Background: Owing to the use of tobacco and the consumption of alcohol and adulterated food, worldwide cancer incidence is increasing at an alarming and frightening rate. Since the last decade of the twentieth century...Background: Owing to the use of tobacco and the consumption of alcohol and adulterated food, worldwide cancer incidence is increasing at an alarming and frightening rate. Since the last decade of the twentieth century, lung cancer has been the most common cancer type. This study aimed to determine the global status of lung cancer and to evaluate the use of computational methods in the early detection of lung cancer.Methods: We used lung cancer data from the United Kingdom(UK), the United States(US), India, and Egypt. For statistical analysis, we used incidence and mortality as well as survival rates to better understand the critical state of lung cancer.Results: In the UK and the US, we found a significant decrease in lung cancer mortalities in the period of 1990–2014, whereas, in India and Egypt, such a decrease was not much promising. Additionally, we observed that, in the UK and the US, the survival rates of women with lung cancer were higher than those of men. We observed that the data mining and evolutionary algorithms were efficient in lung cancer detection.Conclusions: Our findings provide an inclusive understanding of the incidences, mortalities, and survival rates of lung cancer in the UK, the US, India, and Egypt. The combined use of data mining and evolutionary algorithm can be efficient in lung cancer detection.展开更多
In this paper, a wavelet packet feature selection method for lung sounds based on optimization is proposed to obtain the best feature set which maximizes the differences between normal lung sounds and abnormal lung so...In this paper, a wavelet packet feature selection method for lung sounds based on optimization is proposed to obtain the best feature set which maximizes the differences between normal lung sounds and abnormal lung sounds(sounds with wheezes or rales). The proposed method includes two main steps: Firstly, the wavelet packet transform(WPT) is used to extract the original features of lung sounds; then the genetic algorithm(GA) is used to select the best feature set. The obtained optimal feature set is sent to four different classifiers to evaluate the performance of the proposed method. Experimental results show that the feature set obtained by the proposed method provides a higher classification accuracy of 94.6% in comparison with the best wavelet packet basis approach and multi-scale principal component analysis(PCA) approach. Meanwhile, the proposed method has effective generalization performance and can obtain the best feature set without priori knowledge of lung sounds.展开更多
Advanced processing of lung sound (LS) recording is a significant means to separate heart sounds (HS) and combined low frequency noise from instruments (NI), with saving its characteristics. This paper proposes a new ...Advanced processing of lung sound (LS) recording is a significant means to separate heart sounds (HS) and combined low frequency noise from instruments (NI), with saving its characteristics. This paper proposes a new method of LS filtering which separates HS and NI simultaneously. It focuses on the application of least mean squares (LMS) algorithm with adaptive noise cancelling (ANC) technique. The second step of the new method is to modulate the reference input r1(n) of LMS-ANC to acquiesce combining HS and NI signals. The obtained signal is removed from primary signal (original lung sound recording-LS). The original signal is recorded from subjects and derived HS from it and it is modified by a band pass filter. NI is simulated by generating approximately periodic white gaussian noise (WGN) signal. The LMS-ANC designed algorithm is controlled in order to determine the optimum values of the order L and the coefficient convergence μ. The output results are measured using power special density (PSD), which has shown the effectiveness of our suggested method. The result also has shown visual difference PSD (to) normal and abnormal LS recording. The results show that the method is a good technique for heart sound and noise reduction from lung sounds recordings simultaneously with saving LS characteristics.展开更多
目的应用随机森林(Random Forest,RF)算法建立模型在CT平扫数据上对原发性肺癌,包括小细胞肺癌、腺癌以及鳞癌进行分类鉴别和预测,并评估其可行性。方法回顾性纳入2013年1月至2018年8月在复旦大学附属中山医院经穿刺或手术后病理证实的...目的应用随机森林(Random Forest,RF)算法建立模型在CT平扫数据上对原发性肺癌,包括小细胞肺癌、腺癌以及鳞癌进行分类鉴别和预测,并评估其可行性。方法回顾性纳入2013年1月至2018年8月在复旦大学附属中山医院经穿刺或手术后病理证实的,且在术前接受CT检查的852例原发性肺癌患者(肺腺癌525例、肺鳞癌161例、小细胞肺癌166例)。将病理结果与患者CT平扫数据进行匹配并添加标签,利用影像组学特征和RF算法模型对3种不同病理类型的肺癌进行分类诊断和预测。纳入数据分为训练组(724例)和测试组(128例),用于测试评估分类模型诊断效能,采用F1值、受试者工作特征曲线分析及曲线下面积(Area Under Curve,AUC)评估模型的分类预测能力。结果测试组中RF分类模型对腺癌、鳞癌和小细胞肺癌分类诊断的AUC分别为0.74、0.77、0.88,对肺腺癌、鳞癌及小细胞肺癌分类诊断的F1值分别为0.80、0.40、0.73,F1加权平均值为0.71,其中,分类模型对腺癌、鳞癌、小细胞肺癌的分类预测的精确率分别为0.76、0.64、0.70;召回率分别为0.86、0.29、0.76;特异性分别为0.55、0.96、0.92。结论利用影像组学提取特征和RF算法分类模型结合,能够有效地在CT平扫数据上对肺腺癌、鳞癌和小细胞肺癌进行分类预测,可为发展无创性的原发性肺癌病理分类诊断方法提供参考依据。展开更多
文摘Background: Owing to the use of tobacco and the consumption of alcohol and adulterated food, worldwide cancer incidence is increasing at an alarming and frightening rate. Since the last decade of the twentieth century, lung cancer has been the most common cancer type. This study aimed to determine the global status of lung cancer and to evaluate the use of computational methods in the early detection of lung cancer.Methods: We used lung cancer data from the United Kingdom(UK), the United States(US), India, and Egypt. For statistical analysis, we used incidence and mortality as well as survival rates to better understand the critical state of lung cancer.Results: In the UK and the US, we found a significant decrease in lung cancer mortalities in the period of 1990–2014, whereas, in India and Egypt, such a decrease was not much promising. Additionally, we observed that, in the UK and the US, the survival rates of women with lung cancer were higher than those of men. We observed that the data mining and evolutionary algorithms were efficient in lung cancer detection.Conclusions: Our findings provide an inclusive understanding of the incidences, mortalities, and survival rates of lung cancer in the UK, the US, India, and Egypt. The combined use of data mining and evolutionary algorithm can be efficient in lung cancer detection.
基金Funded by the International Science and Technology Cooperation Foundation of Chongqing Science and Technology Commission(Grant No.cstc2012gg-gjhz0023)the 2013 Innovative Team Construction Project of Chongqing Universities
文摘In this paper, a wavelet packet feature selection method for lung sounds based on optimization is proposed to obtain the best feature set which maximizes the differences between normal lung sounds and abnormal lung sounds(sounds with wheezes or rales). The proposed method includes two main steps: Firstly, the wavelet packet transform(WPT) is used to extract the original features of lung sounds; then the genetic algorithm(GA) is used to select the best feature set. The obtained optimal feature set is sent to four different classifiers to evaluate the performance of the proposed method. Experimental results show that the feature set obtained by the proposed method provides a higher classification accuracy of 94.6% in comparison with the best wavelet packet basis approach and multi-scale principal component analysis(PCA) approach. Meanwhile, the proposed method has effective generalization performance and can obtain the best feature set without priori knowledge of lung sounds.
文摘Advanced processing of lung sound (LS) recording is a significant means to separate heart sounds (HS) and combined low frequency noise from instruments (NI), with saving its characteristics. This paper proposes a new method of LS filtering which separates HS and NI simultaneously. It focuses on the application of least mean squares (LMS) algorithm with adaptive noise cancelling (ANC) technique. The second step of the new method is to modulate the reference input r1(n) of LMS-ANC to acquiesce combining HS and NI signals. The obtained signal is removed from primary signal (original lung sound recording-LS). The original signal is recorded from subjects and derived HS from it and it is modified by a band pass filter. NI is simulated by generating approximately periodic white gaussian noise (WGN) signal. The LMS-ANC designed algorithm is controlled in order to determine the optimum values of the order L and the coefficient convergence μ. The output results are measured using power special density (PSD), which has shown the effectiveness of our suggested method. The result also has shown visual difference PSD (to) normal and abnormal LS recording. The results show that the method is a good technique for heart sound and noise reduction from lung sounds recordings simultaneously with saving LS characteristics.
文摘目的应用随机森林(Random Forest,RF)算法建立模型在CT平扫数据上对原发性肺癌,包括小细胞肺癌、腺癌以及鳞癌进行分类鉴别和预测,并评估其可行性。方法回顾性纳入2013年1月至2018年8月在复旦大学附属中山医院经穿刺或手术后病理证实的,且在术前接受CT检查的852例原发性肺癌患者(肺腺癌525例、肺鳞癌161例、小细胞肺癌166例)。将病理结果与患者CT平扫数据进行匹配并添加标签,利用影像组学特征和RF算法模型对3种不同病理类型的肺癌进行分类诊断和预测。纳入数据分为训练组(724例)和测试组(128例),用于测试评估分类模型诊断效能,采用F1值、受试者工作特征曲线分析及曲线下面积(Area Under Curve,AUC)评估模型的分类预测能力。结果测试组中RF分类模型对腺癌、鳞癌和小细胞肺癌分类诊断的AUC分别为0.74、0.77、0.88,对肺腺癌、鳞癌及小细胞肺癌分类诊断的F1值分别为0.80、0.40、0.73,F1加权平均值为0.71,其中,分类模型对腺癌、鳞癌、小细胞肺癌的分类预测的精确率分别为0.76、0.64、0.70;召回率分别为0.86、0.29、0.76;特异性分别为0.55、0.96、0.92。结论利用影像组学提取特征和RF算法分类模型结合,能够有效地在CT平扫数据上对肺腺癌、鳞癌和小细胞肺癌进行分类预测,可为发展无创性的原发性肺癌病理分类诊断方法提供参考依据。
