Localization of contrast-enhanced breast lesions in ultrafast screening MRI using deep convolutional neural networks.

OBJECTIVES: To develop a deep learning-based method for contrast-enhanced breast lesion detection in ultrafast screening MRI. MATERIALS AND METHODS: A total of 837 breast MRI exams of 488 consecutive patients were included. Lesion's location was independently annotated in the maximum intensity projection (MIP) image of the last time-resolved angiography with stochastic trajectories (TWIST) sequence for each individual breast, resulting in 265 lesions (190 benign, 75 malignant) in 163 breasts (133 women). YOLOv5 models were fine-tuned using training sets containing the same number of MIP images with and without lesions. A long short-term memory (LSTM) network was employed to help reduce false positive predictions. The integrated system was then evaluated on test sets containing enriched uninvolved breasts during cross-validation to mimic the performance in a screening scenario. RESULTS: In five-fold cross-validation, the YOLOv5x model showed a sensitivity of 0.95, 0.97, 0.98, and 0.99, with 0.125, 0.25, 0.5, and 1 false positive per breast, respectively. The LSTM network reduced 15.5% of the false positive prediction from the YOLO model, and the positive predictive value was increased from 0.22 to 0.25. CONCLUSIONS: A fine-tuned YOLOv5x model can detect breast lesions on ultrafast MRI with high sensitivity in a screening population, and the output of the model could be further refined by an LSTM network to reduce the amount of false positive predictions. CLINICAL RELEVANCE STATEMENT: The proposed integrated system would make the ultrafast MRI screening process more effective by assisting radiologists in prioritizing suspicious examinations and supporting the diagnostic workup. KEY POINTS: • Deep convolutional neural networks could be utilized to automatically pinpoint breast lesions in screening MRI with high sensitivity. • False positive predictions significantly increased when the detection models were tested on highly unbalanced test sets with more normal scans. • Dynamic enhancement patterns of breast lesions during contrast inflow learned by the long short-term memory networks helped to reduce false positive predictions.

Automated Breast Density Assessment in MRI Using Deep Learning and Radiomics: Strategies for Reducing Inter-Observer Variability.

BACKGROUND: Accurate breast density evaluation allows for more precise risk estimation but suffers from high inter-observer variability. PURPOSE: To evaluate the feasibility of reducing inter-observer variability of breast density assessment through artificial intelligence (AI) assisted interpretation. STUDY TYPE: Retrospective. POPULATION: Six hundred and twenty-one patients without breast prosthesis or reconstructions were randomly divided into training (N = 377), validation (N = 98), and independent test (N = 146) datasets. FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T; T1-weighted spectral attenuated inversion recovery. ASSESSMENT: Five radiologists independently assessed each scan in the independent test set to establish the inter-observer variability baseline and to reach a reference standard. Deep learning and three radiomics models were developed for three classification tasks: (i) four Breast Imaging-Reporting and Data System (BI-RADS) breast composition categories (A-D), (ii) dense (categories C, D) vs. non-dense (categories A, B), and (iii) extremely dense (category D) vs. moderately dense (categories A-C). The models were tested against the reference standard on the independent test set. AI-assisted interpretation was performed by majority voting between the models and each radiologist's assessment. STATISTICAL TESTS: Inter-observer variability was assessed using linear-weighted kappa (κ) statistics. Kappa statistics, accuracy, and area under the receiver operating characteristic curve (AUC) were used to assess models against reference standard. RESULTS: In the independent test set, five readers showed an overall substantial agreement on tasks (i) and (ii), but moderate agreement for task (iii). The best-performing model showed substantial agreement with reference standard for tasks (i) and (ii), but moderate agreement for task (iii). With the assistance of the AI models, almost perfect inter-observer variability was obtained for tasks (i) (mean κ = 0.86), (ii) (mean κ = 0.94), and (iii) (mean κ = 0.94). DATA CONCLUSION: Deep learning and radiomics models have the potential to help reduce inter-observer variability of breast density assessment. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 1.

Root Hair Apex is the Key Site for Symplastic Delivery of Graphene into Plants.

Uptake kinetics and delivery mechanisms of nanoparticles (NPs) in crop plants need to be urgently understood for the application of nanotechnology in agriculture as delivery systems for eco-friendly nanoagrochemicals. Here, we investigated the uptake kinetics, translocation pathway, and key internalization process of graphene in wheat (Triticum aestivum L.) by applying three specific hydroponic cultivation methods (submerging, hanging, and split-root). Quantification results on the uptake of carbon-14 radiolabeled graphene in each tissue indicated that graphene could enter the root of wheat and further translocate to the shoot with a low delivery rate (<2%). Transmission electron microscopy (TEM) images showed that internalized graphene was transported to adjacent cells through the plasmodesmata, clearly indicating the symplastic pathway of graphene translocation. The key site for the introduction of graphene into root cells for translocation through the symplastic pathway is evidenced to be the apex of growing root hair, where the newly constructed primary cell wall is much thinner. The confirmation of uptake kinetics and delivery mechanisms is useful for the development of nanotechnology in sustainable agriculture, especially for graphene serving as the delivery vector for pesticides, genes, and sensors.

Using deep learning to safely exclude lesions with only ultrafast breast MRI to shorten acquisition and reading time.

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.

Breast Tumor Identification in Ultrafast MRI Using Temporal and Spatial Information.

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.

Deep convolutional neural networks for multiplanar lung nodule detection: Improvement in small nodule identification.

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., <6 mm), our designed CAD system reaches a sensitivity of 93.4% (95.0%) of these small nodules at an overall FP rate of 1.0 (2.0) FPs/scan. At the nodule candidate detection stage, results show that the system with a multiplanar method is capable to detect more nodules compared to using a single plane. CONCLUSION: Our approach achieves good performance not only for small nodules but also for large lesions on this dataset. This demonstrates the effectiveness of our developed CAD system for lung nodule detection.

Uptake of iron oxide nanoparticles inhibits the photosynthesis of the wheat after foliar exposure.

Iron oxide nanoparticles (nFe2O3)-filled materials have been widely employed in various products and their effects on plants have attracted considerable attention because of their potential release into the environment. Currently, numerous studies reporting the influences of iron-bearing nanoparticles on plants are focused on root or seed exposure. However, plants exposed to atmospheric iron-bearing nanoparticles through the leaves and their impacts on plants are still not well understood. This study focused on the uptake, translocation, and effects of foliar exposure of nFe2O3 on wheat seedlings. Wheat seedlings were foliar applied to various concentrations of nFe2O3 (0, 60 and 180 µg per plant) for 1, 7, 14 or 21 d. Our results demonstrated that after exposure for 21 d, the concentrations of Fe in leaves, stems, and roots were 1100, 280 and 160 µg kg-1, respectively. Scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS), as well as the backscattered electron (BSE) images, revealed the stomatal opening was likely the pathway for nFe2O3 uptake. Analysis of the transfer rate, translocation of Fe from leaves to stems and roots, suggested the involvement of plant Fe regulation processes. Particularly, the antioxidant enzymatic activities and malondialdehyde levels in leaves were modified, which was ascribed to the excessive hydroxyl radical (OH) generated via the Fenton-like reaction mediated by nFe2O3. Finally, the OH facilitated the degradation of chlorophyll, posting a negative impact on the photosynthesis, and thus inhibited the biomass production. These findings are meaningful to understand the fate and physiological effects of atmospheric nFe2O3 in crops.

Automatic Recognition of Laryngoscopic Images Using a Deep-Learning Technique.

OBJECTIVES/HYPOTHESIS: To develop a deep-learning-based computer-aided diagnosis system for distinguishing laryngeal neoplasms (benign, precancerous lesions, and cancer) and improve the clinician-based accuracy of diagnostic assessments of laryngoscopy findings. STUDY DESIGN: Retrospective study. METHODS: A total of 24,667 laryngoscopy images (normal, vocal nodule, polyps, leukoplakia and malignancy) were collected to develop and test a convolutional neural network (CNN)-based classifier. A comparison between the proposed CNN-based classifier and the clinical visual assessments (CVAs) by 12 otolaryngologists was conducted. RESULTS: In the independent testing dataset, an overall accuracy of 96.24% was achieved; for leukoplakia, benign, malignancy, normal, and vocal nodule, the sensitivity and specificity were 92.8% vs. 98.9%, 97% vs. 99.7%, 89% vs. 99.3%, 99.0% vs. 99.4%, and 97.2% vs. 99.1%, respectively. Furthermore, when compared with CVAs on the randomly selected test dataset, the CNN-based classifier outperformed physicians for most laryngeal conditions, with striking improvements in the ability to distinguish nodules (98% vs. 45%, P < .001), polyps (91% vs. 86%, P < .001), leukoplakia (91% vs. 65%, P < .001), and malignancy (90% vs. 54%, P < .001). CONCLUSIONS: The CNN-based classifier can provide a valuable reference for the diagnosis of laryngeal neoplasms during laryngoscopy, especially for distinguishing benign, precancerous, and cancer lesions. LEVEL OF EVIDENCE: NA Laryngoscope, 130:E686-E693, 2020.

Non-covalent assembled laccase-graphene composite: Property, stability and performance in beta-blocker removal.

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.

BiOCl facilitated photocatalytic degradation of atenolol from water: Reaction kinetics, pathways and products.

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.

[A computer tomography assisted method for the automatic detection of region of interest in dynamic kidney images].

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.

Comparative genomic and functional analyses: unearthing the diversity and specificity of nematicidal factors in Pseudomonas putida strain 1A00316.

We isolated Pseudomonas putida (P. putida) strain 1A00316 from Antarctica. This bacterium has a high efficiency against Meloidogyne incognita (M. incognita) in vitro and under greenhouse conditions. The complete genome of P. putida 1A00316 was sequenced using PacBio single molecule real-time (SMRT) technology. A comparative genomic analysis of 16 Pseudomonas strains revealed that although P. putida 1A00316 belonged to P. putida, it was phenotypically more similar to nematicidal Pseudomonas fluorescens (P. fluorescens) strains. We characterized the diversity and specificity of nematicidal factors in P. putida 1A00316 with comparative genomics and functional analysis, and found that P. putida 1A00316 has diverse nematicidal factors including protein alkaline metalloproteinase AprA and two secondary metabolites, hydrogen cyanide and cyclo-(l-isoleucyl-l-proline). We show for the first time that cyclo-(l-isoleucyl-l-proline) exhibit nematicidal activity in P. putida. Interestingly, our study had not detected common nematicidal factors such as 2,4-diacetylphloroglucinol (2,4-DAPG) and pyrrolnitrin in P. putida 1A00316. The results of the present study reveal the diversity and specificity of nematicidal factors in P. putida strain 1A00316.

Improvement of the Texture of Yogurt by Use of Exopolysaccharide Producing Lactic Acid Bacteria.

19 Streptococcus thermophilus with 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 of Streptococcus thermophilus zlw TM11 were selected because its fermented milk had the highest exopolysaccharide content (380 mg/L) and viscosity (7716 mpa/s). Then Streptococcus thermophilus zlw TM11 was combined with Lactobacillus delbrueckii subsp. bulgaricus 3 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.