Yan Xu1, Lin Lu2, Shawn H Sun3, Lin-Ning E4, Wei Lian5, Hao Yang3, Lawrence H Schwartz3, Zheng-Han Yang1, Binsheng Zhao3. 1. Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. 2. Department of Radiology, New York Presbyterian Hospital, Columbia University Irving Medical Center, 630 West 168th Street, New York, NY, 10032, USA. ll2860@cumc.columbia.edu. 3. Department of Radiology, New York Presbyterian Hospital, Columbia University Irving Medical Center, 630 West 168th Street, New York, NY, 10032, USA. 4. Department of Radiology, Shanxi DAYI Hospital, 99 Longcheng Street, Taiyuan, 030032, Shanxi, China. 5. Department of CT, Third People's Hospital, 75 Juchang Street, Yancheng, 224001, Jiangsu, China.
Abstract
OBJECTIVES: To investigate the effect of CT image acquisition parameters on the performance of radiomics in classifying benign and malignant pulmonary nodules (PNs) with respect to nodule size. METHODS: We retrospectively collected CT images of 696 patients with PNs from March 2015 to March 2018. PNs were grouped by nodule diameter: T1a (diameter ≤ 1.0 cm), T1b (1.0 cm < diameter ≤ 2.0 cm), and T1c (2.0 cm < diameter ≤ 3.0 cm). CT images were divided into four settings according to slice-thickness-convolution-kernels: setting 1 (slice thickness/reconstruction type: 1.25 mm sharp), setting 2 (5 mm sharp), setting 3 (5 mm smooth), and random setting. We created twelve groups from two interacting conditions. Each PN was segmented and had 1160 radiomics features extracted. Non-redundant features with high predictive ability in training were selected to build a distinct model under each of the twelve subsets. RESULTS: The performance (AUCs) on predicting PN malignancy were as follows: T1a group: 0.84, 0.64, 0.68, and 0.68; T1b group: 0.68, 0.74, 0.76, and 0.70; T1c group: 0.66, 0.64, 0.63, and 0.70, for the setting 1, setting 2, setting 3, and random setting, respectively. In the T1a group, the AUC of radiomics model in setting 1 was statistically significantly higher than all others; In the T1b group, AUCs of radiomics models in setting 3 were statistically significantly higher than some; and in the T1c group, there were no statistically significant differences among models. CONCLUSIONS: For PNs less than 1 cm, CT image acquisition parameters have a significant influence on diagnostic performance of radiomics in predicting malignancy, and a model created using images reconstructed with thin section and a sharp kernel algorithm achieved the best performance. For PNs larger than 1 cm, CT reconstruction parameters did not affect diagnostic performance substantially. KEY POINTS: • CT image acquisition parameters have a significant influence on the diagnostic performance of radiomics in pulmonary nodules less than 1 cm. • In pulmonary nodules less than 1 cm, a radiomics model created by using images reconstructed with thin section and a sharp kernel algorithm achieved the best diagnostic performance. • For PNs larger than 1 cm, CT image acquisition parameters do not affect diagnostic performance substantially.
OBJECTIVES: To investigate the effect of CT image acquisition parameters on the performance of radiomics in classifying benign and malignant pulmonary nodules (PNs) with respect to nodule size. METHODS: We retrospectively collected CT images of 696 patients with PNs from March 2015 to March 2018. PNs were grouped by nodule diameter: T1a (diameter ≤ 1.0 cm), T1b (1.0 cm < diameter ≤ 2.0 cm), and T1c (2.0 cm < diameter ≤ 3.0 cm). CT images were divided into four settings according to slice-thickness-convolution-kernels: setting 1 (slice thickness/reconstruction type: 1.25 mm sharp), setting 2 (5 mm sharp), setting 3 (5 mm smooth), and random setting. We created twelve groups from two interacting conditions. Each PN was segmented and had 1160 radiomics features extracted. Non-redundant features with high predictive ability in training were selected to build a distinct model under each of the twelve subsets. RESULTS: The performance (AUCs) on predicting PN malignancy were as follows: T1a group: 0.84, 0.64, 0.68, and 0.68; T1b group: 0.68, 0.74, 0.76, and 0.70; T1c group: 0.66, 0.64, 0.63, and 0.70, for the setting 1, setting 2, setting 3, and random setting, respectively. In the T1a group, the AUC of radiomics model in setting 1 was statistically significantly higher than all others; In the T1b group, AUCs of radiomics models in setting 3 were statistically significantly higher than some; and in the T1c group, there were no statistically significant differences among models. CONCLUSIONS: For PNs less than 1 cm, CT image acquisition parameters have a significant influence on diagnostic performance of radiomics in predicting malignancy, and a model created using images reconstructed with thin section and a sharp kernel algorithm achieved the best performance. For PNs larger than 1 cm, CT reconstruction parameters did not affect diagnostic performance substantially. KEY POINTS: • CT image acquisition parameters have a significant influence on the diagnostic performance of radiomics in pulmonary nodules less than 1 cm. • In pulmonary nodules less than 1 cm, a radiomics model created by using images reconstructed with thin section and a sharp kernel algorithm achieved the best diagnostic performance. • For PNs larger than 1 cm, CT image acquisition parameters do not affect diagnostic performance substantially.
Authors: Denise R Aberle; Sarah DeMello; Christine D Berg; William C Black; Brenda Brewer; Timothy R Church; Kathy L Clingan; Fenghai Duan; Richard M Fagerstrom; Ilana F Gareen; Constantine A Gatsonis; David S Gierada; Amanda Jain; Gordon C Jones; Irene Mahon; Pamela M Marcus; Joshua M Rathmell; JoRean Sicks Journal: N Engl J Med Date: 2013-09-05 Impact factor: 91.245
Authors: Virendra Kumar; Yuhua Gu; Satrajit Basu; Anders Berglund; Steven A Eschrich; Matthew B Schabath; Kenneth Forster; Hugo J W L Aerts; Andre Dekker; David Fenstermacher; Dmitry B Goldgof; Lawrence O Hall; Philippe Lambin; Yoganand Balagurunathan; Robert A Gatenby; Robert J Gillies Journal: Magn Reson Imaging Date: 2012-08-13 Impact factor: 2.546
Authors: Philippe Lambin; Emmanuel Rios-Velazquez; Ralph Leijenaar; Sara Carvalho; Ruud G P M van Stiphout; Patrick Granton; Catharina M L Zegers; Robert Gillies; Ronald Boellard; André Dekker; Hugo J W L Aerts Journal: Eur J Cancer Date: 2012-01-16 Impact factor: 9.162
Authors: Saeed S Alahmari; Dmitry Cherezov; Dmitry Goldgof; Lawrence Hall; Robert J Gillies; Matthew B Schabath Journal: IEEE Access Date: 2018-11-29 Impact factor: 3.367
Authors: Giulia Veronesi; Patrick Maisonneuve; Massimo Bellomi; Cristiano Rampinelli; Iara Durli; Raffaella Bertolotti; Lorenzo Spaggiari Journal: Ann Intern Med Date: 2012-12-04 Impact factor: 25.391