A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques

Abstract Neuroblastoma presents a wide variety of clinical phenotypes, demonstrating different levels of benignity and malignancy among its subtypes. Early diagnosis is essential for effective patient management. Computed tomography (CT) serves as a significant diagnostic tool for neuroblastoma, uti...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuanyuan Wang, Fangfang Wang, Zixin Qin, Yongcheng Fu, Jingyue Wang, Shangkun Li, Da Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-99451-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713605889490944
author Yuanyuan Wang
Fangfang Wang
Zixin Qin
Yongcheng Fu
Jingyue Wang
Shangkun Li
Da Zhang
author_facet Yuanyuan Wang
Fangfang Wang
Zixin Qin
Yongcheng Fu
Jingyue Wang
Shangkun Li
Da Zhang
author_sort Yuanyuan Wang
collection DOAJ
description Abstract Neuroblastoma presents a wide variety of clinical phenotypes, demonstrating different levels of benignity and malignancy among its subtypes. Early diagnosis is essential for effective patient management. Computed tomography (CT) serves as a significant diagnostic tool for neuroblastoma, utilizing machine vision imaging, which offers advantages over traditional X-ray and ultrasound imaging modalities. However, the high degree of similarity among neuroblastoma subtypes complicates the diagnostic process. In response to these challenges, this study presents a modified version of the You Only Look Once (YOLO) algorithm, called YOLOv8-IE. This revised approach integrates feature fusion and inverse residual attention mechanisms. The aim of YOLO-IE is to improve the detection and classification of neuroblastoma tumors. In light of the image features, we have implemented the inverse residual-based attention structure (iRMB) within the detection network of YOLOv8, thereby enhancing the model’s ability to focus on significant features present in the images. Additionally, we have incorporated the centered feature pyramid EVC module. Experimental results show that the proposed detection network, named YOLO-IE, attains a mean Average Precision (mAP) 7.9% higher than the baseline model, YOLO. The individual contributions of iRMB and EVC to the performance improvement are 0.8% and 3.6% above the baseline model, respectively. This study represents a significant advancement in the field, as it not only facilitates the detection and classification of neuroblastoma but also demonstrates the considerable potential of machine learning and artificial intelligence in the realm of medical diagnosis.
format Article
id doaj-art-4e96ff07ada6470b9ccdd9c1f1811ae5
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4e96ff07ada6470b9ccdd9c1f1811ae52025-08-20T03:13:55ZengNature PortfolioScientific Reports2045-23222025-04-0115111610.1038/s41598-025-99451-5A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniquesYuanyuan Wang0Fangfang Wang1Zixin Qin2Yongcheng Fu3Jingyue Wang4Shangkun Li5Da Zhang6Department of Pediatric Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Electronic information, Zhengzhou University Cyberspace Security CollegeDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pediatric Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pediatric Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pediatric Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pediatric Surgery, The First Affiliated Hospital of Zhengzhou UniversityAbstract Neuroblastoma presents a wide variety of clinical phenotypes, demonstrating different levels of benignity and malignancy among its subtypes. Early diagnosis is essential for effective patient management. Computed tomography (CT) serves as a significant diagnostic tool for neuroblastoma, utilizing machine vision imaging, which offers advantages over traditional X-ray and ultrasound imaging modalities. However, the high degree of similarity among neuroblastoma subtypes complicates the diagnostic process. In response to these challenges, this study presents a modified version of the You Only Look Once (YOLO) algorithm, called YOLOv8-IE. This revised approach integrates feature fusion and inverse residual attention mechanisms. The aim of YOLO-IE is to improve the detection and classification of neuroblastoma tumors. In light of the image features, we have implemented the inverse residual-based attention structure (iRMB) within the detection network of YOLOv8, thereby enhancing the model’s ability to focus on significant features present in the images. Additionally, we have incorporated the centered feature pyramid EVC module. Experimental results show that the proposed detection network, named YOLO-IE, attains a mean Average Precision (mAP) 7.9% higher than the baseline model, YOLO. The individual contributions of iRMB and EVC to the performance improvement are 0.8% and 3.6% above the baseline model, respectively. This study represents a significant advancement in the field, as it not only facilitates the detection and classification of neuroblastoma but also demonstrates the considerable potential of machine learning and artificial intelligence in the realm of medical diagnosis.https://doi.org/10.1038/s41598-025-99451-5Deep learningArtificial intelligenceNeuroblastomaMachine learningDiagnosis
spellingShingle Yuanyuan Wang
Fangfang Wang
Zixin Qin
Yongcheng Fu
Jingyue Wang
Shangkun Li
Da Zhang
A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
Scientific Reports
Deep learning
Artificial intelligence
Neuroblastoma
Machine learning
Diagnosis
title A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
title_full A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
title_fullStr A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
title_full_unstemmed A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
title_short A non-invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
title_sort non invasive diagnostic approach for neuroblastoma utilizing preoperative enhanced computed tomography and deep learning techniques
topic Deep learning
Artificial intelligence
Neuroblastoma
Machine learning
Diagnosis
url https://doi.org/10.1038/s41598-025-99451-5
work_keys_str_mv AT yuanyuanwang anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT fangfangwang anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT zixinqin anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT yongchengfu anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT jingyuewang anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT shangkunli anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT dazhang anoninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT yuanyuanwang noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT fangfangwang noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT zixinqin noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT yongchengfu noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT jingyuewang noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT shangkunli noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques
AT dazhang noninvasivediagnosticapproachforneuroblastomautilizingpreoperativeenhancedcomputedtomographyanddeeplearningtechniques