OMGMed: Advanced System for Ocular Myasthenia Gravis Diagnosis via Eye Image Segmentation.

This paper presents an eye image segmentation-based computer-aided system for automatic diagnosis of ocular myasthenia gravis (OMG), called OMGMed. It provides great potential to effectively liberate the diagnostic efficiency of expert doctors (the scarce resources) and reduces the cost of healthcare treatment for diagnosed patients, making it possible to disseminate high-quality myasthenia gravis healthcare to under-developed areas. The system is composed of data pre-processing, indicator calculation, and automatic OMG scoring. Building upon this framework, an empirical study on the eye segmentation algorithm is conducted. It further optimizes the algorithm from the perspectives of "network structure" and "loss function", and experimentally verifies the effectiveness of the hybrid loss function. The results show that the combination of "nnUNet" network structure and "Cross-Entropy + Iou + Boundary" hybrid loss function can achieve the best segmentation performance, and its MIOU on the public and private myasthenia gravis datasets reaches 82.1% and 83.7%, respectively. The research has been used in expert centers. The pilot study demonstrates that our research on eye image segmentation for OMG diagnosis is very helpful in improving the healthcare quality of expert doctors. We believe that this work can serve as an important reference for the development of a similar auxiliary diagnosis system and contribute to the healthy development of proactive healthcare services.

A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis.

Disease diagnosis represents a critical and arduous endeavor within the medical field. Artificial intelligence (AI) techniques, spanning from machine learning and deep learning to large model paradigms, stand poised to significantly augment physicians in rendering more evidence-based decisions, thus presenting a pioneering solution for clinical practice. Traditionally, the amalgamation of diverse medical data modalities (e.g., image, text, speech, genetic data, physiological signals) is imperative to facilitate a comprehensive disease analysis, a topic of burgeoning interest among both researchers and clinicians in recent times. Hence, there exists a pressing need to synthesize the latest strides in multi-modal data and AI technologies in the realm of medical diagnosis. In this paper, we narrow our focus to five specific disorders (Alzheimer's disease, breast cancer, depression, heart disease, epilepsy), elucidating advanced endeavors in their diagnosis and treatment through the lens of artificial intelligence. Our survey not only delineates detailed diagnostic methodologies across varying modalities but also underscores commonly utilized public datasets, the intricacies of feature engineering, prevalent classification models, and envisaged challenges for future endeavors. In essence, our research endeavors to contribute to the advancement of diagnostic methodologies, furnishing invaluable insights for clinical decision making.

Detection and Classification of Bronchiectasis Based on Improved Mask-RCNN.

Bronchiectasis is defined as a permanent dilation of the bronchi that can cause pulmonary ventilation dysfunction. CT examination is an important means of diagnosing bronchiectasis. It can also be used in severity scoring. Current studies on bronchiectasis have focused on high-resolution CT (HRCT), ignoring the more common low-dose CT (LDCT). Methodologically, existing studies have not adopted an authoritative standard to classify the severity of bronchiectasis. In effect, the accuracy of detection and classification needs to be improved for practical application. In this paper, the ACER image enhancement method, RDU-Net lung lobe segmentation method and HDC Mask R-CNN model were proposed to detect and classify bronchiectasis. Moreover, a Python-based system was developed: after inputing an LDCT image of a patient's lung, it can automatically perform a series of processing, then call on the trained deep learning model for detection and classification, and automatically obtain the patient's bronchiectasis final score according to the Reiff and BRICS scoring criteria. In this paper, the mapping relationship between original lung CT image data and bronchiectasis scoring system was established. The accuracy of the method proposed in this paper was 91.4%; the IOU, sensitivity and specificity were 88.8%, 88.6% and 85.4%, respectively; and the recognition speed of one picture was about 1 s. Compared to a human doctor, the system can process large amounts of data simultaneously, quickly and efficiently, with the same judgment accuracy as a human doctor. Doctors only need to judge the uncertain cases, which significantly reduces the burden of doctors and provides a useful reference for doctors to diagnose the disease.

Performance of deep neural network-based artificial intelligence method in diabetic retinopathy screening: a systematic review and meta-analysis of diagnostic test accuracy.

OBJECTIVE: Automatic diabetic retinopathy screening system based on neural networks has been used to detect diabetic retinopathy (DR). However, there is no quantitative synthesis of performance of these methods. We aimed to estimate the sensitivity and specificity of neural networks in DR grading. METHODS: Medline, Embase, IEEE Xplore, and Cochrane Library were searched up to 23 July 2019. Studies that evaluated performance of neural networks in detection of moderate or worse DR or diabetic macular edema using retinal fundus images with ophthalmologists' judgment as reference standard were included. Two reviewers extracted data independently. Risk of bias of eligible studies was assessed using QUDAS-2 tool. RESULTS: Twenty-four studies involving 235 235 subjects were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed a pooled sensitivity of 91.9% (95% CI: 89.6% to 94.3%) and specificity of 91.3% (95% CI: 89.0% to 93.5%). Subgroup analyses and meta-regression did not provide any statistically significant findings for the heterogeneous diagnostic accuracy in studies with different image resolutions, sample sizes of training sets, architecture of convolutional neural networks, or diagnostic criteria. CONCLUSIONS: State-of-the-art neural networks could effectively detect clinical significant DR. To further improve diagnostic accuracy of neural networks, researchers might need to develop new algorithms rather than simply enlarge sample sizes of training sets or optimize image quality.

An Investigation about Gene Modules Associated with hDPSC Differentiation for Adolescents.

Dental pulp stem cells (DPSCs) have the property of self-renewal and multidirectional differentiation so that they have the potential for future regenerative therapy of various diseases. The latest breakthrough in the biology of stem cells and the development of regenerative biology provides an effective strategy for regenerative therapy. However, in the medium promoting differentiation during long-term passage, DPSCs would lose their differentiation capability. Some efforts have been made to find genes influencing human DPSC (hDPSC) differentiation based on hDPSCs isolated from adults. However, hDPSC differentiation is a very complex process, which involves multiple genes and multielement interactions. The purpose of this study is to detect sets of correlated genes (i.e., gene modules) that are associated to hDPSC differentiation at the crown-completed stage of the third molars, by using weighted gene coexpression network analysis (WGCNA). Based on the gene expression dataset GSE10444 from Gene Expression Omnibus (GEO), we identified two significant gene modules: yellow module (742 genes) and salmon module (9 genes). The WEB-based Gene SeT AnaLysis Toolkit showed that the 742 genes in the yellow module were enriched in 59 KEGG pathways (including Wnt signaling pathway), while the 9 genes in the salmon module were enriched in one KEGG pathway (neurotrophin signaling pathway). There were 660 (7) genes upregulated at P10 and 82 (2) genes downregulated at P10 in the yellow (salmon) module. Our results provide new insights into the differentiation capability of hDPSCs.

The effect of interaction between EtOH dosage and exposure time on gene expression in DPSC.

Alcohol (EtOH) dosage and exposure time can affect gene expression. However, whether there exists synergistic effect is unknown. Here, we analyzed the hDPSC gene microarray dataset GSE57255 downloaded from Gene Expression Omnibus and found that the interaction between EtOH dosage and exposure time on gene expression are statistically significant for two probes: 201917_s_at near gene SLC25A36 and 217649_at near gene ZFAND5. GeneMania showed that SLC25A36 and ZFAND5 were related to 20 genes, three of which had alcohol-related functions. WebGestalt revealed that the 22 genes were enriched in 10 KEGG pathways, four of which are related to alcoholic diseases. We explored the possible nonlinear interaction effect and got 172 gene probes with significant p-values. However, no significantly enriched pathways based on the 172 probes were detected. Our analyses indicated a possible molecular mechanism that could help explain why alcohol consumption has both deleterious and beneficial effects on human health.

Development of a computer-aided tool for the pattern recognition of facial features in diagnosing Turner syndrome: comparison of diagnostic accuracy with clinical workers.

Technologies applied for the recognition of facial features in diagnosing certain disorders seem to be promising in reducing the medical burden and improve the efficiency. This pilot study aimed to develop a computer-assisted tool for the pattern recognition of facial features for diagnosing Turner syndrome (TS). Photographs of 54 patients with TS and 158 female controls were collected from July 2016 to May 2017. Finally, photographs of 32 patients with TS and 96 age-matched controls were included in the study that were further divided equally into training and testing groups. The process of automatic classification consisted of image preprocessing, facial feature extraction, feature reduction and fusion, automatic classification, and result presentation. A total of 27 physicians and 21 medical students completed a web-based test including the same photographs used in computer testing. After training, the automatic facial classification system for diagnosing TS achieved a 68.8% sensitivity and 87.5% specificity (and a 67.6% average sensitivity and 87.9% average specificity after resampling), which was significantly higher than the average sensitivity (57.4%, P < 0.001) and specificity (75.4%, P < 0.001) of 48 participants, respectively. The accuracy of this system was satisfactory and better than the diagnosis by clinicians. However, the system necessitates further improvement for achieving a high diagnostic accuracy in clinical practice.

Application of Weighted Gene Co-expression Network Analysis for Data from Paired Design.

Investigating how genes jointly affect complex human diseases is important, yet challenging. The network approach (e.g., weighted gene co-expression network analysis (WGCNA)) is a powerful tool. However, genomic data usually contain substantial batch effects, which could mask true genomic signals. Paired design is a powerful tool that can reduce batch effects. However, it is currently unclear how to appropriately apply WGCNA to genomic data from paired design. In this paper, we modified the current WGCNA pipeline to analyse high-throughput genomic data from paired design. We illustrated the modified WGCNA pipeline by analysing the miRNA dataset provided by Shiah et al. (2014), which contains forty oral squamous cell carcinoma (OSCC) specimens and their matched non-tumourous epithelial counterparts. OSCC is the sixth most common cancer worldwide. The modified WGCNA pipeline identified two sets of novel miRNAs associated with OSCC, in addition to the existing miRNAs reported by Shiah et al. (2014). Thus, this work will be of great interest to readers of various scientific disciplines, in particular, genetic and genomic scientists as well as medical scientists working on cancer.

Coordinated Digital-Assisted Program Improved Door-to-Balloon Time for Acute Chest Pain Patients.

Emergency care for patients with chest pain can be a challenge in remote areas. Digital communication technology has the potential to improve outcomes by allowing early diagnosis and faster treatment. The aim of the present study was to investigate whether implementation of a coordinated digital-assisted program (CDAP) for Chinese hospitals can reduce the door-to-balloon (D2B) time for percutaneous coronary intervention (PCI) in acute chest pain patients in China. From March to December 2011, 609 patients (CDAP group) requiring an emergency response for acute chest pain were evaluated using this CDAP. The results were compared in terms of time interval reduction (including D2B) and economic indices with those of 528 patients (non-CDAP group) previously treated by conventional protocols after admission. We screened 154 and 127 eligible patients under PCI in the CDAP and non-CDAP groups, respectively. PCI patients achieved a D2B time < 90 minutes using CDAP (82.5 versus 26.0%, P < 0.001). CDAP reduced D2B time under PCI and reduced hospitalization lengths and costs (all P < 0.001).

Exploiting ensemble learning for automatic cataract detection and grading.

Cataract is defined as a lenticular opacity presenting usually with poor visual acuity. It is one of the most common causes of visual impairment worldwide. Early diagnosis demands the expertise of trained healthcare professionals, which may present a barrier to early intervention due to underlying costs. To date, studies reported in the literature utilize a single learning model for retinal image classification in grading cataract severity. We present an ensemble learning based approach as a means to improving diagnostic accuracy. Three independent feature sets, i.e., wavelet-, sketch-, and texture-based features, are extracted from each fundus image. For each feature set, two base learning models, i.e., Support Vector Machine and Back Propagation Neural Network, are built. Then, the ensemble methods, majority voting and stacking, are investigated to combine the multiple base learning models for final fundus image classification. Empirical experiments are conducted for cataract detection (two-class task, i.e., cataract or non-cataractous) and cataract grading (four-class task, i.e., non-cataractous, mild, moderate or severe) tasks. The best performance of the ensemble classifier is 93.2% and 84.5% in terms of the correct classification rates for cataract detection and grading tasks, respectively. The results demonstrate that the ensemble classifier outperforms the single learning model significantly, which also illustrates the effectiveness of the proposed approach.