Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of ...Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis,thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis.Methods In total,623 eligible patients were recruited from two medical institutions.Seven deep learning models,namely Alex,GoogLeNet,Resnet18,Resnet101,Vgg16,Vgg19,and MobileNetv3(small),were utilized to extract deep image histological features.The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient(r≥0.9)and Least Absolute Shrinkage and Selection Operator.Eleven machine learning methods,namely Support Vector Machine,K-nearest neighbor,Random Forest,Extra Trees,XGBoost,LightGBM,Naive Bayes,AdaBoost,Gradient Boosting Decision Tree,Linear Regression,and Multilayer Perceptron,were employed to construct classification prediction models for the filtered final features.The diagnostic performances of the models were assessed using various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value.Calibration and decision-curve analyses were also performed.Results The present study demonstrated that using deep radiomic features extracted from Vgg16,in conjunction with a prediction model constructed via a linear regression algorithm,effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer.The performance of the model was evaluated based on various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value,which yielded values of 0.808,0.834,0.851,0.745,0.829,and 0.776,respectively.The validation set of the model was assessed using clinical decision curves,calibration curves,and confusion matrices,which collectively demonstrated the model's stability and accuracy.Conclusion In this study,information on the deep radiomics of Vgg16 was obtained from computed tomography images,and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.展开更多
Since the latest revision of the TNM system reclassified T3N0 tumours into the ⅡB stage, N2 lesions became the major determinant of the ⅢA stage. Concerning the minority of patients with T3N1 tumours in this stage,
Objective: To investigate pathologically the characteristics of lung cancer metastasis by mediastinal lymph node ways (N2). Methods: Of 398 lung cancer patients who underwent radical pulmonectomy and extensive lymph n...Objective: To investigate pathologically the characteristics of lung cancer metastasis by mediastinal lymph node ways (N2). Methods: Of 398 lung cancer patients who underwent radical pulmonectomy and extensive lymph node dissection, 160 patients were diagnosed as with N2 metastasis, their 352 groups of mediastinal lymph nodes invaded were subject to the pathological study. Results: Evidences showed that the N2 metastasis of lung cancer was very active. It appears as single group or multi-group or jumping-form metastasis, rating 41.2%, 58.8% and 29.3% respectively. In addition, the extension of N2 metastasis was large, the most concentrated site was the 7th group lymph node (48.8%), then the 4th, 3rd and 5th group, rating 45.6%, 31.3% and 25.6% respectively. The occurrence of N2 metastasis was highly correlated with the site, size, histopathological type and the grade of differentiation of the cancer. An another feature of N2 metastasis was the invasion of metastasized lymph node into the bronchial wall, especially in adenocarcinoma. Conclusion: In order to achieve the radical removal of tumor, it is necessary to dissect the lymph nodes of the hilar and upper and lower mediastinum at the homolateral thoracic cavity actively and completely; beside, attention may be paid to the bronchial wall invasion caused by the lymph nodes metastasized.展开更多
Objective: Advances in diagnostic imaging techniques, such as 18F-fluorodeoxyglucose positron emission tomography (FDG-PET), have led to greater accuracy in preoperative mediastinal staging for patients with non-small...Objective: Advances in diagnostic imaging techniques, such as 18F-fluorodeoxyglucose positron emission tomography (FDG-PET), have led to greater accuracy in preoperative mediastinal staging for patients with non-small-cell lung cancer (NSCLC), but surgical staging remains the “gold standard” for diagnosis. A proper understanding of the current accuracy of diagnostic imaging is needed for further improvements. Methods: Forty-three patients who underwent resection for NSCLC involving mediastinal lymph node (MLN) metastasis at our hospital between June 2003 and May 2011 were enrolled in this study. We conducted a retrospective study of the radiological and pathological findings for 53 metastatic MLNs in the 43 patients. Results: The preoperative imaging modality was computed tomography (CT) alone for 18 patients (22 MLNs) and CT and FDG-PET for 25 patients (31 MLNs). The sensitivities of CT and FDG-PET were 41.5% and 58.0%, respectively. The sensitivity of CT did not differ according to any clinicopathological factors, but the sensitivity of FDG-PET tended to be higher for primary tumors with high SUVmax values and for non-adenocarcinomas. In the lymph nodes, all micrometastatic foci ≤ 2 mm were PET-negative, but 4 lymph nodes with metastatic foci larger than 10 mm were also PET-negative. Conclusions: For the diagnostic imaging of MLN, FDG-PET has a greater sensitivity than contrast-enhanced CT based on “size criteria”, but it is still not sufficiently sensitive and is influenced by various factors. At present, histological confirmation of MLNs is necessary when making decisions regarding treatment plans and the type of surgical procedure that should be performed.展开更多
Radical gastrectomy has been recognized as the standard surgical treatment for advanced gastric cancer, and essentially applied in a wide variety of clinical settings. The thoroughness of lymph node dissection is an i...Radical gastrectomy has been recognized as the standard surgical treatment for advanced gastric cancer, and essentially applied in a wide variety of clinical settings. The thoroughness of lymph node dissection is an important prognostic factor for patients with advanced gastric cancer. Splenic lymph node dissection is required during D2 radical gastrectomy for upper stomach cancer. This is often accompanied by removal of the spleen in the past few decades. A growing number of investigators believe, however, that the spleen plays an important role as an immune organ, and thus they encourage the application of a spleen- preserving method for splenic hilum lymph node dissection.展开更多
Background： Pathophysiological processes, such as malignancy, can lead to the formation of stiffer tissue in lung cancers. Endobronchial ultrasound rEBUS） elastography is a novel technique for measuring tissue stiff...Background： Pathophysiological processes, such as malignancy, can lead to the formation of stiffer tissue in lung cancers. Endobronchial ultrasound rEBUS） elastography is a novel technique for measuring tissue stiffness during EBUS-guided transbronchial needle aspiration （EBUS-TBNA）. The current study was conducted to investigate the diagnostic value of EBUS elastography tbr mediastinal and hilar lymph node metastasis in lung cancers. Methods： From January 2014 to January 2015, 40 patients suspected of lung cancer were enrolled, and a total of 68 lymph nodes were evaluated by EBUS-TBNA. EBUS-guided elastography of lymph nodes was perfornaed prior to EBUS-TBNA. Standard EBUS characteristics were also described. Pathological determination of malignant or benign lymph nodes was used as the gold standard for this study. If EBUS-TBNA did not result in a tbrmal pathological diagnosis of malignancy, patients were referred for a surgical procedure. Comparisons of elastography and standard EBUS characteristics were made between benign and malignant lymph nodes. Results： Elastography grading scores and strain ratios showed significant differences between benign and malignant lymph nodes （P = 0.000）. The elastography strain ratio was more sensitive and specific for determining malignant lymph nodes than elastography grading score or standard EBUS criteria. The receiver operating characteristic curve for the elastography strain ratio showed an area under the curve of 0.933. The best cut-off point of the strain ratio for differentiating malignant from benign lymph nodes was 32.07. The elastography strain ratio had a sensitivity of 88.1%, the specificity of 80.8%, positive predictive value of 88.1%, and negative predictive value of 80.8% for distinguishing malignant from benign nodes. The overall accuracy of elastography strain ratio was 85.3%. The strain ratio of malignant and benign lymph nodes positively correlated with the elastography grading score （r = 0.561, P = 0.000）. Conclusions： EBUS elastography can be effectively used to predict mediastinal and hilar lymph node metastases in lung cancer. This noninvasive technique may thus complement standard EBUS and help guide EBUS-TBNA procedures.展开更多
目的:探讨乳腺癌患者采取前哨淋巴结活检(sentinel lymph node biopsy,SLNB)联合改良根治术治疗效果。方法:选取南阳市中心医院接受手术治疗的86例乳腺癌疾病患者,以入院次序为分组原则,分为对照组和观察组,各43例,改良根治术作为对照组...目的:探讨乳腺癌患者采取前哨淋巴结活检(sentinel lymph node biopsy,SLNB)联合改良根治术治疗效果。方法:选取南阳市中心医院接受手术治疗的86例乳腺癌疾病患者,以入院次序为分组原则,分为对照组和观察组,各43例,改良根治术作为对照组,SLNB联合改良根治术作为观察组,对比治疗后两组手术时间、术中出血量、住院时间、临床有效率、糖类抗原125(carbohydrate antigen 125,CA125)、癌胚抗原(carcinoembryonic antigen,CEA)、糖类抗原153(cancer antigens 153,CA153)水平及健康调查简表(the MOS 36-item short form health survey,SF-36)的变化。结果:观察组手术时间、术中出血量、住院时间均明显低于对照组(P<0.05);观察组临床有效率为97.67%显著高于对照组76.74%(P<0.05);观察组术后CA125、CEA、CA153水平与对照组相对比无统计学差异(P>0.05);术后观察组的SF-36量表各项分值均高于对照组(P<0.05)。结论:临床治疗乳腺癌患者时,采取SLNB联合改良根治术治疗,不仅能有效缩短手术及住院时间,降低术中出血量,还可控制术后并发症发生率,促进康复,改善生活质量。展开更多
基金the Science and Technology Funding Project of Hunan Province,China(2023JJ50410)(HX)Key Laboratory of Tumor Precision Medicine,Hunan colleges and Universities Project(2019-379)(QL).
文摘Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis,thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis.Methods In total,623 eligible patients were recruited from two medical institutions.Seven deep learning models,namely Alex,GoogLeNet,Resnet18,Resnet101,Vgg16,Vgg19,and MobileNetv3(small),were utilized to extract deep image histological features.The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient(r≥0.9)and Least Absolute Shrinkage and Selection Operator.Eleven machine learning methods,namely Support Vector Machine,K-nearest neighbor,Random Forest,Extra Trees,XGBoost,LightGBM,Naive Bayes,AdaBoost,Gradient Boosting Decision Tree,Linear Regression,and Multilayer Perceptron,were employed to construct classification prediction models for the filtered final features.The diagnostic performances of the models were assessed using various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value.Calibration and decision-curve analyses were also performed.Results The present study demonstrated that using deep radiomic features extracted from Vgg16,in conjunction with a prediction model constructed via a linear regression algorithm,effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer.The performance of the model was evaluated based on various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value,which yielded values of 0.808,0.834,0.851,0.745,0.829,and 0.776,respectively.The validation set of the model was assessed using clinical decision curves,calibration curves,and confusion matrices,which collectively demonstrated the model's stability and accuracy.Conclusion In this study,information on the deep radiomics of Vgg16 was obtained from computed tomography images,and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.
文摘Since the latest revision of the TNM system reclassified T3N0 tumours into the ⅡB stage, N2 lesions became the major determinant of the ⅢA stage. Concerning the minority of patients with T3N1 tumours in this stage,
文摘Objective: To investigate pathologically the characteristics of lung cancer metastasis by mediastinal lymph node ways (N2). Methods: Of 398 lung cancer patients who underwent radical pulmonectomy and extensive lymph node dissection, 160 patients were diagnosed as with N2 metastasis, their 352 groups of mediastinal lymph nodes invaded were subject to the pathological study. Results: Evidences showed that the N2 metastasis of lung cancer was very active. It appears as single group or multi-group or jumping-form metastasis, rating 41.2%, 58.8% and 29.3% respectively. In addition, the extension of N2 metastasis was large, the most concentrated site was the 7th group lymph node (48.8%), then the 4th, 3rd and 5th group, rating 45.6%, 31.3% and 25.6% respectively. The occurrence of N2 metastasis was highly correlated with the site, size, histopathological type and the grade of differentiation of the cancer. An another feature of N2 metastasis was the invasion of metastasized lymph node into the bronchial wall, especially in adenocarcinoma. Conclusion: In order to achieve the radical removal of tumor, it is necessary to dissect the lymph nodes of the hilar and upper and lower mediastinum at the homolateral thoracic cavity actively and completely; beside, attention may be paid to the bronchial wall invasion caused by the lymph nodes metastasized.
文摘Objective: Advances in diagnostic imaging techniques, such as 18F-fluorodeoxyglucose positron emission tomography (FDG-PET), have led to greater accuracy in preoperative mediastinal staging for patients with non-small-cell lung cancer (NSCLC), but surgical staging remains the “gold standard” for diagnosis. A proper understanding of the current accuracy of diagnostic imaging is needed for further improvements. Methods: Forty-three patients who underwent resection for NSCLC involving mediastinal lymph node (MLN) metastasis at our hospital between June 2003 and May 2011 were enrolled in this study. We conducted a retrospective study of the radiological and pathological findings for 53 metastatic MLNs in the 43 patients. Results: The preoperative imaging modality was computed tomography (CT) alone for 18 patients (22 MLNs) and CT and FDG-PET for 25 patients (31 MLNs). The sensitivities of CT and FDG-PET were 41.5% and 58.0%, respectively. The sensitivity of CT did not differ according to any clinicopathological factors, but the sensitivity of FDG-PET tended to be higher for primary tumors with high SUVmax values and for non-adenocarcinomas. In the lymph nodes, all micrometastatic foci ≤ 2 mm were PET-negative, but 4 lymph nodes with metastatic foci larger than 10 mm were also PET-negative. Conclusions: For the diagnostic imaging of MLN, FDG-PET has a greater sensitivity than contrast-enhanced CT based on “size criteria”, but it is still not sufficiently sensitive and is influenced by various factors. At present, histological confirmation of MLNs is necessary when making decisions regarding treatment plans and the type of surgical procedure that should be performed.
文摘Radical gastrectomy has been recognized as the standard surgical treatment for advanced gastric cancer, and essentially applied in a wide variety of clinical settings. The thoroughness of lymph node dissection is an important prognostic factor for patients with advanced gastric cancer. Splenic lymph node dissection is required during D2 radical gastrectomy for upper stomach cancer. This is often accompanied by removal of the spleen in the past few decades. A growing number of investigators believe, however, that the spleen plays an important role as an immune organ, and thus they encourage the application of a spleen- preserving method for splenic hilum lymph node dissection.
文摘Background： Pathophysiological processes, such as malignancy, can lead to the formation of stiffer tissue in lung cancers. Endobronchial ultrasound rEBUS） elastography is a novel technique for measuring tissue stiffness during EBUS-guided transbronchial needle aspiration （EBUS-TBNA）. The current study was conducted to investigate the diagnostic value of EBUS elastography tbr mediastinal and hilar lymph node metastasis in lung cancers. Methods： From January 2014 to January 2015, 40 patients suspected of lung cancer were enrolled, and a total of 68 lymph nodes were evaluated by EBUS-TBNA. EBUS-guided elastography of lymph nodes was perfornaed prior to EBUS-TBNA. Standard EBUS characteristics were also described. Pathological determination of malignant or benign lymph nodes was used as the gold standard for this study. If EBUS-TBNA did not result in a tbrmal pathological diagnosis of malignancy, patients were referred for a surgical procedure. Comparisons of elastography and standard EBUS characteristics were made between benign and malignant lymph nodes. Results： Elastography grading scores and strain ratios showed significant differences between benign and malignant lymph nodes （P = 0.000）. The elastography strain ratio was more sensitive and specific for determining malignant lymph nodes than elastography grading score or standard EBUS criteria. The receiver operating characteristic curve for the elastography strain ratio showed an area under the curve of 0.933. The best cut-off point of the strain ratio for differentiating malignant from benign lymph nodes was 32.07. The elastography strain ratio had a sensitivity of 88.1%, the specificity of 80.8%, positive predictive value of 88.1%, and negative predictive value of 80.8% for distinguishing malignant from benign nodes. The overall accuracy of elastography strain ratio was 85.3%. The strain ratio of malignant and benign lymph nodes positively correlated with the elastography grading score （r = 0.561, P = 0.000）. Conclusions： EBUS elastography can be effectively used to predict mediastinal and hilar lymph node metastases in lung cancer. This noninvasive technique may thus complement standard EBUS and help guide EBUS-TBNA procedures.
文摘目的:探讨乳腺癌患者采取前哨淋巴结活检(sentinel lymph node biopsy,SLNB)联合改良根治术治疗效果。方法:选取南阳市中心医院接受手术治疗的86例乳腺癌疾病患者,以入院次序为分组原则,分为对照组和观察组,各43例,改良根治术作为对照组,SLNB联合改良根治术作为观察组,对比治疗后两组手术时间、术中出血量、住院时间、临床有效率、糖类抗原125(carbohydrate antigen 125,CA125)、癌胚抗原(carcinoembryonic antigen,CEA)、糖类抗原153(cancer antigens 153,CA153)水平及健康调查简表(the MOS 36-item short form health survey,SF-36)的变化。结果:观察组手术时间、术中出血量、住院时间均明显低于对照组(P<0.05);观察组临床有效率为97.67%显著高于对照组76.74%(P<0.05);观察组术后CA125、CEA、CA153水平与对照组相对比无统计学差异(P>0.05);术后观察组的SF-36量表各项分值均高于对照组(P<0.05)。结论:临床治疗乳腺癌患者时,采取SLNB联合改良根治术治疗,不仅能有效缩短手术及住院时间,降低术中出血量,还可控制术后并发症发生率,促进康复,改善生活质量。
