scholarly journals Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival

2020 ◽  
Vol 162 (12) ◽  
pp. 3067-3080
Author(s):  
Yizhou Wan ◽  
Roushanak Rahmat ◽  
Stephen J. Price
Keyword(s):  
Neural Network ◽  
Overall Survival ◽  
Convolutional Neural Network ◽  
Multiple Testing ◽  
Network Performance ◽  
Cox Regression ◽  
Prognostic Significance ◽  
Ground Truth ◽  
Cox Regression Analysis ◽  
Volumetric Features

Abstract Background Measurement of volumetric features is challenging in glioblastoma. We investigate whether volumetric features derived from preoperative MRI using a convolutional neural network–assisted segmentation is correlated with survival. Methods Preoperative MRI of 120 patients were scored using Visually Accessible Rembrandt Images (VASARI) features. We trained and tested a multilayer, multi-scale convolutional neural network on multimodal brain tumour segmentation challenge (BRATS) data, prior to testing on our dataset. The automated labels were manually edited to generate ground truth segmentations. Network performance for our data and BRATS data was compared. Multivariable Cox regression analysis corrected for multiple testing using the false discovery rate was performed to correlate clinical and imaging variables with overall survival. Results Median Dice coefficients in our sample were (1) whole tumour 0.94 (IQR, 0.82–0.98) compared to 0.91 (IQR, 0.83–0.94 p = 0.012), (2) FLAIR region 0.84 (IQR, 0.63–0.95) compared to 0.81 (IQR, 0.69–0.8 p = 0.170), (3) contrast-enhancing region 0.91 (IQR, 0.74–0.98) compared to 0.83 (IQR, 0.78–0.89 p = 0.003) and (4) necrosis region were 0.82 (IQR, 0.47–0.97) compared to 0.67 (IQR, 0.42–0.81 p = 0.005). Contrast-enhancing region/tumour core ratio (HR 4.73 [95% CI, 1.67–13.40], corrected p = 0.017) and necrotic core/tumour core ratio (HR 8.13 [95% CI, 2.06–32.12], corrected p = 0.011) were independently associated with overall survival. Conclusion Semi-automated segmentation of glioblastoma using a convolutional neural network trained on independent data is robust when applied to routine clinical data. The segmented volumes have prognostic significance.

scholarly journals A Comprehensive Prognostic and Immune Analysis of SLC41A3 in Pan-Cancer

2021 ◽  
Vol 10 ◽  
Author(s):  
Jun Liu ◽  
Shanqiang Zhang ◽  
Wenjie Dai ◽  
Chongwei Xie ◽  
Ji-Cheng Li
Keyword(s):  
Overall Survival ◽  
Immune Cells ◽  
Cox Regression ◽  
Expression Profiles ◽  
Prognostic Significance ◽  
Cancer Genome ◽  
The Cancer Genome Atlas ◽  
Cancer Prognosis ◽  
Cox Regression Analysis ◽  
Pan Cancer

SLC41A3, as a member of the 41st family of solute carriers, participates in the transport of magnesium. The role of SLC41A3 in cancer prognosis and immune regulation has rarely been reported. This study was designed to analyze the expression status and prognostic significance of SLC41A3 in pan-cancers. The mRNA expression profiles of SLC41A3 were obtained from The Cancer Genome Atlas (TCGA), the Genotype-Tissue Expression (GTEx), the Broad Institute Cancer Cell Line Encyclopedia (CCLE), and the International Cancer Genome Consortium (ICGC). The Cox regression and Kaplan-Meier analyses were used to evaluate the prognostic value of SLC41A3 in pan-cancer. Furthermore, the correlation between SLC41A3 expression and immune cells infiltration, immune checkpoint, mismatch repair (MMR), DNA methyltransferase (DNMT), tumor mutation burden (TMB), and microsatellite instability (MSI) were calculated using data form TCGA database. The results showed that the expression of SLC41A3 was down-regulated in kidney renal clear cell carcinoma (KIRC), and was associated with poor overall survival and tumor-specific mortality. Whereas, the expression of SLC41A3 was up-regulated in liver hepatocellular carcinoma (LIHC), and the results of Cox regression analysis revealed that SLC41A3 was an independent factor for LIHC prognosis. Meanwhile, a nomogram including SLC41A3 and stage was built and exhibited good predictive power for the overall survival of LIHC patients. Additionally, correlation analysis suggested a significant correlation between SLC41A3 and TMB, MSI, MMR, DNMT, and immune cells infiltration in various cancers. The overall survival and disease-specific survival analysis revealed that the combined SLC41A3 expression and immune cell score, TMB, and MSI were significantly associated with clinical outcomes in ACC, LIHC, and UVM patients. Therefore, we proposed that SLC41A3 may serve as a potential prognostic biomarker for cancer.

scholarly journals Construction of a novel ferroptosis-related gene signature for predicting prognosis and immune microenvironment in acute myeloid leukemia

2021 ◽  
Author(s):  
Xianbo Huang ◽  
De Zhou ◽  
Xiujin Ye ◽  
Jie Jin
Keyword(s):  
Overall Survival ◽  
Acute Myeloid Leukemia ◽  
Myeloid Leukemia ◽  
Risk Model ◽  
Cox Regression ◽  
Prognostic Significance ◽  
Risk Groups ◽  
Low Risk ◽  
Cox Regression Analysis ◽  
Acute Myeloid

Acute myeloid leukemia (AML) is a highly heterogeneous hematopoietic malignancy that strongly correlates with poor clinical outcomes. Ferroptosis is an iron-dependent, non-apoptotic form of regulated cell death which plays an important role in various human cancers. Nevertheless, the prognostic significance and functions of ferroptosis-related genes (FRGs) in AML have not received sufficient attention. The aim of this article was to evaluate the association between FRGs levels and AML prognosis using publicly available RNA-sequencing datasets. The univariate Cox regression analysis identified 20 FRGs that correlate with patient overall survival. The LASSO Cox regression model was used to construct a prognostic 12-gene risk model using a TCGA cohort, and internal and external validation proved the signature efficient. The 12-FRGs signature was then used to assign patients into high- and low-risk groups, with the former exhibiting markedly reduced overall survival, compared to the low-risk group. ROC curve analysis verified the predictive ability of the risk model. Functional analysis showed that immune status and drug sensitivity differed between the 2 risk groups. In summary, FRGs is a promising candidate biomarker and therapeutic target for AML.

Prognostic Significance of Clusterin Expression in Advanced-Stage Cervical Cancer Treated With Curative Intended Radiotherapy

2012 ◽  
Vol 22 (3) ◽  
pp. 465-470 ◽  
Author(s):  
Hidemichi Watari ◽  
Rumiko Kinoshita ◽  
Yimin Han ◽  
Lei Wang ◽  
Masayoshi Hosaka ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Overall Survival ◽  
Prognostic Factors ◽  
Cox Regression ◽  
Univariate Analysis ◽  
Prognostic Significance ◽  
Advanced Stage ◽  
Histologic Type ◽  
Clinicopathological Factors ◽  
Cox Regression Analysis

ObjectiveOverexpression of clusterin (CLU), an antiapoptotic molecule, has been reported to induce resistance to radiotherapy (RT) in a variety of cancer cell types. The aim of this study was to evaluate the significance of CLU expression to predict survival of patients with advanced-stage cervical cancer who received curative intended RT.MethodsBiopsy tissue specimens of advanced-stage cervical cancer before curative intended RT were obtained from 34 patients who were treated at Hokkaido University Hospital between 1998 and 2008 and whose complete medical records were available. The expression of CLU protein was analyzed by immunohistochemistry. Findings were evaluated in relation to several clinicopathological factors. Survival analyses were performed using the Kaplan-Meier curves and the log-rank test. Independent prognostic factors were determined by multivariate Cox regression analysis.ResultsClusterin protein was mainly present in the cytoplasm of cervical cancer cells. The expression of CLU protein in cervical cancer tissues before curative intended RT was not significantly related to any clinicopathological factors analyzed, including age, clinical stage, histologic type, and response to RT. Univariate analysis on prognostic factors showed that histologic type (P= 0.001), and CLU expression (P= 0.02) were related to survival. Multivariate analysis revealed that both histologic type (P= 0.002), and CLU expression (P= 0.02) were independent prognostic factors for overall survival.ConclusionWe conclude that CLU could be a new molecular marker to predict overall survival of patients with advanced-stage cervical cancer treated with curative intended RT.

scholarly journals Prognostic value of the albumin–globulin ratio and albumin–globulin score in patients with multiple myeloma

2021 ◽  
Vol 49 (3) ◽  
pp. 030006052199773
Author(s):  
Ying Cai ◽  
Yu Zhao ◽  
Qiuxin Dai ◽  
Maozhong Xu ◽  
Xin Xu ◽  
...  
Keyword(s):  
Multiple Myeloma ◽  
Overall Survival ◽  
Prognostic Value ◽  
Cox Regression ◽  
Characteristic Curve ◽  
Prognostic Significance ◽  
Progression Free Survival ◽  
Free Survival ◽  
Cox Regression Analysis ◽  
Kaplan Meier

Objective The albumin–globulin ratio (AGR) has been identified as a promising prognostic predictor of mortality in patients with hematological malignancies. This study investigated the prognostic significance of AGR in patients with multiple myeloma. Methods Two hundred patients diagnosed with multiple myeloma from January 2010 to October 2018 were retrospectively analyzed and followed up until December 2019. Kaplan–Meier curves and multivariate Cox regression analysis were applied to detect the prognostic value of AGR. Results The median follow-up period was 36 months. The optimal cutoff of AGR was 1.16 according to receiver operating characteristic curve analysis. High AGR was significantly correlated with better overall survival (OS) and progression-free survival (PFS). Multivariate analysis revealed that low AGR was an independent prognostic factor for worse OS (hazard ratio [HR] = 1.82, 95% confidence interval [CI] = 1.15–2.94) and PFS (HR = 1.53, 95% CI = 1.09–2.17). Conclusions AGR may represent a potential prognostic biomarker in patients with multiple myeloma. Mini Abstract: We demonstrated that high AGR was associated with a favorable overall survival and progression-free survival in patients with multiple myeloma.

scholarly journals Prognostic significance of NDRG2 combined with EGFR patients with lung adenocarcinoma

2020 ◽  
Author(s):  
Bo Yang ◽  
Xiao-Ping Li ◽  
Hong-Gang Zhou ◽  
Tao Jiang ◽  
Ting Xiao ◽  
...  
Keyword(s):  
Overall Survival ◽  
Regression Analysis ◽  
Lung Adenocarcinoma ◽  
Cox Regression ◽  
Prognostic Significance ◽  
Growth Factor Receptor ◽  
Serum Levels ◽  
Clinicopathological Characteristics ◽  
Cox Regression Analysis ◽  
Egfr Expression

Abstract Background: N-myc downstream-regulated gene 2 (NDRG2) plays a substantial role in lung adenocarcinoma (LUAD). Epidermal growth factor receptor (EGFR) mutation could significantly improve prognosis in patients with LUAD. In this study, we aimed to elucidate the prognostic value of NDRG2/EGFR in patients with LUAD. Methods: Immunohistochemistry, western blotting, and real-time polymerase chain reaction (RT-PCR) were conducted to detect the expression levels of NDRG2 protein. Associations between NDRG2/EGFR expression and clinicopathological characteristics of patients with LUAD were examined as well. Serum levels of carcinoembryonic antigen (CEA) were tested prior to treatments. Patients’ overall survival (OS) was assessed by the Kaplan-Meier method. Multivariate Cox regression analysis was carried out to investigate the effects of patients’ demographic characteristics on overall survival . Results: The expression of NDRG2 was significantly decreased in patients with LUAD. The expression of NDRG2 was positively correlated with the levels of CEA and EGFR. Advanced stages were significantly associated with low expression of NDRG2. We found that the patients in the NDRG2-high/EGFR(+) group had the best outcomes, while the patients in the NDRG2-low/EGFR(-) group had the worst outcomes. Cox regression analysis showed that NDRG2-low/EGFR(+), NDRG2-high/EGFR(+), and vascular invasion were independent prognostic factors of LUAD. Conclusion: NDRG2 and EGFR should be considered in patients with LUAD.

scholarly journals Diagnostic and prognostic value of the methylation status of secreted frizzled-related protein 2 in colorectal cancer

2011 ◽  
Vol 34 (1) ◽  
pp. 88 ◽  
Author(s):  
Dong Tang ◽  
Jun Liu ◽  
Dao-rong Wang ◽  
Hai-feng Yu ◽  
Yong-kun Li ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Overall Survival ◽  
Promoter Methylation ◽  
Cox Regression ◽  
Precancerous Lesions ◽  
Methylation Status ◽  
Prognostic Significance ◽  
Related Protein ◽  
Serum Samples ◽  
Cox Regression Analysis

Purpose: The aim of this study was to investigate the diagnostic and prognostic significance of the methylation status of secreted frizzled-related protein 2 (SFRP2) in colorectal cancer (CRC). Methods: Methylation-specific PCR assay was performed to analyze SFRP2 promoter methylation in solid tissue, stool and serum samples collected from 169 CRC patients, 63 patients with advanced adenomas, 46 patients with non-adenomatous polyps and 30 normal healthy controls. Results: Methylated SFRP2 was frequently detected in CRC tissues and precancerous lesions. The sensitivity of SFRP2 methylation levels in tissue, fecal and serum DNA for the detection of CRC was similar, ranging from 66.9 to 88.2%; however, serum SFRP2 methylation levels showed a markedly higher specificity in discriminating CRCs from benign adenomas than those of SFRP2 methylation levels in tumor and fecal DNA. Moreover, serum SFRP2 methylation was significantly associated with poor differentiation grade (P=0.019), serosal/subserosal invasion (P < 0.001), lymph node metastasis status (P < 0.001) and TNM stage (P < 0.001) of CRC. CRC patients with SFRP2 hypermethylation in tumor, stool and serum samples had a significantly shorter overall survival than those negative for SFRP2 methylation (P=0.0216, 0.0219, and 0.0255, respectively). Multivariate Cox regression analysis revealed that SFRP2 promoter methylation in tumor samples was an independent prognostic factor for overall survival. Conclusion: Our data suggest that serum SFRP2 methylation status represents a promising, non-invasive marker for CRC detection and staging. Hypermethylated SFRP2 may have prognostic relevance in patients with CRC.

scholarly journals The clinical and prognostic significance of HER2 and Ki67 expression in 2062 Chinese patients with resectable gastric cancer: a retrospective study

2020 ◽  
Author(s):  
Wenfan Wang ◽  
Zhiqiang Chen ◽  
Qinghua Zhang ◽  
Yanjie You ◽  
Ailing Ma ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Cox Regression ◽  
Prognostic Significance ◽  
Expression Level ◽  
Chinese Patients ◽  
Ki67 Expression ◽  
Cox Regression Analysis ◽  
Expression Levels ◽  
Resectable Gastric Cancer

Abstract Background The purpose of this study was to assess the prognostic value of the expression of human epidermal growth factor receptor 2 (HER2), Ki67, and their combination levels in the prognosis of Chinese patients with resectable gastric cancer (GC). Methods A total of 2062 Chinese GC patients were recruited with HER2 and Ki67 expression being evaluated using immunohistochemistry. Patients were divided into four groups according to HER2 and Ki67 expression. The distributions between HER2 and Ki67 expression levels and clinicopathological characteristics were compared using the Chi-square test. The relationship between HER2 and Ki67 expression level and overall survival were evaluated with the univariate and multivariate Cox regression analysis. Results There was no statistical differences between the overall survival (OS) rate and the expression level of HER2 (P = 0.748) or Ki67 (P = 0.063), but there were significant relationships between the OS rates and the combining expression levels of HER2/Ki67 (P < 0.05). Further, Ki67, sex, T stage, N stage, TNM stage, and adjuvant chemotherapy were significant and independent risk factors for GC survival (P < 0.05). Conclusions Our study illustrated that Ki67, but not HER2 acted as an independent prognostic factor in Chinese resectable GC patients. The evaluation of the combining expression levels of HER2/Ki67 may be more useful to assess patient prognosis with resectable GC.

Carpal Bone Segmentation Using Fully Convolutional Neural Network

2019 ◽  
Vol 15 (10) ◽  
pp. 983-989
Author(s):  
Liang Kim Meng ◽  
Azira Khalil ◽  
Muhamad Hanif Ahmad Nizar ◽  
Maryam Kamarun Nisham ◽  
Belinda Pingguan-Murphy ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Automatic Segmentation ◽  
Ground Truth ◽  
Bone Age ◽  
Image Feature ◽  
Qualitative Assessment ◽  
Carpal Bone ◽  
Radiographic Images ◽  
Accurate Quantitative Analysis

Background: Bone Age Assessment (BAA) refers to a clinical procedure that aims to identify a discrepancy between biological and chronological age of an individual by assessing the bone age growth. Currently, there are two main methods of executing BAA which are known as Greulich-Pyle and Tanner-Whitehouse techniques. Both techniques involve a manual and qualitative assessment of hand and wrist radiographs, resulting in intra and inter-operator variability accuracy and time-consuming. An automatic segmentation can be applied to the radiographs, providing the physician with more accurate delineation of the carpal bone and accurate quantitative analysis. Methods: In this study, we proposed an image feature extraction technique based on image segmentation with the fully convolutional neural network with eight stride pixel (FCN-8). A total of 290 radiographic images including both female and the male subject of age ranging from 0 to 18 were manually segmented and trained using FCN-8. Results and Conclusion: The results exhibit a high training accuracy value of 99.68% and a loss rate of 0.008619 for 50 epochs of training. The experiments compared 58 images against the gold standard ground truth images. The accuracy of our fully automated segmentation technique is 0.78 ± 0.06, 1.56 ±0.30 mm and 98.02% in terms of Dice Coefficient, Hausdorff Distance, and overall qualitative carpal recognition accuracy, respectively.

scholarly journals Propensity score‐matched comparison of stenting as a bridge to surgery and emergency surgery for acute malignant left‐sided colonic obstruction

BMC Surgery ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Yuepeng Cao ◽  
Qing Chen ◽  
Zhizhan Ni ◽  
Feng Wu ◽  
Chenshen Huang ◽  
...  
Keyword(s):  
Overall Survival ◽  
Propensity Score ◽  
Emergency Surgery ◽  
Perineural Invasion ◽  
Cox Regression ◽  
Colonic Obstruction ◽  
Metal Stents ◽  
Bridge To Surgery ◽  
Cox Regression Analysis ◽  
Self Expanding Metal Stents

Abstract Background Bridge to elective surgery (BTS) using self-expanding metal stents (SEMSs) is a common alternative to emergency surgery (ES) for acute malignant left-sided colonic obstruction (AMLCO). However, studies regarding the long-term impact of BTS are limited and have reported unclear results. Methods A multicenter observational study was performed at three hospitals from April 2012 to December 2019. Propensity score matching (PSM) was introduced to minimize selection bias. The primary endpoint was overall survival. The secondary endpoints included surgical approaches, primary resection types, total stent-related adverse effects (AEs), surgical AEs, length of hospital stay, 30-day mortality and tumor recurrence. Results Forty-nine patients in both the BTS and ES groups were matched. Patients in the BTS group more often underwent laparoscopic resection [31 (63.3%) vs. 8 (16.3%), p < 0.001], were less likely to have a primary stoma [13 (26.5%) vs. 26 (53.1%), p = 0.007] and more often had perineural invasion [25 (51.0 %) vs. 13 (26.5 %), p = 0.013]. The median overall survival was significantly lower in patients with stent insertion (41 vs. 65 months, p = 0.041). The 3-year overall survival (53.0 vs. 77.2%, p = 0.039) and 5-year overall survival (30.6 vs. 55.0%, p = 0.025) were significantly less favorable in the BTS group. In multivariate Cox regression analysis, stenting (hazard ratio(HR) = 2.309(1.052–5.066), p = 0.037), surgical AEs (HR = 1.394 (1.053–1.845), p = 0.020) and pTNM stage (HR = 1.706 (1.116–2.607), p = 0.014) were positively correlated with overall survival in matched patients. Conclusions Self-expanding metal stents as “a bridge to surgery” are associated with more perineural invasion, a higher recurrence rate and worse overall survival in patients with acute malignant left-sided colonic obstruction compared with emergency surgery.

scholarly journals Geometric property-based convolutional neural network for indoor object detection

2021 ◽  
Vol 18 (1) ◽  
pp. 172988142199332
Author(s):  
Xintao Ding ◽  
Boquan Li ◽  
Jinbao Wang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Geometric Property ◽  
Ground Truth ◽  
Geometric Constraints ◽  
Depth Information ◽  
Training Set ◽  
Object Knowledge ◽  
The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

Sign in / Sign up

Export Citation Format

Share Document