Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences

Radiomics is a growing field that can still be optimized. Feature selection method impacts radiomics models' performance more than ML algorithms. Best feature selection methods: RFE, LASSO, RF, and Boruta. ADC-derived radiomic features yield more robust models compared to T2w-derived radiomic features.

Authors

Institutions

Publication Details

Journal
Insights into Imaging
Published
2024-11-04
DOI
https://doi.org/10.1186/s13244-024-01783-9
Citations
26
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
10.51

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences

Ali Devrim Karaosmanoğlu, Mustafa Nasuh Ozmen, Fırat Atak, Rodolfo Márquez et al.
26 citations
Insights into Imaging
Radiomics and Machine Learning in Medical Imaging
10.51
article

Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences

Ali Devrim Karaosmanoğlu, Mustafa Nasuh Ozmen, Fırat Atak, Rodolfo Márquez, Muşturay Karçaaltıncaba, Eugenia Mylona, Stelios Sfakianakis, Charalampos Kalantzopoulos, Kostas Marias, Anindo Saha, Audrius Untanas, Giovanni Maimone, Jasper J. Twilt, Varvara Kalokyri, Silvia Navarro, Simone Mazzetti, Jerónimo Mora-Pascual, C Saillant, Nick Papanikolaou, Simon Doran, Gianluca Carloni, Dimitrios I. Fotiadis, Andrea Berti, Jayashree Kalpathy–Cramer, Dow‐Mu Koh, Eva Pachetti, Jurgen J. Fütterer, Maria Antonietta Pascali, Eleftherios Trivizakis, Zoi Giavri, Emanuele Neri, Gloria Ribas, Dimitrios I. Fotiadis, Deniz Akata, Vincenzo Mendola, Gracián García‐Martí, J. Correia, Nikolaos S. Tachos, Nan Nan, Avtantil Dimitriadis, Giulio Del Corso, Theresa Henne, Dimitrios I. Zaridis, Joan Carles Vilanova, Daniele Regge, Ana Sofia Castro Verde, Giacomo Aringhieri, Ana Jiménez Pastor, Luis Martí‐Bonmatí, Ana Carolina Rodrigues, Sara Colantonio, Ana Ribeiro, Danila Germanese, Christopher P. Bridge, Georgiou Georgios, Henkjan Huisman, Lorenzo Tumminello, José Guilherme de Almeida, Grigorios Kalliatakis, Maarten de Rooij, Walter Hernández, Manolis Tsiknakis, Valentina Giannini, Sharon Vit, Nuno M. Rodrigues, Jurgita Ušinskienė, Giovanni Cappello, Rūta Briedienė, Tiaan Jacobs, Robby Emsley, Vincenzo Napolitano, Leonor Cerdá-Alberich, Miguel Chambel, Manuel Marfil, Kristina Slidevska, Katsaros Vasilis, Christos Pollalis, Dimitrios Agraniotis
article en
26 citations

Abstract

Radiomics is a growing field that can still be optimized. Feature selection method impacts radiomics models' performance more than ML algorithms. Best feature selection methods: RFE, LASSO, RF, and Boruta. ADC-derived radiomic features yield more robust models compared to T2w-derived radiomic features.

Insights into ImagingVol. 15(1)
University of Pisa (IT), Champalimaud Foundation (PT), Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT), Royal Marsden NHS Foundation Trust (GB), Institute of Cancer Research (GB), Radboud University Nijmegen (NL), National Technical University of Athens (GR), University of Ioannina (GR), Mediterranean University (ME), Hospital Universitari i Politècnic La Fe (ES), Massachusetts General Hospital (US), Centro de Investigación Biomédica en Red de Salud Mental (ES), FORTH Institute of Molecular Biology and Biotechnology (GR), Institut d'Investigació Biomèdica de Girona (ES), Hospital Quirónsalud Barcelona (ES), Instituto de Tecnología Química (ES), Candiolo Cancer Institute (IT), Istituti di Ricovero e Cura a Carattere Scientifico (IT), National Cancer Institute (LT), Instituto de Investigación Sanitaria La Fe (ES), Hacettepe University (TR), Foundation for Research and Technology Hellas (GR)
European Commission, Horizon 2020 Framework Programme
Reduced inequalities
Openalex Percentile: Top 1%
Radiomics and Machine Learning in Medical Imaging
10.51
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.