Shiman Wu1, Xi Zhang2, Wenting Rui1, Yaru Sheng1, Yang Yu1, Yong Zhang3, Zhenwei Yao1, Tianming Qiu4, Yan Ren5. 1. Department of Radiology, Huashan Hospital, Fudan University, Jing'an District, 12 Middle Urumqi Road, Shanghai, 200040, People's Republic of China. 2. Department of Biomedical Engineering, Fourth Military Medical University, Xi'an, Shaanxi, People's Republic of China. 3. GE Healthcare, Shanghai, People's Republic of China. 4. Department of Neurosurgery, Huashan Hospital, Fudan University, Jing'an District, 12 Middle Urumqi Road, Shanghai, 200040, People's Republic of China. tianming2100@126.com. 5. Department of Radiology, Huashan Hospital, Fudan University, Jing'an District, 12 Middle Urumqi Road, Shanghai, 200040, People's Republic of China. renyan_richard@aliyun.com.
Abstract
OBJECTIVES: To construct a radiomics nomogram based on multiparametric MRI data for predicting isocitrate dehydrogenase 1 mutation (IDH +) and loss of nuclear alpha thalassemia/mental retardation syndrome X-linked expression (ATRX -) in patients with lower-grade gliomas (LrGG; World Health Organization [WHO] 2016 grades II and III). METHODS: A total of 111 LrGG patients (76 mutated IDH and 35 wild-type IDH) were enrolled, divided into a training set (n = 78) and a validation set (n = 33) for predicting IDH mutation. IDH + LrGG patients were further stratified into the ATRX - (n = 38) and ATRX + (n = 38) subtypes. A total of 250 radiomics features were extracted from the region of interest of each tumor, including that from T2 fluid-attenuated inversion recovery (T2 FLAIR), contrast-enhanced T1 WI, ASL-derived cerebral blood flow (CBF), DWI-derived ADC, and exponential ADC (eADC). A radiomics signature was selected using the Elastic Net regression model, and a radiomics nomogram was finally constructed using the age, gender information, and above features. RESULTS: The radiomics nomogram identified LrGG patients for IDH mutation (C-index: training sets = 0.881, validation sets = 0.900) and ATRX loss (C-index: training sets = 0.863, validation sets = 0.840) with good calibration. Decision curve analysis further confirmed the clinical usefulness of the two nomograms for predicting IDH and ATRX status. CONCLUSIONS: The nomogram incorporating age, gender, and the radiomics signature provided a clinically useful approach in noninvasively predicting IDH and ATRX mutation status for LrGG patients. The proposed method could facilitate MRI-based clinical decision-making for the LrGG patients. KEY POINTS: • Non-invasive determination of IDH and ATRX gene status of LrGG patients can be obtained with a radiomics nomogram. • The proposed nomogram is constructed by radiomics signature selected from 250 radiomics features, combined with age and gender. • The proposed radiomics nomogram exhibited good calibration and discrimination for IDH and ATRX gene mutation stratification of LrGG patients in both training and validation sets.
OBJECTIVES: To construct a radiomics nomogram based on multiparametric MRI data for predicting isocitrate dehydrogenase 1 mutation (IDH +) and loss of nuclear alpha thalassemia/mental retardation syndrome X-linked expression (ATRX -) in patients with lower-grade gliomas (LrGG; World Health Organization [WHO] 2016 grades II and III). METHODS: A total of 111 LrGG patients (76 mutated IDH and 35 wild-type IDH) were enrolled, divided into a training set (n = 78) and a validation set (n = 33) for predicting IDH mutation. IDH + LrGG patients were further stratified into the ATRX - (n = 38) and ATRX + (n = 38) subtypes. A total of 250 radiomics features were extracted from the region of interest of each tumor, including that from T2 fluid-attenuated inversion recovery (T2 FLAIR), contrast-enhanced T1 WI, ASL-derived cerebral blood flow (CBF), DWI-derived ADC, and exponential ADC (eADC). A radiomics signature was selected using the Elastic Net regression model, and a radiomics nomogram was finally constructed using the age, gender information, and above features. RESULTS: The radiomics nomogram identified LrGG patients for IDH mutation (C-index: training sets = 0.881, validation sets = 0.900) and ATRX loss (C-index: training sets = 0.863, validation sets = 0.840) with good calibration. Decision curve analysis further confirmed the clinical usefulness of the two nomograms for predicting IDH and ATRX status. CONCLUSIONS: The nomogram incorporating age, gender, and the radiomics signature provided a clinically useful approach in noninvasively predicting IDH and ATRX mutation status for LrGG patients. The proposed method could facilitate MRI-based clinical decision-making for the LrGG patients. KEY POINTS: • Non-invasive determination of IDH and ATRX gene status of LrGG patients can be obtained with a radiomics nomogram. • The proposed nomogram is constructed by radiomics signature selected from 250 radiomics features, combined with age and gender. • The proposed radiomics nomogram exhibited good calibration and discrimination for IDH and ATRX gene mutation stratification of LrGG patients in both training and validation sets.
Authors: Rachel L Delfanti; David E Piccioni; Jason Handwerker; Naeim Bahrami; AnithaPriya Krishnan; Roshan Karunamuni; Jona A Hattangadi-Gluth; Tyler M Seibert; Ashwin Srikant; Karra A Jones; Vivian S Snyder; Anders M Dale; Nathan S White; Carrie R McDonald; Nikdokht Farid Journal: J Neurooncol Date: 2017-09-04 Impact factor: 4.130
Authors: Theresa Schumacher; Lukas Bunse; Stefan Pusch; Felix Sahm; Benedikt Wiestler; Jasmin Quandt; Oliver Menn; Matthias Osswald; Iris Oezen; Martina Ott; Melanie Keil; Jörg Balß; Katharina Rauschenbach; Agnieszka K Grabowska; Isabel Vogler; Jan Diekmann; Nico Trautwein; Stefan B Eichmüller; Jürgen Okun; Stefan Stevanović; Angelika B Riemer; Ugur Sahin; Manuel A Friese; Philipp Beckhove; Andreas von Deimling; Wolfgang Wick; Michael Platten Journal: Nature Date: 2014-06-25 Impact factor: 49.962
Authors: Fonnet E Bleeker; Nadia A Atai; Simona Lamba; Ard Jonker; Denise Rijkeboer; Klazien S Bosch; Wikky Tigchelaar; Dirk Troost; W Peter Vandertop; Alberto Bardelli; Cornelis J F Van Noorden Journal: Acta Neuropathol Date: 2010-02-04 Impact factor: 17.088
Authors: Jason Beiko; Dima Suki; Kenneth R Hess; Benjamin D Fox; Vincent Cheung; Matthew Cabral; Nicole Shonka; Mark R Gilbert; Raymond Sawaya; Sujit S Prabhu; Jeffrey Weinberg; Frederick F Lang; Kenneth D Aldape; Erik P Sulman; Ganesh Rao; Ian E McCutcheon; Daniel P Cahill Journal: Neuro Oncol Date: 2013-12-04 Impact factor: 12.300
Authors: Martin J van den Bent; Hendrikus J Dubbink; Yannick Marie; Alba A Brandes; Martin J B Taphoorn; Pieter Wesseling; Marc Frenay; Cees C Tijssen; Denis Lacombe; Ahmed Idbaih; Ronald van Marion; Johan M Kros; Winand N M Dinjens; Thierry Gorlia; Marc Sanson Journal: Clin Cancer Res Date: 2010-02-16 Impact factor: 13.801
Authors: Catherine S Grasso; Yujie Tang; Nathalene Truffaux; Noah E Berlow; Lining Liu; Marie-Anne Debily; Michael J Quist; Lara E Davis; Elaine C Huang; Pamelyn J Woo; Anitha Ponnuswami; Spenser Chen; Tessa B Johung; Wenchao Sun; Mari Kogiso; Yuchen Du; Lin Qi; Yulun Huang; Marianne Hütt-Cabezas; Katherine E Warren; Ludivine Le Dret; Paul S Meltzer; Hua Mao; Martha Quezado; Dannis G van Vuurden; Jinu Abraham; Maryam Fouladi; Matthew N Svalina; Nicholas Wang; Cynthia Hawkins; Javad Nazarian; Marta M Alonso; Eric H Raabe; Esther Hulleman; Paul T Spellman; Xiao-Nan Li; Charles Keller; Ranadip Pal; Jacques Grill; Michelle Monje Journal: Nat Med Date: 2015-05-04 Impact factor: 53.440
Authors: Sichen Li; Arthur P Chou; Weidong Chen; Ruihuan Chen; Yuzhong Deng; Heidi S Phillips; Julia Selfridge; Mira Zurayk; Jerry J Lou; Richard G Everson; Kuan-Chung Wu; Kym F Faull; Timothy Cloughesy; Linda M Liau; Albert Lai Journal: Neuro Oncol Date: 2012-10-31 Impact factor: 13.029
Authors: Sani H Kizilbash; Caterina Giannini; Jesse S Voss; Paul A Decker; Robert B Jenkins; John Hardie; Nadia N Laack; Ian F Parney; Joon H Uhm; Jan C Buckner Journal: J Neurooncol Date: 2014-07-04 Impact factor: 4.506