Ponnada A Narayana1, Ivan Coronado2, Sheeba J Sujit2, Xiaojun Sun2, Jerry S Wolinsky3, Refaat E Gabr2. 1. Department of Diagnostic and Interventional Imaging, McGovern Medical School, University of Texas Health Science Center, Houston, TX 77030, United States of America. Electronic address: Ponnada.a.narayana@uth.tmc.edu. 2. Department of Diagnostic and Interventional Imaging, McGovern Medical School, University of Texas Health Science Center, Houston, TX 77030, United States of America. 3. Department of Neurology, McGovern Medical School, University of Texas Health Science Center, Houston, TX 77030, United States of America.
Abstract
BACKGROUND: Magnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality. OBJECTIVE: To investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network. METHODS: U-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MS patients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated. RESULTS:Highest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size. CONCLUSIONS: Best performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.
RCT Entities:
BACKGROUND: Magnetic resonance images with multiple contrasts or sequences are commonly used for segmenting brain tissues, including lesions, in multiple sclerosis (MS). However, acquisition of images with multiple contrasts increases the scan time and complexity of the analysis, possibly introducing factors that could compromise segmentation quality. OBJECTIVE: To investigate the effect of various combinations of multi-contrast images as input on the segmented volumes of gray (GM) and white matter (WM), cerebrospinal fluid (CSF), and lesions using a deep neural network. METHODS: U-net, a fully convolutional neural network was used to automatically segment GM, WM, CSF, and lesions in 1000 MSpatients. The input to the network consisted of 15 combinations of FLAIR, T1-, T2-, and proton density-weighted images. The Dice similarity coefficient (DSC) was evaluated to assess the segmentation performance. For lesions, true positive rate (TPR) and false positive rate (FPR) were also evaluated. In addition, the effect of lesion size on lesion segmentation was investigated. RESULTS: Highest DSC was observed for all the tissue volumes, including lesions, when the input was combination of all four image contrasts. All other input combinations that included FLAIR also provided high DSC for all tissue classes. However, the quality of lesion segmentation showed strong dependence on the input images. The DSC and TPR values for inputs with the four contrast combination and FLAIR alone were very similar, but FLAIR showed a moderately higher FPR for lesion size <100 μl. For lesions smaller than 20 μl all image combinations resulted in poor performance. The segmentation quality improved with lesion size. CONCLUSIONS: Best performance for segmented tissue volumes was obtained with all four image contrasts as the input, and comparable performance was attainable with FLAIR only as the input, albeit with a moderate increase in FPR for small lesions. This implies that acquisition of only FLAIR images provides satisfactory tissue segmentation. Lesion segmentation was poor for very small lesions and improved rapidly with lesion size.
Authors: Balasrinivasa Rao Sajja; Sushmita Datta; Renjie He; Meghana Mehta; Rakesh K Gupta; Jerry S Wolinsky; Ponnada A Narayana Journal: Ann Biomed Eng Date: 2006-03-09 Impact factor: 3.934
Authors: Petronella Anbeek; Koen L Vincken; Glenda S van Bochove; Matthias J P van Osch; Jeroen van der Grond Journal: Neuroimage Date: 2005-10-01 Impact factor: 6.556
Authors: Maria A Rocca; Marco Battaglini; Ralph H B Benedict; Nicola De Stefano; Jeroen J G Geurts; Roland G Henry; Mark A Horsfield; Mark Jenkinson; Elisabetta Pagani; Massimo Filippi Journal: Neurology Date: 2016-12-16 Impact factor: 9.910
Authors: Muhammad Febrian Rachmadi; Maria Del C Valdés-Hernández; Maria Leonora Fatimah Agan; Carol Di Perri; Taku Komura Journal: Comput Med Imaging Graph Date: 2018-02-17 Impact factor: 4.790
Authors: Pim Moeskops; Jeroen de Bresser; Hugo J Kuijf; Adriënne M Mendrik; Geert Jan Biessels; Josien P W Pluim; Ivana Išgum Journal: Neuroimage Clin Date: 2017-10-12 Impact factor: 4.881
Authors: Camilo Bermudez; Samuel W Remedios; Karthik Ramadass; Maureen McHugo; Stephan Heckers; Yuankai Huo; Bennett A Landman Journal: J Med Imaging (Bellingham) Date: 2020-12-23