The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening

Rongkai Yan, Saeed Ashrafinia, Seyoun Park, Junghoon Lee, Linda Chi Hang Chu, Cheng Lin, Amira Hussien, Nagina Malguria, Jon Steingrimsson, Arman Rahmim, Peng Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

-Standard computed tomography (CT) scan is performed on lung cancer patients for progression and lesion classification. However, low-dose CT (LDCT) is commonly used in lung cancer screening for high-risk people. Extensive studies have shown that computer-aided diagnosis (CAD) using standard CT could greatly improve the diagnostic accuracy of early lung cancer. Unlike standard CT imaging, the application of radiological texture features extracted by radiologists on LDCT imaging is not well established due to lower resolution and higher variations. The purpose of this study is to investigate possible diagnosis value of texture features by comparing the classification performance of radiologic reading with radiologic reading combined with computer-aided texture features. A total of 186 biopsy-confirmed control and lung cancer cases were obtained from the National Lung Screening Trial (NLST). Cases were matched by various clinical parameters including age, gender, smoking status, chronic obstructive pulmonary disease (COPD) status, body mass index (BMI) and image appearances. We compared the subjective diagnosis of benign/malignant with the consensus readings of three radiologists. We then developed a CAD framework that imports radiologic reading features and extracts CAD features for heterogeneity quantification and data analysis. A total of 1342 CAD features were extracted. After eliminating highly correlated and redundant features, the remaining 458 features were given to a random forest algorithm, and a predicted probability of malignancy score (Pm) was calculated. Patients were grouped into 140 training (70 biopsypositive for cancer and 70 negatives) and 46 testing (20 positives and 26 negatives) sets, and a threshold value over Pm (0.5) was then used to classify the test set into cancer and non-cancer. Clinical accuracy [sensitivity, specificity, positive predictive value (PPV), and negative predictive value (PV)] were [0.95, 0.88, 0.86, 0.96] and [0.70, 0.69, 0.64, 0.75] for the CAD and radiologic reading, respectively. The CAD framework incorporating the clinical reading with the texture features extracted from LDCT increased the PPV and reduced the false positive (FP) rate in the early diagnosis of lung cancer. This approach shows promise for improving the accuracy of lung cancer diagnosis in the clinical environment, especially in patients with well-established risk factors.

Original languageEnglish (US)
Title of host publication2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538622827
DOIs
StatePublished - Nov 12 2018
Event2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Atlanta, United States
Duration: Oct 21 2017Oct 28 2017

Other

Other2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017
CountryUnited States
CityAtlanta
Period10/21/1710/28/17

Fingerprint

Image texture
Computer aided diagnosis
nodules
Early Detection of Cancer
lungs
Tomography
Lung Neoplasms
Screening
screening
textures
tomography
cancer
dosage
Lung
Reading
Textures
Imaging techniques
Pulmonary diseases
Biopsy
Neoplasms

ASJC Scopus subject areas

  • Instrumentation
  • Radiology Nuclear Medicine and imaging
  • Nuclear and High Energy Physics

Cite this

Yan, R., Ashrafinia, S., Park, S., Lee, J., Chu, L. C. H., Lin, C., ... Huang, P. (2018). The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening. In 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings [8532656] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NSSMIC.2017.8532656

The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening. / Yan, Rongkai; Ashrafinia, Saeed; Park, Seyoun; Lee, Junghoon; Chu, Linda Chi Hang; Lin, Cheng; Hussien, Amira; Malguria, Nagina; Steingrimsson, Jon; Rahmim, Arman; Huang, Peng.

2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. 8532656.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yan, R, Ashrafinia, S, Park, S, Lee, J, Chu, LCH, Lin, C, Hussien, A, Malguria, N, Steingrimsson, J, Rahmim, A & Huang, P 2018, The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening. in 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings., 8532656, Institute of Electrical and Electronics Engineers Inc., 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017, Atlanta, United States, 10/21/17. https://doi.org/10.1109/NSSMIC.2017.8532656
Yan R, Ashrafinia S, Park S, Lee J, Chu LCH, Lin C et al. The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening. In 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. 8532656 https://doi.org/10.1109/NSSMIC.2017.8532656
Yan, Rongkai ; Ashrafinia, Saeed ; Park, Seyoun ; Lee, Junghoon ; Chu, Linda Chi Hang ; Lin, Cheng ; Hussien, Amira ; Malguria, Nagina ; Steingrimsson, Jon ; Rahmim, Arman ; Huang, Peng. / The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening. 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{bdf3300155c74babb332989a6509bcae,
title = "The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening",
abstract = "-Standard computed tomography (CT) scan is performed on lung cancer patients for progression and lesion classification. However, low-dose CT (LDCT) is commonly used in lung cancer screening for high-risk people. Extensive studies have shown that computer-aided diagnosis (CAD) using standard CT could greatly improve the diagnostic accuracy of early lung cancer. Unlike standard CT imaging, the application of radiological texture features extracted by radiologists on LDCT imaging is not well established due to lower resolution and higher variations. The purpose of this study is to investigate possible diagnosis value of texture features by comparing the classification performance of radiologic reading with radiologic reading combined with computer-aided texture features. A total of 186 biopsy-confirmed control and lung cancer cases were obtained from the National Lung Screening Trial (NLST). Cases were matched by various clinical parameters including age, gender, smoking status, chronic obstructive pulmonary disease (COPD) status, body mass index (BMI) and image appearances. We compared the subjective diagnosis of benign/malignant with the consensus readings of three radiologists. We then developed a CAD framework that imports radiologic reading features and extracts CAD features for heterogeneity quantification and data analysis. A total of 1342 CAD features were extracted. After eliminating highly correlated and redundant features, the remaining 458 features were given to a random forest algorithm, and a predicted probability of malignancy score (Pm) was calculated. Patients were grouped into 140 training (70 biopsypositive for cancer and 70 negatives) and 46 testing (20 positives and 26 negatives) sets, and a threshold value over Pm (0.5) was then used to classify the test set into cancer and non-cancer. Clinical accuracy [sensitivity, specificity, positive predictive value (PPV), and negative predictive value (PV)] were [0.95, 0.88, 0.86, 0.96] and [0.70, 0.69, 0.64, 0.75] for the CAD and radiologic reading, respectively. The CAD framework incorporating the clinical reading with the texture features extracted from LDCT increased the PPV and reduced the false positive (FP) rate in the early diagnosis of lung cancer. This approach shows promise for improving the accuracy of lung cancer diagnosis in the clinical environment, especially in patients with well-established risk factors.",
author = "Rongkai Yan and Saeed Ashrafinia and Seyoun Park and Junghoon Lee and Chu, {Linda Chi Hang} and Cheng Lin and Amira Hussien and Nagina Malguria and Jon Steingrimsson and Arman Rahmim and Peng Huang",
year = "2018",
month = "11",
day = "12",
doi = "10.1109/NSSMIC.2017.8532656",
language = "English (US)",
booktitle = "2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening

AU - Yan, Rongkai

AU - Ashrafinia, Saeed

AU - Park, Seyoun

AU - Lee, Junghoon

AU - Chu, Linda Chi Hang

AU - Lin, Cheng

AU - Hussien, Amira

AU - Malguria, Nagina

AU - Steingrimsson, Jon

AU - Rahmim, Arman

AU - Huang, Peng

PY - 2018/11/12

Y1 - 2018/11/12

N2 - -Standard computed tomography (CT) scan is performed on lung cancer patients for progression and lesion classification. However, low-dose CT (LDCT) is commonly used in lung cancer screening for high-risk people. Extensive studies have shown that computer-aided diagnosis (CAD) using standard CT could greatly improve the diagnostic accuracy of early lung cancer. Unlike standard CT imaging, the application of radiological texture features extracted by radiologists on LDCT imaging is not well established due to lower resolution and higher variations. The purpose of this study is to investigate possible diagnosis value of texture features by comparing the classification performance of radiologic reading with radiologic reading combined with computer-aided texture features. A total of 186 biopsy-confirmed control and lung cancer cases were obtained from the National Lung Screening Trial (NLST). Cases were matched by various clinical parameters including age, gender, smoking status, chronic obstructive pulmonary disease (COPD) status, body mass index (BMI) and image appearances. We compared the subjective diagnosis of benign/malignant with the consensus readings of three radiologists. We then developed a CAD framework that imports radiologic reading features and extracts CAD features for heterogeneity quantification and data analysis. A total of 1342 CAD features were extracted. After eliminating highly correlated and redundant features, the remaining 458 features were given to a random forest algorithm, and a predicted probability of malignancy score (Pm) was calculated. Patients were grouped into 140 training (70 biopsypositive for cancer and 70 negatives) and 46 testing (20 positives and 26 negatives) sets, and a threshold value over Pm (0.5) was then used to classify the test set into cancer and non-cancer. Clinical accuracy [sensitivity, specificity, positive predictive value (PPV), and negative predictive value (PV)] were [0.95, 0.88, 0.86, 0.96] and [0.70, 0.69, 0.64, 0.75] for the CAD and radiologic reading, respectively. The CAD framework incorporating the clinical reading with the texture features extracted from LDCT increased the PPV and reduced the false positive (FP) rate in the early diagnosis of lung cancer. This approach shows promise for improving the accuracy of lung cancer diagnosis in the clinical environment, especially in patients with well-established risk factors.

AB - -Standard computed tomography (CT) scan is performed on lung cancer patients for progression and lesion classification. However, low-dose CT (LDCT) is commonly used in lung cancer screening for high-risk people. Extensive studies have shown that computer-aided diagnosis (CAD) using standard CT could greatly improve the diagnostic accuracy of early lung cancer. Unlike standard CT imaging, the application of radiological texture features extracted by radiologists on LDCT imaging is not well established due to lower resolution and higher variations. The purpose of this study is to investigate possible diagnosis value of texture features by comparing the classification performance of radiologic reading with radiologic reading combined with computer-aided texture features. A total of 186 biopsy-confirmed control and lung cancer cases were obtained from the National Lung Screening Trial (NLST). Cases were matched by various clinical parameters including age, gender, smoking status, chronic obstructive pulmonary disease (COPD) status, body mass index (BMI) and image appearances. We compared the subjective diagnosis of benign/malignant with the consensus readings of three radiologists. We then developed a CAD framework that imports radiologic reading features and extracts CAD features for heterogeneity quantification and data analysis. A total of 1342 CAD features were extracted. After eliminating highly correlated and redundant features, the remaining 458 features were given to a random forest algorithm, and a predicted probability of malignancy score (Pm) was calculated. Patients were grouped into 140 training (70 biopsypositive for cancer and 70 negatives) and 46 testing (20 positives and 26 negatives) sets, and a threshold value over Pm (0.5) was then used to classify the test set into cancer and non-cancer. Clinical accuracy [sensitivity, specificity, positive predictive value (PPV), and negative predictive value (PV)] were [0.95, 0.88, 0.86, 0.96] and [0.70, 0.69, 0.64, 0.75] for the CAD and radiologic reading, respectively. The CAD framework incorporating the clinical reading with the texture features extracted from LDCT increased the PPV and reduced the false positive (FP) rate in the early diagnosis of lung cancer. This approach shows promise for improving the accuracy of lung cancer diagnosis in the clinical environment, especially in patients with well-established risk factors.

UR - http://www.scopus.com/inward/record.url?scp=85058482956&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058482956&partnerID=8YFLogxK

U2 - 10.1109/NSSMIC.2017.8532656

DO - 10.1109/NSSMIC.2017.8532656

M3 - Conference contribution

AN - SCOPUS:85058482956

BT - 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -