Jennifer S Golia Pernicka1, Johan Gagniere2,3, Jayasree Chakraborty2, Rikiya Yamashita4, Lorenzo Nardo4,5, John M Creasy2, Iva Petkovska4, Richard R K Do4, David D B Bates4, Viktoriya Paroder4, Mithat Gonen6, Martin R Weiser2, Amber L Simpson2, Marc J Gollub4. 1. Body Imaging Service, Department of Radiology, Evelyn H. Lauder Breast Center, Memorial Sloan Kettering Cancer Center, 300 East 66th St., Suite 757, New York, NY, 10065, USA. goliapej@mskcc.org. 2. Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA. 3. Department of Digestive and Hepatobiliary Surgery, U1071 INSERM / Clermont-Auvergne University, University Hospital of Clermont-Ferrand, Clermont-Ferrand, France. 4. Body Imaging Service, Department of Radiology, Evelyn H. Lauder Breast Center, Memorial Sloan Kettering Cancer Center, 300 East 66th St., Suite 757, New York, NY, 10065, USA. 5. Department of Radiology, University of California Davis, Sacramento, CA, USA. 6. Department of Epidemiology & Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Abstract
PURPOSE: To predict microsatellite instability (MSI) status of colon cancer on preoperative CT imaging using radiomic analysis. METHODS: This retrospective study involved radiomic analysis of preoperative CT imaging of patients who underwent resection of stage II-III colon cancer from 2004 to 2012. A radiologist blinded to MSI status manually segmented the tumor region on CT images. 254 Intensity-based radiomic features were extracted from the tumor region. Three prediction models were developed with (1) only clinical features, (2) only radiomic features, and (3) "combined" clinical and radiomic features. Patients were randomly separated into training (n = 139) and test (n = 59) sets. The model was constructed from training data only; the test set was reserved for validation only. Model performance was evaluated using AUC, sensitivity, specificity, PPV, and NPV. RESULTS: Of the total 198 patients, 134 (68%) patients had microsatellite stable tumors and 64 (32%) patients had MSI tumors. The combined model performed slightly better than the other models, predicting MSI with an AUC of 0.80 for the training set and 0.79 for the test set (specificity = 96.8% and 92.5%, respectively), whereas the model with only clinical features achieved an AUC of 0.74 and the model with only radiomic features achieved an AUC of 0.76. The model with clinical features alone had the lowest specificity (70%) compared with the model with radiomic features alone (95%) and the combined model (92.5%). CONCLUSIONS: Preoperative prediction of MSI status via radiomic analysis of preoperative CT adds specificity to clinical assessment and could contribute to personalized treatment selection.
PURPOSE: To predict microsatellite instability (MSI) status of colon cancer on preoperative CT imaging using radiomic analysis. METHODS: This retrospective study involved radiomic analysis of preoperative CT imaging of patients who underwent resection of stage II-III colon cancer from 2004 to 2012. A radiologist blinded to MSI status manually segmented the tumor region on CT images. 254 Intensity-based radiomic features were extracted from the tumor region. Three prediction models were developed with (1) only clinical features, (2) only radiomic features, and (3) "combined" clinical and radiomic features. Patients were randomly separated into training (n = 139) and test (n = 59) sets. The model was constructed from training data only; the test set was reserved for validation only. Model performance was evaluated using AUC, sensitivity, specificity, PPV, and NPV. RESULTS: Of the total 198 patients, 134 (68%) patients had microsatellite stable tumors and 64 (32%) patients had MSI tumors. The combined model performed slightly better than the other models, predicting MSI with an AUC of 0.80 for the training set and 0.79 for the test set (specificity = 96.8% and 92.5%, respectively), whereas the model with only clinical features achieved an AUC of 0.74 and the model with only radiomic features achieved an AUC of 0.76. The model with clinical features alone had the lowest specificity (70%) compared with the model with radiomic features alone (95%) and the combined model (92.5%). CONCLUSIONS: Preoperative prediction of MSI status via radiomic analysis of preoperative CT adds specificity to clinical assessment and could contribute to personalized treatment selection.
Authors: Roberto García-Figueiras; Sandra Baleato-González; Anwar R Padhani; Antonio Luna-Alcalá; Ana Marhuenda; Joan C Vilanova; Iria Osorio-Vázquez; Anxo Martínez-de-Alegría; Antonio Gómez-Caamaño Journal: Radiographics Date: 2018-04-20 Impact factor: 5.333
Authors: Dung T Le; Jennifer N Uram; Hao Wang; Bjarne R Bartlett; Holly Kemberling; Aleksandra D Eyring; Andrew D Skora; Brandon S Luber; Nilofer S Azad; Dan Laheru; Barbara Biedrzycki; Ross C Donehower; Atif Zaheer; George A Fisher; Todd S Crocenzi; James J Lee; Steven M Duffy; Richard M Goldberg; Albert de la Chapelle; Minori Koshiji; Feriyl Bhaijee; Thomas Huebner; Ralph H Hruban; Laura D Wood; Nathan Cuka; Drew M Pardoll; Nickolas Papadopoulos; Kenneth W Kinzler; Shibin Zhou; Toby C Cornish; Janis M Taube; Robert A Anders; James R Eshleman; Bert Vogelstein; Luis A Diaz Journal: N Engl J Med Date: 2015-05-30 Impact factor: 91.245
Authors: Andrea Cercek; Campbell S D Roxburgh; Paul Strombom; J Joshua Smith; Larissa K F Temple; Garrett M Nash; Jose G Guillem; Philip B Paty; Rona Yaeger; Zsofia K Stadler; Kenneth Seier; Mithat Gonen; Neil H Segal; Diane L Reidy; Anna Varghese; Jinru Shia; Efsevia Vakiani; Abraham J Wu; Christopher H Crane; Marc J Gollub; Julio Garcia-Aguilar; Leonard B Saltz; Martin R Weiser Journal: JAMA Oncol Date: 2018-06-14 Impact factor: 31.777
Authors: Roger Sun; Théophraste Henry; Adrien Laville; Alexandre Carré; Anthony Hamaoui; Sophie Bockel; Ines Chaffai; Antonin Levy; Cyrus Chargari; Charlotte Robert; Eric Deutsch Journal: J Immunother Cancer Date: 2022-07 Impact factor: 12.469
Authors: Wei Zhang; Hongkun Yin; Zixing Huang; Jian Zhao; Haoyu Zheng; Du He; Mou Li; Weixiong Tan; Song Tian; Bin Song Journal: Cancer Med Date: 2021-05-08 Impact factor: 4.452