-nitroaniline). When these three nitroaniline isomers were added to the supramolecular white-light array sensor, the fluorescence intensity of the white-light complex decreased to varying degrees. Linear discriminant analysis (LDA) showed that the supramolecular white-light array sensor could recognize and distinguish three nitroaniline isomers and could classify mixtures containing different concentrations. Factor 1 of the array had a good linear relationship with the concentration of pollutants, and the detection limit (LOD) was as low as 0.7 µM. The method has good reproducibility and stability. In addition, it can also qualitatively detect the nitroaniline isomers in river water and contaminated rice seedling extract. It provides an ideal platform for constructing multiresponse sensors.

Three-dimensional visualization and evaluation of hilar cholangiocarcinoma resectability and proposal of a new classification.

BACKGROUND: As digital medicine has exerted profound influences upon diagnosis and treatment of hepatobiliary diseases, our study aims to investigate the accuracy of three-dimensional visualization and evaluation (3DVE) system in assessing the resectability of hilar cholangiocarcinoma (hCCA), and explores its potential clinical value. MATERIALS AND METHODS: The discovery cohort, containing 111 patients from April 2013 to December 2019, was retrospectively included to determine resectability according to revised criteria for unresectability of hCCA. 3D visualization models were reconstructed to evaluate resectability parameters including biliary infiltration, vascular involvement, hepatic atrophy and metastasis. Evaluation accuracy were compared between contrast-enhanced CT and 3DVE. Logistic analysis was performed to identify independent risk factors of R0 resection. A new comprehensive 3DVE classification of hCCA based on factors influencing resectability was proposed to investigate its role in predicting R0 resection and prognosis. The main outcomes were also analyzed in cohort validation, including 34 patients from January 2020 to August 2022. RESULTS: 3DVE showed an accuracy rate of 91% (95%CI 83.6-95.4%) in preoperatively evaluating hCCA resectability, significantly higher than 81% (95%CI 72.8-87.7%) of that of CT (p = 0.03). By multivariable analysis, hepatic artery involvement in 3DVE was identified an independent risk factor for R1 or R2 resection (OR = 3.5, 95%CI 1.4,8.8, P < 0.01). New 3DVE hCCA classification was valuable in predicting patients' R0 resection rate (p < 0.001) and prognosis (p < 0.0001). The main outcomes were internally validated. CONCLUSIONS: 3DVE exhibited a better efficacy in evaluating hCCA resectability, compared with contrast-enhanced CT. Preoperative 3DVE demonstrated hepatic artery involvement was an independent risk factor for the absence of R0 margin. 3DVE classification of hCCA was valuable in clinical practice.

DSANet: Dual-Branch Shape-Aware Network for Echocardiography Segmentation in Apical Views.

Echocardiography is an essential examination for cardiac disease diagnosis, from which anatomical structures segmentation is the key to assessing various cardiac functions. However, the obscure boundaries and large shape deformations due to cardiac motion make it challenging to accurately identify the anatomical structures in echocardiography, especially for automatic segmentation. In this study, we propose a dual-branch shape-aware network (DSANet) to segment the left ventricle, left atrium, and myocardium from the echocardiography. Specifically, the elaborate dual-branch architecture integrating shape-aware modules boosts the corresponding feature representation and segmentation performance, which guides the model to explore shape priors and anatomical dependence using an anisotropic strip attention mechanism and cross-branch skip connections. Moreover, we develop a boundary-aware rectification module together with a boundary loss to regulate boundary consistency, adaptively rectifying the estimation errors nearby the ambiguous pixels. We evaluate our proposed method on the publicly available and in-house echocardiography dataset. Comparative experiments with other state-of-the-art methods demonstrate the superiority of DSANet, which suggests its potential in advancing echocardiography segmentation.

Supramolecular Fluorescence Sensor Array Based on Cucurbit[8]uril Complexes Used for the Detection of Multiplex Quaternary Ammonium Pesticides.

The simultaneous detection of multiple quaternary ammonium pesticides (QAPs) in water is a challenge due to their high solubility in water and similar structures. In this paper, we have developed a quadruple-channel supramolecular fluorescence sensor array for the simultaneous analysis of five QAPs, including paraquat (PQ), diquat (DQ), difenzoquat (DFQ), mepiquat (MQ), and chlormequat (CQ). Not only were QAP samples of different concentrations (10, 50, and 300 µM) in water distinguished with 100% accuracy but also single QAP and binary QAP mixed samples (DFQ-DQ) were sensitively quantified. Our experimental interference study confirmed that the developed array has good anti-interference ability. The array can quickly identify five QAPs in river and tap water samples. In addition, it also qualitatively detected QAP residues in Chinese cabbage and wheat seedlings extract. This array has rich output signals, low cost, easy preparation, and simple technology, demonstrating great potential in environmental analysis.

BSMNet: Boundary-salience multi-branch network for intima-media identification in carotid ultrasound images.

Carotid artery intima-media thickness (CIMT) is an essential factor in signaling the risk of cardiovascular diseases, which is commonly evaluated using ultrasound imaging. However, automatic intima-media segmentation and thickness measurement are still challenging due to the boundary ambiguity of intima-media and inherent speckle noises in ultrasound images. In this work, we propose an end-to-end boundary-salience multi-branch network, BSMNet, to tackle the carotid intima-media identification from ultrasound images, where the prior shape knowledge and anatomical dependence are exploited using a parallel linear structure learning modules followed by a boundary refinement module. Moreover, we design a strip attention model to boost the thin strip region segmentation with shape priors, in which an anisotropic kernel shape captures long-range global relations and scrutinizes meaningful local salient contexts simultaneously. Extensive experimental results on an in-house carotid ultrasound (US) dataset demonstrate the promising performance of our method, which achieves about 0.02 improvement in Dice and HD95 than other state-of-the-art methods. Our method is promising in advancing the analysis of systemic arterial disease with ultrasound imaging.

A supramolecular fluorescence array sensor for toxic heavy metal ion detection in environmental water and rice seedling extracts.

A supramolecular fluorescence array sensor based on cucurbituril-dye host-guest complexes (6-QAA@Q[7], PyY@Q[7], and TO@Q[8]) was constructed. The results showed that it can quickly identify and detect toxic heavy metal ions, such as Ag+, Cr3+, Hg2+, Ni2+, and Pb2+. When these five toxic heavy metal ions were added to the supramolecular fluorescence array sensor, different fluorescence responses were produced due to the different binding capacities of the metal ions to the cucurbituril-dye complex. Linear discriminant analysis (LDA) showed that the supramolecular fluorescence array sensor could identify and distinguish these five toxic heavy metal ions and a mixture containing different concentration ratios could be classified. The linear correlation between the metal ion concentration and factor 1 (F1) was strong, and the detection limit (LOD) was as low as 10-6-10-7 mol L-1. These five toxic heavy metal ions in environmental water and rice seedling extracts were identified using the supramolecular fluorescence array sensor. This sensor provides a quick and convenient method for monitoring toxic heavy metal ions in sewage.

[Nitrogen Metabolism and Flora Characteristics of Bacteria Algae Complex System].

In order to denitrify the urban tail water deeply and control the eutrophication of surface water, the molecular biology methods were used to study the nitrogen metabolism performance of the denitrification complex flora and the algal-bacteria symbiotic system. The results showed that the nitrogen metabolism complex flora was high ammonification and denitrification performance. The removal effect of ammonia nitrogen of group JZ was very well in urban tailwater, and the degradation rate was as high as 95%. The removal effect of total nitrogen of group JZ was better than that of group J in the experimental water distribution. High-throughput sequencing showed that the main dominant flora and proportion of group J were Firmicutes 44.53%, Proteobacteria 43.41%, Actinobacteria 5.37%, Bacteroidetes 3.04%, and Chloroflexi 1.35%. The main dominant bacterial groups in the group JZ were 33.89% Cyanobacteria, 25.34% Chloroflexi, 19.38% Proteobacteria, 10.02% Firmicutes, and 4.20% Acidobacteria. The dominant species in group J were compared with those in group JZ; the proportions were 82% and 18% in Firmicutes, 69% and 31% in Proteobacteria, 1% and 99% in Cyanobacteria, 5.1% and 95% in Chloroflexi, 73% and 27% in Actinobacteria. It was concluded that the removal effect of ammonia nitrogen of group JZ was high in the urban tailwater. With the addition and growth of Micrococcus in group J, the nitrogen metabolism flora in group JZ changed accordingly, so as to adapt to the environment in which the dominant algae formed. It forms a new nitrogen metabolism system of bacteria and algae with Micrococcus. This research provides a theoretical and data basis for the application of algal-bacterial co-metabolism systems.

DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images.

Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.

Automatic Myotendinous Junction Identification In Ultrasound Images Based on Junction-based Template Measurements.

Tracking the myotendinous junction (MTJ) motion in consecutive ultrasound images is essential to assess muscle and tendon interaction and understand the mechanics' muscle-tendon unit and its pathological conditions during motion. However, the inherent speckle noises and ambiguous boundaries deter the reliable identification of MTJ, thus restricting their usage in human motion analysis. This study advances a fully automatic displacement measurement method for MTJ using prior shape knowledge on the Y-shape MTJ, precluding the influence of irregular and complicated hyperechoic structures in muscular ultrasound images. Our proposed method first adopts the junction candidate points using a combined measure of Hessian matrix and phase congruency, followed by a hierarchical clustering technique to refine the candidates approximating the position of the MTJ. Then, based on the prior knowledge of Y-shape MTJ, we finally identify the best matching junction points according to intensity distributions and directions of their branches using multiscale Gaussian templates and a Kalman filter. We evaluated our proposed method using the ultrasound scans of the gastrocnemius from 8 young, healthy volunteers. Our results present more consistent with the manual method in the MTJ tracking method than existing optical flow tracking methods, suggesting its potential in facilitating muscle and tendon function examinations with in vivo ultrasound imaging.