Hybridizing Convolutional Neural Network for Classification of Lung diseases

Pulmonary disease is widespread worldwide. There is persistent blockage of the lungs, pneumonia, asthma, TB, etc. It is essential to diagnose the lungs promptly. For this reason, machine learning models were developed. For lung disease prediction, many deep learning technologies, including the CNN, and the capsule network, are used. The fundamental CNN has low rotating, inclined, or other irregular image orientation efficiency. Therefore by integrating the space transformer network (STN) with CNN, we propose a new hybrid deep learning architecture named STNCNN. The new model is implemented on the dataset from the Kaggle repository for an NIH chest X-ray image. STNCNN has an accuracy of 69% in respect of the entire dataset, while the accuracy values of vanilla grey, vanilla RGB, hybrid CNN are 67.8%, 69.5%, and 63.8%, respectively. When the sample data set is applied, STNCNN takes much less time to train at the cost of a slightly less reliable validation. Therefore both specialists and physicians are simplified by the proposed STNCNN System for the diagnosis of lung disease.

Mineralogical and Geochemical Characteristics of Lead-zinc Ore Deposits, and Potential Accompanying Components in the Cho Don - Cho Dien Area, Bac Kan Province, Vietnam

The Pb-Zn mineralization in the Cho Don - Cho Dien ore districts often occurs in 2 types: (1)oxidized ore near to the surface and (2) sulfide ore at deeper section. Based on microscopic observations,sulfide ores can be divided into sphalerite-galena-pyrite and/or galena-sphalerite mineralization types. Toexamine the geochemical features of the Pb-Zn ores, SEM-EDX and ICP-MS analytical methods wereperformed in this study. Previous δ34S data of Pb-Zn concentrates, and sulfide minerals from variousdeposits suggest that the Pb-Zn ore-forming fluids might be related to the felsic-granitic magmaticactivities rather than a genesis of stratiform type. Geochemical data show that the major, minor, and traceelement compositions of lead-zinc ores have wide ranges of variation even in each deposit. The sulfideores are generally higher in economic components than those in the oxidized ores. The positivecorrelations between Pb-Ag can be found in the entire dataset, whereas excellent Zn-Cd correlation canonly be observed from Cho Don ore samples. Apart from the principal components (Pb and Zn), the oresalso contain other accompanying elements that supply high-technological manufacturing industries. Ofwhich As, Cu, Ag, Sb, and Cd could be potential by-products and can be extracted during smelting Pb/Znconcentrate processes, and need more detailed studies for every deposit.

Nationwide epidemiological characteristics of chronic fatigue syndrome in South Korea

Background Chronic fatigue syndrome (CFS) is a long-term disabling illness accompanied by medically unexplained fatigue. This study aimed to explore the epidemiological characteristics of CFS in South Korea. Methods Using the nationwide medical records provided by the Korean Health Insurance Review & Assessment Service (HIRA), we analyzed the entire dataset for CFS patients diagnosed by physicians in South Korea from January 2010 to December 2020. Results The annual mean incidence of CFS was estimated to be 44.71 ± 6.10 cases per 100,000 individuals [95% CI: 40.57, 48.76], and the prevalence rate was 57.70 ± 12.20 cases per 100,000 individuals [95% CI: 49.40, 65.79]. These two rates increased by 1.53- and 1.94-fold from 2010 to 2020, respectively, and showed an increasing trend with aging and an approximately 1.5-fold female predominance. Conclusions This study is the first to report the nationwide epidemiological features of CFS, which reflects the clinical reality of CFS diagnosis and care in South Korea. This study will be a valuable reference for studies of CFS in the future.

Active Learning Performance in Labeling Radiology Images Is 90% Effective

To train artificial intelligence (AI) systems on radiology images, an image labeling step is necessary. Labeling for radiology images usually involves a human radiologist manually drawing a (polygonal) shape onto the image and attaching a word to it. As datasets are typically large, this task is repetitive, time-consuming, error-prone, and expensive. The AI methodology of active learning (AL) can assist human labelers by continuously sorting the unlabeled images in order of information gain and thus getting the labeler always to label the most informative image next. We find that after about 10%, depending on the dataset, of the images in a realistic dataset are labeled, virtually all the information content has been learnt and the remaining images can be automatically labeled. These images can then be checked by the radiologist, which is far easier and faster to do. In this way, the entire dataset is labeled with much less human effort. We introduce AL in detail and expose the effectiveness using three real-life datasets. We contribute five distinct elements to the standard AL workflow creating an advanced methodology.

Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images

Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.

A clinical specific BERT developed using a huge Japanese clinical text corpus

Generalized language models that are pre-trained with a large corpus have achieved great performance on natural language tasks. While many pre-trained transformers for English are published, few models are available for Japanese text, especially in clinical medicine. In this work, we demonstrate the development of a clinical specific BERT model with a huge amount of Japanese clinical text and evaluate it on the NTCIR-13 MedWeb that has fake Twitter messages regarding medical concerns with eight labels. Approximately 120 million clinical texts stored at the University of Tokyo Hospital were used as our dataset. The BERT-base was pre-trained using the entire dataset and a vocabulary including 25,000 tokens. The pre-training was almost saturated at about 4 epochs, and the accuracies of Masked-LM and Next Sentence Prediction were 0.773 and 0.975, respectively. The developed BERT did not show significantly higher performance on the MedWeb task than the other BERT models that were pre-trained with Japanese Wikipedia text. The advantage of pre-training on clinical text may become apparent in more complex tasks on actual clinical text, and such an evaluation set needs to be developed.

The Identification of Blood Biomarkers of Chronic Neuropathic Pain by Comparative Transcriptomics

In this study, we recruited 50 chronic pain (neuropathic and nociceptive) and 43 pain-free controls to identify specific blood biomarkers of chronic neuropathic pain (CNP). Affymetrix microarray was carried out on a subset of samples selected 10 CNP and 10 pain-free control participants. The most significant genes were cross-validated using the entire dataset by quantitative real-time PCR (qRT-PCR). In comparative analysis of controls and CNP patients, WLS (P = 4.80 × 10–7), CHPT1 (P = 7.74 × 10–7) and CASP5 (P = 2.30 × 10–5) were highly significant, whilst FGFBP2 (P = 0.00162), STAT1 (P = 0.00223), FCRL6 (P = 0.00335), MYC (P = 0.00335), XCL2 (P = 0.0144) and GZMA (P = 0.0168) were significant in all CNP patients. A three-arm comparative analysis was also carried out with control as the reference group and CNP samples differentiated into two groups of high and low S-LANSS score using a cut-off of 12. STAT1, XCL2 and GZMA were not significant but KIR3DL2 (P = 0.00838), SH2D1B (P = 0.00295) and CXCR31 (P = 0.0136) were significant in CNP high S-LANSS group (S-LANSS score > 12), along with WLS (P = 8.40 × 10–5), CHPT1 (P = 7.89 × 10–4), CASP5 (P = 0.00393), FGFBP2 (P = 8.70 × 10–4) and FCRL6 (P = 0.00199), suggesting involvement of immune pathways in CNP mechanisms. None of the genes was significant in CNP samples with low (< 12) S-LANSS score. The area under the receiver operating characteristic (AUROC) analysis showed that combination of MYC, STAT1, TLR4, CASP5 and WLS gene expression could be potentially used as a biomarker signature of CNP (AUROC − 0.852, (0.773, 0.931 95% CI)).

Developing and testing an automated qualitative assistant (AQUA) to support qualitative analysis

Qualitative research remains underused, in part due to the time and cost of annotating qualitative data (coding). Artificial intelligence (AI) has been suggested as a means to reduce those burdens, and has been used in exploratory studies to reduce the burden of coding. However, methods to date use AI analytical techniques that lack transparency, potentially limiting acceptance of results. We developed an automated qualitative assistant (AQUA) using a semiclassical approach, replacing Latent Semantic Indexing/Latent Dirichlet Allocation with a more transparent graph-theoretic topic extraction and clustering method. Applied to a large dataset of free-text survey responses, AQUA generated unsupervised topic categories and circle hierarchical representations of free-text responses, enabling rapid interpretation of data. When tasked with coding a subset of free-text data into user-defined qualitative categories, AQUA demonstrated intercoder reliability in several multicategory combinations with a Cohen’s kappa comparable to human coders (0.62–0.72), enabling researchers to automate coding on those categories for the entire dataset. The aim of this manuscript is to describe pertinent components of best practices of AI/machine learning (ML)-assisted qualitative methods, illustrating how primary care researchers may use AQUA to rapidly and accurately code large text datasets. The contribution of this article is providing guidance that should increase AI/ML transparency and reproducibility.

Nationwide Epidemiological Characteristics of Chronic Fatigue Syndrome in South Korea

Background: Chronic fatigue syndrome (CFS) is a long-term disabling illness accompanied by medically unexplained fatigue. This study aimed to explore the epidemiological characteristics of CFS in South Korea.Methods: Using the nationwide medical records provided by the Korean Health Insurance Review & Assessment Service (HIRA), we analyzed the entire dataset for CFS patients diagnosed by physicians in Korea from January 2010 to December 2020. Results: The annual mean incidence of CFS was estimated to be 44.71 ± 6.10 cases per 100,000 individuals [95% CI: 40.57, 48.76], and the prevalence rate was 57.70 ± 12.20 cases per 100,000 individuals [95% CI: 49.40, 65.79]. These two rates increased by 1.53- and 1.94-fold from 2010 to 2020, respectively, and showed an increasing trend with aging and an approximately 1.5-fold female predominance. Conclusions: This study is the first to report the nationwide epidemiological features of CFS, which reflects the clinical reality of CFS diagnosis and care in South Korea. This study will be a valuable reference for studies of CFS in the future.

Mistic: an open-source multiplexed image t-SNE viewer

Understanding the complex ecology of a tumor tissue and the spatio-temporal relationships between its cellular and microenvironment components is becoming a key component of translational research, especially in immune-oncology. The generation and analysis of multiplexed images from patient samples is of paramount importance to facilitate this understanding. In this work, we present Mistic, an open-source multiplexed image t-SNE viewer that enables the simultaneous viewing of multiple 2D images rendered using multiple layout options to provide an overall visual preview of the entire dataset. In particular, the positions of the images can be taken from t-SNE or UMAP coordinates. This grouped view of all the images further aids an exploratory understanding of the specific expression pattern of a given biomarker or collection of biomarkers across all images, helps to identify images expressing a particular phenotype or to select images for subsequent downstream analysis. Currently there is no freely available tool to generate such image t-SNEs. Mistic is open-source and can be downloaded at: https://github.com/MathOnco/Mistic.