Prediction of pathological nodal involvement by <scp>CT</scp>‐based Radiomic features of the primary tumor in patients with clinically node‐negative peripheral lung adenocarcinomas

Liu, Ying; Kim, Jongphil; Balagurunathan, Yoganand; Hawkins, Samuel; Stringfield, Olya; Schabath, Matthew B.; Li, Qian; Qu, Fangyuan; Liu, Shichang; García, Alberto López; Ye, Zhaoxiang; Gillies, Robert J.

doi:10.1002/mp.12901

Cited by 31 publications

(38 citation statements)

References 49 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The predicative AUC values based on the radiomic analyses regarding the patients who had both pre-surgical node-positive and node-negative in the CT scans were 0.86 from 159 patients [16]. For CT-reported N0 adenocarcinoma patients, the predictive AUC values were 0.91 from 492 patients [17] and 0.76 from 153 patients [18] based on the radiomic analyses, respectively. The distinct factors of our study were that (1) we used a relatively larger data set with 649 presurgical CT-based stage IA NSCLC patients, (2) we retrospectively reviewed all the CECT scans for the confirmation of the patients with imaging LN status, and (3) we applied the radiomic analyses in the three subgroups (age, gender, and smoking status) of the clinical stage IA NSCLC patients.…”

Section: Discussionmentioning

confidence: 92%

“…(6) The ROI included bronchi, blood vessels, and vacuoles within the nodules, excluding normal lung tissue. Previous studies [16][17][18] had reported that the radiomic analyses were capable of predicting the LNM in the patients with lung adenocarcinoma. The predicative AUC values based on the radiomic analyses regarding the patients who had both pre-surgical node-positive and node-negative in the CT scans were 0.86 from 159 patients [16].…”

Section: Discussionmentioning

confidence: 99%

“…A few retrospective studies established that radiomic analyses could predict LNM using CT scans in both pre-surgically node-positive and node-negative lung adenocarcinoma patients [16][17][18]. We have used only the pre-surgical CT-based stage IA (imaging node-negative) NSCLC patients to predict LNM in this study.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer

Cong

Feng

Ren³

et al. 2020

Lung Cancer

View full text Add to dashboard Cite

To develop and validate predictive models using clinical parameters, radiomic features and a combination of both for lymph node metastasis (LNM) in pre-surgical CT-based stage IA non-small cell lung cancer (NSCLC) patients. Methods: This retrospective study included 649 pre-surgical CT-based stage IA NSCLC patients from our hospital. One hundred and thirty-eight (21 %) of the 649 patients had LNM after surgery. A total of 396 radiomic features were extracted from the venous phase contrast enhanced computed tomography (CECT). The training group included 455 patients (97 with and 358 without LNM) and the testing group included 194 patients (41 with and 153 without LNM). The least absolute shrinkage and selection operator (LASSO) algorithm was used for radiomic feature selection. The random forest (RF) was used for model development. Three models (a clinical model, a radiomics model, and a combined model) were developed to predict LNM in early stage NSCLC patients. The area under the receiver operating characteristic (ROC) curve (AUC) value and decision curve analysis were used to evaluate the performance in LNM status (with or without LNM) using the three models. Results: The ROC analysis (also decision curve analysis) showed predictive performance for LNM of the radiomics model (AUC values for training and testing, respectively 0.898 and 0.851) and of the combined model (0.911 and 0.860, respectively). Both performed better than the clinical model (0.739 and 0.614, respectively; delong test p-values both < 0.001). Conclusion: A radiomics model using the venous phase of CE-CT has potential for predicting LNM in pre-surgical CT-based stage IA NSCLC patients.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer

Cong

Feng

Ren³

et al. 2020

Lung Cancer

View full text Add to dashboard Cite

show abstract

“…136,137 These quantitative features can capture important phenotypic variation and predict malignant or metastatic behavior. [138][139][140][141][142][143][144] Most nodule malignancy risk prediction models to date have estimated the probability of malignancy for pulmonary nodules using regression-based methods. Radiomics approaches have shown potential to produce prediction or classification models from very complex data, as acquired in three-dimensional computed tomography, with a main focus on extracting information directly from the CT images.…”

Section: Q What Are the Recent Advances In Radiomics That May Improvmentioning

confidence: 99%

Management of screen-detected lung nodules: A Canadian partnership against cancer guidance document

Lam

Bryant

Donahoe

et al. 2020

Canadian Journal of Respiratory, Critical Care, and Sleep Medic

View full text Add to dashboard Cite

show abstract

“…• estadiamento, e.g. metástases (LIU et al, 2018;ZHOU et al, 2018;WU et al, 2016a;HUYNH et al, 2016;COROLLER et al, 2015;PARMAR et al, 2015b;AERTS et al, 2014);…”

Section: Estado Da Arteunclassified

Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão

Ferreira¹,

Santos²,

Azevedo-Marques³

View full text Add to dashboard Cite

Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão São Carlos 2019 1. Câncer de pulmão. 2. Radiômica. 3. Reconhecimento de padrões. 4. Classificação de imagens médicas. 5. Recuperação de imagens baseada em conteúdo. 6. Análise de imagens médicas. I. Título. Eduardo Graziosi Silva -CRB -8/8907 Aos meus pais, Raniery e Magal, pelo amor e pela educação que sempre me deram. À minha esposa, Priscilla, por sua "paxão" e compreensão em todos os momentos. AGRADECIMENTOS À toda a minha família, em especial, meus irmãos, Bruno e Lígia, meus sogros, Junior e Wirlene, e meus cunhados, Anderson e Deysi, pelo apoio dado durante todo o caminho de pós-graduação percorrido. Aos meus orientadores, Paulo, Marcel e Yoshida, pelas oportunidades dadas, pelos ensinamentos e, principalmente, pela paciência. Aos doutores Marcello, Tinós, Alexandre e Federico por todas as valiosas contribuições dadas durante meu período na USP. Aos amigos do LaTIM/UFAL, Marcelo, Lucas, Ailton e Tércio, pelas sugestões e discussões sempre produtivas para a pesquisa. Aos amigos do CCIFMpelos bons momentos de convivência e todo o suporte dado para o desenvolvimento do trabalho. Aos amigos do MGH, Yasuka, Toru e Janne, por todo o auxílio prestado durante meu estágio no exterior de doutorado sanduíche. Ao pessoal da Bioengenharia, Profa Ana Plepis, Marcia e Janete, pela ajuda nos processos burocráticos desde a seleção do doutorado até o depósito da tese. Aos amigos de SP que fiz ou reencontrei, Diógenes, Felipe, Amanda, Samara, Karina, Juninho, Inaê, Danilo e D. Miralda, pela amizade, incentivo e bons momentos compartilhados. Às instituições e programas CAPES (Código de Financiamento 001), USP, PAE, PDSE (processo nº 88881.134004/2016-01), AUCANI, PROAP e FAPESP (processo nº 2016/17078-0), pelas bolsas e apoios financeiros durante todo o curso e pesquisa. E a todos aqueles que me ajudaram direta ou indiretamente, torceram por mim e acreditaram no meu trabalho. "No meio da dificuldade encontra-se a oportunidade." Albert Einstein Palavras-chave: Câncer de pulmão. Radiômica. Reconhecimento de padrões. Classificação de imagens médicas. Recuperação de imagens baseada em conteúdo. Análise de imagens médicas. ABSTRACT FERREIRA JUNIOR, J.R. Framework for Classification, Content-Based Retrieval, and Radiomics of Medical Images: an investigation of quantitative biomarkers for lung cancer. 2019. 183p. Tese (Doutorado) -Escola de Engenharia de São Carlos, Universidade de São Paulo, São Carlos, 2019.Systems of computer-aided diagnosis (CAD), content-based image retrieval (CBIR), and radiomics have been developed to increase diagnostic accuracy, medical image interpretation consistency, patient prognostic assessment, and therapy decision support. Those tools have great potential to recognize objectively and precisely patterns in images, despite still having several limitations. This work aimed to decrease the feature gap, which refers to inefficient numeric representa...

show abstract

Prediction of pathological nodal involvement by CT‐based Radiomic features of the primary tumor in patients with clinically node‐negative peripheral lung adenocarcinomas

Abstract: Features derived on primary lung tumor described by semantic and radiomic could provide information of pathological nodal involvement in clinical N0 peripheral lung adenocarcinomas.

Cited by 31 publications

References 49 publications

Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer

Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer

Management of screen-detected lung nodules: A Canadian partnership against cancer guidance document

Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão

Contact Info

Product

Resources

About