ADC‐derived spatial features can accurately classify adnexal lesions

Journal of Magnetic Resonance Imaging - Tập 47 Số 4 - Trang 1061-1071 - 2018
Anahita Fathi Kazerooni1,2, Mahnaz Nabil3, Hamidreza Haghighat Khah4, Mohammadreza Alviri2, Maryam Heidari‐Sooreshjaani5, Masoumeh Gity6,7, Mahrooz Malek6,7, Hamidreza Saligheh Rad1,2
1Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Iran
2Quantitative MR Imaging and Spectroscopy Group, Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Iran
3Department of Mathematics, Islamic Azad University, Qazvin Branch, Qazvin, Iran
4Department of Diagnostic Imaging, Shohada-e-Tajrish Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
5Department of Radiology, Modarres Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
6Advanced Diagnostic and Interventional Radiology Research Center (ADIR), Tehran University of Medical Sciences, Tehran, Iran
7Department of Radiology, Medical Imaging Center, Tehran University of Medical Sciences, Tehran, Iran

Tóm tắt

BackgroundThe role of quantitative apparent diffusion coefficient (ADC) maps in differentiating adnexal masses is unresolved.Purpose/HypothesisTo propose an objective diagnostic method devised based on spatial features for predicting benignity/malignancy of adnexal masses in ADC maps.Study TypeProspective.PopulationIn all, 70 women with sonographically indeterminate and histopathologically confirmed adnexal masses (38 benign, 3 borderline, and 29 malignant) were considered for this study.Field Strength/SequenceConventional and diffusion‐weighted magnetic resonance (MR) images (b‐values = 50, 400, 1000 s/mm2) were acquired on a 3T scanner.AssessmentFor each patient, two radiologists in consensus manually delineated lesion borders in whole ADC map volumes, which were consequently analyzed using spatial models (first‐order histogram [FOH], gray‐level co‐occurrence matrix [GLCM], run‐length matrix [RLM], and Gabor filters). Two independent radiologists were asked to identify the attributed (benign/malignant) classes of adnexal masses based on morphological features on conventional MRI.Statistical TestsLeave‐one‐out cross‐validated feature selection followed by cross‐validated classification were applied to the feature space to choose the spatial models that best discriminate benign from malignant adnexal lesions. Two schemes of feature selection/classification were evaluated: 1) including all benign and malignant masses, and 2) scheme 1 after excluding endometrioma, hemorrhagic cysts, and teratoma (14 benign, 29 malignant masses). The constructed feature subspaces for benign/malignant lesion differentiation were tested for classification of benign/borderline/malignant and also borderline/malignant adnexal lesions.ResultsThe selected feature subspace consisting of RLM features differentiated benign from malignant adnexal masses with a classification accuracy of ∼92%. The same model discriminated benign, borderline, and malignant lesions with 87% and borderline from malignant with 100% accuracy. Qualitative assessment of the radiologists based on conventional MRI features reached an accuracy of 80%.Data ConclusionThe spatial quantification methodology proposed in this study, which works based on cellular distributions within ADC maps of adnexal masses, may provide a helpful computer‐aided strategy for objective characterization of adnexal masses.Level of Evidence: 1Technical Efficacy: Stage 2J. Magn. Reson. Imaging 2018;47:1061–1071.

Từ khóa


Tài liệu tham khảo

10.1007/s00330-009-1584-2

10.1148/radiol.10090397

10.2214/AJR.05.0905

10.1016/j.crad.2004.09.007

10.1007/978-1-4471-2942-4_5

10.1007/174_2017_66

Forstner R, 2016, ESUR recommendations for MR imaging of the sonographically indeterminate adnexal mass: An update, Eur Radiol, 1

10.2214/AJR.06.1403

10.1593/neo.81328

10.1007/s00330-009-1299-4

10.1259/bjr/90706205

10.1002/jmri.23794

10.1097/CCO.0000000000000112

10.1016/j.ejogrb.2009.02.048

10.1111/j.1471-0528.1996.tb09882.x

10.1111/j.1600-0412.2012.01359.x

10.1038/bjc.2014.512

10.1109/PROC.1979.11328

10.1016/0167-8655(90)90112-F

10.1002/mrm.22147

10.1007/978-1-4612-1694-0_15

10.1214/aos/1176344136

10.1002/jmri.25359

10.1002/jmri.24119

10.1371/journal.pone.0149465

10.1148/radiol.13121161

10.1097/00004728-200203000-00015

10.1002/jmri.20369

10.1148/radiol.10100751

10.1093/annonc/mdw311

10.3174/ajnr.A2061

10.1002/mrm.26743

10.1007/s00330-011-2329-6

Thông tin
Thông tin xuất bản

Journal of Magnetic Resonance Imaging

Tập 47 Số 4

1061-1071

Thông tin tác giả