Predicting lymphovascular invasion in non-small cell lung cancer using deep convolutional neural networks on preoperative chest CT.

RATIONALE AND OBJECTIVES: Lymphovascular invasion (LVI) plays a significant role in precise treatments of non-small cell lung cancer (NSCLC). This study aims to build a non-invasive LVI prediction diagnosis model by combining preoperative CT images with deep learning technology. MATERIALS AND METHODS: This retrospective observational study included a series of consecutive patients who underwent surgical resection for non-small cell lung cancer (NSCLC) and received pathologically confirmed diagnoses. The cohort was randomly divided into a training group comprising 70 % of the patients and a validation group comprising the remaining 30 %. Four distinct deep convolutional neural network (DCNN) prediction models were developed, incorporating different combination of two-dimensional (2D) and three-dimensional (3D) CT imaging features as well as clinical-radiological data. The predictive capabilities of the models were evaluated by receiver operating characteristic curves (AUC) values and confusion matrices. The Delong test was utilized to compare the predictive performance among the different models. RESULTS: A total of 3034 patients with NSCLC were recruited in this study including 106 LVI+ patients. In the validation cohort, the Dual-head Res2Net_3D23F model achieved the highest AUC of 0.869, closely followed by the models of Dual-head Res2Net_3D3F (AUC, 0.868), Dual-head Res2Net_3D (AUC, 0.867), and EfficientNet-B0_2D (AUC, 0.857). There was no significant difference observed in the performance of the EfficientNet-B0_2D model when compared to the Dual-head Res2Net_3D3F and Dual-head Res2Net_3D23F. CONCLUSION: Findings of this study suggest that utilizing deep convolutional neural network is a feasible approach for predicting pathological LVI in patients with NSCLC.

Overexpression of NtEXPA7 promotes seedling growth and resistance to root-knot nematode in tobacco.

Root-knot nematode (RKN) is one of the most damaging plant pathogen in the world. They exhibit a wide host range and cause serious crop losses. The cell wall, encasing every plant cell, plays a crucial role in defending of RKN invasion. Expansins are a group of cell wall proteins inducing cell wall loosening and extensibility. They are widely involved in the regulation of plant growth and the response to biotic and abiotic stresses. In this study, we have characterized the biological function of tobacco (Nicotiana tabacum) NtEXPA7, the homologue of Solyc08g080060.2 (SlEXPA18), of which the transcription level was significantly reduced in susceptible tomato upon RKN infection. The expression of NtEXPA7 was up-regulated after inoculation of RKNs. The NtEXPA7 protein resided in the cell wall. Overexpression of NtEXPA7 promoted the seedling growth of transgenic tobacco. Meanwhile the increased expression of NtEXPA7 was beneficial to enhance the resistance against RKNs. This study expands the understanding of biological role of expansin in coordinate plant growth and disease resistance.

Convolutional neural network applied to preoperative venous-phase CT images predicts risk category in patients with gastric gastrointestinal stromal tumors.

OBJECTIVE: The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs. METHOD: A total of 425 patients pathologically diagnosed with gastric GISTs at the authors' medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models. RESULTS: In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05). CONCLUSIONS: The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs.

Radiomics analysis of contrast-enhanced computerized tomography for differentiation of gastric schwannomas from gastric gastrointestinal stromal tumors.

PURPOSE: To assess the performance of radiomics-based analysis of contrast-enhanced computerized tomography (CE-CT) images for distinguishing GS from gastric GIST. METHODS: Forty-nine patients with GS and two hundred fifty-three with GIST were enrolled in this retrospective study. CT features were evaluated by two associate chief radiologists. Radiomics features were extracted from portal venous phase images using Pyradiomics software. A non-radiomics dataset (combination of clinical characteristics and radiologist-determined CT features) and a radiomics dataset were used to build stepwise logistic regression and least absolute shrinkage and selection operator (LASSO) logistic regression models, respectively. Model performance was evaluated according to sensitivity, specificity, accuracy, and receiver operating characteristic (ROC) curve, and Delong's test was applied to compare the area under the curve (AUC) between different models. RESULTS: A total of 1223 radiomics features were extracted from portal venous phase images. After reducing dimensions by calculating Pearson correlation coefficients (PCCs), 20 radiomics features, 20 clinical characteristics + CT features were used to build the models, respectively. The AUC values for the models using radiomics features and those using clinical features were more than 0.900 for both the training and validation groups. There were no significant differences in predictive performance between the radiomic and clinical data models according to Delong's test. CONCLUSION: A radiomics-based model applied to CE-CT images showed comparable predictive performance to senior physicians in the differentiation of GS from GIST.

Cutoff value of IC50 for drug sensitivity in patient-derived tumor organoids in colorectal cancer.

Patient-derived tumor organoids (PDTOs) have the potential to be used to predict the patient response to chemotherapy. However, the cutoff value of the half-maximal inhibition concentration (IC50) for PDTO drug sensitivity has not been validated with clinical cohort data. We established PDTOs and performed a drug test in 277 samples from 242 CRC patients who received FOLFOX or XELOX chemotherapy. After follow-up and comparison of the PDTO drug test and final clinical outcome results, the optimal IC50 cutoff value for PDTO drug sensitivity was 43.26 µmol/L. This PDTO drug test-defined cutoff value could predict patient response with 75.36% sensitivity, 74.68% specificity, and 75% accuracy. Moreover, this value distinguished groups of patients with significant differences in survival benefit. Our study is the first to define the IC50 cutoff value for the PDTO drug test to effectively distinguish CRC patients with chemosensitivity or nonsensitivity and predict survival benefits.

Use of Carbon Nanoparticles to Improve the Efficiency of Harvesting Lymph Nodes in Rectal Cancer.

BACKGROUND: The accurate determination of lymph node status in patients with rectal cancer requires harvesting a certain number of lymph nodes. This study investigated whether using carbon nanoparticles (CNs) could improve the efficiency of harvesting lymph nodes in rectal cancer patients. MATERIALS AND METHODS: Data from patients with rectal cancer treated with radical resection were collected from Nanfang Hospital between January 2014 and June 2021. Patients in the CN group received a CN suspension 1 day before surgery, which was endoscopically injected around the tumor. A 1:1 case-matched study was performed using the propensity score. The efficiency of harvesting lymph nodes was investigated by comparing the number of total nodes, total time, and percentage of nodes <5 mm in size between the CN and non-CN groups. RESULTS: A total of 768 patients were included, with 246 patients who underwent CN injection and 522 patients who did not. After matching, 246 pairs of patients were analyzed. After matching, the number of total nodes of each sample was significantly higher in the CN group than in the non-CN group ( P <0.001). The total time for node detection ( P <0.001) was significantly shorter in the CN group. The percentage of nodes <5 mm in size was increased significantly in the CN group ( P <0.001). Among patients with clinical staging I/II, the difference in positive LNs was significant (21.79% vs. 11.95%, P =0.029). CONCLUSIONS: The application of CNs improved the efficiency of harvesting lymph nodes during rectal cancer surgery.

Activation of Sphingomyelin Phosphodiesterase 3 in Liver Regeneration Impedes the Progression of Colorectal Cancer Liver Metastasis Via Exosome-Bound Intercellular Transfer of Ceramides.

BACKGROUND & AIMS: The machinery that prevents colorectal cancer liver metastasis (CRLM) in the context of liver regeneration (LR) remains elusive. Ceramide (CER) is a potent anti-cancer lipid involved in intercellular interaction. Here, we investigated the role of CER metabolism in mediating the interaction between hepatocytes and metastatic colorectal cancer (CRC) cells to regulate CRLM in the context of LR. METHODS: Mice were intrasplenically injected with CRC cells. LR was induced by 2/3 partial hepatectomy (PH) to mimic the CRLM in the context of LR. The alteration of corresponding CER-metabolizing genes was examined. The biological roles of CER metabolism in vitro and in vivo were examined by performing a series of functional experiments. RESULTS: Induction of LR augmented apoptosis but promoted matrix metalloproteinase 2 (MMP2) expression and epithelial-mesenchymal transition (EMT) to increase the invasiveness of metastatic CRC cells, resulting in aggressive CRLM. Up-regulation of sphingomyelin phosphodiesterase 3 (SMPD3) was determined in the regenerating hepatocytes after LR induction and persisted in the CRLM-adjacent hepatocytes after CRLM formation. Hepatic Smpd3 knockdown was found to further promote CRLM in the context of LR by abolishing mitochondrial apoptosis and augmenting the invasiveness in metastatic CRC cells by up-regulating MMP2 and EMT through promoting the nuclear translocation of ß-catenin. Mechanistically, we found that hepatic SMPD3 controlled the generation of exosomal CER in the regenerating hepatocytes and the CRLM-adjacent hepatocytes. The SMPD3-produced exosomal CER critically conducted the intercellular transfer of CER from the hepatocytes to metastatic CRC cells and impeded CRLM by inducing mitochondrial apoptosis and restricting the invasiveness in metastatic CRC cells. The administration of nanoliposomal CER was found to suppress CRLM in the context of LR substantially. CONCLUSIONS: SMPD3-produced exosomal CER constitutes a critical anti-CRLM mechanism in LR to impede CRLM, offering the promise of using CER as a therapeutic agent to prevent the recurrence of CRLM after PH.

Development and validation of a collagen signature to predict the prognosis of patients with stage II/III colorectal cancer.

The tumor, nodes and metastasis (TNM) classification system provides useful but incomplete prognostic information and lacks the assessment of the tumor microenvironment (TME). Collagen, the main component of the TME extracellular matrix, plays a nonnegligible role in tumor invasion and metastasis. In this cohort study, we aimed to develop and validate a TME collagen signature (CSTME) for prognostic prediction of stage II/III colorectal cancer (CRC) and to compare the prognostic values of "TNM stage + CSTME" with that of TNM stage alone. Results indicated that the CSTME was an independent prognostic risk factor for stage II/III CRC (hazard ratio: 2.939, 95% CI: 2.180-3.962, p < 0.0001), and the integration of the TNM stage and CSTME had a better prognostic value than that of the TNM stage alone (AUC(TNM+CSTME) = 0.772, AUC TNM = 0.687, p < 0.0001). This study provided an application of "seed and soil" strategy for prognosis prediction and individualized therapy.

A Clinicopathological Feature-Based Nomogram for Predicting the Likelihood of D3 Lymph Node Metastasis in Right-Sided Colon Cancer Patients.

BACKGROUND: Despite advancements in treating right-sided colon cancer patients, the ideal scope of lymphadenectomy remains controversial. OBJECTIVE: Our objective was to investigate the likelihood of D3 lymph node metastasis in right-sided colon cancer patients and develop a clinicopathological feature-based nomogram for D3 lymphadenectomy. DESIGN: We retrospectively analyzed 286 right-sided colon cancer patients who underwent D3 lymphadenectomy. The patients were divided into 2 groups based on whether D3 lymph node metastasis was positive. Then, univariable and multivariable logistic regression analyses were performed to obtain independent risk factors for predicting D3 lymph node metastasis. Moreover, we performed receiver operating characteristic curve analyses to evaluate the predictive power of the model. SETTING: This study was conducted at Nanfang Hospital of Southern Medical University in China. PATIENTS: A total of 286 consecutive patients who underwent right hemicolectomy and D3 lymphadenectomy as a primary treatment for right-sided colon cancer between January 2016 and December 2019 were enrolled in this study. MAIN OUTCOME MEASURES: The primary measures were independent risk factors for predicting D3 lymph node metastasis in right-sided colon cancer. RESULTS: The D3 lymph node metastasis rate in right-sided colon cancer patients was 16.1% (46/286). D3 lymphadenectasis on CT, lymphatic invasion, and T4 tumors were filtered out as independent risk factors for D3 lymph node metastasis according to the multivariable logistic regression analysis. We established a nomogram that predicted D3 lymph node metastasis of right-sided colon cancer on the combination of the 3 factors with an area under the curve of 0.717 (95% CI, 0.629-0.806). LIMITATIONS: This was a retrospective study from a single center. CONCLUSIONS: We developed a valuable clinicopathological feature-based nomogram to predict the incidence of D3 lymph node metastasis in right-sided colon cancer patients. Patients with D3 lymphadenectasis on CT, preoperative T4 tumors, and lymphatic invasion should undergo D3 lymphadenectomy. See Video Abstract at http://links.lww.com/DCR/B852 . UN NOMOGRAMA BASADO EN CARACTERSTICAS CLNICOPATOLGICAS PARA PREDECIR LA PROBABILIDAD DE METSTASIS EN GANGLIOS LINFTICOS D EN PACIENTES CON CNCER DE COLON DERECHO: ANTECEDENTES:A pesar de los avances en el tratamiento de pacientes con cáncer de colon derecho, el ámbito ideal de la linfadenectomía sigue siendo controvertido.OBJETIVO:Investigar la probabilidad de metástasis en los ganglios linfáticos D3 en pacientes con cáncer de colon derecho y desarrollar un nomograma basado en características clínico-patológicas basado para la linfadenectomía D3.DISEÑO:Analizamos retrospectivamente a 286 pacientes con cáncer de colon derecho que se sometieron a linfadenectomía D3. Los pacientes se dividieron en dos grupos en función de si eran positivos para metástasis en los ganglios linfáticos D3. Luego, se realizaron análisis de regresión logística univariable y multivariable para obtener factores de riesgo independientes para predecir metástasis en los ganglios linfáticos D3. Además, realizamos análisis de las curvas de características operatorias del receptor para evaluar el poder predictivo del modelo.SEDE:Este estudio se realizó en el Hospital Nanfang de la Universidad Médica del Sur en China.PACIENTES:Un total de 286 pacientes consecutivos que se sometieron a hemicolectomía derecha y linfadenectomía D3 como tratamiento primario para el cáncer de colon derecho entre enero de 2016 y diciembre de 2019 se inscribieron en este estudio.PRINCIPALES MEDIDAS DE RESULTADO:Las medidas primarias fueron factores de riesgo independientes para predecir las metástasis en ganglios linfáticos D3 en el cáncer de colon derecho.RESULTADOS:La tasa de metástasis en los ganglios linfáticos D3 en pacientes con cáncer de colon del lado derecho fue del 16,1% (46/286). El aumento de tamaño de ganglios D3 en la TC, la invasión linfática y los tumores T4 se filtraron como factores de riesgo independientes de metástasis en los ganglios linfáticos D3 de acuerdo con el análisis de regresión logística multivariable. Establecimos un nomograma que predijo metástasis en los ganglios linfáticos D3 del cáncer de colon derecho en la combinación de los tres factores con un área bajo la curva de 0,717 (IC del 95%, 0,629-0,806).LIMITACIONES:Este fue un estudio retrospectivo de un solo centro.CONCLUSIONES:Desarrollamos un valioso nomograma basado en características clínico-patológicas para predecir la incidencia de metástasis en los ganglios linfáticos D3 en pacientes con cáncer de colon derecho. Los pacientes con crecimiento de ganglios D3 en TC, tumores con clasificación preoperatoria T4 e invasión linfática, deben ser sometidos a linfadenectomía D3. Consulte Video Resumen en http://links.lww.com/DCR/B852 . (Traducción-Dr. Juan Carlos Reyes ).

Indocyanine green for radical lymph node dissection in patients with sigmoid and rectal cancer: randomized clinical trial.

BACKGROUND: D3 lymph node dissection is recommended for patients with advanced sigmoid and rectal cancer in Japan. This trial aimed to investigate the feasibility of indocyanine green (ICG) as a tracer to increase the nodal harvest during D3 lymph node dissection in patients with sigmoid and rectal cancer. METHODS: This prospective randomized clinical trial was performed between May 2021 and April 2022. The inclusion criteria were patients with stage I-III sigmoid or rectal cancer eligible for laparoscopic resection. Patients were 1: 1 randomized to either the ICG group (endoscopic ICG injection at the tumour site and intraoperative imaging to guide dissection) or the control group (routine laparoscopic white-light imaging). All patients were treated with D3 dissection, and the primary outcome was the number of harvested lymph nodes at the D3 level. RESULTS: Out of 210 patients screened, a total of 66 patients were enrolled and randomized. Patients in the two groups presented similar ages and clinical stages (ICG group versus control group, median age of 58.0 versus 58.5 years; stage III 36.4 per cent versus 36.4 per cent, whereas the rate of rectal cancer was 27.3 per cent versus 48.5 per cent respectively). ICG imaging was helpful for completely dissecting D3 lymph nodes and could identify a median of more than 2 (range 1-6) D3 lymph nodes neglected by routine laparoscopic white-light imaging during surgery. The median number of D3 lymph nodes harvested in the ICG group was significantly higher than that in the control group (7.0 versus 5.0, P = 0.003); however, there was no significant difference in the median numbers of positive D1, D2, and D3 lymph nodes between the two groups. CONCLUSION: ICG is safe and feasible to guide D3 lymph node dissection and can increase the number of harvested D3 lymph nodes in patients with sigmoid and rectal cancer. Registration number: NCT04848311 (http://www.clinicaltrials.gov).

In vivo real-time assessment of the anastomotic blood supply in colorectal surgery using confocal laser endomicroscopy in an anastomotic model.

BACKGROUND AND STUDY AIMS: Anastomotic ischemia can affect healing and eventually lead to anastomotic leakage, and confocal laser endomicroscopy (CLE) can offer detailed observations at the subcellular level. We aimed to evaluate the anastomotic microcirculation in different anastomotic perfusion models using CLE. METHODS: Anastomotic perfusion models were established using twelve rabbits distributed into two groups: group A (good perfusion, n = 6) and group B (poor perfusion, n = 6). Afterward, intraoperative detection of anastomotic perfusion was carried out using CLE, and quantitative analysis of blood cells was performed. Rabbits that satisfied the criteria underwent a second exploratory operation and specimens were stained by hematoxylin and eosin. RESULTS: Enhanced with fluorescein sodium, capillaries were obviously highlighted in group A, while few capillaries were viewed in group B. Delayed development of fluorescence occurred in group B. The average flow of blood cells was 37.0 ± 5.93 per minute in group A and 6.33 ± 2.16 per minute in group B (p < 0.001). In addition, during the second exploratory surgery, rabbits with inadequate anastomotic perfusion exhibited more serious intestinal adhesion and ischemia. Anastomotic leakage and abdominal infection occurred in all rabbits in group B. CONCLUSION: CLE can realize real-time imaging of the anastomotic microcirculation and is a feasible technique for performing intraoperative evaluation in different anastomotic perfusion situations. This animal experiment provides the groundwork for future in vivo research in humans.

Real-time in vivo distal margin selection using confocal laser endomicroscopy in transanal total mesorectal excision for rectal cancer.

BACKGROUND: Transanal total mesorectal excision (TaTME) allows patients with ultralow rectal cancer to be treated with sphincter-saving surgery. However, accurate delineation of the distal resection margin (DRM), which is essential to achieve R0 resection for low rectal cancer in TaTME, is technically demanding. AIM: To assess the feasibility of optical biopsy using probe-based confocal laser endomicroscopy (pCLE) to select the DRM during TaTME for low rectal cancer. METHODS: A total of 43 consecutive patients who were diagnosed with low rectal cancer and scheduled for TaTME were prospectively enrolled from January 2019 to January 2021. pCLE was used to determine the distal edge of the tumor as well as the DRM during surgery. The final pathological report was used as the gold standard. The diagnostic accuracy of pCLE examination was calculated. RESULTS: A total of 86 pCLE videos of 43 patients were included in the analyses. The sensitivity, specificity and accuracy of real-time pCLE examination were 90.00% [95% confidence interval (CI): 76.34%-97.21%], 86.96% (95%CI: 73.74%-95.06%) and 88.37% (95%CI: 79.65%-94.28%), respectively. The accuracy of blinded pCLE reinterpretation was 86.05% (95%CI: 76.89%-92.58%). Furthermore, our results show satisfactory interobserver agreement (κ = 0.767, standard error = 0.069) for the detection of cancer tissue by pCLE. There were no positive DRMs (≤ 1 mm) in this study. The median DRM was 7 mm [interquartile range (IQR) = 5-10 mm]. The median Wexner score was 5 (IQR = 3-6) at 6 mo after stoma closure. CONCLUSION: Real-time in vivo pCLE examination is feasible and safe for selecting the DRM during TaTME for low rectal cancer (clinical trial registration number: NCT04016948).

Salicylic Acid, Jasmonate, and Ethylene Contribute to Rice Defense Against White Tip Nematodes Aphelenchoides besseyi.

Plant hormones have a prominent place in the plant immune and defense mechanism. To gain more information about the plant hormone pathways involved in rice defense against nematodes, here, we studied the roles of three core hormones, namely, salicylic acid (SA), jasmonate (JA), and ethylene (ET) in rice defense to Aphelenchoides besseyi by using the susceptible variety, Nipponbare as well as the resistant variety Tetep. The data showed that Tetep exhibited pre- and post-invasion with suppression of nematode infection, development, and reproduction. The quantitative real-time (qRT)-PCR analysis of plant hormone marker genes in the two cultivars clearly revealed that all the SA-related genes were downregulated in susceptible Nipponbare plants but were significantly upregulated in resistant Tetep plants at the flowering stage. The exogenous application of the SA analog, benzo-1,2,3-thiadiazole-7-carbothioic acid S-methyl ester (BTH), methyl jasmonate (MeJA), and ethephon did induce rice resistance to A. besseyi, and the rice plants treated by hormone inhibitors increased susceptibility to A. besseyi. Similarly, corresponding transgenic biosynthesis or signaling mutants of those hormones also showed an increased susceptibility. Collectively, these results suggest that SA, JA, and ET play important defense roles in rice against A. besseyi.

Differentiation of gastric schwannomas from gastrointestinal stromal tumors by CT using machine learning.

OBJECTIVE: To identify schwannomas from gastrointestinal stromal tumors (GISTs) by CT features using Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT). METHODS: This study enrolled 49 patients with schwannomas and 139 with GISTs proven by pathology. CT features with P < 0.1 derived from univariate analysis were inputted to four models. Five machine learning (ML) versions, multivariate analysis, and radiologists' subjective diagnostic performance were compared to evaluate diagnosis performance of all the traditional and advanced methods. RESULTS: The CT features with P < 0.1 were as follows: (1) CT attenuation value of unenhancement phase (CTU), (2) portal venous enhancement (CTV), (3) degree of enhancement in the portal venous phase (DEPP), (4) CT attenuation value of portal venous phase minus arterial phase (CTV-CTA), (5) enhanced potentiality (EP), (6) location, (7) contour, (8) growth pattern, (9) necrosis, (10) surface ulceration, (11) enlarged lymph node (LN). LR (M1), RF, DT, and GBDT models contained all of the above 11 variables, while LR (M2) was developed using six most predictive variables derived from (M1). LR (M2) model with AUC of 0.967 in test dataset was thought to be optimal model in differentiating the two tumors. Location in gastric body, exophytic and mixed growth pattern, lack of necrosis and surface ulceration, enlarged lymph nodes, and larger EP were the most important CT features suggestive of schwannomas. CONCLUSION: LR (M2) provided the optimal diagnostic potency among other ML versions, multivariate analysis, and radiologists' performance on differentiation of schwannomas from GISTs.

Correcting and reweighting false label masks in brain tumor segmentation.

PURPOSE: Recently, brain tumor segmentation has made important progress. However, the quality of manual labels plays an important role in the performance, while in practice, it could vary greatly and in turn could substantially mislead the learning process and decrease the accuracy. We need to design a mechanism to combine label correction and sample reweighting to improve the effectiveness of brain tumor segmentation. METHODS: We propose a novel sample reweighting and label refinement method, and a novel three-dimensional (3D) generative adversarial network (GAN) is introduced to combine these two models into an united framework. RESULTS: Extensive experiments on the BraTS19 dataset have demonstrated that our approach obtains competitive results when compared with other state-of-the-art approaches when handling the false labels in brain tumor segmentation. CONCLUSIONS: The 3D GAN-based approach is an effective approach to handle false label masks by simultaneously applying label correction and sample reweighting. Our method is robust to variations in tumor shape and background clutter.

Spatial-channel relation learning for brain tumor segmentation.

PURPOSE: Recently, research on brain tumor segmentation has made great progress. However, ambiguous patterns in magnetic resonance imaging data and linear fusion omitting semantic gaps between features in different branches remain challenging. We need to design a mechanism to fully utilize the similarity within the spatial space and channel space and the correlation between these two spaces to improve the result of volumetric segmentation. METHODS: We propose a revised cascade structure network. In each subnetwork, a context exploitation module is introduced between the encoder and decoder, in which the dual attention mechanism is adopted to learn the information within the spatial space and channel space, and space interaction learning is employed to model the relation between the spatial and channel spaces. RESULTS: Extensive experiments on the BraTS19 dataset have evaluated that our approach improves the dice coefficient (DC) by a margin of 2.1, 2.0, and 1.4 for whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively, obtaining results competitive with the state-of-art approaches working on brain tumor segmentation. CONCLUSIONS: Context exploitation in the embedding feature spaces, including intraspace relations and interspace relations, can effectively model dependency in semantic features and alleviate the semantic gap in multimodel data. Our approach is also robust to variations in different modality.

Thiamine-induced priming against root-knot nematode infection in rice involves lignification and hydrogen peroxide generation.

Thiamine (vitamin B1, VB1) can act as a plant defence trigger, or priming agent, leading to a rapid counterattack on pathogen invasion. In this study, the priming effect of thiamine on rice (Oryza sativa cv. Nipponbare) and its activity against root-knot nematode (Meloidogyne graminicola) infection were evaluated. Thiamine treatment and subsequent nematode inoculation activated hydrogen peroxide (H2O2) accumulation and lignin deposition in plant roots, and this correlated with enhanced transcription of OsPAL1 and OsC4H, two genes involved in the phenylpropanoid pathway. The number of nematodes in rice roots was slightly but significantly reduced, and the development of the nematodes was delayed, whereas no direct toxic effects of VB1 on nematode viability and infectivity were observed. The combined application of thiamine with l-2-aminooxy-3-phenylpropionic acid (AOPP), an inhibitor of phenylalanine ammonia-lyase (PAL), significantly hampered the VB1-priming capacity. These findings indicate that thiamine-induced priming in rice involves H2O2 and phenylpropanoid-mediated lignin production, which hampers nematode infection. Further cellular and molecular studies on the mechanism of thiamine-induced defence will be useful for the development of novel nematode control strategies.