Study on the differential diagnosis of benign and malignant breast lesions using a deep learning model based on multimodal images.

OBJECTIVE: To establish a multimodal model for distinguishing benign and malignant breast lesions. MATERIALS AND METHODS: Clinical data, mammography, and MRI images (including T2WI, diffusion-weighted images (DWI), apparent diffusion coefficient (ADC), and DCE-MRI images) of 132 benign and breast cancer patients were analyzed retrospectively. The region of interest (ROI) in each image was marked and segmented using MATLAB software. The mammography, T2WI, DWI, ADC, and DCE-MRI models based on the ResNet34 network were trained. Using an integrated learning method, the five models were used as a basic model, and voting methods were used to construct a multimodal model. The dataset was divided into a training set and a prediction set. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the model were calculated. The diagnostic efficacy of each model was analyzed using a receiver operating characteristic curve (ROC) and an area under the curve (AUC). The diagnostic value was determined by the DeLong test with statistically significant differences set at P < 0.05. RESULTS: We evaluated the ability of the model to classify benign and malignant tumors using the test set. The AUC values of the multimodal model, mammography model, T2WI model, DWI model, ADC model and DCE-MRI model were 0.943, 0.645, 0.595, 0.905, 0.900, and 0.865, respectively. The diagnostic ability of the multimodal model was significantly higher compared with that of the mammography and T2WI models. However, compared with the DWI, ADC, and DCE-MRI models, there was no significant difference in the diagnostic ability of these models. CONCLUSION: Our deep learning model based on multimodal image training has practical value for the diagnosis of benign and malignant breast lesions.

Piezocatalysis for Chemical-Mechanical Polishing of SiC: Dual Roles of t-BaTiO3 as a Piezocatalyst and an Abrasive.

Chemical mechanical polishing (CMP) offers a promising pathway to smooth third-generation semiconductors. However, it is still a challenge to reduce the use of additional oxidants or/and energy in current CMP processes. Here, a new and green atomically smoothing method: Piezocatalytic-CMP (Piezo-CMP) is reported. Investigation shows that the Piezo-CMP based on tetragonal BaTiO3 (t-BT) can polish the rough surface of a reaction sintering SiC (RS-SiC) to the ultra-smooth surface with an average surface roughness (Ra) of 0.45 nm and the rough surface of a single-crystal 4H-SiC to the atomic planarization Si and C surfaces with Ra of 0.120 and 0.157 nm, respectively. In these processes, t-BT plays a dual role of piezocatalyst and abrasive. That is, it piezo-catalytically generates in-situ active oxygen species to selectively oxidize protruding sites of SiC surface, yielding soft SiO2, and subsequently, it acts as a usual abrasive to mechanically remove these SiO2. This mechanism is further confirmed by density functional theory (DFT) calculation and molecular simulation. In this process, piezocatalytic oxidation is driven only by the original pressure and friction force of a conventional polishing process, thus, the piezo-CMP process do not require any additional oxidant and energy, being a green and effective polishing method.

Identification of Luminal A breast cancer by using deep learning analysis based on multi-modal images.

Purpose: To evaluate the diagnostic performance of a deep learning model based on multi-modal images in identifying molecular subtype of breast cancer. Materials and methods: A total of 158 breast cancer patients (170 lesions, median age, 50.8 ± 11.0 years), including 78 Luminal A subtype and 92 non-Luminal A subtype lesions, were retrospectively analyzed and divided into a training set (n = 100), test set (n = 45), and validation set (n = 25). Mammography (MG) and magnetic resonance imaging (MRI) images were used. Five single-mode models, i.e., MG, T2-weighted imaging (T2WI), diffusion weighting imaging (DWI), axial apparent dispersion coefficient (ADC), and dynamic contrast-enhanced MRI (DCE-MRI), were selected. The deep learning network ResNet50 was used as the basic feature extraction and classification network to construct the molecular subtype identification model. The receiver operating characteristic curve were used to evaluate the prediction efficiency of each model. Results: The accuracy, sensitivity and specificity of a multi-modal tool for identifying Luminal A subtype were 0.711, 0.889, and 0.593, respectively, and the area under the curve (AUC) was 0.802 (95% CI, 0.657- 0.906); the accuracy, sensitivity, and AUC were higher than those of any single-modal model, but the specificity was slightly lower than that of DCE-MRI model. The AUC value of MG, T2WI, DWI, ADC, and DCE-MRI model was 0.593 (95%CI, 0.436-0.737), 0.700 (95%CI, 0.545-0.827), 0.564 (95%CI, 0.408-0.711), 0.679 (95%CI, 0.523-0.810), and 0.553 (95%CI, 0.398-0.702), respectively. Conclusion: The combination of deep learning and multi-modal imaging is of great significance for diagnosing breast cancer subtypes and selecting personalized treatment plans for doctors.

Characterization of a novel esterase and construction of a Rhodococcus-Burkholderia consortium capable of catabolism bis (2-hydroxyethyl) terephthalate.

Bis (2-hydroxyethyl) terephthalate (BHET) is one of the main compounds produced by enzymatic hydrolysis or chemical depolymerization of polyethylene terephthalate (PET). However, the lack of understanding on BHET microbial metabolism is a main factor limiting the bio-upcycling of PET. In this study, BHET-degrading strains of Rhodococcus biphenylivorans GA1 and Burkholderia sp. EG1 were isolated and identified, which can grow with BHET as the sole carbon source. Furthermore, a novel esterase gene betH was cloned from strain GA1, which encodes a BHET hydrolyzing esterase with the highest activity at 30 °C and pH 7.0. In addition, the co-culture containing strain GA1 and strain EG1 could completely degrade high concentration of BHET, eliminating the inhibition on strain GA1 caused by the accumulation of intermediate metabolite ethylene glycol (EG). This work will provide potential strains and a feasible strategy for PET bio-upcycling.

Carotenoids production and genome analysis of a novel carotenoid producing Rhodococcus aetherivorans N1.

Carotenoids are a series of natural pigments with unique structure and physiological functions. In this study, a novel Rhodococcus aetherivorans strain N1 was discovered, which can produce 6.4 mg/g carotenoids including ß-carotene, zeaxanthin and isorenieratene from glucose. Moreover, strain N1 can directly produce 3.0 mg/g carotenoids from the undetoxified straw hydrolysate, representing the highest carotenoids production from the undetoxified lignocellulosic hydrolysate. The crude carotenoid extracts of strain N1 showed efficient free radical scavenging activity and stability. Strain N1 has complete methylerythritol 4-phosphate (MEP) pathway and related genes for carotenoid synthesis, especially the rare aromatic carotenoid of isorenieratene. Genomic comparison between strain N1 and other carotenoid producing Rhodococcus sp. strains showed the conservatism and universality of carotenoids synthesis gene. These results proved that R. aetherivorans strain N1 can serve as a promising producer for the industrialization of carotenoid production.

Predicting of axillary lymph node metastasis in invasive breast cancer using multiparametric MRI dataset based on CNN model.

Purpose: To develop a multiparametric MRI model for predicting axillary lymph node metastasis in invasive breast cancer. Methods: Clinical data and T2WI, DWI, and DCE-MRI images of 252 patients with invasive breast cancer were retrospectively analyzed and divided into the axillary lymph node metastasis (ALNM) group and non-ALNM group using biopsy results as a reference standard. The regions of interest (ROI) in T2WI, DWI, and DCE-MRI images were segmented using MATLAB software, and the ROI was unified into 224 × 224 sizes, followed by image normalization as input to T2WI, DWI, and DCE-MRI models, all of which were based on ResNet 50 networks. The idea of a weighted voting method in ensemble learning was employed, and then T2WI, DWI, and DCE-MRI models were used as the base models to construct a multiparametric MRI model. The entire dataset was randomly divided into training sets and testing sets (the training set 202 cases, including 78 ALNM, 124 non-ALNM; the testing set 50 cases, including 20 ALNM, 30 non-ALNM). Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of models were calculated. The receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to evaluate the diagnostic performance of each model for axillary lymph node metastasis, and the DeLong test was performed, P< 0.05 statistically significant. Results: For the assessment of axillary lymph node status in invasive breast cancer on the test set, multiparametric MRI models yielded an AUC of 0.913 (95% CI, 0.799-0.974); T2WI-based model yielded an AUC of 0.908 (95% CI, 0.792-0.971); DWI-based model achieved an AUC of 0.702 (95% CI, 0.556-0.823); and the AUC of the DCE-MRI-based model was 0.572 (95% CI, 0.424-0.711). The improvement in the diagnostic performance of the multiparametric MRI model compared with the DWI and DCE-MRI-based models were significant (P< 0.01 for both). However, the increase was not meaningful compared with the T2WI-based model (P = 0.917). Conclusion: Multiparametric MRI image analysis based on an ensemble CNN model with deep learning is of practical application and extension for preoperative prediction of axillary lymph node metastasis in invasive breast cancer.

Biological production of xylitol by using nonconventional microbial strains.

Xylitol (C5H12O5), an amorphous sugar alcohol of crystalline texture has received great interest on the global market due to its numerous applications in different industries. In addition to its high anticariogenic and sweetening properties, characteristics such as high solubility, stability and low glycemic index confer xylitol its fame in the food and odontological industries. Moreover, it also serves as a building-block in the production of polymers. As a result of the harmful effects of the chemical production of xylitol, the biotechnological means of producing this polyol have evolved over the decades. In contrast to the high consumption of energy, long periods of purification, specialized equipment and high production cost encountered during its chemical synthesis, the biotechnological production of xylitol offers advantages both to the economy and the environment. Non-Saccharomyces yeast strains, also termed as nonconventional, possess the inherent capacity to utilize D-xylose as a sole carbon source, unlike Saccharomyces species.

Advances in the synthesis of three typical tetraterpenoids including ß-carotene, lycopene and astaxanthin.

Carotenoids are natural pigments that widely exist in nature. Due to their excellent antioxidant, anticancer and anti-inflammatory properties, carotenoids are commonly used in food, medicine, cosmetic and other fields. At present, natural carotenoids are mainly extracted from plants, algae and microorganisms. With the rapid development of metabolic engineering and molecular biology as well as the continuous in-depth study of carotenoids synthesis pathways, industrial microorganisms have showed promising applications in the synthesis of carotenoids. In this review, we introduced the properties of several carotenoids and their biosynthetic metabolism process. Then, the microorganisms synthesizing carotenoids through the natural and non-natural pathways and the extraction methods of carotenoids were summarized and compared. Meanwhile, the influence of substrates on the carotenoids production was also listed. The methods and strategies for achieving high carotenoid production are categorized to help with future research.

Current status, challenges and prospects for lignin valorization by using Rhodococcus sp.

Lignin represents the most abundant renewable aromatics in nature, which has complicated and heterogeneous structure. The rapid development of biotransformation technology has brought new opportunities to achieve the complete lignin valorization. Especially, Rhodococcus sp. possesses excellent capabilities to metabolize aromatic hydrocarbons degraded from lignin. Furthermore, it can convert these toxic compounds into high value added bioproducts, such as microbial lipids, polyhydroxyalkanoate and carotenoid et al. Accordingly, this review will discuss the potentials of Rhodococcus sp. as a cell factory for lignin biotransformation, including phenol tolerance, lignin depolymerization and lignin-derived aromatic hydrocarbon metabolism. The detailed metabolic mechanism for lignin biotransformation and bioproducts spectrum of Rhodococcus sp. will be comprehensively discussed. The available molecular tools for the conversion of lignin by Rhodococcus sp. will be reviewed, and the possible direction for lignin biotransformation in the future will also be proposed.

Improvement of sewage sludge dewatering by piezoelectric effect driven directly with pressure from pressure filtration: Towards understanding piezo-dewatering mechanism.

Piezoelectric effect was firstly employed to improve dewatering efficiency of sludge. It was found that the piezoelectric effect could be driven directly by the pressure of pressure filtration process, without any additional energy. This piezo-dewatering process coupled piezoelectric effect with pressure filtration could efficiently remove moisture of sludge. Under 0.6 MPa for 2 h, moisture content (MC) and weight of sludge could be reduced to 63.9% and 3.2 g from 96.7% and 50 g by the piezo-dewatering process with 0.45 g t-BaTiO3. This piezo-dewatering efficiency was much higher than that of usual conditioning-pressure filtrations using CaO, FeCl3 or polyacrylamide (PAM) as the conditioners. And the piezo-dewatering process assisted by PAM could further decrease MC and weight of the sludge to 54.9% and 2.1 g, correspondingly, which complied to the advanced dewatering requirement (MC < 60%). The favorable piezo-dewatering efficiency was contributed to the piezo-catalytic oxidation and the electric role of remnant piezo-field. The finding of this piezo-dewatering mechanism offered an inspiring look at developing the emerging dewatering technology.