1
|
Draye-Carbonnier S, Camus V, Becker S, Tonnelet D, Lévêque E, Zduniak A, Jardin F, Tilly H, Vera P, Decazes P. Prognostic value of the combination of volume, massiveness and fragmentation parameters measured on baseline FDG pet in high-burden follicular lymphoma. Sci Rep 2024; 14:8033. [PMID: 38580734 PMCID: PMC10997640 DOI: 10.1038/s41598-024-58412-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Accepted: 03/28/2024] [Indexed: 04/07/2024] Open
Abstract
The prognostic value of radiomic quantitative features measured on pre-treatment 18F-FDG PET/CT was investigated in patients with follicular lymphoma (FL). We conducted a retrospective study of 126 FL patients (grade 1-3a) diagnosed between 2006 and 2020. A dozen of PET/CT-derived features were extracted via a software (Oncometer3D) from baseline 18F-FDG PET/CT images. The receiver operating characteristic (ROC) curve, Kaplan-Meier method and Cox analysis were used to assess the prognostic factors for progression of disease within 24 months (POD24) and progression-free survival at 24 months. Four different clusters were identified among the twelve PET parameters analyzed: activity, tumor burden, fragmentation-massiveness and dispersion. On ROC analyses, TMTV, the total metabolic tumor volume, had the highest AUC (0.734) followed by medPCD, the median distance between the centroid of the tumors and their periphery (AUC: 0.733). Patients with high TMTV (HR = 4.341; p < 0.001), high Tumor Volume Surface Ratio (TVSR) (HR = 3.204; p < 0.003) and high medPCD (HR = 4.507; p < 0.001) had significantly worse prognosis in both Kaplan-Meier and Cox univariate analyses. Furthermore, a synergistic effect was observed in Kaplan-Meier and Cox analyses combining these three PET/CT-derived parameters (HR = 12.562; p < 0.001). Having two or three high parameters among TMTV, TVSR and medPCD was able to predict POD24 status with a specificity of 68% and a sensitivity of 75%. TMTV, TVSR and baseline medPCD are strong prognostic factors in FL and their combination better predicts disease prognosis.
Collapse
Affiliation(s)
| | - V Camus
- Department of Hematology, Centre Henri Becquerel, Rouen, France
- INSERM U1245, Université de Rouen, IRIB, Rouen, France
| | - S Becker
- Department of Nuclear Medicine, Centre Henri Becquerel, Rouen, France
- QuantIF-LITIS (EA 4108-FR CNRS 3638), Faculty of Medicine, University of Rouen, Rouen, France
| | - D Tonnelet
- Department of Nuclear Medicine, Centre Henri Becquerel, Rouen, France
| | - E Lévêque
- Department of Statistics and Clinical Research Unit, Centre Henri Becquerel, Rouen, France
| | - A Zduniak
- Department of Hematology, Centre Henri Becquerel, Rouen, France
| | - F Jardin
- Department of Hematology, Centre Henri Becquerel, Rouen, France
- INSERM U1245, Université de Rouen, IRIB, Rouen, France
| | - H Tilly
- Department of Hematology, Centre Henri Becquerel, Rouen, France
- INSERM U1245, Université de Rouen, IRIB, Rouen, France
| | - P Vera
- Department of Nuclear Medicine, Centre Henri Becquerel, Rouen, France
- QuantIF-LITIS (EA 4108-FR CNRS 3638), Faculty of Medicine, University of Rouen, Rouen, France
| | - P Decazes
- Department of Nuclear Medicine, Centre Henri Becquerel, Rouen, France.
- QuantIF-LITIS (EA 4108-FR CNRS 3638), Faculty of Medicine, University of Rouen, Rouen, France.
| |
Collapse
|
2
|
Wang H, Sarrami A, Wu JTY, Baratto L, Sharma A, Wong KCL, Singh SB, Daldrup-Link HE, Syeda-Mahmood T. Multimodal Pediatric Lymphoma Detection using PET and MRI. AMIA Annu Symp Proc 2024; 2023:736-743. [PMID: 38222333 PMCID: PMC10785920] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/16/2024]
Abstract
Lymphoma is one of the most common types of cancer for children (ages 0 to 19). Due to the reduced radiation exposure, PET/MR systems that allow simultaneous PET and MR imaging have become the standard of care for diagnosing cancers and monitoring tumor response to therapy in the pediatric population. In this work, we developed a multimodal deep learning algorithm for automatic pediatric lymphoma detection using PET and MRI. Through innovative designs such as standardized uptake value (SUV) guided tumor candidate generation, location aware classification model learning and weighted multimodal feature fusion, our algorithm can be effectively trained with limited data and achieved superior tumor detection performance over the state-of-the-art in our experiments.
Collapse
Affiliation(s)
- Hongzhi Wang
- IBM Almaden Research Center, San Jose, CA, U.S.A
| | | | - Joy Tzung-Yu Wu
- IBM Almaden Research Center, San Jose, CA, U.S.A
- Stanford University, Palo Alto, CA, U.S.A
| | | | - Arjun Sharma
- IBM Almaden Research Center, San Jose, CA, U.S.A
| | - Ken C L Wong
- IBM Almaden Research Center, San Jose, CA, U.S.A
| | | | | | | |
Collapse
|
3
|
Panagiotidis E, Papachristou K, Makridou A, Zoglopitou LA, Paschali A, Kalathas T, Chatzimarkou M, Chatzipavlidou V. Review of artificial intelligence clinical applications in Nuclear Medicine. Nucl Med Commun 2024; 45:24-34. [PMID: 37901920 DOI: 10.1097/mnm.0000000000001786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/31/2023]
Abstract
This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.
Collapse
Affiliation(s)
| | | | - Anna Makridou
- Medical Physics Department, Cancer Hospital of Thessaloniki 'Theagenio', Thessaloniki, Greece
| | | | - Anna Paschali
- Nuclear Medicine Department, Cancer Hospital of Thessaloniki 'Theagenio' and
| | - Theodoros Kalathas
- Nuclear Medicine Department, Cancer Hospital of Thessaloniki 'Theagenio' and
| | - Michael Chatzimarkou
- Medical Physics Department, Cancer Hospital of Thessaloniki 'Theagenio', Thessaloniki, Greece
| | | |
Collapse
|
4
|
Alderuccio JP, Kuker RA, Yang F, Moskowitz CH. Quantitative PET-based biomarkers in lymphoma: getting ready for primetime. Nat Rev Clin Oncol 2023; 20:640-657. [PMID: 37460635 DOI: 10.1038/s41571-023-00799-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/21/2023] [Indexed: 08/20/2023]
Abstract
The use of functional quantitative biomarkers extracted from routine PET-CT scans to characterize clinical responses in patients with lymphoma is gaining increased attention, and these biomarkers can outperform established clinical risk factors. Total metabolic tumour volume enables individualized estimation of survival outcomes in patients with lymphoma and has shown the potential to predict response to therapy suitable for risk-adapted treatment approaches in clinical trials. The deployment of machine learning tools in molecular imaging research can assist in recognizing complex patterns and, with image classification, in tumour identification and segmentation of data from PET-CT scans. Initial studies using fully automated approaches to calculate metabolic tumour volume and other PET-based biomarkers have demonstrated appropriate correlation with calculations from experts, warranting further testing in large-scale studies. The extraction of computer-based quantitative tumour characterization through radiomics can provide a comprehensive view of phenotypic heterogeneity that better captures the molecular and functional features of the disease. Additionally, radiomics can be integrated with genomic data to provide more accurate prognostic information. Further improvements in PET-based biomarkers are imminent, although their incorporation into clinical decision-making currently has methodological shortcomings that need to be addressed with confirmatory prospective validation in selected patient populations. In this Review, we discuss the current knowledge, challenges and opportunities in the integration of quantitative PET-based biomarkers in clinical trials and the routine management of patients with lymphoma.
Collapse
Affiliation(s)
- Juan Pablo Alderuccio
- Department of Medicine, Division of Hematology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA.
| | - Russ A Kuker
- Department of Radiology, Division of Nuclear Medicine, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Fei Yang
- Department of Radiation Oncology, Division of Medical Physics, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Craig H Moskowitz
- Department of Medicine, Division of Hematology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| |
Collapse
|
5
|
Hellström H, Liedes J, Rainio O, Malaspina S, Kemppainen J, Klén R. Classification of head and neck cancer from PET images using convolutional neural networks. Sci Rep 2023; 13:10528. [PMID: 37386289 PMCID: PMC10310830 DOI: 10.1038/s41598-023-37603-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 06/23/2023] [Indexed: 07/01/2023] Open
Abstract
The aim of this study was to develop a convolutional neural network (CNN) for classifying positron emission tomography (PET) images of patients with and without head and neck squamous cell carcinoma (HNSCC) and other types of head and neck cancer. A PET/magnetic resonance imaging scan with 18F-fluorodeoxyglucose (18F-FDG) was performed for 200 head and neck cancer patients, 182 of which were diagnosed with HNSCC, and the location of cancer tumors was marked to the images with a binary mask by a medical doctor. The models were trained and tested with five-fold cross-validation with the primary data set of 1990 2D images obtained by dividing the original 3D images of 178 HNSCC patients into transaxial slices and with an additional test set with 238 images from the patients with head and neck cancer other than HNSCC. A shallow and a deep CNN were built by using the U-Net architecture for classifying the data into two groups based on whether an image contains cancer or not. The impact of data augmentation on the performance of the two CNNs was also considered. According to our results, the best model for this task in terms of area under receiver operator characteristic curve (AUC) is a deep augmented model with a median AUC of 85.1%. The four models had highest sensitivity for HNSCC tumors on the root of the tongue (median sensitivities of 83.3-97.7%), in fossa piriformis (80.2-93.3%), and in the oral cavity (70.4-81.7%). Despite the fact that the models were trained with only HNSCC data, they had also very good sensitivity for detecting follicular and papillary carcinoma of thyroid gland and mucoepidermoid carcinoma of the parotid gland (91.7-100%).
Collapse
Affiliation(s)
- Henri Hellström
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland
| | - Joonas Liedes
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland
| | - Oona Rainio
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland.
| | - Simona Malaspina
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
| | - Jukka Kemppainen
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland
| | - Riku Klén
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland
| |
Collapse
|
6
|
Šedienė S, Kulakienė I, Urbonavičius BG, Korobeinikova E, Rudžianskas V, Povilonis PA, Jaselskė E, Adlienė D, Juozaitytė E. Development of a Model Based on Delta-Radiomic Features for the Optimization of Head and Neck Squamous Cell Carcinoma Patient Treatment. Medicina (Kaunas) 2023; 59:1173. [PMID: 37374377 DOI: 10.3390/medicina59061173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Revised: 05/25/2023] [Accepted: 06/09/2023] [Indexed: 06/29/2023]
Abstract
Background and Objectives: To our knowledge, this is the first study that investigated the prognostic value of radiomics features extracted from not only staging 18F-fluorodeoxyglucose positron emission tomography (FDG PET/CT) images, but also post-induction chemotherapy (ICT) PET/CT images. This study aimed to construct a training model based on radiomics features obtained from PET/CT in a cohort of patients with locally advanced head and neck squamous cell carcinoma treated with ICT, to predict locoregional recurrence, development of distant metastases, and the overall survival, and to extract the most significant radiomics features, which were included in the final model. Materials and Methods: This retrospective study analyzed data of 55 patients. All patients underwent PET/CT at the initial staging and after ICT. Along the classical set of 13 parameters, the original 52 parameters were extracted from each PET/CT study and an additional 52 parameters were generated as a difference between radiomics parameters before and after the ICT. Five machine learning algorithms were tested. Results: The Random Forest algorithm demonstrated the best performance (R2 0.963-0.998) in the majority of datasets. The strongest correlation in the classical dataset was between the time to disease progression and time to death (r = 0.89). Another strong correlation (r ≥ 0.8) was between higher-order texture indices GLRLM_GLNU, GLRLM_SZLGE, and GLRLM_ZLNU and standard PET parameters MTV, TLG, and SUVmax. Patients with a higher numerical expression of GLCM_ContrastVariance, extracted from the delta dataset, had a longer survival and longer time until progression (p = 0.001). Good correlations were observed between Discretized_SUVstd or Discretized_SUVSkewness and time until progression (p = 0.007). Conclusions: Radiomics features extracted from the delta dataset produced the most robust data. Most of the parameters had a positive impact on the prediction of the overall survival and the time until progression. The strongest single parameter was GLCM_ContrastVariance. Discretized_SUVstd or Discretized_SUVSkewness demonstrated a strong correlation with the time until progression.
Collapse
Affiliation(s)
- Severina Šedienė
- Department of Radiology of Lithuanian, University of Health Sciences, Eivenių g. 2, LT-50161 Kaunas, Lithuania
| | - Ilona Kulakienė
- Department of Radiology of Lithuanian, University of Health Sciences, Eivenių g. 2, LT-50161 Kaunas, Lithuania
| | - Benas Gabrielis Urbonavičius
- Department of Physics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, Studentu g. 50, LT-51368 Kaunas, Lithuania
| | - Erika Korobeinikova
- Oncology Institute of Lithuanian, University of Health Sciences, Eiveniu g. 2, LT-50161 Kaunas, Lithuania
| | - Viktoras Rudžianskas
- Oncology Institute of Lithuanian, University of Health Sciences, Eiveniu g. 2, LT-50161 Kaunas, Lithuania
| | - Paulius Algirdas Povilonis
- Medical Academy of Lithuania, University of Health Sciences, A. Mickeviciaus g. 9, LT-44307 Kaunas, Lithuania
| | - Evelina Jaselskė
- Department of Physics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, Studentu g. 50, LT-51368 Kaunas, Lithuania
| | - Diana Adlienė
- Department of Physics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, Studentu g. 50, LT-51368 Kaunas, Lithuania
| | - Elona Juozaitytė
- Oncology Institute of Lithuanian, University of Health Sciences, Eiveniu g. 2, LT-50161 Kaunas, Lithuania
| |
Collapse
|
7
|
Abler D, Courlet P, Dietz M, Gatta R, Girard P, Munafo A, Wicky A, Jreige M, Guidi M, Latifyan S, De Micheli R, Csajka C, Prior JO, Michielin O, Terranova N, Cuendet MA. Semiautomated Pipeline to Quantify Tumor Evolution From Real-World Positron Emission Tomography/Computed Tomography Imaging. JCO Clin Cancer Inform 2023; 7:e2200126. [PMID: 37146261 PMCID: PMC10281365 DOI: 10.1200/cci.22.00126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Revised: 11/04/2022] [Accepted: 02/03/2023] [Indexed: 05/07/2023] Open
Abstract
PURPOSE A semiautomated pipeline for the collection and curation of free-text and imaging real-world data (RWD) was developed to quantify cancer treatment outcomes in large-scale retrospective real-world studies. The objectives of this article are to illustrate the challenges of RWD extraction, to demonstrate approaches for quality assurance, and to showcase the potential of RWD for precision oncology. METHODS We collected data from patients with advanced melanoma receiving immune checkpoint inhibitors at the Lausanne University Hospital. Cohort selection relied on semantically annotated electronic health records and was validated using process mining. The selected imaging examinations were segmented using an automatic commercial software prototype. A postprocessing algorithm enabled longitudinal lesion identification across imaging time points and consensus malignancy status prediction. Resulting data quality was evaluated against expert-annotated ground-truth and clinical outcomes obtained from radiology reports. RESULTS The cohort included 108 patients with melanoma and 465 imaging examinations (median, 3; range, 1-15 per patient). Process mining was used to assess clinical data quality and revealed the diversity of care pathways encountered in a real-world setting. Longitudinal postprocessing greatly improved the consistency of image-derived data compared with single time point segmentation results (classification precision increased from 53% to 86%). Image-derived progression-free survival resulting from postprocessing was comparable with the manually curated clinical reference (median survival of 286 v 336 days, P = .89). CONCLUSION We presented a general pipeline for the collection and curation of text- and image-based RWD, together with specific strategies to improve reliability. We showed that the resulting disease progression measures match reference clinical assessments at the cohort level, indicating that this strategy has the potential to unlock large amounts of actionable retrospective real-world evidence from clinical records.
Collapse
Affiliation(s)
- Daniel Abler
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Institute of Informatics, School of Management, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland
| | - Perrine Courlet
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Centre for Research and Innovation in Clinical Pharmaceutical Sciences, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Matthieu Dietz
- Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- INSERM U1060, CarMeN Laboratory, University of Lyon, Lyon, France
| | - Roberto Gatta
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Pascal Girard
- Translational Medicine, Merck Institute of Pharmacometrics, Lausanne, Switzerland, an Affiliate of Merck KGaA, Darmstadt, Germany
| | - Alain Munafo
- Translational Medicine, Merck Institute of Pharmacometrics, Lausanne, Switzerland, an Affiliate of Merck KGaA, Darmstadt, Germany
| | - Alexandre Wicky
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Mario Jreige
- Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Monia Guidi
- Centre for Research and Innovation in Clinical Pharmaceutical Sciences, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Service of Clinical Pharmacology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Sofiya Latifyan
- Service of Medical Oncology, Department of Oncology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Rita De Micheli
- Service of Medical Oncology, Department of Oncology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Chantal Csajka
- Centre for Research and Innovation in Clinical Pharmaceutical Sciences, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Institute of Pharmaceutical Sciences of Western Switzerland, University of Geneva, University of Lausanne, Geneva, Switzerland
- School of Pharmaceutical Sciences, University of Geneva, Geneva, Switzerland
| | - John O. Prior
- Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Olivier Michielin
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Nadia Terranova
- Translational Medicine, Merck Institute of Pharmacometrics, Lausanne, Switzerland, an Affiliate of Merck KGaA, Darmstadt, Germany
| | - Michel A. Cuendet
- Department of Oncology, Precision Oncology Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Swiss Institute of Bioinformatics, University of Lausanne, Lausanne, Switzerland
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY
| |
Collapse
|
8
|
Karimdjee M, Delaby G, Huglo D, Baillet C, Willaume A, Dujardin S, Bailliez A. Evaluation of a convolution neural network for baseline total tumor metabolic volume on [ 18F]FDG PET in diffuse large B cell lymphoma. Eur Radiol 2023; 33:3386-3395. [PMID: 36600126 DOI: 10.1007/s00330-022-09375-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2022] [Revised: 10/20/2022] [Accepted: 12/09/2022] [Indexed: 01/06/2023]
Abstract
OBJECTIVES New PET data-processing tools allow for automatic lesion selection and segmentation by a convolution neural network using artificial intelligence (AI) to obtain total metabolic tumor volume (TMTV) and total lesion glycolysis (TLG) routinely at the clinical workstation. Our objective was to evaluate an AI implemented in a new version of commercial software to verify reproducibility of results and time savings in a daily workflow. METHODS Using the software to obtain TMTV and TLG, two nuclear physicians applied five methods to retrospectively analyze data for 51 patients. Methods 1 and 2 were fully automated with exclusion of lesions ≤ 0.5 mL and ≤ 0.1 mL, respectively. Methods 3 and 4 were fully automated with physician review. Method 5 was semi-automated and used as reference. Time and number of clicks to complete the measurement were recorded for each method. Inter-instrument and inter-observer variation was assessed by the intra-class coefficient (ICC) and Bland-Altman plots. RESULTS Between methods 3 and 5, for the main user, the ICC was 0.99 for TMTV and 1.0 for TLG. Between the two users applying method 3, ICC was 0.97 for TMTV and 0.99 for TLG. Mean processing time (± standard deviation) was 20 s ± 9.0 for method 1, 178 s ± 125.7 for method 3, and 326 s ± 188.6 for method 5 (p < 0.05). CONCLUSION AI-enabled lesion detection software offers an automated, fast, reliable, and consistently performing tool for obtaining TMTV and TLG in a daily workflow. KEY POINTS • Our study shows that artificial intelligence lesion detection software is an automated, fast, reliable, and consistently performing tool for obtaining total metabolic tumor volume and total lesion glycolysis in a daily workflow.
Collapse
Affiliation(s)
- Mourtaza Karimdjee
- Nuclear Medicine Department, CHU Lille University Hospital, Lille, France.
| | - Gauthier Delaby
- Nuclear Medicine Department, CHU Lille University Hospital, Lille, France
| | - Damien Huglo
- Nuclear Medicine Department, CHU Lille University Hospital, Lille, France
| | - Clio Baillet
- Nuclear Medicine Department, CHU Lille University Hospital, Lille, France
| | - Alexandre Willaume
- Hematology Department, Group of Hospitals of the Catholic Institute of Lille, Lille, France
| | - Simon Dujardin
- Nuclear Medicine Department, CHU Lille University Hospital, Lille, France
| | - Alban Bailliez
- Nuclear Medicine Department, Group of Hospitals of the Catholic Institute of Lille, Lille, France
| |
Collapse
|
9
|
Carreras J, Roncador G, Hamoudi R. Artificial Intelligence Predicted Overall Survival and Classified Mature B-Cell Neoplasms Based on Immuno-Oncology and Immune Checkpoint Panels. Cancers (Basel) 2022; 14:5318. [PMID: 36358737 PMCID: PMC9657332 DOI: 10.3390/cancers14215318] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Revised: 10/20/2022] [Accepted: 10/24/2022] [Indexed: 08/01/2023] Open
Abstract
Artificial intelligence (AI) can identify actionable oncology biomarkers. This research integrates our previous analyses of non-Hodgkin lymphoma. We used gene expression and immunohistochemical data, focusing on the immune checkpoint, and added a new analysis of macrophages, including 3D rendering. The AI comprised machine learning (C5, Bayesian network, C&R, CHAID, discriminant analysis, KNN, logistic regression, LSVM, Quest, random forest, random trees, SVM, tree-AS, and XGBoost linear and tree) and artificial neural networks (multilayer perceptron and radial basis function). The series included chronic lymphocytic leukemia, mantle cell lymphoma, follicular lymphoma, Burkitt, diffuse large B-cell lymphoma, marginal zone lymphoma, and multiple myeloma, as well as acute myeloid leukemia and pan-cancer series. AI classified lymphoma subtypes and predicted overall survival accurately. Oncogenes and tumor suppressor genes were highlighted (MYC, BCL2, and TP53), along with immune microenvironment markers of tumor-associated macrophages (M2-like TAMs), T-cells and regulatory T lymphocytes (Tregs) (CD68, CD163, MARCO, CSF1R, CSF1, PD-L1/CD274, SIRPA, CD85A/LILRB3, CD47, IL10, TNFRSF14/HVEM, TNFAIP8, IKAROS, STAT3, NFKB, MAPK, PD-1/PDCD1, BTLA, and FOXP3), apoptosis (BCL2, CASP3, CASP8, PARP, and pathway-related MDM2, E2F1, CDK6, MYB, and LMO2), and metabolism (ENO3, GGA3). In conclusion, AI with immuno-oncology markers is a powerful predictive tool. Additionally, a review of recent literature was made.
Collapse
Affiliation(s)
- Joaquim Carreras
- Department of Pathology, School of Medicine, Tokai University, 143 Shimokasuya, Isehara 259-1193, Kanagawa, Japan
| | - Giovanna Roncador
- Monoclonal Antibodies Unit, Spanish National Cancer Research Center (Centro Nacional de Investigaciones Oncologicas, CNIO), Melchor Fernandez Almagro 3, 28029 Madrid, Spain
| | - Rifat Hamoudi
- Department of Clinical Sciences, College of Medicine, University of Sharjah, Sharjah P.O. Box 27272, United Arab Emirates
- Division of Surgery and Interventional Science, University College London, Gower Street, London WC1E 6BT, UK
| |
Collapse
|
10
|
Hustinx R, Pruim J, Lassmann M, Visvikis D. An EANM position paper on the application of artificial intelligence in nuclear medicine. Eur J Nucl Med Mol Imaging 2022; 50:61-66. [PMID: 36006443 DOI: 10.1007/s00259-022-05947-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2022] [Accepted: 08/16/2022] [Indexed: 11/04/2022]
Abstract
Artificial intelligence (AI) is coming into the field of nuclear medicine, and it is likely here to stay. As a society, EANM can and must play a central role in the use of AI in nuclear medicine. In this position paper, the EANM explains the preconditions for the implementation of AI in NM and takes position.
Collapse
Affiliation(s)
- Roland Hustinx
- Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège & GIGA-CRC in vivo Imaging, University of Liège, Liège, Belgium
| | - Jan Pruim
- Medical Imaging Center, Dept. of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| | - Michael Lassmann
- Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany
| | | |
Collapse
|
11
|
Visvikis D, Lambin P, Beuschau Mauridsen K, Hustinx R, Lassmann M, Rischpler C, Shi K, Pruim J. Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation. Eur J Nucl Med Mol Imaging 2022; 49:4452-4463. [PMID: 35809090 PMCID: PMC9606092 DOI: 10.1007/s00259-022-05891-w] [Citation(s) in RCA: 22] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2022] [Accepted: 06/25/2022] [Indexed: 02/06/2023]
Abstract
Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.
Collapse
Affiliation(s)
| | - Philippe Lambin
- The D-Lab, Department of Precision Medicine, GROW - School for Oncology, Maastricht University Medical Center (MUMC +), Maastricht, The Netherlands.,Department of Radiology and Nuclear Medicine, GROW - School for Oncology, Maastricht University Medical Center (MUMC +), Maastricht, The Netherlands
| | - Kim Beuschau Mauridsen
- Center of Functionally Integrative Neuroscience and MindLab, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark.,Department of Nuclear Medicine, University of Bern, Bern, Switzerland
| | - Roland Hustinx
- GIGA-CRC in Vivo Imaging, University of Liège, GIGA, Avenue de l'Hôpital 11, 4000, Liege, Belgium
| | - Michael Lassmann
- Klinik Und Poliklinik Für Nuklearmedizin, Universitätsklinikum Würzburg, Würzburg, Germany
| | - Christoph Rischpler
- Department of Nuclear Medicine, University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - Kuangyu Shi
- Department of Nuclear Medicine, University of Bern, Bern, Switzerland.,Department of Informatics, Technical University of Munich, Munich, Germany
| | - Jan Pruim
- Medical Imaging Center, Dept. of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
| |
Collapse
|
12
|
Borrelli P, Góngora JLL, Kaboteh R, Enqvist O, Edenbrandt L. Automated Classification of PET‐CT Lesions in Lung Cancer: An Independent Validation Study. Clin Physiol Funct Imaging 2022; 42:327-332. [PMID: 35760559 PMCID: PMC9540653 DOI: 10.1111/cpf.12773] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Revised: 06/15/2022] [Accepted: 06/22/2022] [Indexed: 12/04/2022]
Abstract
Introduction Recently, a tool called the positron emission tomography (PET)‐assisted reporting system (PARS) was developed and presented to classify lesions in PET/computed tomography (CT) studies in patients with lung cancer or lymphoma. The aim of this study was to validate PARS with an independent group of lung‐cancer patients using manual lesion segmentations as a reference standard, as well as to evaluate the association between PARS‐based measurements and overall survival (OS). Methods This study retrospectively included 115 patients who had undergone clinically indicated (18F)‐fluorodeoxyglucose (FDG) PET/CT due to suspected or known lung cancer. The patients had a median age of 66 years (interquartile range [IQR]: 61–72 years). Segmentations were made manually by visual inspection in a consensus reading by two nuclear medicine specialists and used as a reference. The research prototype PARS was used to automatically analyse all the PET/CT studies. The PET foci classified as suspicious by PARS were compared with the manual segmentations. No manual corrections were applied. Total lesion glycolysis (TLG) was calculated based on the manual and PARS‐based lung‐tumour segmentations. Associations between TLG and OS were investigated using Cox analysis. Results PARS showed sensitivities for lung tumours of 55.6% per lesion and 80.2% per patient. Both manual and PARS TLG were significantly associated with OS. Conclusion Automatically calculated TLG by PARS contains prognostic information comparable to manually measured TLG in patients with known or suspected lung cancer. The low sensitivity at both the lesion and patient levels makes the present version of PARS less useful to support clinical reading, reporting and staging.
Collapse
Affiliation(s)
- Pablo Borrelli
- Region Västra Götaland, Sahlgrenska University HospitalDepartment of Clinical PhysiologyGothenburgSweden
| | - José Luis Loaiza Góngora
- Region Västra Götaland, Sahlgrenska University HospitalDepartment of Clinical PhysiologyGothenburgSweden
| | - Reza Kaboteh
- Region Västra Götaland, Sahlgrenska University HospitalDepartment of Clinical PhysiologyGothenburgSweden
| | | | - Lars Edenbrandt
- Region Västra Götaland, Sahlgrenska University HospitalDepartment of Clinical PhysiologyGothenburgSweden
- Department of Molecular and Clinical Medicine, Institute of MedicineSahlgrenska Academy, University of GothenburgGothenburgSweden
| |
Collapse
|
13
|
Georgi TW, Zieschank A, Kornrumpf K, Kurch L, Sabri O, Körholz D, Mauz-körholz C, Kluge R, Posch S. Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake. PLoS One 2022; 17:e0267275. [PMID: 35436321 PMCID: PMC9015138 DOI: 10.1371/journal.pone.0267275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2022] [Accepted: 04/05/2022] [Indexed: 11/27/2022] Open
Abstract
Introduction The automatic classification of lymphoma lesions in PET is a main topic of ongoing research. An automatic algorithm would enable the swift evaluation of PET parameters, like texture and heterogeneity markers, concerning their prognostic value for patients outcome in large datasets. Moreover, the determination of the metabolic tumor volume would be facilitated. The aim of our study was the development and evaluation of an automatic algorithm for segmentation and classification of lymphoma lesions in PET. Methods Pre-treatment PET scans from 60 Hodgkin lymphoma patients from the EuroNet-PHL-C1 trial were evaluated. A watershed algorithm was used for segmentation. For standardization of the scan length, an automatic cropping algorithm was developed. All segmented volumes were manually classified into one of 14 categories. The random forest method and a nested cross-validation was used for automatic classification and evaluation. Results Overall, 853 volumes were segmented and classified. 203/246 tumor lesions and 554/607 non-tumor volumes were classified correctly by the automatic algorithm, corresponding to a sensitivity, a specificity, a positive and a negative predictive value of 83%, 91%, 79% and 93%. In 44/60 (73%) patients, all tumor lesions were correctly classified. In ten out of the 16 patients with misclassified tumor lesions, only one false-negative tumor lesion occurred. The automatic classification of focal gastrointestinal uptake, brown fat tissue and composed volumes consisting of more than one tissue was challenging. Conclusion Our algorithm, trained on a small number of patients and on PET information only, showed a good performance and is suitable for automatic lymphoma classification.
Collapse
|
14
|
Hasani N, Paravastu SS, Farhadi F, Yousefirizi F, Morris MA, Rahmim A, Roschewski M, Summers RM, Saboury B. Artificial Intelligence in Lymphoma PET Imaging:: A Scoping Review (Current Trends and Future Directions). PET Clin 2022; 17:145-174. [PMID: 34809864 PMCID: PMC8735853 DOI: 10.1016/j.cpet.2021.09.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Malignant lymphomas are a family of heterogenous disorders caused by clonal proliferation of lymphocytes. 18F-FDG-PET has proven to provide essential information for accurate quantification of disease burden, treatment response evaluation, and prognostication. However, manual delineation of hypermetabolic lesions is often a time-consuming and impractical task. Applications of artificial intelligence (AI) may provide solutions to overcome this challenge. Beyond segmentation and detection of lesions, AI could enhance tumor characterization and heterogeneity quantification, as well as treatment response prediction and recurrence risk stratification. In this scoping review, we have systematically mapped and discussed the current applications of AI (such as detection, classification, segmentation as well as the prediction and prognostication) in lymphoma PET.
Collapse
Affiliation(s)
- Navid Hasani
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; University of Queensland Faculty of Medicine, Ochsner Clinical School, New Orleans, LA 70121, USA
| | - Sriram S Paravastu
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA
| | - Faraz Farhadi
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA
| | - Fereshteh Yousefirizi
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
| | - Michael A Morris
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland-Baltimore Country, Baltimore, MD, USA
| | - Arman Rahmim
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada; Department of Radiology, BC Cancer Research Institute, University of British Columbia, 675 West 10th Avenue, Vancouver, British Columbia, V5Z 1L3, Canada
| | - Mark Roschewski
- Lymphoid Malignancies Branch, Center for Cancer Research, National Institutes of Health, Bethesda, MD, USA
| | - Ronald M Summers
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA.
| | - Babak Saboury
- Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, 9000 Rockville Pike, Building 10, Room 1C455, Bethesda, MD 20892, USA; Department of Computer Science and Electrical Engineering, University of Maryland-Baltimore Country, Baltimore, MD, USA; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
| |
Collapse
|
15
|
Decuyper M, Maebe J, Van Holen R, Vandenberghe S. Artificial intelligence with deep learning in nuclear medicine and radiology. EJNMMI Phys 2021; 8:81. [PMID: 34897550 PMCID: PMC8665861 DOI: 10.1186/s40658-021-00426-y] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2021] [Accepted: 11/19/2021] [Indexed: 12/19/2022] Open
Abstract
The use of deep learning in medical imaging has increased rapidly over the past few years, finding applications throughout the entire radiology pipeline, from improved scanner performance to automatic disease detection and diagnosis. These advancements have resulted in a wide variety of deep learning approaches being developed, solving unique challenges for various imaging modalities. This paper provides a review on these developments from a technical point of view, categorizing the different methodologies and summarizing their implementation. We provide an introduction to the design of neural networks and their training procedure, after which we take an extended look at their uses in medical imaging. We cover the different sections of the radiology pipeline, highlighting some influential works and discussing the merits and limitations of deep learning approaches compared to other traditional methods. As such, this review is intended to provide a broad yet concise overview for the interested reader, facilitating adoption and interdisciplinary research of deep learning in the field of medical imaging.
Collapse
Affiliation(s)
- Milan Decuyper
- Department of Electronics and Information Systems, Ghent University, Ghent, Belgium
| | - Jens Maebe
- Department of Electronics and Information Systems, Ghent University, Ghent, Belgium
| | - Roel Van Holen
- Department of Electronics and Information Systems, Ghent University, Ghent, Belgium
| | - Stefaan Vandenberghe
- Department of Electronics and Information Systems, Ghent University, Ghent, Belgium
| |
Collapse
|
16
|
Pinochet P, Texte E, Stamatoullas-Bastard A, Vera P, Mihailescu SD, Becker S. Prognostic value of baseline metabolic tumour volume in advanced-stage Hodgkin's lymphoma. Sci Rep 2021; 11:23195. [PMID: 34853386 DOI: 10.1038/s41598-021-02734-w] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2021] [Accepted: 11/17/2021] [Indexed: 12/22/2022] Open
Abstract
Our aim was to evaluate the prognostic value of initial total metabolic tumour volume (TMTV) in a population of patients with advanced-stage Hodgkin's lymphoma (HL). We retrospectively included 179 patients with stage IIb-III-IV Hodgkin's disease who received BEACOPP or ABVD as the first-line treatment. The initial TMTV was determined using a semi-automatic method for each patient. We analysed its prognostic value in terms of 5-year progression-free survival (PFS), overall survival, and positron emission tomography (PET) response after two courses of chemotherapy. Considering all the treatments and using a threshold of 217 cm3, TMTV was predictive of 5-year PFS and PET response after two courses of chemotherapy. In multivariable analysis involving TMTV, IPI score, and the first treatment received, TMTV remained a baseline prognostic factor for 5-year PFS. In the subgroup of patients treated with BEACOPP with a threshold of 331 cm3, TMTV was predictive of PET response, but not 5-year PFS (p = 0.087). The combined analysis of TMTV and PET response enabled the individualisation of a subgroup of patients (low TMTV and complete response on PET) with a very low risk of recurrence. Baseline TMTV appears to be a useful independent prognostic factor for predicting relapse in advanced-stage HL in ABVD subgroup, with a tendency of survival curves separation in BEACOPP subgroup.
Collapse
|
17
|
Duclos V, Iep A, Gomez L, Goldfarb L, Besson FL. PET Molecular Imaging: A Holistic Review of Current Practice and Emerging Perspectives for Diagnosis, Therapeutic Evaluation and Prognosis in Clinical Oncology. Int J Mol Sci 2021; 22:4159. [PMID: 33923839 PMCID: PMC8073681 DOI: 10.3390/ijms22084159] [Citation(s) in RCA: 30] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2021] [Revised: 04/14/2021] [Accepted: 04/15/2021] [Indexed: 02/06/2023] Open
Abstract
PET/CT molecular imaging has been imposed in clinical oncological practice over the past 20 years, driven by its two well-grounded foundations: quantification and radiolabeled molecular probe vectorization. From basic visual interpretation to more sophisticated full kinetic modeling, PET technology provides a unique opportunity to characterize various biological processes with different levels of analysis. In clinical practice, many efforts have been made during the last two decades to standardize image analyses at the international level, but advanced metrics are still under use in practice. In parallel, the integration of PET imaging with radionuclide therapy, also known as radiolabeled theranostics, has paved the way towards highly sensitive radionuclide-based precision medicine, with major breakthroughs emerging in neuroendocrine tumors and prostate cancer. PET imaging of tumor immunity and beyond is also emerging, emphasizing the unique capabilities of PET molecular imaging to constantly adapt to emerging oncological challenges. However, these new horizons face the growing complexity of multidimensional data. In the era of precision medicine, statistical and computer sciences are currently revolutionizing image-based decision making, paving the way for more holistic cancer molecular imaging analyses at the whole-body level.
Collapse
Affiliation(s)
- Valentin Duclos
- Department of Biophysics and Nuclear Medicine-Molecular Imaging, Hôpitaux Universitaires Paris Saclay, Assistance Publique-Hôpitaux de Paris, CHU Bicêtre, 94270 Le Kremlin-Bicêtre, France; (V.D.); (A.I.); (L.G.)
| | - Alex Iep
- Department of Biophysics and Nuclear Medicine-Molecular Imaging, Hôpitaux Universitaires Paris Saclay, Assistance Publique-Hôpitaux de Paris, CHU Bicêtre, 94270 Le Kremlin-Bicêtre, France; (V.D.); (A.I.); (L.G.)
| | - Léa Gomez
- Department of Biophysics and Nuclear Medicine-Molecular Imaging, Hôpitaux Universitaires Paris Saclay, Assistance Publique-Hôpitaux de Paris, CHU Bicêtre, 94270 Le Kremlin-Bicêtre, France; (V.D.); (A.I.); (L.G.)
| | - Lucas Goldfarb
- Service Hospitalier Frédéric Joliot-CEA, 91401 Orsay, France;
| | - Florent L. Besson
- Department of Biophysics and Nuclear Medicine-Molecular Imaging, Hôpitaux Universitaires Paris Saclay, Assistance Publique-Hôpitaux de Paris, CHU Bicêtre, 94270 Le Kremlin-Bicêtre, France; (V.D.); (A.I.); (L.G.)
- Université Paris Saclay, CEA, CNRS, Inserm, BioMaps, 91401 Orsay, France
- School of Medicine, Université Paris Saclay, 94720 Le Kremlin-Bicêtre, France
| |
Collapse
|