Predicting postoperative prognosis in clear cell renal cell carcinoma using a multiphase CT-based deep learning model.

BACKGROUND: Some clinicopathological risk stratification systems (CRSSs) such as the leibovich score have been used to predict the postoperative prognosis of patients with clear cell renal cell carcinoma (ccRCC), but there are no reliable noninvasive preoperative indicators for predicting postoperative prognosis in clinical practice. PURPOSE: To assess the value of a deep learning (DL) model based on CT images in predicting the postoperative prognosis of patients with ccRCC. MATERIALS AND METHODS: A total of 382 patients with ccRCC were retrospectively enrolled andallocated to training (n = 229) or testing (n = 153) cohorts at a 6:4 ratio. The features were extracted from precontrast-phase (PCP), corticomedullary-phase (CMP) and nephrographic-phase (NP) CT images with ResNet50, and then extreme learning machines (ELMs) were used to construct classification models. The DL model and Leibovich score were compared and combined. A receiver operating characteristic (ROC) curve and integrated discrimination improvement (IDI) were used to evaluate model performance. RESULTS: Compared with other single-phase DL models, the three-phase CT-based DL model achieved the best performance, with an area under the curve (AUC) of 0.839. Combining the three-phase DL model and the Leibovich score (AUC = 0.823) into a nomogram (AUC = 0.888) statistically improved performance (IDINomogram vs. Three-phase = 0.1358, IDINomogram vs. Leibovich = 0.1393, [Formula: see text]< 0.001). CONCLUSION: The CT-based DL model could be valuable for preoperatively predicting the prognosis of patients with ccRCC, and combining it with the Leibovich score can further improve its predictive performance.

Impact of a Potent Strain of Plant Growth-Promoting Bacteria (PGPB), Bacillus subtilis S1 on Bacterial Community Composition, Enzymatic Activity, and Nitrogen Content in Cucumber Rhizosphere Soils.

Antagonistic bacterial strains from Bacillus spp. have been widely studied and utilized in the biocontrol of phytopathogens and the promotion of plant growth, but their impacts on the rhizosphere microecology when applied to crop plants are unclear. Herein, the effects of applying the antagonistic bacterium Bacillus subtilis S1 as a biofertilizer on the rhizosphere microecology of cucumbers were investigated. In a pot experiment on cucumber seedlings inoculated with S1, 3124 bacterial operational taxonomic units (OTUs) were obtained from the rhizosphere soils using high-throughput sequencing of 16S rRNA gene amplicons, and the most abundant phylum was Proteobacteria that accounted for 49.48% in the bacterial community. S1 treatment significantly reduced the abundances of soil bacterial taxa during a period of approximately 30 days but did not affect bacterial diversity in the rhizosphere soils of cucumbers. The enzymatic activities of soil nitrite reductase (S-Nir) and dehydrogenase (S-DHA) were significantly increased after S1 fertilization. However, the activities of soil urease (S-UE), cellulase (S-CL), and sucrase (S-SC) were significantly reduced compared to the control group. Additionally, the ammonium- and nitrate-nitrogen contents of S1-treated soil samples were significantly lower than those of the control group. S1 fertilization reshaped the rhizosphere soil bacterial community of cucumber plants. The S-CL activity and nitrate-nitrogen content in rhizosphere soil affected by S1 inoculation play important roles in altering the abundance of rhizosphere soil microbiota.

A multicenter epidemiological survey of iNO use in preterm infants in China.

OBJECTIVE: To investigate the use of inhaled nitric oxide (iNO) in hospitalized preterm infants in China over 10 years and its clinical outcomes. METHODS: A total of 616 premature infants who were administered iNO in the Neonatology Departments of 5 Class A tertiary hospitals in China for ten years from January 2013 to December 2022 were included retrospectively. Based on their enrollment periods, the patients were divided into two groups: Group 1 from January 2013 to December 2017 and Group 2 from January 2018 to December 2022, respectively. The perinatal characteristics, short-term clinical outcomes, and mortality rates were compared between these two groups. RESULTS: The utilization of iNO in preterm infants grew annually over the past10 years; the utilization of iNO in Group 2 infants increased approximately one-fold when compared with Group 1 (1.52% vs. 0.80%, p < .001), and the increase was greater in gestational age (GA) < 34 weeks compared with 34-36 weeks preterm infants. Moreover, the iNO usage in Group 1 infants with GA < 34 weeks increased from 1.14% to 2.46% and 0.60% to 0.99% in 34-36 weeks preterm infants (p < .001) in Group 2, respectively. Apart from a smaller GA (32.9 w vs. 33.5 w, p < .001) and birth weight (BW, 1900 g vs. 2141 g, p < .001), the initial [14 parts per million (ppm) versus 10 ppm, p < .001] and maximum (15 ppm vs. 10 ppm, p < .001) doses of Group 2 were larger; however, their recent clinical outcomes did not improve with increasing iNO utilization (p > .05)as compared to Group 1, respectively. Although the overall iNO preterm mortality rates over the past 10 years were 25.8%, the mortality rates for preterm infants at 34-36 weeks were significantly lower than for preterm infants at GA < 34 weeks (15.4% vs. 33.8%, p < .001). Nonetheless, no improvement in mortality was observed in Group 2 preterm infants with GA < 34 weeks for the past 5 years when compared with Group 1 (32.9% vs. 35.8%, p > .05) infants, and significantly lower mortality rates were noticed in preterm infants with 34-36 weeks (11.2% vs. 22.7%, p < .001). Patients with hypoxic respiratory failure (HRF) or persistent pulmonary hypertension of the newborn (PPHN) iNO preterm infants did not show lower mortality rates with the increase of iNO use rate (p > .05). The overall mortality rates of preterm PPHN infants with iNO were lower than that of HRF (20.2% vs. 36.5%, p < .001), while the mortality rates of Group 2 preterm PPHN infants with iNO significantly lower than that of HRF (17.7% vs 36.0%, p < .001). CONCLUSION: The iNO has been extensively used in Chinese preterm infants over the past 10 years, this increase was more significant in preterm infants with GA < 34 weeks. Moreover, preterm infants using iNO have lower GA and BW, larger initial and maximum doses, and more aggressive strategies in the last past 5 years. Although iNO use in preterm infants with GA of 34-36 weeks has significantly reduced mortality, mortality rates and short-term clinical outcomes of iNO in preterm infants <34 weeks of GA has no obvious improvement. Further studies are required to investigate the efficacy and safety of iNO in preterm infants <34 weeks of GA.

MolLoG: A Molecular Level Interpretability Model Bridging Local to Global for Predicting Drug Target Interactions.

Developing new pharmaceuticals is a costly and time-consuming endeavor fraught with significant safety risks. A critical aspect of drug research and disease therapy is discerning the existence of interactions between drugs and proteins. The evolution of deep learning (DL) in computer science has been remarkably aided in this regard in recent years. Yet, two challenges remain: (i) balancing the extraction of profound, local cohesive characteristics while warding off gradient disappearance and (ii) globally representing and understanding the interactions between the drug and target local attributes, which is vital for delivering molecular level insights indispensable to drug development. In response to these challenges, we propose a DL network structure, MolLoG, primarily comprising two modules: local feature encoders (LFE) and global interactive learning (GIL). Within the LFE module, graph convolution networks and leap blocks capture the local features of drug and protein molecules, respectively. The GIL module enables the efficient amalgamation of feature information, facilitating the global learning of feature structural semantics and procuring multihead attention weights for abstract features stemming from two modalities, providing biologically pertinent explanations for black-box results. Finally, predictive outcomes are achieved by decoding the unified representation via a multilayer perceptron. Our experimental analysis reveals that MolLoG outperforms several cutting-edge baselines across four data sets, delivering superior overall performance and providing satisfactory results when elucidating various facets of drug-target interaction predictions.

A novel approach has been developed to produce pure plant-based gel soy yogurt by combining soy proteins (7S/11S), high pressure homogenization, and glycation reaction.

This research sought to examine how the physicochemical characteristics of soy globulins and different processing techniques influence the gel properties of soy yogurt. The goal was to improve these gel properties and rectify any texture issues in soy yogurt, ultimately aiming to produce premium-quality plant-based soy yogurt. In this research study, the investigation focused on examining the impact of 7S/11S, homogenization pressure, and glycation modified with glucose on the gel properties of soy yogurt. A plant-based soy yogurt with superior gel and texture properties was successfully developed using a 7S/11S globulin-glucose conjugate at a 1:3 ratio and a homogenization pressure of 110 MPa. Compared to soy yogurt supplemented with pectin or gelatin, this yogurt demonstrated enhanced characteristics. These findings provide valuable insights into advancing plant protein gels and serve as a reference for cultivating new soybean varieties by soybean breeding experts.

Predicting microvascular invasion in hepatocellular carcinoma with a CT- and MRI-based multimodal deep learning model.

PURPOSE: To investigate the value of a multimodal deep learning (MDL) model based on computed tomography (CT) and magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). METHODS: A total of 287 patients with HCC from our institution and 58 patients from another individual institution were included. Among these, 119 patients with only CT data and 116 patients with only MRI data were selected for single-modality deep learning model development, after which select parameters were migrated for MDL model development with transfer learning (TL). In addition, 110 patients with simultaneous CT and MRI data were divided into a training cohort (n = 66) and a validation cohort (n = 44). We input the features extracted from DenseNet121 into an extreme learning machine (ELM) classifier to construct a classification model. RESULTS: The area under the curve (AUC) of the MDL model was 0.844, which was superior to that of the single-phase CT (AUC = 0.706-0.776, P < 0.05), single-sequence MRI (AUC = 0.706-0.717, P < 0.05), single-modality DL model (AUCall-phase CT = 0.722, AUCall-sequence MRI = 0.731; P < 0.05), clinical (AUC = 0.648, P < 0.05), but not to that of the delay phase (DP) and in-phase (IP) MRI and portal venous phase (PVP) CT models. The MDL model achieved better performance than models described above (P < 0.05). When combined with clinical features, the AUC of the MDL model increased from 0.844 to 0.871. A nomogram, combining deep learning signatures (DLS) and clinical indicators for MDL models, demonstrated a greater overall net gain than the MDL models (P < 0.05). CONCLUSION: The MDL model is a valuable noninvasive technique for preoperatively predicting MVI in HCC.

Deep learning vs. robust federal learning for distinguishing adrenal metastases from benign lesions with multi-phase CT images.

Background: Differentiating adrenal adenomas from metastases poses a significant challenge, particularly in patients with a history of extra-adrenal malignancy. This study investigates the performance of three-phase computed tomography (CT) based robust federal learning algorithm and traditional deep learning for distinguishing metastases from benign adrenal lesions. Material and methods: This retrospective analysis includes 1187 instances who underwent three-phase CT scans between January 2008 and March 2021, comprising 720 benign lesions and 467 metastases. Utilizing the three-phase CT images, both a Robust Federal Learning Signature (RFLS) and a traditional Deep Learning Signature (DLS) were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Their diagnostic capabilities were subsequently validated and compared using metrics such as the Areas Under the Receiver Operating Curve (AUCs), Net Reclassification Improvement (NRI), and Decision Curve Analysis (DCA). Results: Compared with DLS, the RFLS showed better capability in distinguishing metastases from benign adrenal lesions (average AUC: 0.816 vs.0.798, NRI = 0.126, P < 0.072; 0.889 vs.0.838, NRI = 0.209, P < 0.001; 0.903 vs.0.825, NRI = 0.643, p < 0.001) in the four-testing cohort, respectively. DCA showed that the RFLS added more net benefit than DLS for clinical utility. Moreover, Comparison with state-of-the-art federal learning methods, the results once again confirmed that the RFLS significantly improved the diagnostic performance based on three-phase CT (AUC: AP, 0.727 vs. 0.757 vs. 0.739 vs. 0.796; PCP, 0.781 vs. 0.851 vs. 0.790 vs. 0.882; VP, 0.789 vs. 0.814 vs. 0.779 vs. 0.886). Conclusion: RFLS was superior to DLS for preoperative distinguishing metastases from benign adrenal lesions with multi-phase CT Images.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence.

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

A transfer learning nomogram for predicting prostate cancer and benign conditions on MRI.

BACKGROUND: Deep learning has been used to detect or characterize prostate cancer (PCa) on medical images. The present study was designed to develop an integrated transfer learning nomogram (TLN) for the prediction of PCa and benign conditions (BCs) on magnetic resonance imaging (MRI). METHODS: In this retrospective study, a total of 709 patients with pathologically confirmed PCa and BCs from two institutions were included and divided into training (n = 309), internal validation (n = 200), and external validation (n = 200) cohorts. A transfer learning signature (TLS) that was pretrained with the whole slide images of PCa and fine-tuned on prebiopsy MRI images was constructed. A TLN that integrated the TLS, the Prostate Imaging-Reporting and Data System (PI-RADS) score, and the clinical factor was developed by multivariate logistic regression. The performance of the TLS, clinical model (CM), and TLN were evaluated in the validation cohorts using the receiver operating characteristic (ROC) curve, the Delong test, the integrated discrimination improvement (IDI), and decision curve analysis. RESULTS: TLS, PI-RADS score, and age were selected for TLN construction. The TLN yielded areas under the curve of 0.9757 (95% CI, 0.9613-0.9902), 0.9255 (95% CI, 0.8873-0.9638), and 0.8766 (95% CI, 0.8267-0.9264) in the training, internal validation, and external validation cohorts, respectively, for the discrimination of PCa and BCs. The TLN outperformed the TLS and the CM in both the internal and external validation cohorts. The decision curve showed that the TLN added more net benefit than the CM. CONCLUSIONS: The proposed TLN has the potential to be used as a noninvasive tool for PCa and BCs differentiation.

Differentiating adrenal metastases from benign lesions with multiphase CT imaging: Deep learning could play an active role in assisting radiologists.

OBJECTIVES: To develop and externally validate multiphase CT-based deep learning (DL) models for differentiating adrenal metastases from benign lesions. MATERIALS AND METHODS: This retrospective two-center study included 1146 adrenal lesions from 1059 patients who underwent multiphase CT scanning between January 2008 and March 2021. The study encompassed 564 surgically confirmed adenomas, along with 135 benign lesions and 447 metastases confirmed by observation. DL models based on multiphase CT images were developed, validated and tested. The diagnostic performance of the classification models, imaging phases and radiologists with or without DL were compared using accuracy (ACC) and receiver operating characteristic (ROC) curves. Integrated discrimination improvement (IDI) analysis and the DeLong test were used to compare the area under the curve (AUC) among models. Decision curve analysis (DCA) was used to assess the clinical usefulness of the predictive models. RESULTS: The DL signature based on LASSO (DLSL) had a higher AUC than that of the other classification models (IDI > 0, P < 0.05). Furthermore, the precontrast phase (PCP)-based DLSL performed best in the independent external validation (AUC = 0.881, ACC = 82.9 %) and clinical test cohorts (AUC = 0.790, ACC = 70.4 %), outperforming DLSL based on the other single-phase or three-phase images (IDI > 0, P < 0.05). DCA demonstrated that PCP-based DLSL provided a higher net benefit (0.01-0.95). The diagnostic performance led to statistically significant improvements when radiologists incorporated the DL model, with the AUC improving by 0.056-0.159 and the ACC improving by 0.069-0.178 (P < 0.05). CONCLUSION: The DL model based on PCP CT images performed acceptably in differentiating adrenal metastases from benign lesions, and it may assist radiologists in accurate tumor staging for patients with a history of extra-adrenal malignancy.

Case series of ovarian neuroendocrine carcinoma: overview of clinicopathological features.

BACKGROUND: Ovarian neuroendocrine carcinoma (O-NEC) is a relatively uncommon neoplasm, and the current knowledge regarding its diagnosis and management is limited. In this series, our objective was to provide an overview of the clinicopathological characteristics of the disease by analyzing clinical case data to establish a theoretical foundation for the diagnosis and management of O-NEC. CASE PRESENTATION: We included three patients in the present case series, all of whom were diagnosed with primary O-NEC based on pathomorphological observation and immunohistochemistry. Patient 1 was a 62-year-old patient diagnosed with small cell carcinoma (SCC) of the pulmonary type. Post-surgery, the patient was diagnosed with stage II SCC of the ovary and underwent standardized chemotherapy; however, imaging examinations conducted at the 16-month follow-up revealed the existence of lymph node metastasis. Unfortunately, she passed away 21 months after the surgery. The other two patients were diagnosed with carcinoid tumors, one at age 39 and the other at age 71. Post-surgery, patient 2 was diagnosed with a carcinoid in the left ovary, whereas patient 3 was diagnosed with a carcinoid in her right ovary based on clinical evaluation. Neither of the cases received adjuvant therapy following surgery; however, they have both survived for 9 and 10 years, respectively, as of date. CONCLUSION: Primary O-NECs are rare and of diverse histological types, each of which has its own unique biological features and prognosis. SCC is a neoplasm characterized by high malignancy and a poor prognosis, whereas carcinoid tumors are of lesser malignancy and have a more favorable prognosis.

Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding.

Introduction: The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information. Methods: In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers. Results: We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively. Conclusion: The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.

Effects of ultrashort wave diathermy on skin wounds in rabbit ears.

PURPOSE: Ultrashort wave diathermy (USWD) is commonly used in diseases associated with osteoarticular and soft tissue injuries. However, while accelerating wound healing and preventing joint stiffness, there have been few reports on whether it leads to excessive hypertrophic scarring. The aim was to investigate the effects of different doses of USWD on hypertrophic scars. MATERIALS AND METHODS: A rabbit model of hypertrophic scars was used to determine which dose of USWD reduced scar hyperplasia. The scar thickness was calculated using Sirius red staining. All protein expression levels were determined by western blotting, including fibrosis, collagen deposition, and neoangiogenesis related proteins. Subsequently, flow cytometry and ELISAs were used to determine the proportions of macrophage and inflammatory levels. RESULTS: The wounds with USWD in histopathology showed the dermis was more markedly thickened in the 120 mA group, whereas the wounds with the 60 mA were less raised, comparing with the 0 mA; all detected protein levels were increased significantly, the 120 mA group comparing with the others, including heat shock, fibrosis, and neoangiogenesis, whereas the collagen deposition relative protein levels were decreased, the 60 mA group comparing with Sham group; Finally, in the proportion of macrophages and inflammatory levels the 120 mA group were the highest, and the group Sham was lower than group 60 mA. CONCLUSIONS: In hypertrophic scars, the 60 mA USWD could relieve scar formation and inflammatory reactions; however, higher doses could result in opposite consequences.

Development and validation of a deep learning radiomics nomogram for preoperatively differentiating thymic epithelial tumor histologic subtypes.

OBJECTIVES: Using contrast-enhanced computed tomography (CECT) and deep learning technology to develop a deep learning radiomics nomogram (DLRN) to preoperative predict risk status of patients with thymic epithelial tumors (TETs). METHODS: Between October 2008 and May 2020, 257 consecutive patients with surgically and pathologically confirmed TETs were enrolled from three medical centers. We extracted deep learning features from all lesions using a transformer-based convolutional neural network and created a deep learning signature (DLS) using selector operator regression and least absolute shrinkage. The predictive capability of a DLRN incorporating clinical characteristics, subjective CT findings and DLS was evaluated by the area under the curve (AUC) of a receiver operating characteristic curve. RESULTS: To construct a DLS, 25 deep learning features with non-zero coefficients were selected from 116 low-risk TETs (subtypes A, AB, and B1) and 141 high-risk TETs (subtypes B2, B3, and C). The combination of subjective CT features such as infiltration and DLS demonstrated the best performance in differentiating TETs risk status. The AUCs in the training, internal validation, external validation 1 and 2 cohorts were 0.959 (95% confidence interval [CI]: 0.924-0.993), 0.868 (95% CI: 0.765-0.970), 0.846 (95% CI: 0.750-0.942), and 0.846 (95% CI: 0.735-0.957), respectively. The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful model. CONCLUSIONS: The DLRN comprised of CECT-derived DLS and subjective CT findings showed a high performance in predicting risk status of patients with TETs. CLINICAL RELEVANCE STATEMENT: Accurate risk status assessment of thymic epithelial tumors (TETs) may aid in determining whether preoperative neoadjuvant treatment is necessary. A deep learning radiomics nomogram incorporating enhancement CT-based deep learning features, clinical characteristics, and subjective CT findings has the potential to predict the histologic subtypes of TETs, which can facilitate decision-making and personalized therapy in clinical practice. KEY POINTS: • A non-invasive diagnostic method that can predict the pathological risk status may be useful for pretreatment stratification and prognostic evaluation in TET patients. • DLRN demonstrated superior performance in differentiating the risk status of TETs when compared to the deep learning signature, radiomics signature, or clinical model. • The DeLong test and decision in curve analysis revealed that the DLRN was the most predictive and clinically useful in differentiating the risk status of TETs.

Risk factors of temperature increase after cytoreductive surgery combined with hyperthermic intraperitoneal chemotherapy.

Background: Cytoreductive surgery combined with hyperthermic intraperitoneal chemotherapy (CRS-HIPEC) is the standard treatment for patients with peritoneal cancer (PC). Following CRS-HIPEC, patients may also face risks caused by whole body hyperthermia. This study analyzed the incidence of temperature increases following CRS-HIPEC and identified the attendant risk factors. Methods: A retrospective analysis was carried out among 458 patients who received CRS-HIPEC at the Fourth Hospital of Hebei Medical University between August 2018 and January 2021. The patients were divided into two groups according to post-HIPEC axillary temperature (≥38°C), with the demographics and the laboratory test results subsequently analyzed and compared, and the risk factors pertaining to temperature increases analyzed using univariate and multivariate logistic regression. Results: During CRS-HIPEC, 32.5% (149/458) of the patients with a temperature increase had an axillary temperature of not lower than 38°C, and 8.5% (39/458) of the patients with hyperpyrexia had an axillary temperature of not lower than 39°C. Female gender, gynecological malignancies, type of chemotherapy drug, increased postoperative neutrophil percentage, and a sharp drop in postoperative prealbumin were associated with the incidence of a temperature increase and axillary temperatures of >38°C. Among these factors, the type of chemotherapy drug was identified as an independent risk factor for a temperature increase during CRS-HIPEC. Conclusion: By determining the risk factors pertaining to temperature increases during CRS-HIPEC, medical staff can identify the attendant risks among the patients and thus take preventive measures in a timely manner to maintain the patient's body temperature at a stable level. This suggests that further clinical research should be conducted to build a risk-prediction model for temperature increases following CRS-HIPEC.

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning.

PURPOSE: This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs). METHODS: Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts. RESULTS: Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance. CONCLUSIONS: The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.

Enzastaurin cardiotoxicity: QT interval prolongation, negative inotropic responses and negative chronotropic action.

Several clinical trials observed that enzastaurin prolonged QT interval in cancer patients. However, the mechanism of enzastaurin-induced QT interval prolongation is unclear. Therefore, this study aimed to assess the effect and mechanism of enzastaurin on QT interval and cardiac function. The Langendorff and Ion-Optix MyoCam systems were used to assess the effects of enzastaurin on QT interval, cardiac systolic function and intracellular Ca2+ transient in guinea pig hearts and ventricular myocytes. The effects of enzastaurin on the rapid delayed rectifier (IKr), the slow delayed rectifier K+ current (IKs), transient outward potassium current (Ito), action potentials, Ryanodine Receptor 2 (RyR2) and the sarcoplasmic/endoplasmic reticulum Ca2+ ATPase 2a (SERCA2a) expression and activity in HEK 293 cell system and primary cardiomyocytes were investigated using whole-cell recording technique and western blotting. We found that enzastaurin significantly prolonged QT interval in guinea pig hearts and increased the action potential duration (APD) in guinea pig cardiomyocytes in a dose-dependent manner. Enzastaurin potently inhibited IKr by binding to the human Ether-à-go-go-Related gene (hERG) channel in both open and closed states, and hERG mutant channels, including S636A, S631A, and F656V attenuated the inhibitory effect of enzastaurin. Enzastaurin also moderately decreased IKs. Additionally, enzastaurin also induced negative chronotropic action. Moreover, enzastaurin impaired cardiac systolic function and reduced intracellular Ca2+ transient via inhibition of RyR2 phosphorylation. Taken together, we found that enzastaurin prolongs QT, reduces heart rate and impairs cardiac systolic function. Therefore, we recommend that electrocardiogram (ECG) and cardiac function should be continuously monitored when enzastaurin is administered to cancer patients.

Construction, Characterization, and Application of an Ammonium Transporter (AmtB) Deletion Mutant of the Nitrogen-Fixing Bacterium Kosakonia radicincitans GXGL-4A in Cucumis sativus L. Seedlings.

Nitrogen is an important factor affecting crop yield, but excessive use of chemical nitrogen fertilizer has caused decline in nitrogen utilization and soil and water pollution. Reducing the utilization of chemical nitrogen fertilizers by biological nitrogen fixation (BNF) is feasible for green production of crops. However, there are few reports on how to have more ammonium produced by nitrogen-fixing bacteria (NFB) flow outside the cell. In the present study, the amtB gene encoding an ammonium transporter (AmtB) in the genome of NFB strain Kosakonia radicincitans GXGL-4A was deleted and the △amtB mutant was characterized. The results showed that deletion of the amtB gene had no influence on the growth of bacterial cells. The extracellular ammonium nitrogen (NH4+) content of the △amtB mutant under nitrogen-free culture conditions was significantly higher than that of the wild-type strain GXGL-4A (WT-GXGL-4A), suggesting disruption of NH4+ transport. Meanwhile, the plant growth-promoting effect in cucumber seedlings was visualized after fertilization using cells of the △amtB mutant. NFB fertilization continuously increased the cucumber rhizosphere soil pH. The nitrate nitrogen (NO3-) content in soil in the △amtB treatment group was significantly higher than that in the WT-GXGL-4A treatment group in the short term but there was no difference in soil NH4+ contents between groups. Soil enzymatic activities varied during a 45-day assessment period, indicating that △amtB fertilization influenced soil nitrogen cycling in the cucumber rhizosphere. The results will provide a solid foundation for developing the NFB GXGL-4A into an efficient biofertilizer agent.

Distinguishing common renal cell carcinomas from benign renal tumors based on machine learning: comparing various CT imaging phases, slices, tumor sizes, and ROI segmentation strategies.

OBJECTIVES: To determine whether a CT-based machine learning (ML) can differentiate benign renal tumors from renal cell carcinomas (RCCs) and improve radiologists' diagnostic performance, and evaluate the impact of variable CT imaging phases, slices, tumor sizes, and region of interest (ROI) segmentation strategies. METHODS: Patients with pathologically proven RCCs and benign renal tumors from our institution between 2008 and 2020 were included as the training dataset for ML model development and internal validation (including 418 RCCs and 78 benign tumors), and patients from two independent institutions and a public database (TCIA) were included as the external dataset for individual testing (including 262 RCCs and 47 benign tumors). Features were extracted from three-phase CT images. CatBoost was used for feature selection and ML model establishment. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of the ML model. RESULTS: The ML model based on 3D images performed better than that based on 2D images, with the highest AUC of 0.81 and accuracy (ACC) of 0.86. All three radiologists achieved better performance by referring to the classifier's decision, with accuracies increasing from 0.82 to 0.87, 0.82 to 0.88, and 0.76 to 0.87. The ML model achieved higher negative predictive values (NPV, 0.82-0.99), and the radiologists achieved higher positive predictive values (PPV, 0.91-0.95). CONCLUSIONS: A ML classifier based on whole-tumor three-phase CT images can be a useful and promising tool for differentiating RCCs from benign renal tumors. The ML model also perfectly complements radiologist interpretations. KEY POINTS: • A machine learning classifier based on CT images could be a reliable way to differentiate RCCs from benign renal tumors. • The machine learning model perfectly complemented the radiologists' interpretations. • Subtle variances in ROI delineation had little effect on the performance of the ML classifier.