Using single-voxel magnetic resonance spectroscopy data acquired at 1.5T to classify multivoxel data at 3T: a proof-of-concept study

In vivo magnetic resonance spectroscopy (MRS) has two modalities, single-voxel (SV) and multivoxel (MV), in which one or more contiguous grids of SVs are acquired. Purpose: To test whether MV grids can be classified with models trained with SV. Methods: Retrospective study. Training dataset: Multice...

Descripción completa

Detalles Bibliográficos
Autores: Ungan, Gülnur, Pons Escoda, Albert, Ulinic, Daniel, Arus Caraltó, Carles, Vellido Alcacena, Alfredo|||0000-0002-9843-1911, Julia Sape, Margarida
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/394657
Acceso en línea:https://hdl.handle.net/2117/394657
https://dx.doi.org/10.3390/cancers15143709
Access Level:acceso abierto
Palabra clave:Brain -- Tumors -- Diagnosis
Brain -- Magnetic resonance imaging
Machine learning
Decision support systems
Magnetic resonance spectroscopy
Brain tumors
Glioblastoma
Nosologic imaging
Metabolic pattern
Cervell -- Tumors -- Diagnòstic
Cervell -- Imatgeria per ressonància magnètica
Aprenentatge automàtic
Sistemes d'ajuda a la decisió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica
Descripción
Sumario:In vivo magnetic resonance spectroscopy (MRS) has two modalities, single-voxel (SV) and multivoxel (MV), in which one or more contiguous grids of SVs are acquired. Purpose: To test whether MV grids can be classified with models trained with SV. Methods: Retrospective study. Training dataset: Multicenter multiformat SV INTERPRET, 1.5T. Testing dataset: MV eTumour, 3T. Two classification tasks were completed: 3-class (meningioma vs. aggressive vs. normal) and 4-class (meningioma vs. low-grade glioma vs. aggressive vs. normal). Five different methods were tested for feature selection. The classification was implemented using linear discriminant analysis (LDA), random forest, and support vector machines. The evaluation was completed with balanced error rate (BER) and area under the curve (AUC) on both sets. The accuracy in class prediction was calculated by developing a solid tumor index (STI) and segmentation accuracy with the Dice score. Results: The best method was sequential forward feature selection combined with LDA, with AUCs = 0.95 (meningioma), 0.89 (aggressive), 0.82 (low-grade glioma), and 0.82 (normal). STI was 66% (4-class task) and 71% (3-class task) because two cases failed completely and two more had suboptimal STI as defined by us. Discussion: The reasons for failure in the classification of the MV test set were related to the presence of artifacts.