Lung cancer is the most common tumor and one of the malignant tumors with the lowest livability after diagnosis, as is known so far. Large-scale image database is the foundation of developing computer-aided diagnosis methods, education and training in lung cancer diagnosis to improve medical diagnostic efficiency and to reduce the doctors' burden. In this study, aiming at improving the low data storage efficiency and solving the lacking of tool for data visualization and data retrieval existing in the use of traditional Lung Image Database Consortium (LIDC) from the lung cancer database, we developed a new lung cancer image database platform including an improved data model, a data integration tool, an image and annotation visualization tool and a data retrieving component. Firstly, the data format in LIDC was analyzed and an improved information model was provided to manage and manipulate large amount data stored in it. Next, some tools such as data integration component, DICOM, image and annotation visualization tool, and data query were designed and implemented. The study demonstrated that the lung cancer image database platform had the capacity of data collection, visualization, and query, and could promote diagnose lung cancer research.
Algorithms ; Databases, Factual ; Diagnosis, Computer-Assisted ; Humans ; Information Storage and Retrieval ; methods ; Lung Neoplasms ; diagnostic imaging ; pathology ; Radiographic Image Interpretation, Computer-Assisted ; methods ; Tomography, X-Ray Computed ; methods ; standards

Objective To explore the diagnostic value of qualitative and quantitative analysis for wrist and hand changes of rheumatoid arthritis (RA) patients based on 3.0T MR images.Methods A total of 39 RA patients were enrolled and divided into 2 groups according to the course of the diseases,including 20 cases defined as early stage group (≤24 months) and 19 cases defined as middle-late stage group (＞24 months).MRI features such as joint synovitis,bone marrow edema,bone erosion,the tenosynovitis in wrists and hands were observed emphatically.Volumes of synovitis and bone marrow edema for all patients were quantified with the software developed by Kunming University of Science and Technology.Results Among the 78 sides of hands and wrists in 39 patients,the incidence rate of synovitis,bone marrow edema,bone erosion,tenosynovitis was 94.87％ (37/39),64.10％ (25/39),61.54％ (24/39) and 76.92％ (30/39),respectively.The highest incidence rate of synovitis,bone marrow edema and bone erosion was respectively found in the wrist (72/78,92.31 ％),carpus (48/78,61.54 ％) andtriangular bone (50/78,64.1 ％).There was no statistical significance difference of the occurrence of peritendinitis between the flexor tendons (74.36％ [58/78]) and extensor tendons (61.54％ [48/78];x2 =2.94,P=0.09).No statistical difference of the incidence rates of synovitis,bone marrow edema,bone erosion and tenosynovitis was found between the early stage group and middle-late stage group (all P＞0.05).There was no significant difference of synovitis and bone marrow edema volumes between the early stage group and the middle-late stage group (both P＞0.05) with MRI quantitative analysis.Conclusion 3.0T MRI can clearly demonstrate the pathological changes of the wrists and hands in RA patients.The quantitative analysis software can provide more accurate indicators for the assessment of disease severity.

Objective:To develop a deep learning model based on multimodal data for glaucoma diagnosis and severity assessment.Methods:A diagnostic test was conducted.A total of 145 normal eyes from 86 participants and 507 eyes with primary open-angle glaucoma from 314 participants were collected at the First Affiliated Hospital of Kunming Medical University from June to December in 2023.Fundus photographs and visual field data were obtained, and glaucoma eyes were divided into three groups based on the mean deviation value of the visual field, namely mild group (154 eyes), moderate group (113 eyes), and severe group (240 eyes).Three convolutional neural network (CNN) models, including DenseNet 121, ResNet 50 and VGG 19, were used to build an artificial intelligence (AI) model.The impact of single-modal and multimodal data on the classification results was evaluated, and the most appropriate CNN network architecture for multimodal data was identified.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of The First Affiliated Hospital of Kunming Medical University (No.2023L93).Written informed consent was obtained from each subject.Results:A total of 652 eyes had both fundus photographs and visual field test results.Images were randomly assigned to training and test datasets in a 4∶1 ratio by using computer random number method.AI models built with different CNN models showed high accuracy, with DenseNet 121 outperforming ResNet 50 and VGG 19 on various effectiveness measures.In the single-modal algorithm using fundus photographs, single-modal algorithm using visual field tests, and multimodal algorithm combining fundus photographs and visual field data, the area under the curve for early glaucoma detection was 0.87, 0.93 and 0.95, respectively.Conclusions:The use of multimodal data enables the development of a highly accurate tool for the glaucoma diagnosis and severity grading.

Objective:To analyze and verify the expression of ISL1 gene in myocardial infarction, and explore its mechanism of action in myocardial infarction.Methods:By analyzing the chip expression profile data in the GEO database, the expression characteristics of the ISL1 gene in myocardial infarction, as well as the highly co expressed related genes and enriched pathway functions of the ISL1 gene, were identified. Patients with myocardial infarction and their healthy controls were included, and the expression of genes such as ISL1 and GRIN2D was verified using real-time polymerase chain reaction (RT-PCR).Results:The expression level of ISL1 gene in myocardial infarction samples was higher than that in the control group samples. In the GSE59867 and GSE29111 datasets, there are a total of 152, 231, and 329 intersections of the top 2000, top 2500, and top 3000 related genes, respectively. The functional annotation of co-expressed genes revealed that intersection genes were closely related to organ development, matrix protein formation, epithelial cell differentiation, and the activity of related signaling pathways during embryonic development. Finally, in the construction of the ISL1 related ceRNA regulatory network, 12 genes were located in the ISL1 top 2000 related mating set, and together with miRNAs, they participated in the formation of 21 pairs of miRNA-mRNA. And through multiple queues, the key regulatory gene was identified as GRIN2D, which competitively bound to multiple miRNAs with ISL1 and its expression was highly negatively correlated with ISL1 in two independent datassets ( r=-0.52, -0.41). The RT-PCR results showed that the expression levels of miR-128-3p, miR 27a-3p, and miR-27b-3p in the acute myocardial infarction group were lower than those in the control group, while the expression levels of ISL1 and GRIN2D were higher than those in the control group (all P<0.01). Conclusions:ISL1 may play a protective role in myocardial infarction by participating in the formation of matrix proteins, differentiation of epithelial cells, and activity of related signaling pathways.

Cutaneous malignant melanoma is a common malignant tumor. Accurate segmentation of the lesion area is extremely important for early diagnosis of the disease. In order to achieve more effective and accurate segmentation of skin lesions, a parallel network architecture based on Transformer is proposed in this paper. This network is composed of two parallel branches: the former is the newly constructed multiple residual frequency channel attention network (MFC), and the latter is the visual transformer network (ViT). First, in the MFC network branch, the multiple residual module and the frequency channel attention module (FCA) module are fused to improve the robustness of the network and enhance the capability of extracting image detailed features. Second, in the ViT network branch, multiple head self-attention (MSA) in Transformer is used to preserve the global features of the image. Finally, the feature information extracted from the two branches are combined in parallel to realize image segmentation more effectively. To verify the proposed algorithm, we conducted experiments on the dermoscopy image dataset published by the International Skin Imaging Collaboration (ISIC) in 2018. The results show that the intersection-over-union (IoU) and Dice coefficients of the proposed algorithm achieve 90.15% and 94.82%, respectively, which are better than the latest skin melanoma segmentation networks. Therefore, the proposed network can better segment the lesion area and provide dermatologists with more accurate lesion data.
Humans ; Dermoscopy/methods* ; Neural Networks, Computer ; Melanoma/pathology* ; Skin Neoplasms/pathology* ; Image Processing, Computer-Assisted/methods*