Zhenzhen Li1,2, Jian Guo1,2, Xiaolin Xu2,3, Wenbin Wei2,3, Junfang Xian1,2. 1. Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No. 1 of Dongjiaominxiang, Dongcheng District, Beijing, China. 2. Clinical Center for Eye Tumors, Capital Medical University, Beijing, China. 3. Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
Abstract
OBJECTIVES: To develop an MRI-based radiomics model to predict postlaminar optic nerve invasion (PLONI) in retinoblastoma (RB) and compare its predictive performance with subjective radiologists' assessment. METHODS: We retrospectively enrolled 124 patients with pathologically proven RB (90 in training set and 34 in validation set) who had MRI scans before surgery. A radiomics model for predicting PLONI was developed by extracting quantitative imaging features from axial T2W images and contrast-enhanced T1W images in the training set. The Kruskal-Wallis test, least absolute shrinkage and selection operator regression, and recursive feature elimination were used for feature selection, where upon a radiomics model was built with a logistic regression (LR) classifier. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and the accuracy were assessed to evaluate the predictive performance in the training and validation set. The performance of the radiomics model was compared to radiologists' assessment by DeLong test. RESULTS: The AUC of the radiomics model for the prediction of PLONI was 0.928 in the training set and 0.841 in the validation set. Radiomics model produced better sensitivity than radiologists' assessment (81.1% vs 43.2% in training set, 82.4vs 52.9% in validation set). In all 124 patients, the AUC of the radiomics model was 0.897, while that of radiologists' assessment was 0.674 (p < 0.001, DeLong test). CONCLUSION: MRI-based radiomics model to predict PLONI in RB patients was shown to be superior to visual assessment with improved sensitivity and AUC, and may serve as a potential tool to guide personalized treatment.
OBJECTIVES: To develop an MRI-based radiomics model to predict postlaminar optic nerve invasion (PLONI) in retinoblastoma (RB) and compare its predictive performance with subjective radiologists' assessment. METHODS: We retrospectively enrolled 124 patients with pathologically proven RB (90 in training set and 34 in validation set) who had MRI scans before surgery. A radiomics model for predicting PLONI was developed by extracting quantitative imaging features from axial T2W images and contrast-enhanced T1W images in the training set. The Kruskal-Wallis test, least absolute shrinkage and selection operator regression, and recursive feature elimination were used for feature selection, where upon a radiomics model was built with a logistic regression (LR) classifier. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and the accuracy were assessed to evaluate the predictive performance in the training and validation set. The performance of the radiomics model was compared to radiologists' assessment by DeLong test. RESULTS: The AUC of the radiomics model for the prediction of PLONI was 0.928 in the training set and 0.841 in the validation set. Radiomics model produced better sensitivity than radiologists' assessment (81.1% vs 43.2% in training set, 82.4vs 52.9% in validation set). In all 124 patients, the AUC of the radiomics model was 0.897, while that of radiologists' assessment was 0.674 (p < 0.001, DeLong test). CONCLUSION: MRI-based radiomics model to predict PLONI in RB patients was shown to be superior to visual assessment with improved sensitivity and AUC, and may serve as a potential tool to guide personalized treatment.
Authors: F Khelfaoui; P Validire; A Auperin; E Quintana; J Michon; H Pacquement; L Desjardins; B Asselain; P Schlienger; P Vielh Journal: Cancer Date: 1996-03-15 Impact factor: 6.860
Authors: Hervé J Brisse; Pim de Graaf; Paolo Galluzzi; Kristel Cosker; Philippe Maeder; Sophia Göricke; Firazia Rodjan; Marcus C de Jong; Alexia Savignoni; Isabelle Aerts; Laurence Desjardins; Annette C Moll; Theodora Hadjistilianou; Paolo Toti; Paul van der Valk; Jonas A Castelijns; Xavier Sastre-Garau Journal: Eur Radiol Date: 2014-11-30 Impact factor: 5.315
Authors: Marcus C de Jong; Pim de Graaf; Daniel P Noij; Sophia Göricke; Philippe Maeder; Paolo Galluzzi; Hervé J Brisse; Annette C Moll; Jonas A Castelijns Journal: Ophthalmology Date: 2014-03-01 Impact factor: 12.079
Authors: Ursula Winter; Daiana Ganiewich; Daniela Ottaviani; Santiago Zugbi; Rosario Aschero; Juan Martin Sendoya; Eduardo G Cafferata; Marcela Mena; Mariana Sgroi; Claudia Sampor; Fabiana Lubieniecki; Adriana Fandiño; Martin C Abba; François Doz; Osvaldo Podhjacer; Angel Montero Carcaboso; Eric Letouzé; François Radvanyi; Guillermo L Chantada; Andrea S Llera; Paula Schaiquevich Journal: JAMA Ophthalmol Date: 2020-05-01 Impact factor: 7.389