Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surge...Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surgery.This study aimed to develop and validate a computed tomography(CT)-based radiomics and deep learning(DL)fusion model for predicting non-invasive OLNM.Methods:Patients with radiologically node-negative lung adenocarcinoma from two centers were retrospectively analyzed.We developed clinical,radiomics,and radiomics-clinical models using logistic regression.A DL model was established using a three-dimensional squeeze-and-excitation residual network-34(3D SE-ResNet34)and a fusion model was created by integrating seleted clinical,radiomics features and DL features.Model performance was assessed using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve,calibration curves,and decision curve analysis(DCA).Five predictive models were compared;SHapley Additive exPlanations(SHAP)and Gradient-weighted Class Activation Mapping(Grad-CAM)were employed for visualization and interpretation.Results:Overall,358 patients were included:186 in the training cohort,48 in the internal validation cohort,and 124 in the external testing cohort.The DL fusion model incorporating 3D SE-Resnet34 achieved the highest AUC of 0.947 in the training dataset,with strong performance in internal and external cohorts(AUCs of 0.903 and 0.907,respectively),outperforming single-modal DL models,clinical models,radiomics models,and radiomicsclinical combined models(DeLong test:P<0.05).DCA confirmed its clinical utility,and calibration curves demonstrated excellent agreement between predicted and observed OLNM probabilities.Features interpretation highlighted the importance of textural characteristics and the surrounding tumor regions in stratifying OLNM risk.Conclusions:The DL fusion model reliably and accurately predicts OLNM in early-stage lung adenocarcinoma,offering a non-invasive tool to refine staging and guide personalized treatment decisions.These results may aid clinicians in optimizing surgical and radiotherapy strategies.展开更多
Objective:This study aimed to explore the prognostic effect of neck dissection and to identify risk factors associated with occult lymph node metastasis(OLNM)in clinically node-negative(cN0)parotid carcinoma(PC).Metho...Objective:This study aimed to explore the prognostic effect of neck dissection and to identify risk factors associated with occult lymph node metastasis(OLNM)in clinically node-negative(cN0)parotid carcinoma(PC).Methods:A retrospective analysis was conducted on cN0 PC patients who underwent primary surgery at the National Cancer Center/Cancer Hospital,Chinese Academy of Medical Sciences,between 2012 and 2022.Kaplan–Meier(KM)survival analyses were carried out to evaluate differences in progression-free survival(PFS)and overall survival(OS)between patients undergoing neck dissection and those who did not.Clinical variables associated with OLNM in the neck dissection group were assessed using univariate and multivariate logistic regression analyses.Results:Among 472 PC patients,133 were classified as cN0 following initial surgery,of whom 75(56.4%)underwent neck dissection.Pathological lymph node metastases were confirmed in 20(26.7%)patients in the neck dissection cohort.Poor tumor differentiation was identified as an independent risk factor for OLNM(p=0.017).No significant differences in PFS or OS were observed between the no-neck dissection and neck dissection groups for patients with low-grade or well-differentiated tumors(p>0.05).However,neck dissection was associated with significantly prolonged PFS in patients with tumors of higher grade or low to moderate differentiation(p<0.05).Notably,OS did not improve with neck dissection across all subgroups(p>0.05).Conclusion:Poorly differentiated tumors in cN0 PC are independently associated with a higher risk of OLNM.While prophylactic neck dissection may enhance PFS in patients with higher grade or poorly differentiated tumors,it does not confer a survival benefit in terms of OS.These findings support the selective use of neck dissection in patients with higher risk tumor profiles.展开更多
Objective： To explore the treatment of clinically negative neck （CN0） patients with squamous cell carcinoma of the tongue. Methods： 165 CN0 patients with squamous cell carcinoma of the tongue from 1985 to 2002 wer...Objective： To explore the treatment of clinically negative neck （CN0） patients with squamous cell carcinoma of the tongue. Methods： 165 CN0 patients with squamous cell carcinoma of the tongue from 1985 to 2002 were investigated retrospectively. Parts of the patients staged at T1, T2 and T3 underwent resection of primary lesion followed by neck observation, and other patients staged above T2 or at T1 but without follow-up were treated with elective neck dissection （END）. All patients were followed up for more than 3 y or until their death. Results： Lymphatic metastasis was identified histologically after operation in 33 of 120 patients treated with END, and 9 of 45 patients treated with resection of primary lesion alone. The overall rate of occult lymphatic metastasis was 25.45%, which increased with the elevating of clinical T stage. The overall rate of neck uncontrolled death was 20.00% for observation group and 5.00% for END group, and significant difference was found between them （P〈0.05）. For T~ patients in the two groups, the rate of neck uncontrolled death was 7.71% and 4.00% respectively, and no significance was found between them （P〉0.05）. When stage T2 and T3 were considered as middle stage together, significant difference （P〈0.05） could be obtained between observation （70.00%） and END group （0%）. Conclusion： The occult metastasis rate of squamous cell carcinoma of tongue increases with the elevating of clinical stage, and elective neck dissection could be considered for NO patients staged over T2 to improve neck control and survival rate; and regional resection alone of primary lesion could be considered for T1N0 patients to improve quality of life if closely followed up is conducted.展开更多
目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多...目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多个临床及影像学特征。采用单因素和多因素Logistic回归分析筛选独立预测因子,并构建多个CT特征的影像模型。建立受试者工作特征(receiver operating characteristic,ROC)曲线评估各模型的预测效能和临床实用价值。结果:在最终纳入的780例肺腺癌伴大小正常的淋巴结患者中,145例发生淋巴结转移。单因素分析结果提示,肿瘤大小、轴向位置、结节性质、形态学特征、胸膜牵拉征、胸膜毗邻类型与淋巴结转移显著相关。多因素分析结果提示,肿瘤大小(OR=1.019,95%CI:1.002~1.036,P=0.028)、结节性质(OR=0.361,95%CI:0.202~0.646,P=0.001)、胸膜牵拉(OR=1.835,95%CI:1.152~2.924,P=0.011)和纵隔胸膜毗邻(OR=1.796,95%CI:1.106~2.919,P=0.018)是隐匿性纵隔淋巴结转移的独立预测因子。基于预测因子建立的影像学模型,ROC曲线下面积(area under the curve,AUC)为0.75,灵敏度为86.2%,特异度为53.1%。结论:基于胸部CT平扫建立的影像学特征模型,在预测肺腺癌隐匿性纵隔淋巴结转移上具有较好的临床价值,可为临床医生的无创性术前决策及手术治疗方案选择提供依据。展开更多
Background Squamous cell carcinoma （SCC） of the tongue maxillofacial region. To provide clinical evidence for selective analyzing the characteristics and correlation of factors of occult with SCC of the tongue. is o...Background Squamous cell carcinoma （SCC） of the tongue maxillofacial region. To provide clinical evidence for selective analyzing the characteristics and correlation of factors of occult with SCC of the tongue. is one of the most common cancers in the oral and neck dissection in management of cN0 patients by cervical lymph node metastases （OCLNM） in patients Methods From 2002 to 2006, 100 consecutive patients with SCC of the tongue were reviewed by analyzing the characteristics of OCLNM, diameter of the tumor, T classifications, depth of invasion, forms of growth, pathological grade and degree of differentiation. Results The rate of OCLNM in 100 patients with SCC of the tongue was 22%. The most common region with OCLNM was level Ⅱ in the ipsilateral neck, followed by levels Ⅰ and Ⅲ. There were 51.61% （16/31） of OCLNM in level Ⅱ and 87.10% （27/31） of OCLNM in levels Ⅰ-Ⅲ. There was no significant correlation between the diameter of tumor and OCLNM （P 〉0.05）. OCLNM was statistically significantly correlated with the depth of invasion, forms of growth, pathological grade and degree of differentiation （P 〈0.05）. The rate of occult metastases increased with the increased pathological grade, the decreased degree of differentiation and the increased depth of invasion. Conclusions The most common regions with OCLNM in cN0 patients with SCC of the tongue were levels Ⅰ-Ⅲ in the ipsilateral neck. Supraomohyoid neck dissection should be the elective treatment to the neck in patients with cN0 SCC of the tongue by consideration of the clinical and pathological factors for the depth of invasion, forms of growth, pathological grade, and degree of differentiation.展开更多
基金supported by the National Natural Science Foundation of China(No.82272845)the Natural Science Foundation of Shandong(No.ZR2023ZD26).
文摘Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surgery.This study aimed to develop and validate a computed tomography(CT)-based radiomics and deep learning(DL)fusion model for predicting non-invasive OLNM.Methods:Patients with radiologically node-negative lung adenocarcinoma from two centers were retrospectively analyzed.We developed clinical,radiomics,and radiomics-clinical models using logistic regression.A DL model was established using a three-dimensional squeeze-and-excitation residual network-34(3D SE-ResNet34)and a fusion model was created by integrating seleted clinical,radiomics features and DL features.Model performance was assessed using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve,calibration curves,and decision curve analysis(DCA).Five predictive models were compared;SHapley Additive exPlanations(SHAP)and Gradient-weighted Class Activation Mapping(Grad-CAM)were employed for visualization and interpretation.Results:Overall,358 patients were included:186 in the training cohort,48 in the internal validation cohort,and 124 in the external testing cohort.The DL fusion model incorporating 3D SE-Resnet34 achieved the highest AUC of 0.947 in the training dataset,with strong performance in internal and external cohorts(AUCs of 0.903 and 0.907,respectively),outperforming single-modal DL models,clinical models,radiomics models,and radiomicsclinical combined models(DeLong test:P<0.05).DCA confirmed its clinical utility,and calibration curves demonstrated excellent agreement between predicted and observed OLNM probabilities.Features interpretation highlighted the importance of textural characteristics and the surrounding tumor regions in stratifying OLNM risk.Conclusions:The DL fusion model reliably and accurately predicts OLNM in early-stage lung adenocarcinoma,offering a non-invasive tool to refine staging and guide personalized treatment decisions.These results may aid clinicians in optimizing surgical and radiotherapy strategies.
基金funded by the Beijing Hope Run Special Fund of Cancer Foundation of China(Grant no.LC2017L04).
文摘Objective:This study aimed to explore the prognostic effect of neck dissection and to identify risk factors associated with occult lymph node metastasis(OLNM)in clinically node-negative(cN0)parotid carcinoma(PC).Methods:A retrospective analysis was conducted on cN0 PC patients who underwent primary surgery at the National Cancer Center/Cancer Hospital,Chinese Academy of Medical Sciences,between 2012 and 2022.Kaplan–Meier(KM)survival analyses were carried out to evaluate differences in progression-free survival(PFS)and overall survival(OS)between patients undergoing neck dissection and those who did not.Clinical variables associated with OLNM in the neck dissection group were assessed using univariate and multivariate logistic regression analyses.Results:Among 472 PC patients,133 were classified as cN0 following initial surgery,of whom 75(56.4%)underwent neck dissection.Pathological lymph node metastases were confirmed in 20(26.7%)patients in the neck dissection cohort.Poor tumor differentiation was identified as an independent risk factor for OLNM(p=0.017).No significant differences in PFS or OS were observed between the no-neck dissection and neck dissection groups for patients with low-grade or well-differentiated tumors(p>0.05).However,neck dissection was associated with significantly prolonged PFS in patients with tumors of higher grade or low to moderate differentiation(p<0.05).Notably,OS did not improve with neck dissection across all subgroups(p>0.05).Conclusion:Poorly differentiated tumors in cN0 PC are independently associated with a higher risk of OLNM.While prophylactic neck dissection may enhance PFS in patients with higher grade or poorly differentiated tumors,it does not confer a survival benefit in terms of OS.These findings support the selective use of neck dissection in patients with higher risk tumor profiles.
基金This work was supported by the Shantou Municipal Key Sci & Tech Project (No.2004-102).
文摘Objective： To explore the treatment of clinically negative neck （CN0） patients with squamous cell carcinoma of the tongue. Methods： 165 CN0 patients with squamous cell carcinoma of the tongue from 1985 to 2002 were investigated retrospectively. Parts of the patients staged at T1, T2 and T3 underwent resection of primary lesion followed by neck observation, and other patients staged above T2 or at T1 but without follow-up were treated with elective neck dissection （END）. All patients were followed up for more than 3 y or until their death. Results： Lymphatic metastasis was identified histologically after operation in 33 of 120 patients treated with END, and 9 of 45 patients treated with resection of primary lesion alone. The overall rate of occult lymphatic metastasis was 25.45%, which increased with the elevating of clinical T stage. The overall rate of neck uncontrolled death was 20.00% for observation group and 5.00% for END group, and significant difference was found between them （P〈0.05）. For T~ patients in the two groups, the rate of neck uncontrolled death was 7.71% and 4.00% respectively, and no significance was found between them （P〉0.05）. When stage T2 and T3 were considered as middle stage together, significant difference （P〈0.05） could be obtained between observation （70.00%） and END group （0%）. Conclusion： The occult metastasis rate of squamous cell carcinoma of tongue increases with the elevating of clinical stage, and elective neck dissection could be considered for NO patients staged over T2 to improve neck control and survival rate; and regional resection alone of primary lesion could be considered for T1N0 patients to improve quality of life if closely followed up is conducted.
文摘目的:基于肺腺癌原发灶的临床及影像学特征构建肺腺癌隐匿性纵隔淋巴结转移的预测模型。方法:回顾性分析南京医科大学第一附属医院2009—2019年行手术治疗和淋巴结清扫、病理结果为有/无隐匿性纵隔淋巴结转移的肺腺癌患者,收集患者的多个临床及影像学特征。采用单因素和多因素Logistic回归分析筛选独立预测因子,并构建多个CT特征的影像模型。建立受试者工作特征(receiver operating characteristic,ROC)曲线评估各模型的预测效能和临床实用价值。结果:在最终纳入的780例肺腺癌伴大小正常的淋巴结患者中,145例发生淋巴结转移。单因素分析结果提示,肿瘤大小、轴向位置、结节性质、形态学特征、胸膜牵拉征、胸膜毗邻类型与淋巴结转移显著相关。多因素分析结果提示,肿瘤大小(OR=1.019,95%CI:1.002~1.036,P=0.028)、结节性质(OR=0.361,95%CI:0.202~0.646,P=0.001)、胸膜牵拉(OR=1.835,95%CI:1.152~2.924,P=0.011)和纵隔胸膜毗邻(OR=1.796,95%CI:1.106~2.919,P=0.018)是隐匿性纵隔淋巴结转移的独立预测因子。基于预测因子建立的影像学模型,ROC曲线下面积(area under the curve,AUC)为0.75,灵敏度为86.2%,特异度为53.1%。结论:基于胸部CT平扫建立的影像学特征模型,在预测肺腺癌隐匿性纵隔淋巴结转移上具有较好的临床价值,可为临床医生的无创性术前决策及手术治疗方案选择提供依据。
文摘Background Squamous cell carcinoma （SCC） of the tongue maxillofacial region. To provide clinical evidence for selective analyzing the characteristics and correlation of factors of occult with SCC of the tongue. is one of the most common cancers in the oral and neck dissection in management of cN0 patients by cervical lymph node metastases （OCLNM） in patients Methods From 2002 to 2006, 100 consecutive patients with SCC of the tongue were reviewed by analyzing the characteristics of OCLNM, diameter of the tumor, T classifications, depth of invasion, forms of growth, pathological grade and degree of differentiation. Results The rate of OCLNM in 100 patients with SCC of the tongue was 22%. The most common region with OCLNM was level Ⅱ in the ipsilateral neck, followed by levels Ⅰ and Ⅲ. There were 51.61% （16/31） of OCLNM in level Ⅱ and 87.10% （27/31） of OCLNM in levels Ⅰ-Ⅲ. There was no significant correlation between the diameter of tumor and OCLNM （P 〉0.05）. OCLNM was statistically significantly correlated with the depth of invasion, forms of growth, pathological grade and degree of differentiation （P 〈0.05）. The rate of occult metastases increased with the increased pathological grade, the decreased degree of differentiation and the increased depth of invasion. Conclusions The most common regions with OCLNM in cN0 patients with SCC of the tongue were levels Ⅰ-Ⅲ in the ipsilateral neck. Supraomohyoid neck dissection should be the elective treatment to the neck in patients with cN0 SCC of the tongue by consideration of the clinical and pathological factors for the depth of invasion, forms of growth, pathological grade, and degree of differentiation.
