CT Texture Analysis and Machine Learning Improve Post-ablation Prognostication in Patients with Adrenal Metastases: A Proof of Concept

被引:34
作者
Daye, Dania [1 ]
Staziaki, Pedro, V [2 ]
Furtado, Vanessa Fiorini [3 ]
Tabari, Azadeh [1 ]
Fintelmann, Florian J. [1 ]
Frenk, Nathan Elie [1 ]
Shyn, Paul [4 ]
Tuncali, Kemal [4 ]
Silverman, Stuart [4 ]
Arellano, Ronald [1 ]
Gee, Michael S. [1 ]
Uppot, Raul Nirmal [1 ]
机构
[1] Harvard Med Sch, Massachusetts Gen Hosp, Dept Radiol, 55 Fruit St,GRB 290, Boston, MA 02114 USA
[2] Boston Univ, Sch Med, Dept Radiol, Boston Med Ctr, Boston, MA 02118 USA
[3] Univ Massachusetts, Dept Internal Med, UMass, Worcester, MA 01605 USA
[4] Harvard Med Sch, Brigham & Womens Hosp, Dept Radiol, Boston, MA 02114 USA
关键词
Radiomics; Machine learning; Prognostication; Texture analysis; Ablation; Adrenal metastasis; PERCUTANEOUS MICROWAVE ABLATION; RADIOFREQUENCY ABLATION; ARTIFICIAL-INTELLIGENCE; SINGLE-INSTITUTION; GUIDED ABLATION; CARCINOMA; TUMORS; EXPERIENCE; IMAGES;
D O I
10.1007/s00270-019-02336-0
中图分类号
R5 [内科学];
学科分类号
100201 [内科学];
摘要
Introduction To assess the performance of pre-ablation computed tomography texture features of adrenal metastases to predict post-treatment local progression and survival in patients who underwent ablation using machine learning as a prediction tool. Materials and Methods This is a pilot retrospective study of patients with adrenal metastases undergoing ablation. Clinical variables were collected. Thirty-two texture features were extracted from manually segmented adrenal tumors. A univariate cox proportional hazard model was used for prediction of local progression and survival. A linear support vector machine (SVM) learning technique was applied to the texture features and clinical variables, with leave-one-out cross-validation. Receiver operating characteristic analysis and the area under the curve (AUC) were used to assess performance between using clinical variables only versus clinical variables and texture features. Results Twenty-one patients (61% male, age 64.1 +/- 10.3 years) were included. Mean time to local progression was 29.8 months. Five texture features exhibited association with progression (p < 0.05). The SVM model based on clinical variables alone resulted in an AUC of 0.52, whereas the SVM model that included texture features resulted in an AUC 0.93 (p = 0.01). Mean overall survival was 35 months. Fourteen texture features were associated with survival in the univariate model (p < 0.05). While the trained SVM model based on clinical variables resulted in an AUC of 0.68, the SVM model that included texture features resulted in an AUC of 0.93 (p = 0.024). Discussion Pre-ablation texture analysis and machine learning improve local tumor progression and survival prediction in patients with adrenal metastases who undergo ablation.
引用
收藏
页码:1771 / 1776
页数:6
相关论文
共 34 条
[21]
Artificial intelligence and deep learning - Radiology's next frontier? [J].
Mayo, Ray Cody ;
Leung, Jessica .
CLINICAL IMAGING, 2018, 49 :87-88
[22]
Colorectal Cancer: Texture Analysis of Portal Phase Hepatic CT Images as a Potential Marker of Survival [J].
Miles, Kenneth A. ;
Ganeshan, Balaji ;
Griffiths, Matthew R. ;
Young, Rupert C. D. ;
Chatwin, Christopher R. .
RADIOLOGY, 2009, 250 (02) :444-452
[23]
Radio-frequency Ablation of Solitary Adrenal Gland Metastasis From Renal Cell Carcinoma [J].
Mouracade, Pascal ;
Dettloff, Herve ;
Schneider, Marc ;
Debras, Bertrand ;
Jung, Jean-Luc .
UROLOGY, 2009, 74 (06) :1341-1343
[24]
Percutaneous microwave ablation of adrenal tumours under ultrasound guidance in 33 patients with 35 tumours: A single-centre experience [J].
Ren, Chao ;
Liang, Ping ;
Yu, Xiao-ling ;
Cheng, Zhi-gang ;
Han, Zhi-yu ;
Yu, Jie .
INTERNATIONAL JOURNAL OF HYPERTHERMIA, 2016, 32 (05) :517-523
[25]
Differentiation of Benign From Metastatic Adrenal Masses in Patients With Renal Cell Carcinoma on Contrast-Enhanced CT [J].
Sasaguri, Kohei ;
Takahashi, Naoki ;
Takeuchi, Mitsuru ;
Carter, Rickey E. ;
Leibovich, Bradley C. ;
Kawashima, Akira .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2016, 207 (05) :1031-1038
[26]
Utility of MRI to Differentiate Clear Cell Renal Cell Carcinoma Adrenal Metastases From Adrenal Adenomas [J].
Schieda, Nicola ;
Krishna, Satheesh ;
McInnes, Matthew D. F. ;
Moosavi, Bardia ;
Alrashed, Abdulmohsen ;
Moreland, Robert ;
Siegelman, Evan S. .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2017, 209 (03) :W152-W159
[27]
Texture information in run-length matrices [J].
Tang, XO .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (11) :1602-1609
[28]
Can Adrenal Adenomas Be Differentiated From Adrenal Metastases at Single-Phase Contrast-Enhanced CT? [J].
Tu, Wendy ;
Verma, Raman ;
Krishna, Satheesh ;
McInnes, Matthew D. F. ;
Flood, Trevor A. ;
Schieda, Nicola .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2018, 211 (05) :1044-1050
[29]
Ultrasound-guided percutaneous microwave ablation of adrenal metastasis: Preliminary results [J].
Wang, Yang ;
Liang, Ping ;
Yu, Xiaoling ;
Cheng, Zhigang ;
Yu, Jie ;
Dong, Jun .
INTERNATIONAL JOURNAL OF HYPERTHERMIA, 2009, 25 (06) :455-461
[30]
A Single-Institution Experience in Image-Guided Thermal Ablation of Adrenal Gland Metastases [J].
Welch, Brian T. ;
Callstrom, Matthew R. ;
Carpenter, Paul C. ;
Wass, C. Thomas ;
Welch, Tasha L. ;
Boorjian, Stephen A. ;
Nichols, Douglas A. ;
Thompson, Geoffrey B. ;
Lohse, Christine M. ;
Erickson, Dana ;
Leibovich, Bradley C. ;
Atwell, Thomas D. .
JOURNAL OF VASCULAR AND INTERVENTIONAL RADIOLOGY, 2014, 25 (04) :593-598