MRI-based radiomics prediction of somatostatin receptor ligand response in acromegaly: an automated pipeline study
Year: 2026
Type: article
Abstract: Context Radiomics may capture tumor characteristics predicting therapeutic response. Objective To develop an MRI-based radiomics pipeline for predicting response to SRLs in acromegaly. Methods MRI data from 267 subjects across 3 datasets were used to develop an automated tumor detection and segmentation pipeline (Spanish multicenter acromegaly IGTP cohort, n = 81; 2 public datasets, n = 186). The 3-stage pipeline comprised: (1) automated tumor detection (YOLOv8), (2) 3D segmentation (SegResNet), and (3) radiomic feature extraction (PyRadiomics) with supervised classification. Treatment-response radiomics included contrast-enhanced T1-weighted (Ce-T1W1) MRI from 49 patients treated with SRL. SRL response was defined as ≥50% IGF-1 reduction or normalization. Eleven machine-learning classifiers were evaluated using stratified repeated k-fold cross-validation. Results Automated segmentation achieved a Dice coefficient of 0.795 using combined Ce-T1WI and T2-weighted images (T2WI), decreasing to 0.765 in the acromegaly-specific cohort. The best-performing model was a 3-feature logistic regression classifier, with an out-of-fold AUC of 0.798 (95% CI: 0.671-0.918), balanced accuracy of 0.793, F1-score of 0.815, and correct classification of 39/49 patients (79.6%). Performance improved as the radiomic feature set was reduced from 5 to 2. The most consistent feature was log-sigma-3-0-mm-3D_glcm_ClusterShade, which appeared in 98% of cross-validation folds and contributed most to the model-derived discriminative signal. Conclusion In this multicenter radiomics study of SRL response prediction in acromegaly, an automated pipeline achieved good discriminative performance (AUC = 0.798). These findings highlight both the promise and the current challenges of radiomics-based treatment prediction.
Source: Journal of the Endocrine Society
Authors: Sabina Ruiz, Roger Mateu-Estivill, Ariadna Izquierdo-Gómez, Miriam López-Máñez, Jesús A Alzate, Gemma Monté-Rubio, Maria de la Iglesia-Vayá, Marta Araujo-Castro, Betina Biagetti, Silvana Sarria-Estrada, Federico Vázquez, Fabiola Romero, Elena Valassi, Victor Navas, Mónica Marazuela, Paloma Puyalto, Manel Puig-Domingo, Manel Puig-Domingo, Elena Valassi, Montserrat Marques-Pamies, Silvia Martínez-Couselo, Cristina Carrato, Joan Gil, Paula de Pedro, Federico Vázquez, Mireia Jordà, Betina Biagetti, Silvana Sarria, Olga Giménez-Palop, Anna Aulinas, Susan M Webb, Marta Hernández, Jordi Ferri, Rocío Villar-Taibo, Ignacio Bernabéu, Marta Araujo-Castro, Eider Pascual, Concepción Blanco, Inmaculada Simón, Roxana Zavala, Andreu Simó-Servat, Gemma Xifra, Isabel Pavón, José Antonio Rosado, Rogelio Garcìa-Centeno, Felicia A Hanzu, Mireia Mora, Nuria Vilarrasa, Fernando Guerrero, Soledad Librizzi, María Calatayud, Paz de Miguel, Cristina Alvarez-Escola, Antonio Picó, Carmen Fajardo-Montañana, Eva Benegas, Alfonso Soto, María-Angeles Galvez, Raúl Luque, Cristina Lama, Edelmiro Menéndez, Esteban Delgado, Guillermo Serra, Miguel Sampedro, Mónica Marazuela
Institutions: Institut d'Investigació en Ciències de la Salut Germans Trias i Pujol, Hospital Universitari de Vic, Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana, Centro de Investigacion Principe Felipe, Hospital Universitario Ramón y Cajal, Vall d'Hebron Hospital Universitari, IPS Central, Hospital Universitario de La Princesa, Universitat Internacional de Catalunya, Universitat Autònoma de Barcelona, Hospital Clínico Universitario de Valencia, Complejo Hospitalario Universitario de Santiago, Hospital de La Ribera, Hebron University, Hospital de Sant Pau, Hospital Universitari Joan XXIII de Tarragona, Instituto Maimónides de Investigación Biomédica de Córdoba, Hospital Universitario Reina Sofía, Hospital Universitario Central de Asturias, Hospital Universitario Son Espases
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,255
OpenAlex ID: W7204249080
FWCI:
Cites:
Cited by:
Related to: