A radiomics model can distinguish solitary pulmonary capillary haemangioma from lung adenocarcinoma

 Open in a separate windowOBJECTIVESSolitary pulmonary capillary haemangioma (SPCH) is a benign lung tumour that presents as ground-glass nodules on computed tomography (CT) images and mimics lepidic-predominant adenocarcinoma. This study aimed to establish a discriminant model using a radiomic feature analysis to distinguish SPCH from lepidic-predominant adenocarcinoma.METHODSIn the adenocarcinoma group, all tumours were of the lepidic-predominant subtype with high purity (>70%). A classification model was proposed based on a two-level decision tree and 26 radiomic features extracted from each segmented lesion. For comparison, a baseline model was built with the same 26 features using a support vector machine as the classifier. Both models were assessed by the leave-one-out cross-validation method.RESULTSThis study included 13 and 49 patients who underwent complete resection for SPCH and adenocarcinoma, respectively. Two sets of features were identified for discrimination between the 2 different histology types. The first set included 2 principal components corresponding to the 2 largest eigenvalues for the root node of the two-level decision tree. The second set comprised 4 selected radiomic features. The area under the receiver operating characteristic curve, accuracy, sensitivity, specificity were 0.954, 91.9%, 92.3% and 91.8% in the proposed classification model, and were 0.805, 85.5%, 61.5% and 91.8% in the baseline model, respectively. The proposed classification model significantly outperformed the baseline model (P < 0.05).CONCLUSIONSThe proposed model could differentiate the 2 different histology types on CT images, and this may help surgeons to preoperatively discriminate SPCH from adenocarcinoma.     

Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: Predicting pathological and survival outcomes

ObjectiveFor patients with thymic epithelial tumors, accurately predicting clinicopathological outcomes remains challenging. We aimed to investigate the performance of machine learning-based radiomic computed tomography phenotyping for predicting pathological (World Health Organization [WHO] type and TNM stage) and survival outcomes (overall and progression-free survival) in patients with thymic epithelial tumors.MethodsThis retrospective study included patients with thymic epithelial tumors between January 2001 and January 2022. The radiomic features were extracted from preoperative unenhanced computed tomography images. After strict feature selection, random forest and random survival forest models were fitted to predict pathological and survival outcomes, respectively. The model performance was assessed by the area under the curve (AUC) and validated internally by the bootstrap method.ResultsIn total, 124 patients with a median age of 61 years were included. The radiomics random forest models of WHO type and TNM stage showed satisfactory performance with an AUC_WHO of 0.898 (95% CI, 0.753-1.000) and an AUC_TNM of 0.766 (95% CI, 0.642-0.886). For overall survival and progression-free survival prediction, the radiomics random survival forest models showed good performance (integrated AUCs, 0.923; 95% CI, 0.691-1.000 and 0.702; 95% CI, 0.513-0.875, respectively), and the integrated AUCs increased to 0.935 (95% CI, 0.705-1.000) and 0.811 (95% CI, 0.647-0.942), respectively, when combined with clinicopathological features.ConclusionsMachine learning-based radiomic computed tomography phenotyping might allow for the satisfactory prediction of pathological and survival outcomes and further improve prognostic performance when integrated with clinicopathological features in patients with thymic epithelial tumors.     

增强CT影像组学鉴别卵巢良性与交界性浆液性肿瘤

目的建立基于增强CT的影像组学模型,探讨其鉴别卵巢浆液性囊腺瘤(SC)与交界性浆液性肿瘤(SBT)的诊断价值。方法回顾性分析经病理证实的49例卵巢SC患者及31例SBT患者的CT资料。由2名医师分别采用AK软件分析CT图像,勾画ROI,提取影像组学参数。对获得的影像组学特征参数进行多因素Logistic回归分析,建立预测模型;采用ROC曲线分析预测模型对卵巢SC与SBT的诊断效能。结果共提取396个影像组学参数,经降维处理后得到5个特征参数,分别为Percentile_(10)、Percentile_(15)、SA、LRHGLE_(a90,o1)及LRHGLE_(a90,o7)。2名医师提取参数的一致性良好(组内相关系数均0.75)。以上述5个特征参数构建Radscore预测模型,在训练集中Radscore模型对鉴别诊断卵巢SC与SBT的AUC、敏感度、特异度分别为0.90、0.91、0.79,在测试集的AUC、敏感度、特异度分别为0.86、0.90、0.73。结论基于增强CT的影像组学模型能够有效鉴别卵巢SC与SBT。     

Preoperative neutrophil-lymphocyte ratio predicts death among patients with localized clear cell renal carcinoma undergoing nephrectomy

ObjectivesThe neutrophil-lymphocyte ratio (NLR) is an indicator of the systemic inflammatory response. An increased pretreatment NLR has been associated with adverse outcomes in other malignancies, but its role in localized (M0) clear cell renal cell carcinoma (ccRCC) remains unclear. As such, we evaluated the ability of preoperative NLR to predict oncologic outcomes in patients with M0 ccRCC undergoing radical nephrectomy (RN).Methods and materialsFrom 1995 to 2008, 952 patients underwent RN for M0 ccRCC. Of these, 827 (87%) had pretreatment NLR collected within 90 days before RN. Metastasis-free, cancer-specific, and overall survival was estimated using the Kaplan-Meier method and compared using the log-rank test. Multivariate models were used to analyze the association of NLR with clinicopathologic outcomes.ResultsAt a median follow-up of 9.3 years, 302, 233, and 436 patients had distant metastasis, death from ccRCC, and all-cause mortality, respectively. Higher NLR was associated with larger tumor size, higher nuclear grade, histologic tumor necrosis, and sarcomatoid differentiation (all, P<0.001). A NLR≥4.0 was significantly associated with worse 5-year cancer-specific (66% vs. 85%) and overall survival (66% vs. 85%). Finally, after controlling for clinicopathologic features, NLR remained independently associated with risks of death from ccRCC and all-cause mortality (hazard ratio for 1-unit increase: 1.02, P< 0.01).ConclusionsOur results suggest that NLR is independently associated with increased risks of cancer-specific and all-cause mortality among patients with M0 ccRCC undergoing RN. Accordingly, NLR, an easily obtained marker of biologically aggressive ccRCC, may be useful in preoperative patient risk stratification.     

MRI-based radiomics in distinguishing Kaposiform hemangioendothelioma (KHE) and fibro-adipose vascular anomaly (FAVA) in extremities: A preliminary retrospective study

ObjectiveTo investigate the pretreatment differentiation between Kaposiform hemangioendothelioma (KHE) and fibro-adipose vascular anomaly (FAVA) in extremities of pediatric patients. To build and validate an MRI-based radiomic model.MethodIn this retrospective study, we obtained imaging data from 43 patients. We collected and compared clinical information, sketched region of interest (ROI), and extracted radiomic features from fat-suppressed T2-weighted (T2FS) images of the two cohorts of 30 and 13 patients respectively (training versus testing cohort 7:3). To select features, we used two sample t-test and the least absolute shrinkage and selection operator (LASSO) regression. The support vector machine (SVM) classification was constructed and evaluated by receiver operating characteristic (ROC) analysis.ResultsThirty patients with KHE and 13 patients with FAVA in the extremities were included. Most lesions demonstrated low to intermediate signal intensity on T1-weighted images and hyperintense signals on T2-weighted ones. They also showed similar traits pathologically. Initially, 107 radiomic features were acquired and then three were finally selected. The support vector machine (SVM) model was able to differentiate the two anomalies from each other with an area under the curve (AUC) of 0.807 (95%CI 0.602–1.000) and 0.846 (95%CI 0.659–1.000) in training and testing cohort, respectively.ConclusionThe derived radiomic features were helpful in differentiating KHE from FAVA. A model which contained these features might further improve the performance and hopefully could serve as a potential tool for identification.     

Magnetic resonance imaging radiomics signatures for predicting endocrine resistance in hormone receptor-positive non-metastatic breast cancer

BackgroundOne-third of patients with hormone receptor (HR)-positive breast cancers fail to respond to hormone therapy, and some patients even progress within two years of adjuvant endocrine therapy (ET) toward primary endocrine resistance. However, there is no effective way to predict endocrine resistance.ObjectiveTo build a model that incorporates the radiomic signature of pretreatment magnetic resonance imaging (MRI) with clinical information to predict endocrine resistance.MethodsClinical data of non-metastatic breast cancer patients diagnosed between May 1, 2015 and December 31, 2018 and preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) were retrospectively collected from three hospitals in China. The significant clinicopathological characteristics and radiomic signatures were included in multivariable logistic regression to establish a combined model to predict endocrine resistance in the training set, and validate the internal and external validation set.ResultsA total of 744 female non-metastatic breast cancer patients from three hospitals in China were included. In the training cohort, the AUC of the Radiomic-Clinical combined model to predict endocrine resistance was 0.975, which was higher than clinical model (0.849), IHC4 model (0.682) and similar as radiomic model (0.941). Also, the AUC of the combined model in the internal (0.921) and external validation cohort (0.955) were higher than clinical model and IHC4 model. The sensitivity of combined model was higher than radiomic alone, and got the best thresholding of the AUC.ConclusionThis study developed and validated a pretreatment multiparametric MRI-based radiomic-clinical combined model and showed good performance in predicting endocrine resistance.     

Immune inactivation by CD47 expression predicts clinical outcomes and therapeutic responses in clear cell renal cell carcinoma patients

BackgroundCD47 has been identified as a phagocytosis checkpoint conferring poor clinical outcomes in various cancer types. A flurry of clinical trials designed to evaluate agents that block CD47 have been initiated. We aimed to explore the clinical significance of CD47 and its correlation with immune infiltration and molecular features in clear cell renal cell carcinoma (ccRCC).Methods235 tumor tissue microarray specimens of ccRCC patients from Zhongshan Hospital, 530 ccRCC patients from The Cancer Genome Atlas and 726 ccRCC patients from JAVELIN Renal 101 study were analyzed. CD47 expression and immune contexture were examined by immunohistochemistry and CIBERSORT algorithm. Survival analyses were conducted through Kaplan-Meier curves and Cox regression model.ResultsWe demonstrated that ccRCC patients with high CD47 expression exhibited inferior overall survival and recurrence-free survival. CD47 expression associated with heavily immune infiltrated but immunosuppressed microenvironment. CD8⁺ T cells infiltration had discordant prognostic value based on CD47 expression, where high CD8⁺ T cell infiltration was associated with worse clinical outcome in CD47^hi patients and with favorable prognosis in CD47^lo patients. Patients with mutated PBRM1 and SETD2 correlated with decreased CD47 mRNA expression. Patients with higher CD47 expression possessed improved PFS in ICI + VEGFR TKI combination therapy.ConclusionsCD47 expression was an independent prognosticator of clinical outcome for ccRCC patients. CD47 expression correlated with ccRCC molecular classification and response to combination therapy. The phagocytosis checkpoint CD47 could be applied as an attractive candidate for immunotherapeutic approach in ccRCC.     

NDUFA4L2 expression predicts poor prognosis in clear cell renal cell carcinoma patients

Background: NDUFA4L2 is overexpressed in VHL-deficient cell lines and neuroblastoma. The clinical significance of NDUFA4L2 in clear cell renal cell carcinoma (ccRCC) has not been well studied. Therefore, we evaluated the prognostic value of NDUFA4L2 in ccRCC patients.

Methods: In our study, NDUFA4L2 expression in 86 cases of ccRCC and adjacent normal tissues was monitored by immunohistochemistry, semi-quantitative RT-PCR, and Western blot analyses. The relationship between NDUFA4L2 expression and the clinical features of ccRCC was assessed.

Results: The results showed that NDUFA4L2 protein expression was found to be higher in ccRCC tissues 81.4% (70/86) than in normal tissues 26.7% (23/86) (p?=?0.021). The average level of NDUFA4L2 mRNA expression was found to be 122.23?±?6.018 and 21.34?±?1.036 in ccRCC tissue and adjacent normal tissue (p?Conclusions: Our study has provided the significant clinical relevance of NDUFA4L2 in ccRCC and suggested that ccRCC patients with NDUFA4L2 overexpression may be suitable as a potential therapeutic target for ccRCC patients.     

Predictive radiomics signature for treatment response to nivolumab in patients with advanced renal cell carcinoma

IntroductionThe anti-programmed cell death protein-1 (PD-1) immune checkpoint inhibitor nivolumab is currently approved for the treatment of patients with metastatic renal cell carcinoma (mRCC); approximately 25% of patients respond. We hypothesized that we could identify a biomarker of response using radiomics to train a machine learning classifier to predict nivolumab response outcomes.MethodsPatients with mRCC of different histologies treated with nivolumab in a single institution between 2013 and 2017 were retrospectively identified. Patients were labelled as responders (complete response [CR]/partial response [PR]/durable stable disease [SD]) or non-responders based on investigator tumor assessment using RECIST 1.1 criteria. For each patient, lesions were contoured from pre-treatment and first post-treatment computed tomography (CT) scans. This information was used to train a radial basis function support vector machine classifier to learn a prediction rule to distinguish responders from non-responders. The classifier was internally validated by a 10-fold nested cross-validation.ResultsThirty-seven patients were identified; 27 (73%) met the inclusion criteria. One hundred and four lesions were contoured from these 27 patients. The median patient age was 56 years, 78% were male, 89% had clear-cell histology, 89% had prior nephrectomy, and 89% had prior systemic therapy. There were 19 responders vs. eight non-responders. The lesions selected were lymph nodes (60%), lung metastases (23%), and renal/adrenal metastases (17%). For the classifier trained on the baseline CT scans, 69% accuracy was achieved. For the classifier trained on the first post-treatment CT scans, 66% accuracy was achieved.ConclusionsThe set of radiomic signatures was found to have limited ability to discriminate nivolumab responders from non-responders. The use of novel texture features (two-point correlation measure, two-point cluster measure, and minimum spanning tree measure) did not improve performance.     

DDX41 expression is associated with tumor necrosis in clear cell renal cell carcinoma and in cooperation with VHL loss leads to worse prognosis

BackgroundHistologic tumor necrosis (TN) is a well-established independent prognostic indicator in patients treated surgically for clear cell renal cell carcinoma (ccRCC). However, the precise mechanisms by which TN alters disease progression remain unknown. The DEAD-box protein DDX41, a member of a large family of helicases, has been characterized as a pattern recognition receptor against an array of double-stranded (ds)DNA produced from bacteria, dsDNA viruses, and nearby cells that have released dsDNA fragments through necrosis. We hypothesized that DDX41 expression may be upregulated in ccRCC with TN, leading to worse prognosis.MethodsRelationship between the presence of TN and DDX41 expression were examined using The Cancer Genome Atlas data sets or using ccRCC samples in our institution. Further, the molecular functions of DDX41 were investigated with human ccRCC cells.ResultsThe presence of TN was significantly associated with the upregulation of mRNA and protein expression of DDX41 in the 2different patient cohorts with ccRCC. In addition, the mRNA and protein expression levels of DDX41 revealed a worse prognosis. In vitro analyses with ccRCC cells revealed that DDX41 expression promotes tumor-promoting activity. Furthermore, VHL loss, 1of the most common features in ccRCC, was shown to play an extremely important role in increasing the expression of the CXCL family in DDX41-expressing ccRCC, leading to the acquisition of a worse malignant phenotype.ConclusionsDDX41 expression is associated with TN in ccRCC and leads to a worse prognosis in cooperation with VHL loss.     

Lymphovascular invasion in clear cell renal cell carcinoma—Association with disease-free and cancer-specific survival

ObjectivesThe objective is to evaluate the effect of lymphovascular invasion (LVI) on disease-free survival (DFS) and cancer-specific survival (CSS) in patients with clinically localized clear cell renal cell carcinoma (ccRCC).MethodsPatients with ccRCC who were treated surgically in 1997 to 2010 were identified. Retrospective chart review was performed to identify clinical outcomes. Independent pathologic re-review was performed by a single pathologist to confirm LVI status. Pathologic features were correlated with clinical outcomes using Kaplan-Meier and Cox regression analyses.ResultsFour hundred and nineteen patients with nonmetastatic ccRCC comprised the study cohort. Three hundred and thirty-three of these patients had an organ-confined (pT1-2, N any, and M0) disease. LVI was present in 14.3% of all nonmetastatic patients. In all patients with nonmetastatic ccRCC, presence of LVI was correlated with significantly shorter DFS (P <0.001) and CSS (P = 0.001) on Kaplan-Meier analysis. In cases of organ-confined, nonmetastatic ccRCC, presence of LVI was a significant predictor of DFS (hazard ratio = 4.0, P = 0.026) and CSS (hazard ratio = 12.7, P = 0.01) on multivariate analysis. Patients with organ-confined RCC who were LVI positive had similar DFS (P = 0.957) and CSS (P = 0.799) to patients with locally advanced tumors (pT3-pT4, N any, and M0) on Kaplan-Meier analysis.ConclusionsThe presence of LVI is an independent predictor of both DFS and CSS in organ-confined, nonmetastatic ccRCC. LVI positivity in patients with otherwise pathologically organ-confined ccRCC confers oncologic outcomes similar to those of patients with locally advanced disease. If confirmed by others, future revisions to the tumor-node-metastasis staging system may incorporate LVI status into the prognostic algorithm of patients with RCC.     

Natural history and growth kinetics of clear cell renal cell carcinoma in sporadic and von Hippel-Lindau disease

BackgroundTo evaluate and compare the natural history and growth kinetics of sporadic clear cell renal cell carcinoma (ccRCC) with those of ccRCC in von Hippel-Lindau disease (VHL).MethodsSixty patients in the sporadic group with 61 tumors and 15 patients in the VHL group with 30 tumors whom all underwent delayed surgery after at least 12 months of active surveillance (AS) were enrolled to conduct a retrospective cohort study. The growth rate was calculated, and the growth kinetics between the sporadic and VHL groups were compared. The patient and tumor characteristics were reviewed, and their correlation with growth rate was analyzed.ResultsThe mean growth rate of sporadic ccRCC was 0.91 cm/year (ranging from 0–4.74 cm/year) and that of VHL ccRCC was 0.47 cm/year (ranging from 0.04–1.89 cm/year). The growth rate of sporadic ccRCC showed a tendency of being faster than that of VHL ccRCC but did not reach statistical significance (P=0.07). The factors affecting the growth rate were different between the two groups. For VHL ccRCC, the only factor that correlated with growth rate was initial tumor diameter (P<0.001), but for sporadic ccRCC, the only factor was pathological nuclear grade (P<0.001).ConclusionsThe growth rate of VHL-associated ccRCC might be slower than that of sporadic ccRCC. Furthermore, we identified a disparity in growth kinetics between sporadic and VHL-associated ccRCC.     

A 13-gene risk score system and a nomogram survival model for predicting the prognosis of clear cell renal cell carcinoma

BackgroundRenal cell carcinoma (RCC) is the second common malignant tumor in the urinary system, and 85% of RCC cases are clear cell RCC (ccRCC). This study is designed to build a risk score system for ccRCC.MethodsThe gene methylation and expression data of ccRCC samples were downloaded from The Cancer Genome Atlas database (training set) and ArrayExpress database (validation set). The differentially methylated genes (DMGs) and differentially expressed genes (DEGs) were identified by limma package, and their intersecting genes with negative Pearson correlation coefficients were remained using cor.test function. Prognosis-associated genes were identified by survival package, and the optimal DMGs were obtained using penalized package. After risk score system was built, nomogram survival model was constructed using rms package. Additionally, pathways were enriched for the DEGs between high- and low-risk groups using Gene Set Enrichment Analysis.ResultsThere were 3,638 DMGs and 2,702 DEGs between tumor and normal samples. Among the 312 intersecting genes, 43 prognosis-associated genes were identified. A total of 13 optimal DMGs (BTBD19, ADAM8, BGLAP, TNFRSF13C, JPH4, BEST1, GNRH2, UBE2QL1, CHODL, GDF9, UPB1, KCNH3; and ADAMTSL4) were obtained for building the risk score system. After pathological M, pathological T, platelet qualitative, and RS status were revealed to be independent prognostic factors, a nomogram survival model was constructed. For the 920 DEGs between the high- and low-risk samples, 6 significant pathways were enriched.ConclusionThe 13-gene risk score system and the nomogram survival model might be used for prognostic prediction of ccRCC patients.     

Interleukin-6 as an emerging regulator of renal cell cancer

BackgroundOur knowledge on the molecular basis of kidney cancer metastasisis still relatively low. About 25-30% of patients suffering from clear cell renal cell carcinoma (ccRCC)present metastatic disease at the time of primary diagnosis. Only 10% of patients diagnosed with stage IV disease survive 5 years and 20-50% of patients diagnosed with localized tumor develop metastases within 3 years. High mortality of patients with this cancer is associated with a large potential for metastasis and resistance to oncologic treatments such as chemo- and radiotherapy. Literature data based on studies conducted on other types of cancers suggest that in metastatic ccRCC, the complex of interleukin-6 (IL-6) and its soluble receptor (sIL-6R; complex IL-6/sIL-6R) and the signal transduction pathway (gp130/STAT3) might play a key role in this process.PurposeTherefore, in this review we focus on the role of IL-6 and its signaling pathways as a factor for development and spread of RCC. Analyzing the molecular basis of cancer spreading will enable the development of prognostic tests, evaluate individual predisposition for metastasis, and produce drugs that target metastases. As the development of effective systemic treatments evolve from advancements in molecular biology, continued studies directed at understanding the genetic and molecular complexities of this disease are critical to improve RCC treatment options.     

Identification of genes that correlate clear cell renal cell carcinoma and obesity and exhibit potential prognostic value

BackgroundRenal cell carcinoma (RCC) is a common urologic malignancy. Although the relationship between clear cell RCC (ccRCC) and obesity has been well-established by several large-scale retrospective studies, the molecular mechanisms and genetic characteristics behind this correlation remains unclear. In the current study, several bioinformatics tools were used to identify the key genes in ccRCC related to obesity.MethodsMicroarray data comparing ccRCC with normal renal tissues in patients with and without obesity were downloaded from the GEO database for screening of differentially expressed genes (DEGs). The DEGs were verified with expression level and survival analysis using several online bioinformatics tools.ResultsIn the current study, the differential expression of five genes correlated with both ccRCC and obesity; IGHA1 and IGKC as oncogenes, and MAOA, MUC20 and TRPM3 as tumor suppressor genes. These genes were verified by comparing the relationship between the expression levels and survival outcomes from open-source data in The Cancer Genome Atlas (TCGA) dataset.ConclusionsIn conclusion, the five genes differentially expressed in ccRCC and obesity are related to disease progression and prognosis, and therefore could provide prognostic value for patients with ccRCC.     

The contrasting roles of Dysferlin during tumor progression in renal cell carcinoma

BackgroundThe vesicle fusion protein Dysferlin (DYSF) is mainly known as a membrane repair protein in muscle cells. Mutations of DYSF lead to muscular dystrophies and cardiomyopathies. In contrast to other members of the Ferlin protein family, few is known about its role in cancer. Our study was designed to investigate the expression and functional properties of DYSF in ccRCC and its association with clinicopathological parameters and survival.Material and methodsTCGA cohort: mRNA expression data of DYSF were extracted from TCGA for patients with ccRCC (n = 603; ccRCC n = 522, benign n = 81). Study cohort: mRNA expression of DYSF in ccRCC was determined using qPCR (n = 126; ccRCC n = 82, benign n = 44). Immunohistochemical staining against DYSF was performed on tissue microarrays to validate protein expression (n = 172; ccRCC n = 142, benign n = 30). Correlations between mRNA/protein expression and clinicopathological data were statistically tested. Following siRNA-mediated knockdown of DYSF in ccRCC cell line ACHN, cell migration, invasion and proliferation were investigated.ResultsBoth DYSF mRNA and protein expression are significantly up-regulated in ccRCC tissue. DYSF mRNA expression decreased during tumor progression: lower expression levels were measured in higher stage/grade and metastatic ccRCC with independent prognostic significance for overall and cancer-specific survival. In contrast, protein expression correlated positively with pathological parameters. Overexpression showed tendency toward poor survival. Accordingly, knockdown of DYSF suppressed migration and invasion of ccRCC cells.ConclusionDYSF mRNA and protein expression are opposingly involved in tumor progression of ccRCC. DYSF could be used as a prognostic biomarker to predict survival of patients with ccRCC.