Literature DB >> 33727148

Handcrafted MRI radiomics and machine learning: Classification of indeterminate solid adrenal lesions.

Arnaldo Stanzione1, Renato Cuocolo2, Francesco Verde1, Roberta Galatola1, Valeria Romeo3, Pier Paolo Mainenti4, Giovanni Aprea5, Elia Guadagno1, Marialaura Del Basso De Caro1, Simone Maurea1.   

Abstract

PURPOSE: To assess a radiomic machine learning (ML) model in classifying solid adrenal lesions (ALs) without fat signal drop on chemical shift (CS) as benign or malignant.
METHOD: 55 indeterminate ALs (21 lipid poor adenomas, 15 benign pheocromocytomas, 1 oncocytoma, 12 metastases, 6 primary tumors) showing no fat signal drop on CS were retrospectively included. Manual 3D segmentation on T2-weighted and CS images was performed for subsequent radiomic feature extraction. After feature stability testing and an 80-20% train-test split, the train set was balanced via oversampling. Following a multi-step feature selection, an Extra Trees model was tuned with 5-fold stratified cross-validation in the train set and then tested on the hold-out test set.
RESULTS: A total of 3396 features were extracted from each AL, of which 133 resulted unstable while none had low variance (< 0.01). Highly correlated (r > 0.8) features were also excluded, leaving 440 parameters. Among these, Support Vector Machine 5-fold stratified cross-validated recursive feature elimination selected a subset of 6 features. ML obtained a cross-validation accuracy of 0.94 on the train and 0.91 on the test sets. Precision, recall and F1 score were respectively 0.92, 0.91 and 0.91.
CONCLUSIONS: Our MRI handcrafted radiomics and ML pipeline proved useful to characterize benign and malignant solid indeterminate adrenal lesions.
Copyright © 2021 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Adrenal glands; Chemical shift imaging; Machine learning; Magnetic resonance imaging; Neoplasms

Year:  2021        PMID: 33727148     DOI: 10.1016/j.mri.2021.03.009

Source DB:  PubMed          Journal:  Magn Reson Imaging        ISSN: 0730-725X            Impact factor:   2.546


  5 in total

1.  A machine learning approach to distinguishing between non-functioning and autonomous cortisol secreting adrenal incidentaloma on magnetic resonance imaging using texture analysis.

Authors:  Ferhat Can Piskin; Gamze Akkus; Sevinc Puren Yucel; Ilker Unal; Huseyin Tugsan Balli; Mehtap Evran Olgun; Murat Sert; Bekir Tamer Tetiker; Kairgeldy Aikimbaev
Journal:  Ir J Med Sci       Date:  2022-07-25       Impact factor: 2.089

Review 2.  Adrenal Mass Characterization in the Era of Quantitative Imaging: State of the Art.

Authors:  Maxime Barat; Anne-Ségolène Cottereau; Sébastien Gaujoux; Florence Tenenbaum; Mathilde Sibony; Jérôme Bertherat; Rossella Libé; Martin Gaillard; Anne Jouinot; Guillaume Assié; Christine Hoeffel; Philippe Soyer; Anthony Dohan
Journal:  Cancers (Basel)       Date:  2022-01-23       Impact factor: 6.639

3.  Diagnostic performance of radiomics in adrenal masses: A systematic review and meta-analysis.

Authors:  Hao Zhang; Hanqi Lei; Jun Pang
Journal:  Front Oncol       Date:  2022-09-02       Impact factor: 5.738

Review 4.  Radiomics in Cross-Sectional Adrenal Imaging: A Systematic Review and Quality Assessment Study.

Authors:  Arnaldo Stanzione; Roberta Galatola; Renato Cuocolo; Valeria Romeo; Francesco Verde; Pier Paolo Mainenti; Arturo Brunetti; Simone Maurea
Journal:  Diagnostics (Basel)       Date:  2022-02-24

5.  Qualitative Heterogeneous Signal Drop on Chemical Shift (CS) MR Imaging: Correlative Quantitative Analysis between CS Signal Intensity Index and Contrast Washout Parameters Using T1-Weighted Sequences.

Authors:  Arnaldo Stanzione; Francesco Verde; Roberta Galatola; Valeria Romeo; Raffaele Liuzzi; Pier Paolo Mainenti; Giovanni Aprea; Michele Klain; Elia Guadagno; Marialaura Del Basso De Caro; Simone Maurea
Journal:  Tomography       Date:  2021-12-14
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.