This study aims to apply ResNet-18 convolutional neural network(CNN)and XGBoost to preoperative computed tomography(CT)images and clinical data for distinguishing Xp11.2 translocation renal cell carcinoma(Xp11.2 tRCC)...This study aims to apply ResNet-18 convolutional neural network(CNN)and XGBoost to preoperative computed tomography(CT)images and clinical data for distinguishing Xp11.2 translocation renal cell carcinoma(Xp11.2 tRCC)from common subtypes of renal cell carcinoma(RCC)in order to provide patients with individualized treatment plans.Data from45 patients with Xp11.2 tRCC fromJanuary 2007 to December 2021 are collected.Clear cell RCC(ccRCC),papillary RCC(pRCC),or chromophobe RCC(chRCC)can be detected from each patient.CT images are acquired in the following three phases:unenhanced,corticomedullary,and nephrographic.A unified framework is proposed for the classification of renal masses.In this framework,ResNet-18 CNN is employed to classify renal cancers with CT images,while XGBoost is adopted with clinical data.Experiments demonstrate that,if applying ResNet-18 CNN or XGBoost singly,the latter outperforms the former,while the framework integrating both technologies performs similarly or better than urologists.Especially,the possibility of misclassifying Xp11.2 tRCC,pRCC,and chRCC as ccRCC by the proposed framework is much lower than urologists.展开更多
Pleomorphic adenoma(PA)is the most common benign tumour in the salivary gland and has high morphological complexity.However,the origin and intratumoral heterogeneity of PA are largely unknown.Here,we constructed a com...Pleomorphic adenoma(PA)is the most common benign tumour in the salivary gland and has high morphological complexity.However,the origin and intratumoral heterogeneity of PA are largely unknown.Here,we constructed a comprehensive atlas of PA at single-cell resolution and showed that PA exhibited five tumour subpopulations,three recapitulating the epithelial states of the normal parotid gland,and two PA-specific epithelial cell(PASE)populations unique to tumours.Then,six subgroups of PASE cells were identified,which varied in epithelium,bone,immune,metabolism,stemness and cell cycle signatures.Moreover,we revealed that CD36+myoepithelial cells were the tumour-initiating cells(TICs)in PA,and were dominated by the PI3K-AKT pathway.Targeting the PI3K-AKT pathway significantly inhibited CD36+myoepithelial cell-derived tumour spheres and the growth of PA organoids.Our results provide new insights into the diversity and origin of PA,offering an important clinical implication for targeting the PI3K-AKT signalling pathway in PA treatment.展开更多
基金supported by Beijing Ronghe Medical Development Foundation。
文摘This study aims to apply ResNet-18 convolutional neural network(CNN)and XGBoost to preoperative computed tomography(CT)images and clinical data for distinguishing Xp11.2 translocation renal cell carcinoma(Xp11.2 tRCC)from common subtypes of renal cell carcinoma(RCC)in order to provide patients with individualized treatment plans.Data from45 patients with Xp11.2 tRCC fromJanuary 2007 to December 2021 are collected.Clear cell RCC(ccRCC),papillary RCC(pRCC),or chromophobe RCC(chRCC)can be detected from each patient.CT images are acquired in the following three phases:unenhanced,corticomedullary,and nephrographic.A unified framework is proposed for the classification of renal masses.In this framework,ResNet-18 CNN is employed to classify renal cancers with CT images,while XGBoost is adopted with clinical data.Experiments demonstrate that,if applying ResNet-18 CNN or XGBoost singly,the latter outperforms the former,while the framework integrating both technologies performs similarly or better than urologists.Especially,the possibility of misclassifying Xp11.2 tRCC,pRCC,and chRCC as ccRCC by the proposed framework is much lower than urologists.
基金supported by the National Natural Science Foundation of China(82141112,82073265)Guangdong Financial Fund for High-Caliber Hospital Construction(174-2018-XMZC-0001-03-0125/D-14)to C.W.
文摘Pleomorphic adenoma(PA)is the most common benign tumour in the salivary gland and has high morphological complexity.However,the origin and intratumoral heterogeneity of PA are largely unknown.Here,we constructed a comprehensive atlas of PA at single-cell resolution and showed that PA exhibited five tumour subpopulations,three recapitulating the epithelial states of the normal parotid gland,and two PA-specific epithelial cell(PASE)populations unique to tumours.Then,six subgroups of PASE cells were identified,which varied in epithelium,bone,immune,metabolism,stemness and cell cycle signatures.Moreover,we revealed that CD36+myoepithelial cells were the tumour-initiating cells(TICs)in PA,and were dominated by the PI3K-AKT pathway.Targeting the PI3K-AKT pathway significantly inhibited CD36+myoepithelial cell-derived tumour spheres and the growth of PA organoids.Our results provide new insights into the diversity and origin of PA,offering an important clinical implication for targeting the PI3K-AKT signalling pathway in PA treatment.