Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images

Objectives: To develop and validate a deep learning model using multimodal PET/CT imaging for detecting and classifying focal liver lesions (FLL). Methods: This study included 185 patients who underwent 18F-FDG PET/CT imaging at our institution from March 2022 to February 2023. We analyzed serologic...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingqi Luo, Qingqi Yang, Jinglang Hu, Xiaowen Qin, Shengnan Jiang, Ying Liu
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:European Journal of Radiology Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352047724000790
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063145505128448
author Yingqi Luo
Qingqi Yang
Jinglang Hu
Xiaowen Qin
Shengnan Jiang
Ying Liu
author_facet Yingqi Luo
Qingqi Yang
Jinglang Hu
Xiaowen Qin
Shengnan Jiang
Ying Liu
author_sort Yingqi Luo
collection DOAJ
description Objectives: To develop and validate a deep learning model using multimodal PET/CT imaging for detecting and classifying focal liver lesions (FLL). Methods: This study included 185 patients who underwent 18F-FDG PET/CT imaging at our institution from March 2022 to February 2023. We analyzed serological data and imaging. Liver lesions were segmented on PET and CT, serving as the ''reference standard''. Deep learning models were trained using PET and CT images to generate predicted segmentations and classify lesion nature. Model performance was evaluated by comparing the predicted segmentations with the reference segmentations, using metrics such as Dice, Precision, Recall, F1-score, ROC, and AUC, and compared it with physician diagnoses. Results: This study finally included 150 patients, comprising 46 patients with benign liver nodules, 51 patients with malignant liver nodules, and 53 patients with no FLLs. Significant differences were observed among groups for age, AST, ALP, GGT, AFP, CA19–9and CEA. On the validation set, the Dice coefficient of the model was 0.740. For the normal group, the recall was 0.918, precision was 0.904, F1-score was 0.909, and AUC was 0.976. For the benign group, the recall was 0.869, precision was 0.862, F1-score was 0.863, and AUC was 0.928. For the malignant group, the recall was 0.858, precision was 0.914, F1-score was 0.883, and AUC was 0.979. The model's overall diagnostic performance was between that of junior and senior physician. Conclusion: This deep learning model demonstrated high sensitivity in detecting FLLs and effectively differentiated between benign and malignant lesions.
format Article
id doaj-art-4c4a541df5944367be14fb67a32a317e
institution DOAJ
issn 2352-0477
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series European Journal of Radiology Open
spelling doaj-art-4c4a541df5944367be14fb67a32a317e2025-08-20T02:49:44ZengElsevierEuropean Journal of Radiology Open2352-04772025-06-011410062410.1016/j.ejro.2024.100624Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT imagesYingqi Luo0Qingqi Yang1Jinglang Hu2Xiaowen Qin3Shengnan Jiang4Ying Liu5Department of Nuclear medicine, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, ChinaDepartment of Vascular Surgery, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, ChinaSchool of Medicine, Sun Yat-Sen University, Guangzhou, ChinaDepartment of Nuclear medicine, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, ChinaDepartment of Nuclear medicine, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, ChinaDepartment of Nuclear medicine, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, China; Correspondence to: No. 250 Changgang East Road, Haizhu District, Guangzhou City, Guangdong Province, China.Objectives: To develop and validate a deep learning model using multimodal PET/CT imaging for detecting and classifying focal liver lesions (FLL). Methods: This study included 185 patients who underwent 18F-FDG PET/CT imaging at our institution from March 2022 to February 2023. We analyzed serological data and imaging. Liver lesions were segmented on PET and CT, serving as the ''reference standard''. Deep learning models were trained using PET and CT images to generate predicted segmentations and classify lesion nature. Model performance was evaluated by comparing the predicted segmentations with the reference segmentations, using metrics such as Dice, Precision, Recall, F1-score, ROC, and AUC, and compared it with physician diagnoses. Results: This study finally included 150 patients, comprising 46 patients with benign liver nodules, 51 patients with malignant liver nodules, and 53 patients with no FLLs. Significant differences were observed among groups for age, AST, ALP, GGT, AFP, CA19–9and CEA. On the validation set, the Dice coefficient of the model was 0.740. For the normal group, the recall was 0.918, precision was 0.904, F1-score was 0.909, and AUC was 0.976. For the benign group, the recall was 0.869, precision was 0.862, F1-score was 0.863, and AUC was 0.928. For the malignant group, the recall was 0.858, precision was 0.914, F1-score was 0.883, and AUC was 0.979. The model's overall diagnostic performance was between that of junior and senior physician. Conclusion: This deep learning model demonstrated high sensitivity in detecting FLLs and effectively differentiated between benign and malignant lesions.http://www.sciencedirect.com/science/article/pii/S2352047724000790Deep learningFocal liver lesionPET/CT
spellingShingle Yingqi Luo
Qingqi Yang
Jinglang Hu
Xiaowen Qin
Shengnan Jiang
Ying Liu
Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
European Journal of Radiology Open
Deep learning
Focal liver lesion
PET/CT
title Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
title_full Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
title_fullStr Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
title_full_unstemmed Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
title_short Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images
title_sort preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal pet ct images
topic Deep learning
Focal liver lesion
PET/CT
url http://www.sciencedirect.com/science/article/pii/S2352047724000790
work_keys_str_mv AT yingqiluo preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages
AT qingqiyang preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages
AT jinglanghu preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages
AT xiaowenqin preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages
AT shengnanjiang preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages
AT yingliu preliminarystudyondetectionanddiagnosisoffocalliverlesionsbasedonadeeplearningmodelusingmultimodalpetctimages