A Deep Learning-Based Approach for Glomeruli Instance Segmentation from Multistained Renal Biopsy Pathologic Images.

Glomeruli instance segmentation from pathologic images is a fundamental step in the automatic analysis of renal biopsies. Glomerular histologic manifestations vary widely among diseases and cases, and several special staining methods are necessary for pathologic diagnosis. A robust model is needed to segment and classify glomeruli with different staining methods and apply in cases with various glomerular pathologic changes. Herein, pathologic images from renal biopsy slides stained with three basic special staining methods were used to build the data sets. The snapshot group included 1970 glomeruli from 516 patients, and the whole-slide image group included 8665 glomeruli from 148 patients. Cascade Mask region-based convolutional neural net architecture was trained to detect, classify, and segment glomeruli into three categories: i) GN, structural normal; ii) global sclerosis; and iii) glomerular with other lesions. In the snapshot group, total glomeruli, GN, global sclerosis, and glomerular with other lesions achieved an F1 score of 0.914, 0.896, 0.681, and 0.756, respectively, which were comparable with those in the whole-slide image group (0.940, 0.839, 0.806, and 0.753, respectively). Among the three categories, GN achieved the best instance segmentation effect in both groups, as determined by average precision, average recall, F1 score, and Mask mean Intersection over Union. The present model segments and classifies multistained glomeruli with efficiency and robustness. It can be applied as the first step for more detailed glomerular histologic analysis.

Optimization of PEC and photocathodic protection performance of TiO2/CuInS2heterojunction photoanodes.

The establishment of heterojunction is a powerful strategy to enhance the photoresponse performance of photoanode. Here, TiO2/CuInS2(T/CIS) composites were prepared via a two-step hydrothermal method, and their morphologies were controlled by adjusting the reaction time. The absorption spectra show that CuInS2can significantly improve the absorption of visible light. The T/CIS2 (2 h reaction time) photoanode exhibited the most outstanding photoelectrochemical (PEC) performance, with a photocurrent density of 168% that of the pure TiO2photoanode. Under simulated sunlight, this photoanode can supply a protective photocurrent of 0.49 mA cm-2and a protective voltage of 0.36 V to stainless steel (304ss), which are about 4 and 2 times those of the TiO2sample. The enhancement in the photocathodic protection performance is attributed to enlarged visible light absorbance and higher charge separation rate. This study demonstrates that the TiO2/CuInS2photoanode is a promising candidate for application in photoinduced cathodic protection of metallic materials.

Deep learning for automatic diagnosis of gastric dysplasia using whole-slide histopathology images in endoscopic specimens.

BACKGROUND: Distinguishing gastric epithelial regeneration change from dysplasia and histopathological diagnosis of dysplasia is subject to interobserver disagreement in endoscopic specimens. In this study, we developed a method to distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia. Meanwhile, optimized the cross-hospital diagnosis using domain adaption (DA). METHODS: 897 whole slide images (WSIs) of endoscopic specimens from two hospitals were divided into training, internal validation, and external validation cohorts. We developed a deep learning (DL) with DA (DLDA) model to classify gastric dysplasia and epithelial regeneration change into three categories: negative for dysplasia (NFD), low-grade dysplasia (LGD), and high-grade dysplasia (HGD)/intramucosal invasion neoplasia (IMN). The diagnosis based on the DLDA model was compared to 12 pathologists using 100 gastric biopsy cases. RESULTS: In the internal validation cohort, the diagnostic performance measured by the macro-averaged area under the receiver operating characteristic curve (AUC) was 0.97. In the independent external validation cohort, our DLDA models increased macro-averaged AUC from 0.67 to 0.82. In terms of the NFD and HGD cases, our model's diagnostic sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were significantly higher than junior and senior pathologists. Our model's diagnostic sensitivity, NPV, was higher than specialist pathologists. CONCLUSIONS: We demonstrated that our DLDA model could distinguish gastric epithelial regeneration change from dysplasia and further subclassify dysplasia in endoscopic specimens. Meanwhile, achieved significant improvement of diagnosis cross-hospital.

Quality Factor Enhancement of Piezoelectric MEMS Resonator Using a Small Cross-Section Connection Phononic Crystal.

Anchor loss is usually the most significant energy loss factor in Micro-Electro-Mechanical Systems (MEMS) resonators, which seriously hinders the application of MEMS resonators in wireless communication. This paper proposes a cross-section connection phononic crystal (SCC-PnC), which can be used for MEMS resonators of various overtone modes. First, using the finite element method to study the frequency characteristics and delay line of the SCC-PnC band, the SCC-PnC has an ultra-wide bandgap of 56.6-269.6 MHz. Next, the effects of the height h and the position h1 of the structural parameters of the small cross-connected plate on the band gap are studied, and it is found that h is more sensitive to the width of the band gap. Further, the SCC-PnC was implanted into the piezoelectric MEMS resonator, and the admittance and insertion loss curves were obtained. The results show that when the arrangement of 4 × 7 SCC-PnC plates is adopted, the anchor quality factors of the third-order overtone, fifth-order overtone, and seventh-order overtone MEMS resonators are increased by 1656 times, 2027 times, and 16 times, respectively.

A novel tool to provide predictable alignment data irrespective of source and image quality acquired on mobile phones: what engineers can offer clinicians.

PURPOSE: Existing automated spine alignment is based on original X-rays that are not applicable for teleradiology for spinal deformities patients. We aim to provide a novel automated vertebral segmentation method enabling accurate sagittal alignment detection, with no restrictions imposed by image quality or pathology type. METHODS: A total of 428 optical images of original sagittal X-rays taken by smartphones or screenshots for consecutive patients attending our spine clinic were prospectively collected. Of these, 300 were randomly selected and their vertebrae were labelled with Labelme. The ground truth was specialists measured sagittal alignment parameters. Pre-trained Mask R-CNN was fine-tuned and trained to predict the vertebra level(s) on the remaining 128 testing cases. The sagittal alignment parameters including the thoracic kyphosis (TK), lumbar lordosis (LL) and sacral slope (SS) were auto-detected, based on the segmented vertebra. Dice similarity coefficient (DSC) and mean intersection over union (mIoU) were calculated to evaluate the accuracy of the predicted vertebra. The detected sagittal alignments were then quantitatively compared with the ground truth. RESULTS: The DSC was 84.6 ± 3.8% and mIoU was 72.1 ± 4.8% indicating accurate vertebra prediction. The sagittal alignments detected were all strongly correlated with the ground truth (p < 0.001). Standard errors of the estimated parameters had a small difference from the specialists' results (3.5° for TK and SS; 3.4° for LL). CONCLUSION: This is the first study using fine-tuned Mask R-CNN to predict vertebral locations on optical images of X-rays accurately and automatically. We provide a novel alignment detection method that has a significant application on teleradiology aiding out-of-hospital consultations. These slides can be retrieved under Electronic Supplementary Material.

A Nature-Inspired, Flexible Substrate Strategy for Future Wearable Electronics.

Flexibility plays a vital role in wearable electronics. Repeated bending often leads to the dramatic decrease of conductivity because of the numerous microcracks formed in the metal coating layer, which is undesirable for flexible conductors. Herein, conductive textile-based tactile sensors and metal-coated polyurethane sponge-based bending sensors with superior flexibility for monitoring human touch and arm motions are proposed, respectively. Tannic acid, a traditional mordant, is introduced to attach to various flexible substrates, providing a perfect platform for catalyst absorbing and subsequent electroless deposition (ELD). By understanding the nucleation, growth, and structure of electroless metal deposits, the surface morphology of metal nanoparticles can be controlled in nanoscale with simple variation of the plating time. When the electroless plating time is 20 min, the normalized resistance (R/R0 ) of as-made conductive fibers is only 1.6, which is much lower than a 60 min ELD sample at the same conditions (R/R0 ≈ 5). This is because a large number of unfilled gaps between nanoparticles prevent metal films from cracking under bending. Importantly, the Kelvin problem is relevant to deposited conductive coatings because metallic cells have a honeycomb-like structure, which is a rationale to explain the relationships of conductivity and flexibility.

Breast cancer histopathology image classification through assembling multiple compact CNNs.

BACKGROUND: Breast cancer causes hundreds of thousands of deaths each year worldwide. The early stage diagnosis and treatment can significantly reduce the mortality rate. However, the traditional manual diagnosis needs intense workload, and diagnostic errors are prone to happen with the prolonged work of pathologists. Automatic histopathology image recognition plays a key role in speeding up diagnosis and improving the quality of diagnosis. METHODS: In this work, we propose a breast cancer histopathology image classification by assembling multiple compact Convolutional Neural Networks (CNNs). First, a hybrid CNN architecture is designed, which contains a global model branch and a local model branch. By local voting and two-branch information merging, our hybrid model obtains stronger representation ability. Second, by embedding the proposed Squeeze-Excitation-Pruning (SEP) block into our hybrid model, the channel importance can be learned and the redundant channels are thus removed. The proposed channel pruning scheme can decrease the risk of overfitting and produce higher accuracy with the same model size. At last, with different data partition and composition, we build multiple models and assemble them together to further enhance the model generalization ability. RESULTS: Experimental results show that in public BreaKHis dataset, our proposed hybrid model achieves comparable performance with the state-of-the-art. By adopting the multi-model assembling scheme, our method outperforms the state-of-the-art in both patient level and image level accuracy for BACH dataset. CONCLUSIONS: We propose a novel compact breast cancer histopathology image classification scheme by assembling multiple compact hybrid CNNs. The proposed scheme achieves promising results for the breast cancer image classification task. Our method can be used in breast cancer auxiliary diagnostic scenario, and it can reduce the workload of pathologists as well as improve the quality of diagnosis.

Comparative effects of green and black tea extracts on lowering serum uric acid in hyperuricemic mice.

CONTEXT: Tea (Camellia sinensis (L.) Kuntze [Theaceae]) is used to induce urination and inducing nervous excitation. Green and black teas have multifarious physiological functions. The different effects of green and black tea aqueous extracts (GTEs and BTEs) on hyperuricemia are not definitely reported. OBJECTIVE: The different effects of GTEs and BTEs on lowering serum uric acid (UA) in hyperuricemic mice were determined. MATERIALS AND METHODS: Kunming mice were divided into nine groups (n = 6/each group). GTEs and BTEs at the doses of 0.5, 1 and 2 g/kg were orally administrated to mice for seven days, respectively. Hepatic xanthine oxidase (XOD) and adenosine deaminase (ADA) activities as mechanisms of actions were assessed. RESULTS: Research indicated that the LD50 of tea extract is greater than 2 g/kg in mice. UA levels were suppressed significantly with dose-dependent treatment of 0.5, 1 and 2 g/kg BTEs (up to 25.5%, 28.7% and 29.8%, respectively); the serum UA levels were decreased by GTEs but not significant. The activities of XOD and ADA in high dose (2 g/kg) groups of both GTEs and BTEs were notably lower than those of the model group. DISCUSSION AND CONCLUSIONS: The results suggested that both GTEs and BTEs have hypouricaemic and renal protective effects on hyperuricemic mice and the latter one was better. Our study sheds light on the research and development of anti-hyperuricemic functional foods and drugs from tea.

Exploration of the structural mechanism of hydrogen (H2)-promoted horseradish peroxidase (HRP) activity via multiple spectroscopic and molecular dynamics simulation techniques.

Horseradish peroxidase (HRP) is an enzyme that is widely used in various fields. In this study, the effects of molecular hydrogen (H2) on the activity and structural characteristics of HRP were investigated by employing multiple spectroscopic techniques, atomic force microscopy (AFM) and molecular dynamics (MD) simulations. The results demonstrated that H2 could enhance HRP activity, especially in 1.5 mg/L hydrogen-rich water (HRW). The structural analysis results showed that H2 might alter HRP activity by affecting the active sites, secondary structure, hydrogen bonding network, CS groups, and morphological characteristics. The MD results also confirmed that H2 could increase the FeN bond distance in the active site, affect the secondary structure, and increase the number of hydrogen bonds. The MD results further suggested that H2 could increase the number of salt bridges, and lengthen the SS bonds in HRP. This study primarily revealed the mechanism by which H2 enhances the HRP activity, providing insight into the interactions between gas and macromolecular proteins. However, some of the results obtained via MD simulations still need to be verified experimentally. In addition, our study also provided a new convenient strategy to enhance enzyme activity.

Elucidation of the beneficial role of co-fermented whole grain quinoa and black barley with Lactobacillus on rats fed a western-style diet via a multi-omics approach.

Long-term consumption of Western-style diet (WSD) can lead to metabolic disorders and dysbiosis of gut microbiota, presenting a critical risk factor for various chronic conditions such as fatty liver disease. In the present study, we investigated the beneficial role of co-fermented whole grain quinoa and black barley with Lactobacillus kisonensis on rats fed a WSD. Male Sprague-Dawley (SD) rats, aged six weeks and weighing 180 ± 10 g, were randomly assigned to one of three groups: the normal control group (NC, n = 7), the WSD group (HF, n = 7), and the WSD supplemented with a co-fermented whole grain quinoa with black barley (FQB) intervention group (HFF, n = 7). The findings indicated that FQB was effective in suppressing body weight gain, mitigating hepatic steatosis, reducing perirenal fat accumulation, and ameliorating pathological damage in the livers and testicular tissues of rats. Additionally, FQB intervention led to decreased levels of serum uric acid (UA), aspartate aminotransferase (AST), and alanine aminotransferase (ALT). These advantageous effects can be ascribed to the regulation of FQB on gut microbiota dysbiosis, which includes the restoration of intestinal flora diversity, reduction of the F/B ratio, and promotion of probiotics abundance, such as Akkermansia and [Ruminococcus] at the genus level. The study employed the UPLC-Q-TOF-MSE technique to analyze metabolites in fecal and hepatic samples. The findings revealed that FQB intervention led to a regression in the levels of specific metabolites in feces, including oxoadipic acid and 20a, 22b-dihydroxycholesterol, as well as in the liver, such as pyridoxamine, xanthine and xanthosine. The transcriptome sequencing of liver tissues revealed that FQB intervention modulated the mRNA expression of specific genes, including Cxcl12, Cidea, and Gck, known for their roles in anti-inflammatory and anti-insulin resistance mechanisms in the context of WSD. Our findings indicate that co-fermented whole-grain quinoa with black barley has the potential to alleviate metabolic disorders and chronic inflammation resulting from the consumption of WSD.

Multi-Material Radial Phononic Crystals to Improve the Quality Factor of Piezoelectric MEMS Resonators.

In this paper, a multi-material radial phononic crystal (M-RPC) structure is proposed to reduce the anchor-point loss of piezoelectric micro-electro-mechanical system (MEMS) resonators and improve their quality factor. Compared with single-material phononic crystal structures, an M-RPC structure can reduce the strength damage at the anchor point of a resonator due to the etching of the substrate. The dispersion curve and frequency transmission response of the M-RPC structure were calculated by applying the finite element method, and it was shown that the M-RPC structure was more likely to produce a band-gap range with strong attenuation compared with a single-material radial phononic crystal (S-RPC) structure. Then, the effects of different metal-silicon combinations on the band gap of the M-RPC structures were studied, and we found that the largest band-gap range was produced by a Pt and Si combination, and the range was 84.1-118.3 MHz. Finally, the M-RPC structure was applied to a piezoelectric MEMS resonator. The results showed that the anchor quality factor of the M-RPC resonator was increased by 33.5 times compared with a conventional resonator, and the insertion loss was reduced by 53.6%. In addition, the loaded and unloaded quality factors of the M-RPC resonator were improved by 75.7% and 235.0%, respectively, and at the same time, there was no effect on the electromechanical coupling coefficient.

Quality Factor Improvement of a Thin-Film Piezoelectric-on-Silicon Resonator Using a Radial Alternating Material Phononic Crystal.

This paper studies the radial alternating material phononic crystal (RAM-PnC). By simulating the band gap structure of the phononic crystal, a complete acoustic band gap was verified at the resonant frequency of 175.14 MHz, which can prevent the propagation of elastic waves in a specific direction. The proposed alternately arranged radial phononic crystal structure is applied to the thin-film piezoelectric-on-silicon (TPOS) MEMS resonator. The finite element simulation method increases the anchor quality factor (Qanchor) from 60,596 to 659,536,011 at the operating frequency of 175.14 MHz, which is about 10,000 times higher. The motion resistance of the RAM-PnC resonator is reduced from 156.25 Ω to 48.31 Ω compared with the traditional resonator. At the same time, the insertion loss of the RAM-PnC resonator is reduced by 1.1 dB compared with the traditional resonator.

Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph.

Importance: Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children. Objective: To assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression. Design, Setting, and Participants: This diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants' spines. The GTs and app results were blindly compared with another 2 spine surgeons' assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023. Exposure: Acquisitions of unclothed back photographs using a mobile app. Main Outcomes and Measures: Outcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up. Results: The training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone. Conclusions: This diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.

A Five Glutamine-Associated Signature Predicts Prognosis of Prostate Cancer and Links Glutamine Metabolism with Tumor Microenvironment.

Glutamine has been recognized as an important amino acid that provide a variety of intermediate products to fuel biosynthesis. Glutamine metabolism participates in the progression of the tumor via various mechanisms. However, glutamine-metabolism-associated signatures and its significance in prostate cancer are still unclear. In this current study, we identified five genes associated with glutamine metabolism by univariate and Lasso regression analysis and constructed a model to predict the biochemical recurrence free survival (BCRFS) of PCa. Further validation of the prognostic risk model demonstrated a good efficacy in predicting the BCRFS in PCa patients. Interestingly, based on the CIBERSORTx, ssGSEA and ESTIMATE algorithms predictions, we noticed a distinct immune cell infiltration and immune pathway pattern in the prediction of the two risk groups stratified by the risk model. Drug sensitivity prediction revealed that patients in the high-risk group were more suitable for chemotherapy. Last but not least, glutamine deprivation significantly inhibited cell growth in GLUL or ASNS knock down prostate cancer cell lines. Therefore, we proposed a novel prognostic model by using glutamine metabolism genes for PCa patients and identified potential mechanism of PCa progression through glutamine-related tumor microenvironment remodeling.

Deep learning-assisted development and validation of an algorithm for predicting the growth of persistent pure ground-glass nodules.

Background: The prediction of the persistent pure ground-glass nodule (pGGN) growth is challenging and limited by subjective assessment and variation across radiologists. A chest computed tomography (CT) image-based deep learning classification model (DLCM) may provide a more accurate growth prediction. Methods: This retrospective study enrolled consecutive patients with pGGNs from January 2010 to December 2020 from two independent medical institutions. Four DLCM algorithms were built to predict the growth of pGGNs, which were extracted from the nodule areas of chest CT images annotated by two radiologists. All nodules were assigned to either the study, the inner validation, or the external validation cohort. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUROCs) were analyzed to evaluate our models. Results: A total of 286 patients were included, with 419 pGGN. In total, 197 (68.9%) of the patients were female and the average age was 59.5±12.0 years. The number of pGGN assigned to the study, the inner validation, and the external validation cohort were 193, 130, and 96, respectively. The follow-up time of stable pGGNs for the primary and external validation cohorts were 3.66 (range, 2.01-10.08) and 4.63 (range, 2.00-9.91) years, respectively. Growth of the pGGN occurred in 166 nodules [83 (43%), 39 (30%), and 44 (45%) in the study, inner and external validation cohorts respectively]. The best-performing DLCM algorithm was DenseNet_DR, which achieved AUROCs of 0.79 [95% confidence interval (CI): 0.70, 0.86] in predicting pGGN growth in the inner validation cohort and 0.70 (95% CI: 0.60, 0.79) in the external validation cohort. Conclusions: DLCM algorithms that use chest CT images can help predict the growth of pGGNs.

Deep learning for real-time detection of breast cancer presenting pathological nipple discharge by ductoscopy.

Objective: As a common breast cancer-related complaint, pathological nipple discharge (PND) detected by ductoscopy is often missed diagnosed. Deep learning techniques have enabled great advances in clinical imaging but are rarely applied in breast cancer with PND. This study aimed to design and validate an Intelligent Ductoscopy for Breast Cancer Diagnostic System (IDBCS) for breast cancer diagnosis by analyzing real-time imaging data acquired by ductoscopy. Materials and methods: The present multicenter, case-control trial was carried out in 6 hospitals in China. Images for consecutive patients, aged ≥18 years, with no previous ductoscopy, were obtained from the involved hospitals. All individuals with PND confirmed from breast lesions by ductoscopy were eligible. Images from Beijing Chao-Yang Hospital were randomly assigned (8:2) to the training (IDBCS development) and internal validation (performance evaluation of the IDBCS) datasets. Diagnostic performance was further assessed with internal and prospective validation datasets from Beijing Chao-Yang Hospital; further external validation was carried out with datasets from 5 primary care hospitals. Diagnostic accuracies, sensitivities, specificities, and positive and negative predictive values for IDBCS and endoscopists (expert, competent, or trainee) in the detection of malignant lesions were obtained by the Clopper-Pearson method. Results: Totally 11305 ductoscopy images in 1072 patients were utilized for developing and testing the IDBCS. Area under the curves (AUCs) in breast cancer detection were 0·975 (95%CI 0·899-0·998) and 0·954 (95%CI 0·925-0·975) in the internal validation and prospective datasets, respectively, and ranged between 0·922 (95%CI 0·866-0·960) and 0·965 (95%CI 0·892-0·994) in the 5 external validation datasets. The IDBCS had superior diagnostic accuracy compared with expert (0.912 [95%CI 0.839-0.959] vs 0.726 [0.672-0.775]; p<0.001), competent (0.699 [95%CI 0.645-0.750], p<0.001), and trainee (0.703 [95%CI 0.648-0.753], p<0.001) endoscopists. Conclusions: IDBCS outperforms clinical oncologists, achieving high accuracy in diagnosing breast cancer with PND. The novel system could help endoscopists improve their diagnostic efficacy in breast cancer diagnosis.

Hard Sample Aware Noise Robust Learning for Histopathology Image Classification.

Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/.

Hydrogen-rich water partially alleviate inflammation, oxidative stress and intestinal flora dysbiosis in DSS-induced chronic ulcerative colitis mice.

PURPOSE: Oxidative damage and intestinal flora dysbiosis play important roles in the progression of chronic ulcerative colitis (UC). This study explored the effect and mechanism of molecular hydrogen in chronic UC. MATERIALS AND METHODS: Male C57BL/6 mice (19.6 â€‹± â€‹0.4 â€‹g, 7 weeks) were randomly divided into 3 groups: normal control (NC) group, UC (Dextran Sulfate Sodium, DSS) group, and hydrogen-rich water (HRW, 0.8 â€‹ppm)-treated UC (DSS â€‹+ â€‹HRW) group. Mice in the DSS treatment group were treated with DSS for the following 3 cycles to establish chronic UC model: the first 2 cycles consisted of 2.5% DSS for 5 days, followed by drinking water for 16 days, and a third cycle consisted of 2% DSS for 4 days, followed by drinking water for 10 days. The mice in the DSS â€‹+ â€‹HRW group were administered HRW daily throughout the experiment. RESULTS: The mice in the DSS groups developed typical clinical signs of colitis. HRW treatment partially ameliorated colitis symptoms, improved histopathological changes, significantly increased glutathione (GSH) concentration and decreased TNF-α level. Notably, HRW treatment significantly inhibited the growth of Enterococcus faecalis, Clostridium perfringens and Bacteroides fragilis (P â€‹< â€‹0.05 vs. DSS group), with the relative abundance that was close to the levels in the NC group. Microarray analysis revealed that 252 genes were significantly modified after HRW treatment compared with those in the DSS treatment alone group, and 17 genes were related to inflammation, including 9 interferon-stimulated genes (ISGs). CONCLUSIONS: Hydrogen-rich water partially alleviates inflammation, oxidative stress and intestinal flora dysbiosis in DSS-induced chronic UC mice.

DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system.

Examination of pathological images is the golden standard for diagnosing and screening many kinds of cancers. Multiple datasets, benchmarks, and challenges have been released in recent years, resulting in significant improvements in computer-aided diagnosis (CAD) of related diseases. However, few existing works focus on the digestive system. We released two well-annotated benchmark datasets and organized challenges for the digestive-system pathological cell detection and tissue segmentation, in conjunction with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). This paper first introduces the two released datasets, i.e., signet ring cell detection and colonoscopy tissue segmentation, with the descriptions of data collection, annotation, and potential uses. We also report the set-up, evaluation metrics, and top-performing methods and results of two challenge tasks for cell detection and tissue segmentation. In particular, the challenge received 234 effective submissions from 32 participating teams, where top-performing teams developed advancing approaches and tools for the CAD of digestive pathology. To the best of our knowledge, these are the first released publicly available datasets with corresponding challenges for the digestive-system pathological detection and segmentation. The related datasets and results provide new opportunities for the research and application of digestive pathology.

Optimized lung tumor diagnosis system using enhanced version of crow search algorithm, Zernike moments, and support vector machine.

Early detection of lung tumors is so important to heal this disease in the initial steps. Automatic computer-aided detection of this disease is a good method for reducing human mistakes and improving detection precision. The major concept here is to propose the best CAD system for lung tumor detection. In the presented technique, after pre-processing and segmentation of the lung area, its features including different orders of Zernike moments have been extracted. After features extraction, they have been injected into an optimized version of Support Vector Machine (SVM) for final diagnosis. The optimization of the SVM is based on an enhanced design of the Crow Search Algorithm (ECSA). For validating the proposed method, it was applied to three datasets including Lung CT-Diagnosis, TCIA, and RIDER Lung CT collection, and the results are validated by comparing with three state-of-the-art methods including Walwalker method, Mon method, and Naik method to indicate the system superiority toward the compared methods. The system is also analyzed based on different orders of Zernike moment to select the best order. The final results indicate that the suggested method has a suitable accuracy for diagnosing lung cancer.