Training of a deep learning based digital subtraction angiography method using synthetic data.

BACKGROUND: Digital subtraction angiography (DSA) is a fluoroscopy method primarily used for the diagnosis of cardiovascular diseases (CVDs). Deep learning-based DSA (DDSA) is developed to extract DSA-like images directly from fluoroscopic images, which helps in saving dose while improving image quality. It can also be applied where C-arm or patient motion is present and conventional DSA cannot be applied. However, due to the lack of clinical training data and unavoidable artifacts in DSA targets, current DDSA models still cannot satisfactorily display specific structures, nor can they predict noise-free images. PURPOSE: In this study, we propose a strategy for producing abundant synthetic DSA image pairs in which synthetic DSA targets are free of typical artifacts and noise commonly found in conventional DSA targets for DDSA model training. METHODS: More than 7,000 forward-projected computed tomography (CT) images and more than 25,000 synthetic vascular projection images were employed to create contrast-enhanced fluoroscopic images and corresponding DSA images, which were utilized as DSA image pairs for training of the DDSA networks. The CT projection images and vascular projection images were generated from eight whole-body CT scans and 1,584 3D vascular skeletons, respectively. All vessel skeletons were generated with stochastic Lindenmayer systems. We trained DDSA models on this synthetic dataset and compared them to the trainings on a clinical DSA dataset, which contains nearly 4,000 fluoroscopic x-ray images obtained from different models of C-arms. RESULTS: We evaluated DDSA models on clinical fluoroscopic data of different anatomies, including the leg, abdomen, and heart. The results on leg data showed for different methods that training on synthetic data performed similarly and sometimes outperformed training on clinical data. The results on abdomen and cardiac data demonstrated that models trained on synthetic data were able to extract clearer DSA-like images than conventional DSA and models trained on clinical data. The models trained on synthetic data consistently outperformed their clinical data counterparts, achieving higher scores in the quantitative evaluation of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) metrics for DDSA images, as well as accuracy, precision, and Dice scores for segmentation of the DDSA images. CONCLUSIONS: We proposed an approach to train DDSA networks with synthetic DSA image pairs and extract DSA-like images from contrast-enhanced x-ray images directly. This is a potential tool to aid in diagnosis.

A CT-Based Radiomics Model for Prediction of Prognosis in Patients with Novel Coronavirus Disease (COVID-19) Pneumonia: A Preliminary Study.

This study aimed to develop a computed tomography (CT)-based radiomics model to predict the outcome of COVID-19 pneumonia. In total of 44 patients with confirmed diagnosis of COVID-19 were retrospectively enrolled in this study. The radiomics model and subtracted radiomics model were developed to assess the prognosis of COVID-19 and compare differences between the aggravate and relief groups. Each radiomic signature consisted of 10 selected features and showed good performance in differentiating between the aggravate and relief groups. The sensitivity, specificity, and accuracy of the first model were 98.1%, 97.3%, and 97.6%, respectively (AUC = 0.99). The sensitivity, specificity, and accuracy of the second model were 100%, 97.3%, and 98.4%, respectively (AUC = 1.00). There was no significant difference between the models. The radiomics models revealed good performance for predicting the outcome of COVID-19 in the early stage. The CT-based radiomic signature can provide valuable information to identify potential severe COVID-19 patients and aid clinical decisions.

Qualitative (and Quantitative) Values of the Lung-RADS and Computed Tomography in Diagnosing Solitary Pulmonary Nodules.

Background: Lung-RADS classification and CT signs can both help in the differential diagnosis of SPNs. The purpose of this study was to investigate the diagnostic value of these two methods and the combination of the two methods for solitary pulmonary nodules (SPNs). Methods: A total of 296 cases of SPNs were retrospectively analyzed. All the SPNs were classified according to the Lung-RADS grading version 1.1. The scores of each lesion were calculated according to their CT signs. Imaging features, such as the size and margin of the lesions, pleural traction, spiculation, lobulation, bronchial cutoff, air bronchogram, vacuoles, tumor vasculature, and cavity signs, were analyzed. The imaging results were compared with the pathology examination findings. Receiver operating characteristic (ROC) curves were applied to compare the values of the different methods in differentially diagnosing benign and malignant SPNs. Results: The sensitivity, specificity, and accuracy of Lung-RADS grading for diagnosing SPNs were 34.0%, 94.4%, and 47.6%, respectively. The area under the ROC curve (AUC) was 0.600 (p < 0.001). The sensitivity, specificity, and accuracy of the CT sign scores were 56.3%, 70.0%, and 60.5%, respectively, and the AUC was 0.657 (p < 0.001). The sensitivity, specificity, and accuracy of the combination of the two methods for diagnosing SPNs were 93.2%, 61.1%, and 83.5%, and the AUC was 0.777 (p < 0.001). Conclusion: The combination of Lung-RADS classification and CT signs significantly improved the differential diagnosis of SPNs.

Blind Deblurring Based on Sigmoid Function.

Blind image deblurring, also known as blind image deconvolution, is a long-standing challenge in the field of image processing and low-level vision. To restore a clear version of a severely degraded image, this paper proposes a blind deblurring algorithm based on the sigmoid function, which constructs novel blind deblurring estimators for both the original image and the degradation process by exploring the excellent property of sigmoid function and considering image derivative constraints. Owing to these symmetric and non-linear estimators of low computation complexity, high-quality images can be obtained by the algorithm. The algorithm is also extended to image sequences. The sigmoid function enables the proposed algorithm to achieve state-of-the-art performance in various scenarios, including natural, text, face, and low-illumination images. Furthermore, the method can be extended naturally to non-uniform deblurring. Quantitative and qualitative experimental evaluations indicate that the algorithm can remove the blur effect and improve the image quality of actual and simulated images. Finally, the use of sigmoid function provides a new approach to algorithm performance optimization in the field of image restoration.

Study on the Optimization of Cu-Zn-Sn-O to Prepare Cu2ZnSnS4 Thin Film via a Nano Ink Coating Method.

To reduce the formation of the impurity phase, a buffer volume can be used to expands and smooths the surface of Cu2ZnSnS4(CZTS) thin film. In this study, a Cu-Zn-Sn-O(CZTO) precursor was synthesized through the process of coprecipitation-calcination-ball milling-spin coating. The influence of pH, temperature, and PVP on the constituent of hydroxides was investigated in the process of coprecipitation. Cu-Zn-Sn-O with appropriate compositions could be obtained by regulating the temperature and preservation time of the calcination stage. After ball milling to form a nano ink, and then spin coating, SEM images proved the generation of CZTO precursors, which effectively promoted the formation of Cu2ZnSnS4 thin films. Finally, the phase, microstructure, chemical composition, and optical properties of the Cu2ZnSnS4 thin films prepared by sulfurized annealing CZTO precursors were characterized by EDX, XRD, Raman, FESEM, Hall effect, and UV methods. The prepared CZTS thin film demonstrated a band gap of 1.30 eV, which was suitable for improving the performance of CZTS thin film solar cells.

Using Cu-Zn-Sn-O Precursor to Optimize CZTSSe Thin Films Fabricated by Se Doping With CZTS Thin Films.

The copper-zinc-tin oxide (CZTO) precursor was synthesized to avoid sudden volume expansion from CZTO precursor to Cu2ZnSnS4 (CZTS) thin films and smooth CZTSSe thin-film surfaces without pinholes. The CZTO precursor was prepared by coprecipitation and ball milling to form nanoink of CZTO. Based on the CZTO precursor, the CZTS thin film was fabricated and then selenized to make pinhole-free and flat Cu2ZnSn(S,Se)4(CZTSSe) thin films. The results show that the CZTO precursor greatly contributed to elevating the homologous surface characteristics and crystallinity of CZTSSe thin films by controlling selenium temperature, selenium time, and selenium source temperature. Finally, the conversion efficiency of the CZTSSe thin-film solar cell fabricated from the CZTO precursor was 4.11%, with an open-circuit voltage (Voc) of 623 mV, a short circuit current density (Jsc) of 16.02 mA cm-2, and a fill factor (FF) of 41.2%.

Radiomic signature: a non-invasive biomarker for discriminating invasive and non-invasive cases of lung adenocarcinoma.

PURPOSE: We aimed to assess the classification performance of a computed tomography (CT)-based radiomic signature for discriminating invasive and non-invasive lung adenocarcinoma. PATIENTS AND METHODS: A total of 192 patients (training cohort, n=116; validation cohort, n=76) with pathologically confirmed lung adenocarcinoma were retrospectively enrolled in the present study. Radiomic features were extracted from preoperative unenhanced chest CT images to build a radiomic signature. Predictive performance of the radiomic signature were evaluated using an intra-cross validation cohort. Diagnostic performance of the radiomic signature was assessed via receiver operating characteristic (ROC) analysis. RESULTS: The radiomic signature consisted of 14 selected features and demonstrated good discrimination performance between invasive and non-invasive adenocarcinoma. The area under the ROC curve (AUC) for the training cohort was 0.83 (sensitivity, 0.84 ; specificity, 0.78; accuracy, 0.82), while that for the validation cohort was 0.77 (sensitivity, 0.94; specificity, 0.52 ; accuracy, 0.82). CONCLUSION: The CT-based radiomic signature exhibited good classification performance for discriminating invasive and non-invasive lung adenocarcinoma, and may represent a valuable biomarker for determining therapeutic strategies in this patient population.

INTERNAL TRANSCRIBED SPACER (ITS), AN IDEAL DNA BARCODE FOR SPECIES DISCRIMINATION IN CRAWFURDIA WALL. (GENTIANACEAE).

BACKGROUND: DNA barcoding is a technique used to identify species based on species-specific differences in short regions of their DNA. It is widely used in species discrimination of medicinal plants and traditional medicines. MATERIALS AND METHODS: In the present study, four potential DNA barcodes, namely rbcL, matK, trnH-psbA and ITS (nuclear ribosomal internal transcribed spacer) were adopted for species discrimination in Crawfurdia Wall (Genetiaceae). Identification ability of these DNA barcodes and combinations were evaluated using three classic methods (Distance, Blast and Tree-Building). RESULTS: As a result, ITS, trnH-psbA and rbcL regions showed great universality for a success rate of 100%; whereas matK was disappointing for which only 65% samples gained useful DNA sequences. ITS region, which could clearly and effectively identify the five species in Crawfurdia, performed very well in this study. On the contrary, trnH-psbA and rbcL performed poorly in discrimination among these species. CONCLUSION: ITS marker was an ideal DNA barcode in Crawfurdia and it should be incorporated into one of the core barcodes for seed plants.

Market survey on traditional medicine of the third month fair in Dali Prefecture in Yunnan Province, South West China.

BACKGROUND: The Third Month Fair in Dali is a historical festival and fair. The market of traditional medicine (TM) is one of the main parts in the fair, which has important influence on local and peripheral people. MATERIALS AND METHODS: In this study, approaches of ethnobotany, pharmacognosy, and participatory rural appraisal were used in market survey. Twenty-six druggists were selected randomly as informants and their TMs were recorded. RESULTS: As a result, 427 TMs were recorded including 362 plant medicines, 33 animal medicines, 13 mineral medicines and 19 unidentified medicines. Xinyi, Shanza and Gancao were the most popular medicines due to their popular usages, whereas Sanqi, Tianma and Renshen were relatively fewer in this investigation probably owing to high price and limited output. The plant medicines were from medicinal plants of 117 families belonged to Angiosperm, Gymnospermae, Pteridophyta, Bryophyta, Lichenes and Fungi. Asteraceae, Apiaceae and Fabaceae provided the maximum numbers of TMs successively. Moreover, these TMs were mainly from the cultivated especially familiar TMs, which reflected significant progress in utilization and conservation of medicinal resource in China. CONCLUSION: Medicinal market in the Third Month Fair is the most important traditional bazaar in Yunnan province. This study systematically surveyed TMs in the fair for the first time, analyzing and revealing resource compositions and current market situations. These newly gathered data provided precious information for development of medicine cultivation, resource protection and market management as well as further pharmacognostical, pharmacological and clinical researches.

[Effect of water and nitrogen fertilizer coupling on yield and growth of genuine medicinal materials Chuzhou Chrysanthemum morifolium].

OBJECTIVE: To discuss the suitable water and nitrogen management mode in artificial cultivation of Chuzhou Chrysanthemum morifolium. METHODS: According to two factors quadratic regression rotation design experience, pot experiment was conducted. RESULTS: There were remarkable effects of water and nitrogen coupling on inflorescence number, yield and overground part biomass of Chuzhou Chrysanthemum morifolium, and there were significant positive interaction between water and nitrogen. Effects of water on early-term inflorescence yield and overground part biomass of Chuzhou Chrysanthemum morifolium were higher than that of nitrogen fertilizer, but the effect on total inflorescence yield was opposite. CONCLUSION: Considering for the fresh inflorescence yield, the suitable water and nitrogen management mode is to keep 93% of the water holding capacity and nitrogen fertilizer (N) 0.34 g/kg of Chuzhou Chrysanthemum morifolium in pot experiment, and as for the dry inflorescence yield, the suitable water and nitrogen management mode is to keep 75% of the water holding capacity and nitrogen fertilizer (N) 0.2 g/kg.