Investigator

Alejandro Rodríguez‐Ortega

PhD Researcher · Universitat Politècnica de València, Department of Graphics Engineering

About

ARAlejandro Rodrígu…
Papers(1)
Machine Learning‐Base…
Collaborators(1)
Amadeo Ten‐Esteve
Institutions(1)
Instituto De Investig…

Papers

Machine Learning‐Based Integration of Prognostic Magnetic Resonance Imaging Biomarkers for Myometrial Invasion Stratification in Endometrial Cancer

BackgroundEstimation of the depth of myometrial invasion (MI) in endometrial cancer is pivotal in the preoperatively staging. Magnetic resonance (MR) reports suffer from human subjectivity. Multiparametric MR imaging radiomics and parameters may improve the diagnostic accuracy.PurposeTo discriminate between patients with MI ≥ 50% using a machine learning‐based model combining texture features and descriptors from preoperatively MR images.Study TypeRetrospective.PopulationOne hundred forty‐three women with endometrial cancer were included. The series was split into training (n = 107, 46 with MI ≥ 50%) and test (n = 36, 16 with MI ≥ 50%) cohorts.Field Strength/SequencesFast spin echo T2‐weighted (T2W), diffusion‐weighted (DW), and T1‐weighted gradient echo dynamic contrast‐enhanced (DCE) sequences were obtained at 1.5 or 3 T magnets.AssessmentTumors were manually segmented slice‐by‐slice. Texture metrics were calculated from T2W and ADC map images. Also, the apparent diffusion coefficient (ADC), wash‐in slope, wash‐out slope, initial area under the curve at 60 sec and at 90 sec, initial slope, time to peak and peak amplitude maps from DCE sequences were obtained as parameters. MR diagnostic models using single‐sequence features and a combination of features and parameters from the three sequences were built to estimate MI using Adaboost methods. The pathological depth of MI was used as gold standard.Statistical TestArea under the receiver operating characteristic curve (AUROC), sensitivity, specificity, accuracy, positive predictive value, negative predictive value, precision and recall were computed to assess the Adaboost models performance.ResultsThe diagnostic model based on the features and parameters combination showed the best performance to depict patient with MI ≥ 50% in the test cohort (accuracy = 86.1% and AUROC = 87.1%). The rest of diagnostic models showed a worse accuracy (accuracy = 41.67%–63.89% and AUROC = 41.43%–63.13%).Data ConclusionThe model combining the texture features from T2W and ADC map images with the semi‐quantitative parameters from DW and DCE series allow the preoperative estimation of myometrial invasion.Evidence Level4Technical EfficacyStage 3

57Works
1Papers
1Collaborators

Positions

2021–

PhD Researcher

Universitat Politècnica de València · Department of Graphics Engineering

2017–

PhD Researcher

Instituto de Investigación Sanitaria La Fe · Biomedical Imaging Research Group (GIBI230)

Education

2015

PhD

Universitat Politècnica de València · Department of Electronic Engineering

2010

Telecommunications Engineer

Universitat Politècnica de València

Country

ES

Keywords
Virtual RealityEEGECGPainEmotional RegulationDoppler TranscranialMRIImaging BiomarkerDiffusion Weighted ImagingOncologyLiverDynamic Contrast EnhancedEndometrial CancerDigital PathologyHyperspectral Image
Links & IDs
0000-0003-4781-6368ResearchgateLinkedIn

Scopus: 57221297500

Researcher Id: AAC-2208-2019