Topochemical Polymerization at Diacetylene Metal-Organic Framework Thin Films for Tuning Nonlinear Optics.

Developing the topochemical polymerization of metal-organic frameworks (MOFs) is of pronounced significance for expanding their functionalities but is still a challenge on third-order nonlinear optics (NLO). Here, we report diacetylene MOF (CAS-1-3) films prepared using a stepwise deposition method and film structural transformation approach, featuring dynamic structural diversity. The MOF structures were determined by the three-dimensional electron diffraction (3D ED) method from nanocrystals collected from the films, which provides a reliable strategy for determining the precise structure of unknown MOF films. We demonstrate the well-aligned diacetylene groups in the MOFs can promote topological polymerization to produce a highly conjugated system under thermal stimulation. As a result, the three MOF films have distinct NLO properties: the CAS-1 film exhibits saturable absorption (SA) while CAS-2 and CAS-3 films exhibit reverse saturable absorption (RSA). Interestingly, due to the topochemical polymerization of the MOF films, a transition from SA to RSA response was observed with increasing temperatures, and the optical limiting effect was significantly enhanced (∼46 times). This study provides a new strategy for preparing NLO materials and thermally regulation of nonlinear optics.

Chiral Liquid Crystalline Metal-Organic Framework Thin Films for Highly Circularly Polarized Luminescence.

Combining metal-organic frameworks (MOFs) with liquid crystals to construct liquid crystalline MOFs (LCMOF) offers the advantage of endowing and enhancing their functionality, yet it remains a challenging task. Herein, we report chiral liquid crystalline MOF (CLCMOF) thin films by cross-linking the chiral liquid crystals (CLC) with MOF thin films to realize highly circular polarization luminescence (CPL) performance with photo and thermal switching. By layer by layer cross-linking stilbene-containing CLC with stilbene-based MOF (CLC/MOF) thin film, the CLCMOF thin films were successfully obtained after UV irradiation due to the abundant [2 + 2] photocycloaddition. The resulted CLCMOF thin films have strong chirality, obvious photochromic fluorescent, and strong CPL performance (the asymmetry factor reaches to 0.4). Furthermore, due to the photochromic fluorescent MOF and thermotropic CLC, the CPL can be reversed and red-shifted after heating and UV irradiation treatment, showing photo- and thermal CPL switching. Such MOF-based CPL thin films with photo/thermal CPL switching were prepared to patterns and codes for the demonstration of potential application in advanced information anticounterfeit and encryption. This study not only opens a strategy for developing chiral thin films combining MOFs and liquid crystals but also offers a new route to achieve CPL switching in optical applications.

Demonstration Study of Reflector-Based Volumetric Speed-of-Sound Imaging With Linear Ultrasound Arrays.

Conventional B-mode ultrasound imaging has difficulty in delineating homogeneous soft tissues with similar acoustic impedances, as the reflectivity depends on the acoustic impedance at the interface. As a quantitative imaging biomarker sensitive to alteration of biomechanical properties, speed-of-sound (SoS) holds promising potential for tissue and disease differentiation such as delineation of different breast tissue types with similar acoustic impedance. Compared to two-dimensional (2D) SoS images, three-dimensional (3D) volumetric SoS images achieved through a full-angle ultrasound scan can reveal more intricate morphological structures of tissues; however, they generally require a ring transducer. In this study, we introduce a 3D SoS reconstruction system that utilizes hand-held linear arrays instead. This system employs a passive reflector positioned opposite the linear arrays, serving as an echogenic reference for time-of-flight (ToF) measurements, and a high-definition camera to track the location corresponding to each group of transmit-receive data. To merge these two streams of ToF measurements and location tracking, a voxel-based reconstruction algorithm is implemented. Experimental results with gelatin phantom and ex vivo tissue have demonstrated the stability of our proposed method. Moreover, the results underscore the potential of this system as a complementary diagnostic modality, particularly in the context of diseases such as breast cancer.

Volumetric B-mode ultrasound and Doppler Imaging: Automatic Tracking With One Single Camera.

Vascular diseases may occur in the upper extremities, and the lesions can span the entire length of the blood vessel. One of the most popular methods to identify vascular disorders is ultrasound Doppler imaging. However, traditional two-dimensional (2D) ultrasound Doppler imaging cannot capture the entire length of a long vessel in one image. Medical professionals often have to painstakingly reconstruct three-dimensional (3D) data using 2D ultrasound images to locate the lesions, especially for large blood vessels. 3D ultrasound Doppler imaging can display the morphological structure of blood vessels and the distribution of lesions more directly, providing a more comprehensive view compared to 2D imaging. In this work, we propose a wide-range 3D volumetric ultrasound Doppler imaging system with dual modality, in which a high-definition camera is adopted to automatically track the movement of the ultrasound transducer, simultaneously capturing a corresponding sequence of 2D ultrasound Doppler images. We conducted experiments on human arms using our proposed system and separately with X-ray computerized tomography (X-CT). The comparison results prove the potential value of our proposed system in the diagnosis of arm vascular diseases.

Association between specific ultrasound features of joints and impaired kidney function among gout patients.

OBJECTIVE: To investigate the relationship between the specific ultrasonic manifestations of lower limb joints and impaired kidney function in gouty arthritis. METHODS: In this cross-sectional study, 408 patients with gouty arthritis were divided into two groups based on the status of renal function: normal group (n = 240) and renal impairment (n = 168) group. All patients underwent ultrasound examination of the bilateral knee, ankle, and first metatarsophalangeal joints to detect ultrasound features of double-contour sign (DC) and tophus. Multiple logistic regression analysis was conducted to assess the association between kidney dysfunction and ultrasound features. A number of potential clinical confounders were adjusted in the model. RESULTS: Univariable conditional logistic regression produces several significant risk factors of impaired kidney function which were the highest and current lever of serum urate acid, course of disease, frequency of attack, hyperlipidemia, hypertension, diabetes, coronary heart disease, presence of multiple tophus, and DC (P < 0.05). After correcting the course of disease and other risk factors, tophus was still an independent risk factor of impaired kidney function and the multivariable adjusted odds ratios (95% CI) was 1.789 (1.005-3.185, P = 0.05), however, the association was not significant in DC (OR = 1.098, 95% CI: 0.668-1.803, P = 0.71). CONCLUSION: The ultrasound feature of tophus was associated with kidney dysfunction in patients with gout, independent of clinical risk factors, which may be helpful in guiding clinical practice.

Age-related severity and distribution of haemophilic arthropathy of the knee, ankle and elbow among Chinese patients with haemophilia.

INTRODUCTION AND AIMS: Age-related severity and distribution of haemophilic arthropathy (HA) among Chinese patients with haemophilia using the Haemophilia Early Detection with Ultrasound (HEAD-US) system have not been extensively studied. METHODS: In our study, 89 patients with moderate and severe haemophilia were recruited. A total of 534 joints (knees, ankles and elbows on both sides included) were evaluated using musculoskeletal ultrasound (MSKUS) and scored using the HEAD-US system. RESULTS: Prevalence and average number of HA were 39.1% and 0.7, 90.6% and 3.2, 94.1% and 4.5, and 100% and 4.3 for ages ≤10, 11-20, 21-30 and 31-40 years, respectively. Prevalence and mean number of knee, ankle and elbow arthropathies also increased with age, although joint damages progressed in unparallel patterns. A significant difference in synovium subscores was observed between patients aged <10 and >10 years. An increasing tendency was observed in cartilage and subchondral bone subscores along with age before 30 years. No significant difference in mean joint scores was found between patients receiving on-demand therapy and those receiving on-demand to low-dose prophylactic therapy. CONCLUSIONS: Haemophilic arthropathy developed in early childhood and progressed mainly before 30 years of age among Chinese patients with haemophilia, although in different ways among the knee, ankle and elbow.

Ultrasonographic Features of Lower-Limb Joints in Gout: Which Joints and Clinical Characteristics Would Provide More Information for Diagnosis?

OBJECTIVE: This observational cross-sectional study evaluated the distribution of ultrasound (US) features of lower-limb joints and the risk factors of tophus in gout patients. METHODS: We examined 588 joints including the bilateral knee, ankle, and first metatarsophalangeal (MTP) joints in 98 gout patients by US between March to August in 2017. The distribution of double-contour (DC), tophus, aggregates, synovitis, effusion and erosion in different joint, course, and age groups were investigated by Cochran Q and χ test. The risk factors of tophus were analyzed using logistic regression method. RESULTS: Double-contour was most commonly observed in the knee (p = 0.005). Tophus, aggregates, synovitis, and erosion were mostly detected in the first MTP (p < 0.001, p = 0.01, p = 0.001, p < 0.001, respectively). The prevalence rates of DC, tophus, and erosion in patients with a longer course were significantly higher (p = 0.029, p = 0.002, p < 0.001, respectively). Older patients had more detectable tophus and erosion than younger patients (p = 0.028, p = 0.021). Patients of older age (odds ratio [OR], 3.83; 95% confidence interval [CI], 1.27-11.48), with frequent attacks (OR, 3.80; 95% CI, 1.10-13.15), and with longer course (OR, 6.52; 95% CI, 1.37-30.96) had higher risks of tophus. CONCLUSIONS: Most signs were detected by US in the first MTP, except that DC was most commonly observed in the knees. Patients of older age with frequent attacks and longer course may experience higher risks for tophus. Comprehensive assessment of the lower limbs, particularly the knee and first MTP, can significantly help diagnosis.

Diffuse parenchymal pulmonary amyloidosis associated with multiple myeloma: a case report and systematic review of the literature.

BACKGROUND: Pulmonary is an uncommon site of extramedullary involvement in multiple myeloma (MM). Diffuse parenchymal amyloidosis as pulmonary manifestation of MM is even rarer. We report a rare case of diffuse parenchymal pulmonary amyloidosis associated with MM diagnosed by video-assisted thoracoscopic lung biopsy (VATLB). CASE PRESENTATION: A 58-year-old woman complained of cough and shortness of breath. HRCT disclosed diffuse ground-glass opacifications with interlobular septal thickening in bilateral lungs. A lung-biopsy sample obtained by VATLB revealed Congo Red-positive amorphous eosinophilic deposits in the alveolar septa. Surgical biopsy of abdominal wall skin and subcutaneous fat was also performed, which showed the apple-green birefringence with polarized light on Congo red stain was demonstrated in dermis. The serum immunoelectrophoresis showed monoclonal lambda light chains. A bone marrow biopsy specimen comprised 11.5% plasma cells. She was therefore diagnosed with diffuse parenchymal pulmonary amyloidosis accompanied by MM. The patient was referred to the hematology department for further chemotherapy. CONCLUSIONS: It is important to recognize diffuse parenchymal pulmonary amyloidosis to avoid misdiagnosis.

[Contrast-enhanced ultrasonography in the diagnosis of venous erectile dysfunction].

OBJECTIVE: To investigate the effect and safety of contrast-enhanced ultrasonography (CEUS) in the diagnosis of venous erectile dysfunction (VED). METHODS: From June 2015 to March 2016, 43 ED patients underwent corpus cavernography, of whom 23 were diagnosed with and the other 20 without corpus cavernosal venous leakage (CCVL). All the patients received intracorporal injection of a vasoactive drug and CEUS. RESULTS: Of the 23 patients with CCVL, 21 were confirmed by CEUS, including 12 cases of double venous leakage, 2 cases of single venous leakage, 5 cases of crural venous leakage, and 2 cases of the mixed type, while the other 2 showed no CCVL on CEUS. Of the 20 patients with CCVL, 2 presented CCVL on CEUS. CONCLUSIONS: CEUS has the advantages of accuracy, safety, and less invasiveness in the diagnosis of VED.

Transparent sparse graph pathway network for analyzing the internal relationship of lung cancer.

While it is important to find the key biomarkers and improve the accuracy of disease models, it is equally important to understand their interaction relationships. In this study, a transparent sparse graph pathway network (TSGPN) is proposed based on the structure of graph neural networks. This network simulates the action of genes in vivo, adds to prior knowledge, and improves the model's accuracy. First, the graph connection was constructed according to protein-protein interaction networks and competing endogenous RNA (ceRNA) networks, from which some noise or unimportant connections were spontaneously removed based on the graph attention mechanism and hard concrete estimation. This realized the reconstruction of the ceRNA network representing the influence of other genes in the disease on mRNA. Next, the gene-based interpretation was transformed into a pathway-based interpretation based on the pathway database, and the hidden layer was added to realize the high-dimensional analysis of the pathway. Finally, the experimental results showed that the proposed TSGPN method is superior to other comparison methods in F1 score and AUC, and more importantly, it can effectively display the role of genes. Through data analysis applied to lung cancer prognosis, ten pathways related to LUSC prognosis were found, as well as the key biomarkers closely related to these pathways, such as HOXA10, hsa-mir-182, and LINC02544. The relationship between them was also reconstructed to better explain the internal mechanism of the disease.

A Novel High-Dimensional Kernel Joint Non-Negative Matrix Factorization With Multimodal Information for Lung Cancer Study.

Judging and identifying biological activities and biomarkers inside tissues from imaging features of diseases is challenging, so correlating pathological image data with genes inside organisms is of great significance for clinical diagnosis. This paper proposes a high-dimensional kernel non-negative matrix factorization (NMF) method based on muti-modal information fusion. This algorithm can project RNA gene expression data and pathological images (WSI) into a common feature space, where the heterogeneous variables with the largest coefficient in the same projection direction form a co-module. In addition, the miRNA-mRNA and miRNA-lncRNA interaction networks in the ceRNA network are added to the algorithm as a priori information to explore the relationship between the images and the internal activities of the gene. Furthermore, the radial basis kernel function is used to calculate the feature proportion between different kinds of genes mapped in the high-dimensional feature space and projected into the common feature space to explore the gene interaction in the high-dimensional situation. The original feature matrix is regularized to improve biological correlation, and the feature factors are sparse by orthogonal constraints to reduce redundancy. Experimental results show that the proposed NMF method is better than the traditional NMF method in stability, decomposition accuracy, and robustness. Through data analysis applied to lung cancer, genes related to tissue morphology are found, such as COL7A1, CENPF and BIRC5. In addition, gene pairs with a correlation degree exceeding 0.8 are found, and potential biomarkers of significant correlation with survival are obtained such as CAPN8. It has potential application value for the clinical diagnosis of lung cancer.

Photo-Curable 3D Printing of Circularly Polarized Afterglow Metal-Organic Framework Monoliths.

Developing coordination complexes (such as metal-organic frameworks, MOFs) with circularly polarized luminescence (CPL) is currently attracting tremendous attention and remains a significant challenge in achieving MOF with circularly polarized afterglow. Herein, MOFs-based circularly polarized afterglow is first reported by combining the chiral induction approach and tuning the afterglow times by using the auxiliary ligands regulation strategy. The obtained chiral R/S-ZnIDC, R/S-ZnIDC(bpy), and R/S-ZnIDC(bpe)(IDC = 1H-Imidazole-4,5-dicarboxylate, bpy = 4,4'-Bipyridine, bpe = trans-1,2-Bis(4-pyridyl) ethylene) containing a similar structure unit display different afterglow times with 3, 1, and <0.1 s respectively which attribute to that the longer auxiliary ligand hinders the energy transfer through the hydrogen bonding. The obtained chiral complexes reveal a strong chiral signal, obvious photoluminescence afterglow feature, and strong CPL performance (glum up to 3.7 × 10-2). Furthermore, the photo-curing 3D printing method is first proposed to prepare various chiral MOFs based monoliths from 2D patterns to 3D scaffolds for anti-counterfeiting and information encryption applications. This work not only develops chiral complexes monoliths by photo-curing 3D printing technique but opens a new strategy to achieve tunable CPL afterglow in optical applications.

Integrative analysis of single-cell and bulk transcriptome data reveal the significant role of macrophages in lupus nephritis.

OBJECTIVE: We attempted to identify abnormal immune cell components and signaling pathways in lupus nephritis (LN) and to identify potential therapeutic targets. METHODS: Differentially expressed genes (DEGs) between LN and normal kidney tissues were identified from bulk transcriptome data, and functional annotation was performed. The phenotypic changes in macrophages and aberrant intercellular signaling communications within immune cells were imputed from LN scRNA-seq data using trajectory analysis and verified using immunofluorescence staining. Finally, lentivirus-mediated overexpression of LGALS9, the gene encoding Galectin 9, in THP-1 cells was used to study the functional effect of this gene on monocytic cells. RESULTS: From bulk transcriptome data, a significant activation of interferon (IFN) signaling was observed, and its intensity showed a significantly positive correlation with the abundance of infiltrating macrophages in LN. Analysis of scRNA-seq data revealed 17 immune cell clusters, with macrophages showing the highest enrichment of intercellular signal communication in LN. Trajectory analysis revealed macrophages in LN undergo a phenotypic change from inflammatory patrolling macrophages to phagocytic and then to antigen-presenting macrophages, and secrete various pro-inflammatory factors and complement components. LGALS9 was found significantly upregulated in macrophages in LN, which was confirmed by the immunofluorescence assay. Gene functional study showed that LGALS9 overexpression in THP-1 cells significantly elicited pro-inflammatory activation, releasing multiple immune cell chemoattractants. CONCLUSION: Our results present an important pathophysiological role for macrophages in LN, and our preliminary results demonstrate significant pro-inflammatory effects of LGALS9 gene in LN macrophages.

Th17/Treg imbalance in peripheral blood from patients with intracranial aneurysm.

BACKGROUND: Spontaneous subarachnoid hemorrhage (SAH) is highly associated with ruptured intracranial aneurysm (IA), which dramatically increases neurological disabilities or mortality in patients. The balance between T helper cells (Th17) and regulatory T cells (Treg) plays a crucial role in regulating immune-inflammatory response. In the current study, we aim to obtain a better understanding of the role of Th17 and Treg cells in patients with IA. METHODS: 138 patients total participated in this study, including ruptured aneurysms group (Ruptured IA, RIA, N.=70 cases) and unruptured aneurysms group (Unruptured IA, URIA, N.=68 cases). Additionally, 76 cases of healthy subjects were selected as control group. The frequencies of Th17 and Treg cells were determined using flow cytometry. The serum levels of cytokines including IL-17, IL-23, IL-10, and TGF-ß1 were determined using ELISA. mRNA was isolated from the whole blood. FOXP3 and RCRc mRNA expressions were detected using RT-qPCR. RESULTS: The percentage of Th17 cells in peripheral blood from RIA patients was higher than URIA patients (P<0.01), whereas the percentage of Treg cells in peripheral blood from RIA was significantly lower when compared with URIA patients (P<0.001). The serum levels of IL-17 (P<0.01) and IL-23 (P<0.05) were markedly increased while the levels of IL-10 (P<0.01) and TGF-ß1 (P<0.05) were decreased in RIA patients when compared with URIA patients. Lastly, the mRNA level of RCRc was significantly increased in RIA vs. URIA patients (P<0.001). By contrast, FOXP3 mRNA level was significantly decreased in RIA vs. URIA patients (P<0.001). CONCLUSIONS: In the current study, we demonstrated the imbalance of Th17/Treg in patients with IA, and the frequencies of Th17 cells were positively correlated with the severity of IA-induced SAH. These results provided data to support that targeting Th17/Treg could act as an effective approach for the management of IA.

Characterization of anisotropy of elastic modulus with three-dimensional freehand scan shear wave elasticity imaging.

Purpose: The purpose of this study is to develop a freehand scan three-dimensional (3D) shear wave elasticity imaging (SWEI) method for characterizing the anisotropy of elastic properties in biological tissues. The motivation behind this work lies in addressing the limitations of traditional two-dimensional (2D) SWEI, which only measures shear wave speeds in a single direction, as well as fulfilling the clinical demand for improved medical imaging. Approach: Our imaging system utilizes a high-definition optical camera to continuously track the ultrasonic transducer, collecting spatial position-angle data of the transducer and corresponding two-dimensional SWEI data. By reconstructing three-dimensional SWEI images using these data, we achieved freehand SWEI. Results: We validated the accuracy of 2D SWEI on a standard elastic phantom, and then performed 3D SWEI on the pork tenderloin and the triceps brachii of two volunteers. We obtained shear wave speed of 1.82 to 3.12 m/s in the pork tenderloin, shear wave speed of 1.16 to 2.36 m/s in the triceps brachii of non-exercising volunteers, and shear wave speed of 0.55 to 1.63 m/s in the triceps brachii of exercising volunteers, and the maximum shear wave speed directions were generally aligned with the orientation of muscle fibers. Conclusions: We proposed a method that can overcome the limitations of 2D-SWEI regarding imaging angle while also extending the imaging angle of 3D-SWEI, which could have significant implications for improving the accuracy and safety of medical diagnoses.

Effects of Intracranial Interventional Embolization and Intracranial Clipping on the Cognitive and Neurologic Function of Patients with Intracranial Aneurysms.

BACKGROUND: Intracranial interventional embolization and intracranial clipping have been two typical therapies for the emergent rescue of intracranial aneurysm. However, there are still controversies over the impact of these two surgical treatments of aneurysms on cognitive and neurological functions of patients. METHODS: A total of 144 patients with intracranial aneurysms were enrolled as the test subjects, who were randomly and evenly divided into the Intracranial Clipping group and the Interventional Embolization group. Cognitive and neurologic functions were evaluated by Glasgow Outcome Scale, Montreal Cognitive Assessment (MoCA), Mini-Mental State Examination (MMSE) scales, National Institutes of Health Stroke Scale (NIHSS) and Activities of Daily Living (ADL) scale. Enzyme-linked immunosorbent assay was used to analyze the serum levels of neuron-specific enolase (NSE) and S100ß. RESULTS: There were no significant differences in the preoperative MMSE, MoCA, NIHSS or ADL scale between two groups (p > 0.05). However, after operation, the MMSE and MoCA scores of the interventional embolization group were significantly higher, whereas the NIHSS and ADL scales were significantly lower than those of the intracranial clipping group (p < 0.05). The levels of NSE and S100ß in the intracranial clipping group were significantly higher than in the interventional embolization group. CONCLUSION: Intracranial interventional embolization exerts better effects on the cognitive and neurologic functions than intracranial clipping.

MicroRNA-1269 is downregulated in glioblastoma and its maturation is regulated by long non-coding RNA SLC16A1 Antisense RNA 1.

MicroRNA-1269 (miR-1296) promotes esophageal cancer. However, its role in other cancers, such as glioblastoma (GBM) is unclear. We predicted that miR-1269 might interact with long non-coding RNA (lncRNA) SLC16A1 Antisense RNA 1 (SLC16A1-AS1), a critical player in GBM. We then studied the interaction between SLC16A1-AS1 and miR-1269 in GBM. In this study, paired GBM and non-tumor tissues were used to analyze the expression of SLC16A1-AS1 and premature and mature miR-1269. The interaction of SLC16A1-AS1 with premature miR-1269 was analyzed with RNA pull-down assay and dual-luciferase reporter assay. Cellular fractionation assay was applied to determine the subcellular location of SLC16A1-AS1. Overexpression assays were applied to determine the role of SLC16A1-AS1 in miR-1269 maturation. BrdU, Transwell and cell apoptosis assays were performed to analyze the role of SLC16A1-AS1 and miR-1269 in GBM cell proliferation, migration, and invasion. Interestingly, we observed the upregulation of premature miR-1269 and downregulation of mature miR-1269 in GBM. SLC16A1-AS1 was also overexpressed in GBM. The direct interaction of SLC16A1-AS1 with premature miR-1269 was observed. SLC16A1-AS1 suppressed miR-1269 maturation and promoted cell proliferation, migration, and invasion, and inhibited cell apoptosis, while miR-1269 displayed the opposite trend. SLC16A1-AS1 partly reversed the effects of miR-1269 on GBM cell proliferation, movement and apoptosis. Moreover, SLC16A1-AS1 overexpression increased the level of ki-67, CDK4 and Bcl-2 in LN-229 and LN-18 cells. However, miR-1269 could partly reverse the effect of SLC16A-AS1 on protein levels. Overall, miR-1269 is downregulated in GBM and its maturation is regulated by SLC16A1-AS1.

Diagnosis of Metacarpophalangeal Synovitis with Musculoskeletal Ultrasound Images.

Rheumatoid arthritis (RA) is a chronic autoimmune disease that can result in considerable disability and pain. The metacarpophalangeal (MCP) joint is the most common diseased joint in RA. In clinical practice, MCP synovitis is commonly diagnosed on the basis of musculoskeletal ultrasound (MSUS) images. However, because of the vague criteria, the consistency in grading MCP synovitis based on MSUS images fluctuates between ultrasound imaging practitioners. Therefore, a new method for diagnosis of MCP synovitis is needed. Deep learning has developed rapidly in the medical area, which often requires a large-scale data set. However, the total number of MCP-MSUS images fell far short of the demand, and the distribution of different medical grades of images was unbalanced. With use of the traditional image augmentation methods, the diversity of the data remains insufficient. In this study, a high-resolution generative adversarial network (HRGAN) method that generates enough images for network training and enriches the diversity of the training data set is described. In comparison experiments, our proposed diagnostic system based on MSUS images provided more consistent results than those provided by clinical physicians. As the proposed method is image relevant, this study might provide a reference for other medical image classification research with insufficient data sets.