Article (Scientific journals)
Distinction of lymphoma from sarcoidosis at FDG PET/CT - evaluation of radiomic-feature guided machine learning versus human reader performance.
LOVINFOSSE, Pierre; Ferreira, Marta; WITHOFS, Nadia et al.
2022In Journal of Nuclear Medicine, 63, p. 1933-1940
Peer Reviewed verified by ORBi
 

Files


Full Text
1933.full.pdf
Publisher postprint (802.51 kB)
Request a copy

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
18F-FDG PET/CT; Lymphoma; Machine Learning; Oncology: Lymphoma; Other; PET/CT; Radiomics; Sarcoidosis; Radiology, Nuclear Medicine and imaging
Abstract :
[en] Sarcoidosis and lymphoma often share common features on 18F-FDG PET/CT, such as intense hypermetabolic lesions of lymph nodes and multiple organs. We aimed at developing and validating radiomics signatures to differentiate sarcoidosis from Hodgkin (HL) and diffuse large B-cell (DLBCL) lymphoma. Methods: We retrospectively collected 420 patients (169 sarcoidosis, 140 HL and 111 DLBCL) who underwent a pretreatment 18F-FDG PET/CT at the University Hospital of Liege. The studies were randomly distributed to 4 physicians who gave their diagnostic suggestion between the 3 diseases. Individual and pooled performances of physicians were then calculated. The inter-observer variability was evaluated using a sample of 34 studies interpreted by all physicians. Volumes of interest (VOI) were delineated over the lesions and the liver using MIM software, and 215 radiomic features were extracted using Radiomics toolbox. Models were developed combining clinical data (age, gender and weight) and radiomics (original and tumor-to-liver TLR radiomics), with 7 different feature selection approaches and 4 different machine learning (ML) classifiers, to differentiate sarcoidosis and lymphomas on both lesion-based and patient-based approaches. Results: For identifying lymphoma vs. sarcoidosis, physicians' pooled sensitivity, specificity, area under the curve (AUC) and accuracy were 0.99 (CI95%:0.97-1.00), 0.75 (CI95%: 0.68-0.81), 0.87 (CI95%: 0.84-0.90) and 89.3%, respectively, whereas for identifying HL in the tumor population, it was 0.58 (CI95%: 0.49-0.66), 0.82 (CI95%: 0.74-0.89), 0.70 (CI95%: 0.64-0.75) and 68.5%, respectively. A moderate agreement was found between observers for the diagnosis of lymphoma vs. sarcoidosis and HL vs. DLBCL with Fleiss kappa values of 0.66 (CI95%: 0.45-0.87) and 0.69 (CI95%: 0.45-0.93), respectively. The best ML models for identifying lymphoma vs. sarcoidosis showed AUC of 0.94 (CI95%: 0.93-0.95) and 0.85 (CI95%: 0.82-0.88) in lesion- and patient-based approaches, respectively, using TLR radiomics (+ age for the second). To differentiate HL and DLBCL, we obtained AUC of 0.95 (CI95%: 0.93-0.96) in lesion-based approach using TLR radiomics, and 0.86 (CI95%: 0.80-0.91) in patient-based using original radiomics and age. Conclusion: Characterization of sarcoidosis and lymphoma lesions is feasible using ML and radiomics, with very good to excellent performances, equivalent or better than those of doctors who showed significant interobserver variability in their assessment.
Disciplines :
Life sciences: Multidisciplinary, general & others
Author, co-author :
LOVINFOSSE, Pierre ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
Ferreira, Marta;  GIGA-CRC in vivo Imaging, University of Liege, Belgium
WITHOFS, Nadia ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
JADOUL, Alexandre ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
Derwael, Céline ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
Frix, Anne-Noëlle ;  Centre Hospitalier Universitaire de Liège - CHU > > Service de pneumologie - allergologie
GUIOT, Julien  ;  Centre Hospitalier Universitaire de Liège - CHU > > Service de pneumologie - allergologie
BERNARD, Claire ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
Diep, Anh Nguyet;  Biostatistics Unit, Department of Public Health, University of Liege, Belgium
Donneau, Anne-Françoise ;  Université de Liège - ULiège > Santé publique : de la Biostatistique à la Promotion de la Santé
LEJEUNE, Marie ;  Centre Hospitalier Universitaire de Liège - CHU > > Service d'hématologie clinique
BONNET, Christophe ;  Centre Hospitalier Universitaire de Liège - CHU > > Service d'hématologie clinique
Vos, Wim;  Radiomics SA, Belgium
Meyer, Patrick ;  Université de Liège - ULiège > Integrative Biological Sciences (InBioS)
HUSTINX, Roland  ;  Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
More authors (5 more) Less
Language :
English
Title :
Distinction of lymphoma from sarcoidosis at FDG PET/CT - evaluation of radiomic-feature guided machine learning versus human reader performance.
Publication date :
19 May 2022
Journal title :
Journal of Nuclear Medicine
ISSN :
0161-5505
eISSN :
1535-5667
Publisher :
Society of Nuclear Medicine, United States
Volume :
63
Pages :
1933-1940
Peer reviewed :
Peer Reviewed verified by ORBi
Available on ORBi :
since 15 June 2022

Statistics


Number of views
88 (23 by ULiège)
Number of downloads
5 (5 by ULiège)

Scopus citations®
 
10
Scopus citations®
without self-citations
10
OpenCitations
 
2

Bibliography


Similar publications



Contact ORBi