Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study

Abstract Background Adrenocortical carcinoma (ACC), a rare and highly malignant adrenal gland tumor, exhibits computed tomography (CT) characteristics that resemble those of the less malignant pheochromocytoma (PHEO). While biochemical evaluation is widely accepted for differentiating between ACC an...

Full description

Saved in:
Bibliographic Details
Main Authors: Yinyao Chao, Hongzhang Zhu, Wenyi Yang, Haohua Yao, Nan Ma, Xianda Chen, Jing Zhao, Huali Ma, Zhenhua Liu, Hui Han, Zhuowei Liu, Kai Yao, Yiyao Li, Peng Wu, Jingtong Zhang, Bin Li, Shengjie Guo
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01842-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738692130766848
author Yinyao Chao
Hongzhang Zhu
Wenyi Yang
Haohua Yao
Nan Ma
Xianda Chen
Jing Zhao
Huali Ma
Zhenhua Liu
Hui Han
Zhuowei Liu
Kai Yao
Yiyao Li
Peng Wu
Jingtong Zhang
Bin Li
Shengjie Guo
author_facet Yinyao Chao
Hongzhang Zhu
Wenyi Yang
Haohua Yao
Nan Ma
Xianda Chen
Jing Zhao
Huali Ma
Zhenhua Liu
Hui Han
Zhuowei Liu
Kai Yao
Yiyao Li
Peng Wu
Jingtong Zhang
Bin Li
Shengjie Guo
author_sort Yinyao Chao
collection DOAJ
description Abstract Background Adrenocortical carcinoma (ACC), a rare and highly malignant adrenal gland tumor, exhibits computed tomography (CT) characteristics that resemble those of the less malignant pheochromocytoma (PHEO). While biochemical evaluation is widely accepted for differentiating between ACC and PHEO, non-functioning tumors remain a diagnostic challenge. The similarity in CT imaging and atypical hormone levels can lead to suboptimal accuracy in diagnosis, leading to inappropriate clinical interventions. This study aims to differentiate between large (≥ 4 cm) ACC and PHEO with radiomics features based on contrast-enhanced CT. Methods In this retrospective study, 158 patients who received pathological diagnoses of ACC or PHEO between January 2011 and September 2023 were enrolled from three institutions. Radiomics features were extracted from different phases of contrast-enhanced CT and then selected by a two-step procedure. The radiomics model was developed in a cohort of 109 patients from Institution 1, then the model performance was evaluated in the external test cohort of 49 patients from Institutions 2 and 3. The area under the receiver operating characteristic curve (AUC) of the radiomics model was compared with two radiologists using the DeLong test. Hormone testing results were collected to determine the presence of excess cortisol or catecholamines. SHapley Additive exPlanations (SHAP) was used to improve the interpretability of the radiomics model. Results We developed and evaluated a radiomics model consisting of ten selected CT-based radiomics features. In the external test cohort, the proposed radiomics model achieved high accuracy (86%), specificity (88%), and sensitivity (81%) in differentiating between ACC and PHEO and outperformed 2 radiologists (AUC 0.920 vs. 0.786, 0.629). This radiomics model showed strong capabilities in differentiating biochemically negative ACC and PHEO (with an accuracy of 80%). Moreover, its performance remained consistent even when cortisol and catecholamine levels were simultaneously elevated. Furthermore, SHAP provided quantitative explanations for the radiomics model and visualized the diagnostic process. Conclusions The interpretable CT-based radiomics model outperforms radiologists in differentiating between ACC and PHEO, especially when hormone testing results are atypical.
format Article
id doaj-art-5a25d5514f3040bd850f3b4db55f595e
institution DOAJ
issn 1471-2342
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-5a25d5514f3040bd850f3b4db55f595e2025-08-20T03:06:29ZengBMCBMC Medical Imaging1471-23422025-08-0125111110.1186/s12880-025-01842-7Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective studyYinyao Chao0Hongzhang Zhu1Wenyi Yang2Haohua Yao3Nan Ma4Xianda Chen5Jing Zhao6Huali Ma7Zhenhua Liu8Hui Han9Zhuowei Liu10Kai Yao11Yiyao Li12Peng Wu13Jingtong Zhang14Bin Li15Shengjie Guo16Zhongshan School of Medicine, Sun Yat-sen UniversityDepartment of Radiology, The First Affiliated Hospital, Sun Yat-sen UniversitySchool of Automation Science and Engineering, South China University of TechnologyDepartment of Urology, Guangdong Provincial People’s HospitalDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityState Key Laboratory of Oncology in Southern China, Collaborative Innovation Center of Cancer MedicineState Key Laboratory of Oncology in Southern China, Collaborative Innovation Center of Cancer MedicineDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityDepartment of Urology, Nanfang Hospital, Southern Medical UniversityDepartment of Urology, Nanfang Hospital, Southern Medical UniversityDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversitySchool of Automation Science and Engineering, South China University of TechnologyDepartment of Urology, Sun Yat-sen University Cancer Center, Sun Yat-sen UniversityAbstract Background Adrenocortical carcinoma (ACC), a rare and highly malignant adrenal gland tumor, exhibits computed tomography (CT) characteristics that resemble those of the less malignant pheochromocytoma (PHEO). While biochemical evaluation is widely accepted for differentiating between ACC and PHEO, non-functioning tumors remain a diagnostic challenge. The similarity in CT imaging and atypical hormone levels can lead to suboptimal accuracy in diagnosis, leading to inappropriate clinical interventions. This study aims to differentiate between large (≥ 4 cm) ACC and PHEO with radiomics features based on contrast-enhanced CT. Methods In this retrospective study, 158 patients who received pathological diagnoses of ACC or PHEO between January 2011 and September 2023 were enrolled from three institutions. Radiomics features were extracted from different phases of contrast-enhanced CT and then selected by a two-step procedure. The radiomics model was developed in a cohort of 109 patients from Institution 1, then the model performance was evaluated in the external test cohort of 49 patients from Institutions 2 and 3. The area under the receiver operating characteristic curve (AUC) of the radiomics model was compared with two radiologists using the DeLong test. Hormone testing results were collected to determine the presence of excess cortisol or catecholamines. SHapley Additive exPlanations (SHAP) was used to improve the interpretability of the radiomics model. Results We developed and evaluated a radiomics model consisting of ten selected CT-based radiomics features. In the external test cohort, the proposed radiomics model achieved high accuracy (86%), specificity (88%), and sensitivity (81%) in differentiating between ACC and PHEO and outperformed 2 radiologists (AUC 0.920 vs. 0.786, 0.629). This radiomics model showed strong capabilities in differentiating biochemically negative ACC and PHEO (with an accuracy of 80%). Moreover, its performance remained consistent even when cortisol and catecholamine levels were simultaneously elevated. Furthermore, SHAP provided quantitative explanations for the radiomics model and visualized the diagnostic process. Conclusions The interpretable CT-based radiomics model outperforms radiologists in differentiating between ACC and PHEO, especially when hormone testing results are atypical.https://doi.org/10.1186/s12880-025-01842-7Adrenocortical carcinomaPheochromocytomaRadiomics modelContrast-enhanced CTSHapley additive explanations
spellingShingle Yinyao Chao
Hongzhang Zhu
Wenyi Yang
Haohua Yao
Nan Ma
Xianda Chen
Jing Zhao
Huali Ma
Zhenhua Liu
Hui Han
Zhuowei Liu
Kai Yao
Yiyao Li
Peng Wu
Jingtong Zhang
Bin Li
Shengjie Guo
Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
BMC Medical Imaging
Adrenocortical carcinoma
Pheochromocytoma
Radiomics model
Contrast-enhanced CT
SHapley additive explanations
title Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
title_full Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
title_fullStr Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
title_full_unstemmed Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
title_short Differentiating between adrenocortical carcinoma and pheochromocytoma by a CT-based radiomics model: a multicenter retrospective study
title_sort differentiating between adrenocortical carcinoma and pheochromocytoma by a ct based radiomics model a multicenter retrospective study
topic Adrenocortical carcinoma
Pheochromocytoma
Radiomics model
Contrast-enhanced CT
SHapley additive explanations
url https://doi.org/10.1186/s12880-025-01842-7
work_keys_str_mv AT yinyaochao differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT hongzhangzhu differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT wenyiyang differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT haohuayao differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT nanma differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT xiandachen differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT jingzhao differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT hualima differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT zhenhualiu differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT huihan differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT zhuoweiliu differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT kaiyao differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT yiyaoli differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT pengwu differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT jingtongzhang differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT binli differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy
AT shengjieguo differentiatingbetweenadrenocorticalcarcinomaandpheochromocytomabyactbasedradiomicsmodelamulticenterretrospectivestudy