Ethynyl-B(dan) in [3+2] Cycloaddition and Larock Indole Synthesis: Synthesis of Stable Boron-Containing Heteroaromatic Compounds.

The cycloaddition of nitrile oxides with ethynyl-B(dan) (dan=naphthalene-1,8-diaminato) allowed the facile preparation of diverse isoxazolyl-B(dan) compounds, all of which displayed excellent protodeborylation-resistant properties. The dan-installation on the boron center proves vital to the high stability of the products as well as the perfect regioselectivity arising from hydrogen bond-directed orientation in the cycloaddition. The diminished boron-Lewis acidity of ethynyl-B(dan) also renders it amenable to azide-alkyne cycloaddition, Larock indole synthesis and related heteroannulations. The obtained boron-containing triazole, indoles, benzofuran and indenone exhibit sufficient resistance toward protodeborylation. Despite the commonly accepted transmetalation-inactive property derived from the diminished Lewis acidity, the synthesized heteroaryl-B(dan) compound was still found to be convertible to the oligoarene via sequential Suzuki-Miyaura coupling.

Simple and field-adapted species identification of biological specimens combining multiplex multienzyme isothermal rapid amplification, lateral flow dipsticks, and universal primers for initial rapid screening without standard PCR laboratory.

Species identification of biological specimens can provide the valuable clues and accelerate the speed of prosecution material processing for forensic investigation, especially when the case scene is inaccessible and the physical evidence is cumbersome. Thus, establishing a rapid, simple, and field-adapted species identification method is crucial for forensic scientists, particularly as first-line technology at the crime scene for initial rapid screening. In this study, we established a new field-adapted species identification method by combining multiplex multienzyme isothermal rapid amplification (MIRA), lateral flow dipstick (LFD) system, and universal primers. Universal primers targeting COX I and COX II genes were used in multiplex MIRA-LFD system for seven species identification, and a dedicated MIRA-LFD system primer targeting CYT B gene was used to detect the human material. DNA extraction was performed by collecting DNA directly from the centrifuged supernatant. Our study found that the entire amplification process took only 15 min at 37 °C and the results of LFDs could be visually observed after 10 min. The detection sensitivity of human material could reach 10 pg, which is equivalent to the detection of single cell. Different common animal samples mixed at the ratio of 1 ng:1 ng, 10 ng:1 ng, and 1 ng:10 ng could be detected successfully. Furthermore, the damaged and degraded samples could also be detected. Therefore, the convenient, feasible, and rapid approach for species identification is suitable for popularization as first-line technology at the crime scene for initial rapid screening and provides a great convenient for forensic application.

A quantitative evaluation of the deep learning model of segmentation and measurement of cervical spine MRI in healthy adults.

PURPOSE: To evaluate the 3D U-Net model for automatic segmentation and measurement of cervical spine structures using magnetic resonance (MR) images of healthy adults. MATERIALS AND METHODS: MR images of the cervical spine from 160 healthy adults were collected retrospectively. A previously constructed deep-learning model was used to automatically segment anatomical structures. Segmentation and localization results were checked by experienced radiologists. Pearson's correlation analyses were conducted to examine relationships between patient and image parameters. RESULTS: No measurement was significantly correlated with age or sex. The mean values of the areas of the subarachnoid space and spinal cord from the C2/3 (cervical spine 2-3) to C6/7 intervertebral disc levels were 102.85-358.12 mm2 and 53.71-110.32 mm2 , respectively. The ratios of the areas of the spinal cord to the subarachnoid space were 0.25-0.68. The transverse and anterior-posterior diameters of the subarachnoid space were 14.77-26.56 mm and 7.38-17.58 mm, respectively. The transverse and anterior-posterior diameters of the spinal cord were 9.11-16.02 mm and 5.47-10.12 mm, respectively. CONCLUSION: A deep learning model based on 3D U-Net automatically segmented and performed measurements on cervical spine MR images from healthy adults, paving the way for quantitative diagnosis models for spinal cord diseases.

Linking nuclear matrix-localized PIAS1 to chromatin SUMOylation via direct binding of histones H3 and H2A.Z.

As a conserved posttranslational modification, SUMOylation has been shown to play important roles in chromatin-related biological processes including transcription. However, how the SUMOylation machinery associates with chromatin is not clear. Here, we present evidence that multiple SUMOylation machinery components, including SUMO E1 proteins SAE1 and SAE2 and the PIAS (protein inhibitor of activated STAT) family SUMO E3 ligases, are primarily associated with the nuclear matrix rather than with chromatin. We show using nuclease digestion that all PIAS family proteins maintain nuclear matrix association in the absence of chromatin. Of importance, we identify multiple histones including H3 and H2A.Z as directly interacting with PIAS1 and demonstrate that this interaction requires the PIAS1 SAP (SAF-A/B, Acinus, and PIAS) domain. We demonstrate that PIAS1 promotes SUMOylation of histones H3 and H2B in both a SAP domain- and an E3 ligase activity-dependent manner. Furthermore, we show that PIAS1 binds to heat shock-induced genes and represses their expression and that this function also requires the SAP domain. Altogether, our study reveals for the first time the nuclear matrix as the compartment most enriched in SUMO E1 and PIAS family E3 ligases. Our finding that PIAS1 interacts directly with histone proteins also suggests a molecular mechanism as to how nuclear matrix-associated PIAS1 is able to regulate transcription and other chromatin-related processes.

Automatic segmentation of hepatic metastases on DWI images based on a deep learning method: assessment of tumor treatment response according to the RECIST 1.1 criteria.

BACKGROUND: Evaluation of treated tumors according to Response Evaluation Criteria in Solid Tumors (RECIST) criteria is an important but time-consuming task in medical imaging. Deep learning methods are expected to automate the evaluation process and improve the efficiency of imaging interpretation. OBJECTIVE: To develop an automated algorithm for segmentation of liver metastases based on a deep learning method and assess its efficacy for treatment response assessment according to the RECIST 1.1 criteria. METHODS: One hundred and sixteen treated patients with clinically confirmed liver metastases were enrolled. All patients had baseline and post-treatment MR images. They were divided into an initial (n = 86) and validation cohort (n = 30) according to the examined time. The metastatic foci on DWI images were annotated by two researchers in consensus. Then the treatment responses were assessed by the two researchers according to RECIST 1.1 criteria. A 3D U-Net algorithm was trained for automated liver metastases segmentation using the initial cohort. Based on the segmentation of liver metastases, the treatment response was assessed automatically with a rule-based program according to the RECIST 1.1 criteria. The segmentation performance was evaluated using the Dice similarity coefficient (DSC), volumetric similarity (VS), and Hausdorff distance (HD). The area under the curve (AUC) and Kappa statistics were used to assess the accuracy and consistency of the treatment response assessment by the deep learning model and compared with two radiologists [attending radiologist (R1) and fellow radiologist (R2)] in the validation cohort. RESULTS: In the validation cohort, the mean DSC, VS, and HD were 0.85 ± 0.08, 0.89 ± 0.09, and 25.53 ± 12.11 mm for the liver metastases segmentation. The accuracies of R1, R2 and automated segmentation-based assessment were 0.77, 0.65, and 0.74, respectively, and the AUC values were 0.81, 0.73, and 0.83, respectively. The consistency of treatment response assessment based on automated segmentation and manual annotation was moderate [K value: 0.60 (0.34-0.84)]. CONCLUSION: The deep learning-based liver metastases segmentation was capable of evaluating treatment response according to RECIST 1.1 criteria, with comparable results to the junior radiologist and superior to that of the fellow radiologist.

Enhanced performance of asymmetric supercapacitor based on NiZn-LDH@NiCoSe2electrode materials.

While supercapacitors have been widely studied as the next generation of energy storage devices, to develop active electrode materials for enhancing device performance is still challenging. Herein, we fabricated asymmetric supercapacitors based on NiZn-Layered double hydroxide (LDH) @NiCoSe2hierarchical nanostructures as electrode materials. The NiZn-LDH@NiCoSe2composites are deposited on Ni foam by a two-step strategy, in which NiZn-LDH nanosheets were firstly grown on Ni foam by hydrothermal method, and then NiCoSe2particles were prepared by electrodeposition. Due to the synergistic effect between NiZn-LDH and NiCoSe2, excellent device performance was achieved. In a three-electrode system, the NiZn-LDH@NiCoSe2exhibits a specific capacitance of 2980 F g-1at 1 A g-1. Furthermore, the asymmetric supercapacitor of NiZn-LDH@NiCoSe2//activated carbon (AC) device was assembled, which exhibits the energy density of 49.2 Wh kg-1at the power density of 160 W kg-1, with the capacity retention rate is 91% after 8000 cycles. The results indicates that NiZn-LDH@NiCoSe2is a promising candidate as electrode materials for efficient energy storage devices.

A role for LSH in facilitating DNA methylation by DNMT1 through enhancing UHRF1 chromatin association.

LSH, a SNF2 family DNA helicase, is a key regulator of DNA methylation in mammals. How LSH facilitates DNA methylation is not well defined. While previous studies with mouse embryonic stem cells (mESc) and fibroblasts (MEFs) derived from Lsh knockout mice have revealed a role of Lsh in de novo DNA methylation by Dnmt3a/3b, here we report that LSH contributes to DNA methylation in various cell lines primarily by promoting DNA methylation by DNMT1. We show that loss of LSH has a much bigger effect in DNA methylation than loss of DNMT3A and DNMT3B. Mechanistically, we demonstrate that LSH interacts with UHRF1 but not DNMT1 and facilitates UHRF1 chromatin association and UHRF1-catalyzed histone H3 ubiquitination in an ATPase activity-dependent manner, which in turn promotes DNMT1 recruitment to replication fork and DNA methylation. Notably, UHRF1 also enhances LSH association with the replication fork. Thus, our study identifies LSH as an essential factor for DNA methylation by DNMT1 and provides novel insight into how a feed-forward loop between LSH and UHRF1 facilitates DNMT1-mediated maintenance of DNA methylation in chromatin.

Quantitative influence and performance analysis of virtual reality laparoscopic surgical training system.

BACKGROUND: Virtual reality (VR) surgery training has become a trend in clinical education. Many research papers validate the effectiveness of VR-based surgical simulators in training medical students. However, most existing articles employ subjective methods to study the residents' surgical skills improvement. Few of them investigate how to improve the surgery skills on specific dimensions substantially. METHODS: Our paper resorts to physiological approaches to objectively study the quantitative influence and performance analysis of VR laparoscopic surgical training system for medical students. Fifty-one participants were recruited from a pool of medical students. They conducted four pre and post experiments in the training box. They were trained on VR-based laparoscopic surgery simulators (VRLS) in the middle of pre and post experiments. Their operation and physiological data (heart rate and electroencephalogram) are recorded during the pre and post experiments. The physiological data is used to compute cognitive load and flow experience quantitatively. Senior surgeons graded their performance using newly designed hybrid standards for fundamental tasks and Global operative assessment of laparoscopic skills (GOALS) standards for colon resection tasks. Finally, the participants were required to fill the questionnaires about their cognitive load and flow experience. RESULTS: After training on VRLS, the time of the experimental group to complete the same task could drop sharply (p < 0.01). The performance scores are enhanced significantly (p < 0.01). The performance and cognitive load computed from EEG are negatively correlated (p < 0.05). CONCLUSION: The results show that the VRLS could highly improve medical students' performance and enable the participants to obtain flow experience with a lower cognitive load. Participants' performance is negatively correlated with cognitive load through quantitative physiological analysis. This might provide a new way of assessing skill acquirement.

SET8 prevents excessive DNA methylation by methylation-mediated degradation of UHRF1 and DNMT1.

Faithful inheritance of DNA methylation across cell division requires DNMT1 and its accessory factor UHRF1. However, how this axis is regulated to ensure DNA methylation homeostasis remains poorly understood. Here we show that SET8, a cell-cycle-regulated protein methyltransferase, controls protein stability of both UHRF1 and DNMT1 through methylation-mediated, ubiquitin-dependent degradation and consequently prevents excessive DNA methylation. SET8 methylates UHRF1 at lysine 385 and this modification leads to ubiquitination and degradation of UHRF1. In contrast, LSD1 stabilizes both UHRF1 and DNMT1 by demethylation. Importantly, SET8 and LSD1 oppositely regulate global DNA methylation and do so most likely through regulating the level of UHRF1 than DNMT1. Finally, we show that UHRF1 downregulation in G2/M by SET8 has a role in suppressing DNMT1-mediated methylation on post-replicated DNA. Altogether, our study reveals a novel role of SET8 in promoting DNA methylation homeostasis and identifies UHRF1 as the hub for tuning DNA methylation through dynamic protein methylation.

Neurotized free VRAM used to create myoelectric signals in a muscle-depleted area for targeted muscle reinnervation for intuitive prosthesis control: A case report.

Targeted muscle reinnervation enables native muscles to send electromyographic signals to myoelectric receptors, which drive movements in a prosthesis. This system requires voluntary contracture of muscles for sequential control of powered prosthetic joints. This report describes a surgical solution for cases where the chest wall is depleted of muscle targets. A 13-year-old boy with left forequarter amputation and pectoralis major resection as a result of extended necrotizing facilities 8 years prior received a neurotized free Vertical Rectus Abdominus Mycocutaneous (VRAM) flap (28 × 10 cm) designed to produce myoelectric signals, reduce pain, and provide stability for prosthetic fitting. Five intercostal nerves from the VRAM were coapted to portions of the brachial plexus to create a myoelectric interface for targeted muscle reinnervation. The postoperative course was uneventful. At 39 months of follow-up, the patient gained control of the transferred VRAM and was able to operate a custom-fitted myoelectric prosthesis together with contraction of the ipsilateral infraspinatus muscle. The neurotized VRAM transfer created a neural interface in an area with depleted neuromuscular targets while decreasing pain and adding tissue bulk for proper prosthesis fitting. Such a surgical strategy may have applications in other areas of the body.

Characterization and a RT-RPA assay for rapid detection of Chilli Veinal mottle virus (ChiVMV) in tobacco.

BACKGROUND: Chilli veinal mottle virus (ChiVMV), which belongs to the genus Potyvirus of the family Potyviridae, mainly infects solanaceous plants and has caused serious economic losses in Asia and Africa. Tobacco plants infected with ChiVMV suffered from punctate necrosis of leaves, leaf deformation, systemic necrosis of leaves and stems, and eventually plant death. However, ChiVMV infection could not usually be identified given the lack of rapid and efficient detection assays in tobacco plants. Therefore, an isolate of tobacco-infecting ChiVMV (ChiVMV-LZ) was obtained, and a novel isothermal amplification and detection technique, reverse transcription-recombinase polymerase amplification (RT-RPA), was established to detect ChiVMV in tobacco plants. METHODS: In this study, the full-length genome of ChiVMV-LZ was obtained using reverse transcription-polymerase chain reaction (RT-PCR) and rapid amplification of cDNA ends (RACE) assays. The genome sequence of ChiVMV-LZ was characterized by sequence alignment and phylogenetic analysis. Then, a RT-RPA assay was established for rapid and sensitive detection of ChiVMV-LZ in tobacco. Additionally, the established RT-RPA assay was compared to the RT-PCR assay in aspect of sensitivity and application in field-collected tobacco samples. RESULTS: ChiVMV-LZ was isolated from diseased tobacco in Luzhou, Sichuan, China. The tobacco plants inoculated with ChiVMV-LZ showed typical symptoms of yellow and round spots on the leaves, and curled and folded leaf margin, similar to those observed on naturally ChiVMV-infected tobacco in the field. The full-length genomic sequence of ChiVMV-LZ was determined to be 9742 nucleotides. Sequence alignment and phylogenetic analysis showed that ChiVMV-LZ was most closely related to ChiVMV-Yp8 isolated from pepper plants in Sichuan province while distantly related to ChiVMV-YN from tobacco in Yunnan province, indicating a possibly geographical differentiation of ChiVMV isolates. Additionally, a RT-RPA assay was established for rapid detection of ChiVMV in tobacco. The RT-RPA has no cross-reaction with other related tobacco viruses and is about 10-fold more sensitive than conventional RT-PCR method. CONCLUSION: The characterization of ChiVMV-LZ infecting tobacco was determined, and the established RT-RPA assay provides a reliable and effective method for rapid detection of ChiVMV in tobacco.

Experimental models for cutaneous hypertrophic scar research.

Human skin wound repair may result in various outcomes with most of them leading to scar formation. Commonly seen in many cutaneous wound healing cases, hypertrophic scars are considered as phenotypes of abnormal wound repair. To prevent the formation of hypertrophic scars, efforts have been made to understand the mechanism of scarring following wound closure. Numerous in vivo and in vitro models have been created to facilitate investigations into cutaneous scarring and the development of antiscarring treatments. To select the best model for a specific study, background knowledge of the current models of hypertrophic scars is necessary. In this review, we describe in vivo and in vitro models for studying hypertrophic scars, as well as the distinct characteristics of these models. The choice of models for a specific study should be based on the characteristics of the model and the goal of the study. In general, in vivo animal models are often used in phenotypical scar formation analysis, development of antiscarring treatment, and functional analyses of individual genes. In contrast, in vitro models are chosen to pathway identification during scar formation as well as in high-throughput analysis in drug development. Besides helping investigators choose the best scarring model for their research, the goal of this review is to provide knowledge for improving the existing models and development of new models. These will contribute to the progress of scarring studies.

Rif1 promotes a repressive chromatin state to safeguard against endogenous retrovirus activation.

Transposable elements, including endogenous retroviruses (ERVs), constitute a large fraction of the mammalian genome. They are transcriptionally silenced during early development to protect genome integrity and aberrant transcription. However, the mechanisms that control their repression are not fully understood. To systematically study ERV repression, we carried out an RNAi screen in mouse embryonic stem cells (ESCs) and identified a list of novel regulators. Among them, Rif1 displays the strongest effect. Rif1 depletion by RNAi or gene deletion led to increased transcription and increased chromatin accessibility at ERV regions and their neighboring genes. This transcriptional de-repression becomes more severe when DNA methylation is lost. On the mechanistic level, Rif1 directly occupies ERVs and is required for repressive histone mark H3K9me3 and H3K27me3 assembly and DNA methylation. It interacts with histone methyltransferases and facilitates their recruitment to ERV regions. Importantly, Rif1 represses ERVs in human ESCs as well, and the evolutionally-conserved HEAT-like domain is essential for its function. Finally, Rif1 acts as a barrier during somatic cell reprogramming, and its depletion significantly enhances reprogramming efficiency. Together, our study uncovered many previously uncharacterized repressors of ERVs, and defined an essential role of Rif1 in the epigenetic defense against ERV activation.

A Coalitional Formation Game for Physical Layer Security of Cooperative Compressive Sensing Multi-Relay Networks.

Cooperative relaying is an effective technology to improve the capacity of physical-layer security, in which the relay helps forward the received signal to the destination. In this paper, a cooperative compressive sensing and amplify-and-forward (CCS-AF) scheme, which combines the compressive sensing theory and amplify-and-forward strategy, is proposed to increase the secrecy capacity. To optimize the secrecy performance, a coalition formation algorithm based on coalitional game theory of optimal relay selection is proposed to maximize the secrecy capacity. Different to maximizing the individual utility based on the traditional pareto order, the max-coalition order rule is newly defined to guide the coalitional formation. Simulation results indicate that with the proposed algorithm, part of the relays could form a coalition to forward the information and the proposed algorithm could significantly improve the secrecy capacity of cooperative multi-relay networks.

Molecular structure of glycogen in diabetic liver.

Liver glycogen (involved in maintaining blood-sugar levels) is a hyperbranched glucose polymer containing ß particles (diameter ~20 nm), which can form composite α particles (diameter ~50-300 nm), and includes a small but significant amount of bound protein. Size distributions of glycogen from livers of healthy and diabetic mice were examined using size-exclusion chromatography with two separate eluents: aqueous eluent and dimethylsulfoxide (DMSO) eluent. Morphologies were examined with transmission electron microscopy. Diabetic glycogen (DG) exhibited many α particles in the mild water-based solvent, but in DMSO, which breaks H bonds, these degraded to ß particles; α particles however were always present in healthy glycogen (HG). This DG fragility shows the binding of ß into α particles is different in HG and DG. The diabetic α particle fragility may be involved with the uncontrolled blood-sugar release symptomatic of diabetes: small ß particles degrade more easily to glucose than α particles. This has implications for diabetes management.

Nanozyme-based Clusterphene for Enhanced Electrically Catalytic Cancer Therapy.

Nanozyme mediated catalytic therapy is an attractive strategy for cancer therapy. However, the nanozymes are tended to assemble into 3D architectures, resulting in poor catalytic efficiency for therapy. This study designs the assembly of nanozymes and natural enzymes into the layered structures featuring hexagonal pores as nanozyme clusterphene and investigates their catalytic therapy with the assistance of electric field. The nanozyme-based clusterphene consists of polyoxometalate (POM) and natural glucose oxidase (GOx), named POMG-based clusterphene, which facilitate multi-enzyme activities including peroxidase (POD), catalase (CAT), and glutathione oxidase (GPx). The highly ordered layers with hexagonal pores of POMG units significantly improve the peroxidase-like (POD-like) activity of the nanozyme and thus the sustained production of reactive oxygen species (ROS). At the same time, GOx can increase endogenous H2O2 and produce gluconic acid while consuming glucose, the nutrient of tumor cell growth. The results indicate that the POD-like activity of POMG-based clusterphene increase approximately sevenfold under electrical stimulation compared with Nd-substituted keggin type POM cluster (NdPW11). The experiments both in vitro and in vivo show that the proposed POMG-based clusterphene mediated cascade catalytic therapy is capable of efficient tumor inhibiting and preventing tumor proliferation in tumor-bearing mice model, promising as an excellent candidate for catalytic therapy.

Strategies to Reverse Hypoxic Tumor Microenvironment for Enhanced Sonodynamic Therapy.

Sonodynamic therapy (SDT) has emerged as a highly effective modality for the treatment of malignant tumors owing to its powerful penetration ability, noninvasiveness, site-confined irradiation, and excellent therapeutic efficacy. However, the traditional SDT, which relies on oxygen availability, often fails to generate a satisfactory level of reactive oxygen species because of the widespread issue of hypoxia in the tumor microenvironment of solid tumors. To address this challenge, various approaches are developed to alleviate hypoxia and improve the efficiency of SDT. These strategies aim to either increase oxygen supply or prevent hypoxia exacerbation, thereby enhancing the effectiveness of SDT. In view of this, the current review provides an overview of these strategies and their underlying principles, focusing on the circulation of oxygen from consumption to external supply. The detailed research examples conducted using these strategies in combination with SDT are also discussed. Additionally, this review highlights the future prospects and challenges of the hypoxia-alleviated SDT, along with the key considerations for future clinical applications. These considerations include the development of efficient oxygen delivery systems, the accurate methods for hypoxia detection, and the exploration of combination therapies to optimize SDT outcomes.

Quantitative measurement of the ureter on three-dimensional magnetic resonance urography images using deep learning.

BACKGROUND: Accurate measurement of ureteral diameters plays a pivotal role in diagnosing and monitoring urinary tract obstruction (UTO). While three-dimensional magnetic resonance urography (3D MRU) represents a significant advancement in imaging, the traditional manual methods for assessing ureteral diameters are characterized by labor-intensive procedures and inherent variability. In the realm of medical image analysis, deep learning has led to a paradigm shift, yet the development of a comprehensive automated tool for the precise segmentation and measurement of ureters in MR images is an unaddressed challenge. PURPOSE: The ureter was quantitatively measured on 3D MRU images using a deep learning model. METHODS: A retrospective cohort of 445 3D MRU scans (443 patients, 52 ± 18 years; 217 female patients) was collected and split into training, validation, and internal testing cohorts. A 3D V-Net model was trained for urinary tract segmentation, and a post-processing algorithm was developed for ureteral measurements. The accuracy of the segmentation was evaluated using the Dice similarity coefficient (DSC) and volume intraclass correlation coefficient (ICC), with ground truth segmentations provided by experienced radiologists. The external cohort comprised 50 scans (50 patients, 55 ± 21 years; 30 female patients), and the model-predicted ureteral diameter measurements were compared with manual measurements to assess system performance. The various diameter parameters of ureter among the different measurement methods (ground truth, auto-segmentation with automatic diameter extraction, and manual segmentation with automatic diameter extraction) were assessed with Friedman tests and post hoc Dunn test. The effectiveness of the UTO diagnosis was assessed by receiver operating characteristic (ROC) curves and their respective areas under the curve (AUC) between different methods. RESULTS: In both the internal test and external cohorts, the mean DSC values for bilateral ureters exceeded 0.70. The ICCs for the bilateral ureter volume obtained by comparing the model and manual segmentation were all greater than 0.96 (p  < â€¯0.05), except for the right ureter in the internal test cohort, for which the ICC was 0.773 (p  < â€¯0.05). The mean DSCs for interobserver and intraobserver reliability were all above 0.97. The maximum diameter of the ureter exhibited no statistically significant differences either in the dilated (p = 0.08) or in the non-dilated (p = 0.32) ureters across the three measurement methods. The AUCs of ground truth, auto-segmentation with automatic diameter extraction, and manual segmentation with automatic diameter extraction in diagnosing UTO were 0.988 (95% CI: 0.934, 1.000), 0.961 (95% CI: 0.893, 0.991), and 0.979 (95% CI: 0.919, 0.998), respectively. There was no statistical difference between AUCs of the different methods (p > 0.05). CONCLUSION: The proposed deep learning model and post-processing algorithm provide an effective means for the quantitative evaluation of urinary diseases using 3D MRU images.

Automatic Segmentation and Quantification of Abdominal Aortic Calcification in Lateral Lumbar Radiographs Based on Deep-Learning-Based Algorithms.

To investigate the performance of deep-learning-based algorithms for the automatic segmentation and quantification of abdominal aortic calcification (AAC) in lateral lumbar radiographs, we retrospectively collected 1359 consecutive lateral lumbar radiographs. The data were randomly divided into model development and hold-out test datasets. The model development dataset was used to develop U-shaped fully convolutional network (U-Net) models to segment the landmarks of vertebrae T12-L5, the aorta, and anterior and posterior aortic calcifications. The AAC lengths were calculated, resulting in an automatic Kauppila score output. The vertebral levels, AAC scores, and AAC severity were obtained from clinical reports and analyzed by an experienced expert (reference standard) and the model. Compared with the reference standard, the U-Net model demonstrated a good performance in predicting the total AAC score in the hold-out test dataset, with a correlation coefficient of 0.97 (p <0.001). The overall accuracy for the AAC severity was 0.77 for the model and 0.74 for the clinical report. Additionally, the Kendall coefficient of concordance of the total AAC score prediction was 0.89 between the model-predicted score and the reference standard, and 0.88 between the structured clinical report and the reference standard. In conclusion, the U-Net-based deep learning approach demonstrated a relatively high model performance in automatically segmenting and quantifying ACC.

Semiautomated pelvic lymph node treatment response evaluation for patients with advanced prostate cancer: based on MET-RADS-P guidelines.

BACKGROUND: The evaluation of treatment response according to METastasis Reporting and Data System for Prostate Cancer (MET-RADS-P) criteria is an important but time-consuming task for patients with advanced prostate cancer (APC). A deep learning-based algorithm has the potential to assist with this assessment. OBJECTIVE: To develop and evaluate a deep learning-based algorithm for semiautomated treatment response assessment of pelvic lymph nodes. METHODS: A total of 162 patients who had undergone at least two scans for follow-up assessment after APC metastasis treatment were enrolled. A previously reported deep learning model was used to perform automated segmentation of pelvic lymph nodes. The performance of the deep learning algorithm was evaluated using the Dice similarity coefficient (DSC) and volumetric similarity (VS). The consistency of the short diameter measurement with the radiologist was evaluated using Bland-Altman plotting. Based on the segmentation of lymph nodes, the treatment response was assessed automatically with a rule-based program according to the MET-RADS-P criteria. Kappa statistics were used to assess the accuracy and consistency of the treatment response assessment by the deep learning model and two radiologists [attending radiologist (R1) and fellow radiologist (R2)]. RESULTS: The mean DSC and VS of the pelvic lymph node segmentation were 0.82 ± 0.09 and 0.88 ± 0.12, respectively. Bland-Altman plotting showed that most of the lymph node measurements were within the upper and lower limits of agreement (LOA). The accuracies of automated segmentation-based assessment were 0.92 (95% CI: 0.85-0.96), 0.91 (95% CI: 0.86-0.95) and 75% (95% CI: 0.46-0.92) for target lesions, nontarget lesions and nonpathological lesions, respectively. The consistency of treatment response assessment based on automated segmentation and manual segmentation was excellent for target lesions [K value: 0.92 (0.86-0.98)], good for nontarget lesions [0.82 (0.74-0.90)] and moderate for nonpathological lesions [0.71 (0.50-0.92)]. CONCLUSION: The deep learning-based semiautomated algorithm showed high accuracy for the treatment response assessment of pelvic lymph nodes and demonstrated comparable performance with radiologists.