Search

Objectives To investigate the feasibility of automatically identifying normal scans in ultrafast breast MRI with artificial intelligence (AI) to increase efficiency and reduce workload. Methods In this retrospective analysis, 837 breast MRI examinations performed on 438 women from April 2016 to October 2019 were included. The left and right breasts in each examination were labelled normal (without suspicious lesions) or abnormal (with suspicious lesions) based on final interpretation. Maximum intensity projection (MIP) images of each breast were then used to train a deep learning model. A high sensitivity threshold was calculated based on the detection trade - off (DET) curve on the validation set. The performance of the model was evaluated by receiver operating characteristic analysis of the independent test set. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with the high sensitivity threshold were calculated. Results The independent test set consisted of 178 examinations of 149 patients (mean age, 44 years ± 14 [standard deviation]). The trained model achieved an AUC of 0.81 (95% CI: 0.75–0.88) on the independent test set. Applying a threshold of 0.25 yielded a sensitivity of 98% (95% CI: 90%; 100%), an NPV of 98% (95% CI: 89%; 100%), a workload reduction of 15.7%, and a scan time reduction of 16.6%. Conclusion This deep learning model has a high potential to help identify normal scans in ultrafast breast MRI and thereby reduce radiologists’ workload and scan time. Key Points • Deep learning in TWIST may eliminate the necessity of additional sequences for identifying normal breasts during MRI screening. • Workload and scanning time reductions of 15.7% and 16.6%, respectively, could be achieved with the cost of 1 (1 of 55) false negative prediction.

Purpose: Early detection of lung cancer is of importance since it can increase patients’ chances of survival. To detect nodules accurately during screening, radiologists would commonly take the axial, coronal, and sagittal planes into account, rather than solely the axial plane in clinical evaluation. Inspired by clinical work, the paper aims to develop an accurate deep learning framework for nodule detection by a combination of multiple planes. Methods: The nodule detection system is designed in two stages, multiplanar nodule candidate detection, multiscale false positive (FP) reduction. At the first stage, a deeply supervised encoder–decoder network is trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are merged. To further refine results, a three-dimensional multiscale dense convolutional neural network that extracts multiscale contextual information is applied to remove non-nodules. In the public LIDC-IDRI dataset, 888 computed tomography scans with 1186 nodules accepted by at least three of four radiologists are selected to train and evaluate our proposed system via a tenfold cross-validation scheme. The free-response receiver operating characteristic curve is used for performance assessment. Results: The proposed system achieves a sensitivity of 94.2% with 1.0 FP/scan and a sensitivity of 96.0% with 2.0 FPs/scan. Although it is difficult to detect small nodules (i.e.

Purpose: To investigate the feasibility of using deep learning methods to differentiate benign from malignant breast lesions in ultrafast MRI with both temporal and spatial information. Methods: A total of 173 single breasts of 122 women (151 examinations) with lesions above 5 mm were retrospectively included. A total of 109 out of 173 lesions were benign. Maximum intensity projection (MIP) images were generated from each of the 14 contrast-enhanced T1-weighted acquisitions in the ultrafast MRI scan. A 2D convolutional neural network (CNN) and a long short-term memory (LSTM) network were employed to extract morphological and temporal features, respectively. The 2D CNN model was trained with the MIPs from the last four acquisitions to ensure the visibility of the lesions, while the LSTM model took MIPs of an entire scan as input. The performance of each model and their combination were evaluated with 100-times repeated stratified four-fold cross-validation. Those models were then compared with models developed with standard DCE-MRI which followed the same data split. Results: In the differentiation between benign and malignant lesions, the ultrafast MRI-based 2D CNN achieved a mean AUC of 0.81 ± 0.06, and the LSTM network achieved a mean AUC of 0.78 ± 0.07; their combination showed a mean AUC of 0.83 ± 0.06 in the cross-validation. The mean AUC values were significantly higher for ultrafast MRI-based models than standard DCE-MRI-based models. Conclusion: Deep learning models developed with ultrafast breast MRI achieved higher performances than standard DCE-MRI for malignancy discrimination. The improved AUC values of the combined models indicate an added value of temporal information extracted by the LSTM model in breast lesion characterization.

Immobilization of enzymes on carriers have been pursued to make the enzyme stable, reusable and obtaining even better enzyme activity. Due to the highly stable two-dimensional layer structure, large surface area and pore volume, graphene materials were seemed as ideal carrier for enzyme immobilization. In this paper, pristine few layer graphene (FLG) was applied to interact with laccase to synthesize laccase-graphene composite and the results of AFM, FT-IR and adsorption isotherm suggested that laccase was loaded on the FLG with a very high loading dosage (221.1 mg g−1). Based on the measured interaction force and binding type between laccase and graphene, we proposed that the great enzyme loading on FLG is likely due to the non-covalent π-π stacking in addition to the large surface area of FLG. The composite has better stability to the variance of pH and storage temperature than free laccase. The synthesized composite can effectively transform beta-blocker labetalol with an enhanced efficiency, though the possible reaction pathways kept not changing. We further performed molecular simulation study on the crystal structure variation of laccase binding on FLG and proposed that catalytic activity enhancement may be attributed to the more exposure extent of the catalytic center of laccase. In addition, the laccase-graphene composite can be reused more than ten times in catalyzing the labetalol removal.

Atenolol (ATL), a kind of largely used beta-blockers, has been widely detected in the aquatic environment, which could cause adverse impact on human beings. In this study, bismuth oxychloride (BiOCl) photocatalyst was synthesized and applied to remove ATL in the aqueous system under simulated natural light. Emphasis was laid on the reaction kinetics and the impact of natural organic matter (NOM) (0–20 mg/L). Possible transformation pathways were systematically investigated based on identification of reaction products via liquid chromatography-mass spectrometry (LC-MS). As a consequence, BiOCl presents highly photocatalytic efficiency yielding up to nearly 100% ATL conversion after 60 min of interaction, together with fairly high photostability evidenced by considerably efficient removal of ATL after 10 catalytic cycles. Four kinds of possible products are detected using LC-MS in the process of reaction, indicating possible transformation ways of ATL photocatalysis. NOM has an inhibiting impact on the removal of ATL and influences the products distribution. This study provides an emerging nanocatalyst for ATL photodegradation and could eventually lead to development of novel methods to control pharmaceutical contamination in water.

Glomerular filtration rate (GFR), which can be estimated by Gates method with dynamic kidney single photon emission computed tomography (SPECT) imaging, is a key indicator of renal function. In this paper, an automatic computer tomography (CT)-assisted detection method of kidney region of interest (ROI) is proposed to achieve the objective and accurate GFR calculation. In this method, the CT coronal projection image and the enhanced SPECT synthetic image are firstly generated and registered together. Then, the kidney ROIs are delineated using a modified level set algorithm. Meanwhile, the background ROIs are also obtained based on the kidney ROIs. Finally, the value of GFR is calculated via Gates method. Comparing with the clinical data, the GFR values estimated by the proposed method were consistent with the clinical reports. This automatic method can improve the accuracy and stability of kidney ROI detection for GFR calculation, especially when the kidney function has been severely damaged.肾小球滤过率（GFR）是评估肾脏功能的重要指标，可采用肾动态显像联合 Gates 法计算获得。针对 GFR 计算问题，本文提出一种计算机断层（CT）图像辅助的肾动态图像感兴趣区（ROI）自动检测方法，以实现客观准确的 GFR 计算。该方法首先获得 CT 冠状面投影图像与单光子发射计算机断层成像（SPECT）的增强合成图像，完成双模态图像配准后，采用改进的水平集方法实现肾脏 ROI 的自动检测并获取本底 ROI，最后利用 Gates 法计算 GFR 值。经临床数据验证，该方法能够自动完成肾脏 GFR 值计算，所得结果与临床报告一致。该方法在消除人工勾画环节的同时，还能提高 ROI 检测的准确性和稳定性，尤其有利于肾功能严重受损时的 GFR 计算。.

19Streptococcus thermophiluswith high exopolysaccharide production were isolated from traditional Chinese fermented dairy products. The exopolysaccharide and viscosity of milk fermented by these 19 isolates were assayed. The strains ofStreptococcus thermophiluszlw TM11 were selected because its fermented milk had the highest exopolysaccharide content (380 mg/L) and viscosity (7716 mpa/s). ThenStreptococcus thermophiluszlw TM11 was combined withLactobacillus delbrueckiisubsp.bulgaricus3 4.5 and the combination was named SH-1. The quality of the yogurt fermented by SH-1 and two commercial starter cultures (YO-MIX 465, YF-L711) were compared. It was shown that the exopolysaccharide content of yogurt fermented by SH-1 was similar to that of yogurt fermented by YF-L711 and significantly higher than YO-MIX 465 (p<0.05). In addition, the yogurt fermented by SH-1 had the lowest syneresis (8.5%) and better texture and sensory than the samples fermented by YO-MIX 465 and YF-L711. It manifested that the selected higher exopolysaccharide production starter SH-1 could be used as yogurt starter and reduce the amount of adding stabilizer, which can compare with the imported commercial starter culture.