Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

Hatt, Mathieu; Rest, Catherine Cheze Le; Antonorsi, Nils; Tixier, Florent; Tankyevych, Olena; Jaouen, Vincent; Lucia, François; Bourbonne, Vincent; Schick, Ulrike; Badic, Bogdan; Visvikis, Dimitris

doi:10.1053/j.semnuclmed.2020.09.002

Cited by 39 publications

(60 citation statements)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this single-center study, we reviewed 228 GGN patients who underwent 18 F-FDG PET/CT examinations in our hospital from November 2011 to November 2020. The Institutional Ethics Committee reviewed the retrospective analysis (No.…”

Section: Participantsmentioning

confidence: 99%

“…Within one month before surgery, the patient received 18 F-FDG PET/CT examination (Biograph mCT 64, Siemens, Erlangen, Germany). According to the European Association for Nuclear Medicine (EANM) guideline 1.0 (version 2.0 was released in February 2015) [28], 18 F-FDG PET/CT images were acquired at 60 ± 5 minutes after 18 F-FDG injection. All PET/CT images were reconstructed on the processing workstation (TrueD software, Siemens Healthcare).…”

Section: Fdg Pet/ct Image Acquisitionmentioning

confidence: 99%

“…For comparison, we constructed three 3D-CNNs: CT, PET, and PET/CT. The supplementary material provides more detailed 18 F-FDG PET/CT image acquisition methods, tumor segmentation, and deep learning model generation.…”

Section: The Training Of Deep Learning Modelmentioning

confidence: 99%

“…Radiomics can perform a comprehensive analysis of the region of interest, while the biopsy can only capture a small part of the lesion [17]. Radiomics has been extensively studied in PET/CT imaging [18]. The latest study from Palumbo et al [19] found that the shape and texture features of 18 F-FDG PET/CT could provide more information for distinguishing benign and malignant lung nodules than conventional imaging functions alone.…”

Section: Introductionmentioning

confidence: 99%

“…Since the clinical management strategies for treating benign lesions and invasive adenocarcinoma (IAC) are completely different [9], the accurate identi cation of benign and malignant GGN is of great importance. Therefore, this study aims to train, validate, and test the 3D-CNN based on 18 F-FDG PET/CT images and evaluate CT, PET, and PET/CT 3D-CNN performance in distinguishing benign lesions and IAC.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Shao¹,

Niu²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Purpose: This work aims to train, validate and test a dual-stream three-dimensional convolutional neural network (3D-CNN) based on Fluorine 18 (18F)-fluorodeoxyglucose (FDG) PET/CT to distinguish benign lesions and invasive adenocarcinoma (IAC) in ground-glass nodules (GGNs).Methods: We retrospectively analyzed patients with suspicious GGNs who underwent 18F-FDG PET/CT in our hospital from November 2011 to November 2020. The patients with benign lesions or IAC were selected for this study. According to the ratio of 7:3, the data was randomly divided into training data and testing data. Partial image feature extraction software was used to segment PET and CT images, and the training data after using the data augmentation was used for the training and validation (5-fold cross-validation) of the three CNNs (PET, CT, and PET/CT networks).Results: A total of 23 benign nodules and 92 IAC nodules from 106 patients were included in this study. In the validation set, the performance of PET network (accuracy of 0.92 ± 0.02; sensitivity and specificity of 0.97 ± 0.03 and 0.94 ± 0.04) were better than CT network (accuracy of 0.84 ± 0.03; sensitivity and specificity of 0.90 ± 0.07 and 0.90 ± 0.04); in the testing set, the performance of both networks declined. However, when the specificity was close, the accuracy and sensitivity of PET network (0.79 ± 0.05 and 0.90 ± 0.05) were still higher than CT network (0.72 ± 0.05 and 0.79 ± 0.08). For the dual-stream PET/CT network, its performance was almost the same as PET network in the validation set; while in testing set, although its performance decreased (accuracy was 0.81 ± 0.03; sensitivity and specificity were 0.92 ± 0.03 and 0.86 ± 0.00), it was still higher than CT or PET networks. Moreover, the accuracy of PET/CT network was higher than two nuclear medicine physicians [Physician 1 (3-year experience): 0.70 and Physician 2 (10-year experience): 0.73]. Conclusion: The 3D-CNN based on 18F-FDG PET/CT can be used to distinguish benign lesions and IAC in GGNs, and the performance is better when both CT and PET images are used together.

show abstract

Section: Participantsmentioning

confidence: 99%

Section: Fdg Pet/ct Image Acquisitionmentioning

confidence: 99%

Section: The Training Of Deep Learning Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Shao¹,

Niu²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Impact of respiratory motion on ¹⁸F‐FDG PET radiomics stability: Clinical evaluation with a digital PET scanner

Chen,

Kan,

Liu

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose18F‐FDG PET quantitative features are susceptible to respiratory motion. However, studies using clinical patient data to explore the impact of respiratory motion on 18F‐FDG PET radiomic features are limited. In this study, we investigated the impact of respiratory motion on radiomics stability with clinical 18F‐FDG PET images using a data‐driven gating (DDG) algorithm on the digital PET scanner.Materials and MethodsA total of 101 patients who underwent oncological 18F‐FDG PET scans were retrospectively included. A DDG algorithm combined with a motion compensation technique was used to extract the PET images with respiratory motion correction. 18F‐FDG‐avid lesions from the thorax to the upper abdomen were analyzed on the non‐DDG and DDG PET images. The lesions were segmented with a 40% threshold of the maximum standardized uptake. A total of 725 radiomic features were computed from the segmented lesions, including first‐order, shape, texture, and wavelet features. The intraclass correlation coefficient (ICC) and coefficient of variation (COV) were calculated to evaluate feature stability. An ICC above 0.9 and a COV below 5% were considered high stability.ResultsIn total, 168 lesions with and without respiratory motion correction were analyzed. Our results indicated that most 18F‐FDG PET radiomic features are sensitive to respiratory motion. Overall, only 27 out of 725 (3.72%) radiomic features were identified as highly stable, including one from the first‐order features (entropy), one from the shape features (sphericity), four from the gray‐level co‐occurrence matrix features (normalized and unnormalized inverse difference moment, joint entropy, and sum entropy), one from the gray‐level run‐length matrix features (run entropy), and 20 from the wavelet filter‐based features.ConclusionRespiratory motion has a significant impact on 18F‐FDG PET radiomics stability. The highly stable features identified in our study may serve as potential candidates for further applications, such as machine learning modeling.

show abstract

Combined 18F‐FDG PET‐CT markers in dementia with Lewy bodies

Mattoli,

Cocciolillo,

Chiacchiaretta

et al. 2023

Alz & Dem Diag Ass & Dis Mo

View full text Add to dashboard Cite

INTRODUCTION18F‐Fluoro‐deoxyglucose–positron emission tomography (FDG‐PET) is a supportive biomarker in dementia with Lewy bodies (DLB) diagnosis and its advanced analysis methods, including radiomics and machine learning (ML), were developed recently. The aim of this study was to evaluate the FDG‐PET diagnostic performance in predicting a DLB versus Alzheimer's disease (AD) diagnosis.METHODSFDG‐PET scans were visually and semi‐quantitatively analyzed in 61 patients. Radiomics and ML analyses were performed, building five ML models: (1) clinical features; (2) visual and semi‐quantitative PET features; (3) radiomic features; (4) all PET features; and (5) overall features.RESULTSAt follow‐up, 34 patients had DLB and 27 had AD. At visual analysis, DLB PET signs were significantly more frequent in DLB, having the highest diagnostic accuracy (86.9%). At semi‐quantitative analysis, the right precuneus, superior parietal, lateral occipital, and primary visual cortices showed significantly reduced uptake in DLB. The ML model 2 had the highest diagnostic accuracy (84.3%).DISCUSSIONFDG‐PET is a valuable tool in DLB diagnosis, having visual and semi‐quantitative analyses with the highest diagnostic accuracy at ML analyses.

show abstract

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

Cited by 39 publications

References 92 publications

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Impact of respiratory motion on ¹⁸F‐FDG PET radiomics stability: Clinical evaluation with a digital PET scanner

Combined 18F‐FDG PET‐CT markers in dementia with Lewy bodies

Contact Info

Product

Resources

About

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

Cited by 39 publications

References 92 publications

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Application of dual-stream 3D convolutional neural network based on 18F-FDG PET/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules

Impact of respiratory motion on 18F‐FDG PET radiomics stability: Clinical evaluation with a digital PET scanner

Combined 18F‐FDG PET‐CT markers in dementia with Lewy bodies

Contact Info

Product

Resources

About

Impact of respiratory motion on ¹⁸F‐FDG PET radiomics stability: Clinical evaluation with a digital PET scanner