Transformaer-based model for lung adenocarcinoma subtypes.

BACKGROUND: Lung cancer has the highest morbidity and mortality rate among all types of cancer. Histological subtypes serve as crucial markers for the development of lung cancer and possess significant clinical values for cancer diagnosis, prognosis, and prediction of treatment responses. However, existing studies only dichotomize normal and cancerous tissues, failing to capture the unique characteristics of tissue sections and cancer types. PURPOSE: Therefore, we have pioneered the classification of lung adenocarcinoma (LAD) cancer tissues into five subtypes (acinar, lepidic, micropapillary, papillary, and solid) based on section data in whole-slide image sections. In addition, a novel model called HybridNet was designed to improve the classification performance. METHODS: HybridNet primarily consists of two interactive streams: a Transformer and a convolutional neural network (CNN). The Transformer stream captures rich global representations using a self-attention mechanism, while the CNN stream extracts local semantic features to optimize image details. Specifically, during the dual-stream parallelism, the feature maps of the Transformer stream as weights are weighted and summed with those of the CNN stream backbone; at the end of the parallelism, the respective final features are concatenated to obtain more discriminative semantic information. RESULTS: Experimental results on a private dataset of LAD showed that HybridNet achieved 95.12% classification accuracy, and the accuracy of five histological subtypes (acinar, lepidic, micropapillary, papillary, and solid) reached 94.5%, 97.1%, 94%, 91%, and 99% respectively; the experimental results on the public BreakHis dataset show that HybridNet achieves the best results in three evaluation metrics: accuracy, recall and F1-score, with 92.40%, 90.63%, and 91.43%, respectively. CONCLUSIONS: The process of classifying LAD into five subtypes assists pathologists in selecting appropriate treatments and enables them to predict tumor mutation burden (TMB) and analyze the spatial distribution of immune checkpoint proteins based on this and other clinical data. In addition, the proposed HybridNet fuses CNN and Transformer information several times and is able to improve the accuracy of subtype classification, and also shows satisfactory performance on public datasets with some generalization ability.

Immune subtype identification and multi-layer perceptron classifier construction for breast cancer.

Introduction: Breast cancer is a heterogeneous tumor. Tumor microenvironment (TME) has an important effect on the proliferation, metastasis, treatment, and prognosis of breast cancer. Methods: In this study, we calculated the relative proportion of tumor infiltrating immune cells (TIICs) in the breast cancer TME, and used the consensus clustering algorithm to cluster the breast cancer subtypes. We also developed a multi-layer perceptron (MLP) classifier based on a deep learning framework to detect breast cancer subtypes, which 70% of the breast cancer research cohort was used for the model training and 30% for validation. Results: By performing the K-means clustering algorithm, the research cohort was clustered into two subtypes. The Kaplan-Meier survival estimate analysis showed significant differences in the overall survival (OS) between the two identified subtypes. Estimating the difference in the relative proportion of TIICs showed that the two subtypes had significant differences in multiple immune cells, such as CD8, CD4, and regulatory T cells. Further, the expression level of immune checkpoint molecules (PDL1, CTLA4, LAG3, TIGIT, CD27, IDO1, ICOS) and tumor mutational burden (TMB) also showed significant differences between the two subtypes, indicating the clinical value of the two subtypes. Finally, we identified a 38-gene signature and developed a multilayer perceptron (MLP) classifier that combined multi-gene signature to identify breast cancer subtypes. The results showed that the classifier had an accuracy rate of 93.56% and can be robustly used for the breast cancer subtype diagnosis. Conclusion: Identification of breast cancer subtypes based on the immune signature in the tumor microenvironment can assist clinicians to effectively and accurately assess the progression of breast cancer and formulate different treatment strategies for different subtypes.

LAD-GCN: Automatic diagnostic framework for quantitative estimation of growth patterns during clinical evaluation of lung adenocarcinoma.

Quantitative estimation of growth patterns is important for diagnosis of lung adenocarcinoma and prediction of prognosis. However, the growth patterns of lung adenocarcinoma tissue are very dependent on the spatial organization of cells. Deep learning for lung tumor histopathological image analysis often uses convolutional neural networks to automatically extract features, ignoring this spatial relationship. In this paper, a novel fully automated framework is proposed for growth pattern evaluation in lung adenocarcinoma. Specifically, the proposed method uses graph convolutional networks to extract cell structural features; that is, cells are extracted and graph structures are constructed based on histopathological image data without graph structure. A deep neural network is then used to extract the global semantic features of histopathological images to complement the cell structural features obtained in the previous step. Finally, the structural features and semantic features are fused to achieve growth pattern prediction. Experimental studies on several datasets validate our design, demonstrating that methods based on the spatial organization of cells are appropriate for the analysis of growth patterns.

A semi-supervised learning framework for micropapillary adenocarcinoma detection.

PURPOSE: Micropapillary adenocarcinoma is a distinctive histological subtype of lung adenocarcinoma with poor prognosis. Computer-aided diagnosis method has the potential to provide help for its early diagnosis. But the implementation of the existing methods largely relies on massive manually labeled data and consumes a lot of time and energy. To tackle these problems, we propose a framework that applies semi-supervised learning method to detect micropapillary adenocarcinoma, which aims to utilize labeled and unlabeled data better. METHODS: The framework consists of a teacher model and a student model. The teacher model is first obtained by using the labeled data. Then, it makes predictions on unlabeled data as pseudo-labels for students. Finally, high-quality pseudo-labels are selected and associated with the labeled data to train the student model. During the learning process of the student model, augmentation is added so that the student model generalizes better than the teacher model. RESULTS: Experiments are conducted on our own whole slide micropapillary lung adenocarcinoma histopathology image dataset and we selected 3527 patches for the experiment. In the supervised learning, our detector achieves a precision of 0.762 and recall of 0.884. In the semi-supervised learning, our method achieves a precision of 0.775 and recall of 0.896; it is superior to other methods. CONCLUSION: We proposed a semi-supervised learning framework for micropapillary adenocarcinoma detection, which has better performance in utilizing both labeled and unlabeled data. In addition, the detector we designed improves the detection accuracy and speed and achieves promising results in detecting micropapillary adenocarcinoma.

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis.

Introduction: Manual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem. Methods: To solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called"Semi- supervised Histopathology Analysis Network"(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training. Results: Our Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893. Discussion: To overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.

SymReg-GAN: Symmetric Image Registration With Generative Adversarial Networks.

Symmetric image registration estimates bi-directional spatial transformations between images while enforcing an inverse-consistency. Its capability of eliminating bias introduced inevitably by generic single-directional image registration allows more precise analysis in different interdisciplinary applications of image registration, e.g., computational anatomy and shape analysis. However, most existing symmetric registration techniques especially for multimodal images are limited by low speed from the commonly-used iterative optimization, hardship in exploring inter-modality relations or high labor cost for labeling data. We propose SymReg-GAN to shatter these limits, which is a novel generative adversarial networks (GAN) based approach to symmetric image registration. We formulate symmetric registration of unimodal/multimodal images as a conditional GAN and train it with a semi-supervised strategy. The registration symmetry is realized by introducing a loss for encouraging that the cycle composed of the geometric transformation from one image to another and its reverse should bring an image back. The semi-supervised learning enables both the precious labeled data and large amounts of unlabeled data to be fully exploited. Experimental results from six public brain magnetic resonance imaging (MRI) datasets and 1 our own computed tomography (CT) and MRI dataset demonstrate the superiority of SymReg-GAN to several existing state-of-the-art methods.

Picroside II Improves Severe Acute Pancreatitis-Induced Hepatocellular Injury in Rats by Affecting JAK2/STAT3 Phosphorylation Signaling.

Picroside II is an important ingredient agent in Traditional Chinese medicine and hoped to reduce hepatocellular injury caused by severe acute pancreatitis (SAP). An SAP-induced hepatocellular injury model was established in rats by using pentobarbital sodium. 27 rats were divided into 3 groups: the sham group (SG), model group (MG), and Picroside groups (PG). SAP-induced hepatocellular injury was assessed using hematoxylin and eosin staining. We measured hepatocellular enzymes (amylase (AMY), alanine aminotransferase (ALT), and aspartate aminotransferase (AST)), oxidative stress factors (superoxidase dismutase (SOD) and malondialdehyde (MDA)), and inflammatory factors (tumor necrosis factor α (TNF-α), interleukin- (IL-) 6, and IL-10), apoptotic factors (BAX and cleaved caspase 3), and inflammatory signaling (Janus kinase 2 (JAK2)/signal transducer and activator of transcription 3 (STAT3), p-JAK2, and p-STAT3) in hepatocellular tissues. The SAP-induced hepatocellular injury model was successfully established. Picroside II treatment repaired hepatocellular injury by reducing the activities of AMY, ALT, and AST; reducing the levels of MDA, TNF-α, IL-1, IL-6, p-JAK2, p-STAT3, BAX, and cleaved caspase 3; and increasing the levels of SOD and IL-10. Picroside II exerted protective function for the SAP-induced hepatocellular injury model. Picroside II improved SAP-induced hepatocellular injury and antioxidant and anti-inflammatory properties by affecting JAK2/STAT3 phosphorylation signaling.

Symmetric Deformable Registration via Learning a Pseudomean for MR Brain Images.

Image registration is a fundamental task in medical imaging analysis, which is commonly used during image-guided interventions and data fusion. In this paper, we present a deep learning architecture to symmetrically learn and predict the deformation field between a pair of images in an unsupervised fashion. To achieve this, we design a deep regression network to predict a deformation field that can be used to align the template-subject image pair. Specifically, instead of estimating the single deformation pathway to align the images, herein, we predict two halfway deformations, which can move the original template and subject into a pseudomean space simultaneously. Therefore, we train a symmetric registration network (S-Net) in this paper. By using a symmetric strategy, the registration can be more accurate and robust particularly on the images with large anatomical variations. Moreover, the smoothness of the deformation is also significantly improved. Experimental results have demonstrated that the trained model can directly predict the symmetric deformations on new image pairs from different databases, consistently producing accurate and robust registration results.

Deep multispectral image registration network.

Multispectral imaging (MSI) of the ocular fundus provides a sequence of narrow-band images to show the different depths in the retina and choroid. One challenge in analyzing MSI images comes from the image-to-image spatial misalignment, which occurs because the acquisition time of eye MSI images is commonly longer than the natural time scale of the eye's saccadic movement. It is necessary to align images because ophthalmologists usually overlay two of the images to analyze specific features when analyzing MSI images. In this paper, we propose a weakly supervised MSI image registration network, called MSI-R-NET, for multispectral fundus image registration. Compared to other deep-learning-based registration methods, MSI-R-NET utilizes the blood vessel segmentation label to provide spatial correspondence. In addition, we employ a feature equilibrium module to connect the aggregating layers better, and propose a multiresolution auto-context structure to adapt the registration task. In the testing stage, given a new pair of MSI images, the trained model can predict the pixelwise spatial correspondence without labeled blood vessel information. The experimental results demonstrate that the proposed segmentation-driven registration method is highly accurate.

Picroside II Improves Severe Acute Pancreatitis-Induced Intestinal Barrier Injury by Inactivating Oxidative and Inflammatory TLR4-Dependent PI3K/AKT/NF-κB Signaling and Improving Gut Microbiota.

BACKGROUND: Picroside II exerts anti-inflammatory and antidiarrheal effects for treating the diseases associated with oxidative injury. However, its function on pancreatitis-induced intestinal barrier injury remains unclear. Hypothesis/Purpose. We hypothesized that picroside II will have protective effects against pancreatitis-induced intestinal barrier injury by affecting oxidative and inflammatory signaling (Toll-like receptor 4- (TLR4-) dependent phosphatidylinositol 3-kinase (PI3K), protein kinase B (AKT), and nuclear factor kappa B (NF-κB)). Study Design and Methods. A Sprague-Dawley (SD) rat model with severe acute pancreatitis (SAP) was induced via the injection of sodium taurocholate (4% wt/vol; 1 mL/kg). All rats were divided into 3 groups: sham (CG), SAP-induced intestinal barrier injury (MG), and picroside II (PG) groups. Intestinal barrier injury was assessed by scanning electron microscopy (SEM), hematoxylin and eosin staining, and pathological scores. We measured the levels of pancreatitis biomarkers (amylase and lipase), oxidative and inflammatory signaling (TLR4-dependent PI3K/AKT/NF-κB), oxidative stress marker (superoxidase dismutase (SOD), catalase (CAT), glutathione peroxidases (GPx), and malondialdehyde), and inflammatory markers (tumor necrosis factor α (TNFα), interleukin- (IL-) 1, IL-6, and IL-10) in serum and/or gut tissues. Gut microbiota composition in feces was measured by using 16S rRNA sequencing. RESULTS: SEM showed that intestinal barrier injury was caused with the loss of intestinal villi and mitochondria destruction, and pathological scores were increased in the MG group. The levels of amylase, lipase, malondialdehyde, TNFα, IL-1, IL-6, TLR4, PI3K, AKT, and NF-κB were increased, and the levels of SOD, GPx, CAT, and IL-10 was reduced in the MG group when compared with CG group (P < 0.05). Picroside II treatment inhibited the symptoms in the MG group and showed antioxidant and anti-inflammatory activities. The serum levels of picroside II had strong correlation with the levels of inflammatory and oxidative stress biomarkers (P < 0.05). Picroside II treatment increased the proportion of Lactobacillus and Prevotella and decreased the proportion of Helicobacter and Escherichia_Shigella in the model. CONCLUSIONS: Picroside II improved the SAP-induced intestinal barrier injury in the rat model by inactivating oxidant and inflammatory signaling and improving gut microbiota.

IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge.

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

Hydrostatin-SN10 Ameliorates Pancreatitis-Induced Lung Injury by Affecting IL-6-Induced JAK2/STAT3-Associated Inflammation and Oxidative Stress.

Hydrostatin-SN1 (peptide sequence, DEQHLETELHTLTSVLTANGFQ), a kind of peptides extracted from snake venom, has been reported to have anti-inflammatory effect, but its truncated mutant hydrostatin-SN10 (peptide sequence, DEQHLETELH) on pancreatitis-induced acute lung injury has not been well documented. Interleukin- (IL-) 6-induced Janus Kinase 2/Signal Transducer and Activator of Transcription 3 (JAK2/STAT3) pathway is involved with inflammatory and oxidative stress activities and may be associated with the pathogenesis of lung injury, and related molecules were measured. Taurocholate-induced pancreatitis associated with acute lung injury was established and treated with hydrostatin-SN10. Pancreatitis was confirmed by measuring the serum levels of amylase, lipase, and trypsinogen and urinary amylase. Lung injury was determined by histologically assessing acinar cell changes. The related molecules of IL-6-induced JAK2/STAT3-associated inflammation and oxidative stress were quantitated by real time-PCR, Western blot, and/or immunochemical assay. Hydrostatin-SN10 reduced the levels of serum amylase, lipase, and trypsinogen and urinary amylase when compared with the model group (p < 0.05). Hydrostatin-SN10 significantly inhibited the IL-6-stimulated JAK2/STAT3 pathway and reduced the number of apoptotic cells via the downregulation of caspase 3 and BAX (proapoptotic) and upregulation of Bcl2 (antiapoptotic) (p < 0.05). IL-6 induced the increase in the levels of JAK2 and STAT3, which was reversed by hydrostatin-SN10 treatment (p < 0.05). In addition, hydrostatin-SN10 reduced the expression of IL-6 and TNF- (tumor necrosis factor-) α and increased the level of IL-10 (p < 0.05). On the other hand, hydrostatin-SN10 treatment increased the levels of superoxide dismutase (SOD) and reduced glutathione (GSH) and the levels of malondialdehyde (MDA) and alanine aminotransferase (ALT) (p < 0.05). These results suggest that hydrostatin-SN10 may inhibit pancreatitis-induced acute lung injury by affecting IL-6-mediated JAK2/STAT3 pathway-associated inflammation and oxidative stress.

1-Deoxynojirimycin (DNJ) Ameliorates Indomethacin-Induced Gastric Ulcer in Mice by Affecting NF-kappaB Signaling Pathway.

Gastric ulcer (GU) is a main threat to public health. 1-Deoxynojirimycin (DNJ) has antioxidant and anti-inflammatory properties and may prevent GU but related mechanism remains unclear. DNJ was extracted from the supernatants of Bacillus subtilis by using ethanol and purified by using CM-Sepharose chromatography. A GU mouse model was induced by indomethacin. The functional role of DNJ in GU mice was explored by measuring the main molecules in the NF-KappaB pathway. After the model establishment, 40 GU mice were evenly assigned into five categories: IG (received vehicle control), LG (10 µg DNJ daily), MG (20 µg DNJ daily), HG (40 µg DNJ daily), and RG (0.5 mg ranitidine daily). Meanwhile, eight healthy mice were assigned as a control group (CG). After 1-month therapy, weight and gastric volume were investigated. The levels of serum inflammatory cytokines (IL-6 and TNF-α), antioxidant indices [superoxide dismutase (SOD), catalase (CAT), and reduced glutathione (GSH)], and oxidant biomarker malondialdehyde (MDA) were examined via ELISA. Meanwhile, inflammatory cytokine (IL-6 and TNF-α) levels, and key molecules (NF-κB p65), cyclooxygenase 1 (COX-1 and COX2) involved in NF-κB pathway, were analyzed by using Western Blot. COX-1 and COX-2 levels were further measured by immunohistochemistry. The effects of DNJ on gastric functions were explored by measuring the changes of Motilin (MOT), Substance P (SP), Somatostatin (SS), and Vasoactive intestinal peptide (VIP) in GU mouse models with ELISA Kits. The results indicated that DNJ prevented indomethacin-caused increase of gastric volume. DNJ improved histopathology of GU mice when compared with the mice from IG group (P < 0.05). DNJ consumption decreased the levels of IL-6 and TNF-α (P < 0.05). DNJ increased antioxidant indices of GU mice by improving the activities of SOD, CAT and reduced GSH, and reduced MDA levels (P < 0.05). DNJ increased the levels of prostaglandin E2, COX-1, COX2, and reduced the levels of and NF-κB p65 (P < 0.05). DNJ showed protection for gastric functions of GU mice by reducing the levels of MOT and SP, and increasing the levels of SS and VIP. DNJ treatment inactivates NF-κB signaling pathway, and increases anti-ulceration ability of the models.

Root Extract of Polygonum cuspidatum Siebold & Zucc. Ameliorates DSS-Induced Ulcerative Colitis by Affecting NF-kappaB Signaling Pathway in a Mouse Model via Synergistic Effects of Polydatin, Resveratrol, and Emodin.

Background:Polygonum cuspidatum Siebold & Zucc. (PCS) has antibacterial properties and may prevent Ulcerative colitis (UC) but related molecular mechanism remains unknown. NF-κB signaling pathway is associated with inflammatory responses and its inactivation may be critical for effective therapy of UC. Methods: UC mouse (C57BL/6J) model was established by using dextran sulfate sodium (DSS). The extract of PCS (PCSE) was prepared by using ethanol and its main ingredients were measured by HPLC. Thirty-two UC mice were evenly assigned into DG (received vehicle control), LG (0.1 g/kg PCSE daily), MG (0.2 g/kg PCSE daily) and HG (0.4 g/kg PCSE daily) groups. Meanwhile, 8 healthy mice were assigned as a control group (CG). Serum pharmacokinetics of PCS was measured by using HPLC. After 8-day treatment, weight, colon length and disease activity index (DAI) were measured. Inflammatory cytokines and oxidant biomarkers were measured by ELISA kits. The levels of cytokines, and key molecules in NF-κB pathway, were measured by using Western Blot. The effects of main ingredients of PCSE on cytokines and NF-κB signaling pathway were explored by using intestinal cells of a mouse UC model. The normality criterion was evaluated using the Saphiro-Wilk test. The quantitative variables were compared using the paired Student's-t test. Results: The main ingredients of PCSE were polydatin, resveratrol and emodin. Polydatin may be transformed into resveratrol in the intestine of the mice. PCSE prevented DSS-caused weight loss and colon length reduction, and improved histopathology of UC mice (P < 0.05). PCSE treatment increased the serum levels of IL-10 and reduced the levels of IL-1 beta, IL-6 and TNF-α (P < 0.05). PCSE increased the activities of SOD, CAT, GPX and reduced the level of MDA, BCL-2, beta-arrestin, NF-κB p65 and the activity of MPO (P < 0.05). The combination of polydatin, resveratrol or emodin, and or PCSE exhibited higher inhibitory activities for cytokines and NF-κB signaling related molecules than any one of the three ingredients with same concentration treatment. Conclusion: Oral administration of PCSE suppressed NF-κB signaling pathway and exerts its anti-colitis effects via synergistic effects of polydatin, resveratrol or emodin.