- 1
- 2
Publications de l’unité
Année de publication : 2020
Deep learning FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma.
Journal of nuclear medicine : official publication, Society of Nuclear Medicine : DOI : jnumed.120.242412 En savoir plusRésumé
Total metabolic tumor volume (TMTV), calculated from F-labeled fluoro-2-deoxyglucose (F-FDG) positron-emission tomography-computed tomography (PET/CT) baseline studies, is a prognostic factor in diffuse large B-cell lymphoma (DLBCL) whose measurement requires the segmentation of all malignant foci throughout the body. No consensus currently exists regarding the most accurate approach for such segmentation. Further, all methods still require extensive manual input from an experienced reader. We examined whether an artificial intelligence (AI)-based method could estimate TMTV with a comparable prognostic value to TMTV measured by experts. Baseline F-FDG PET/CT scans of 301 DLBCL patients from the REMARC trial (NCT01122472) were retrospectively analyzed. An automated whole-body high-uptake segmentation algorithm identified all three-dimensional regions of interest (ROI) with increased tracer uptake. The resulting ROIs were processed using a convolutional neural network trained on an independent cohort and classified as nonsuspicious or suspicious uptake. The AI-based TMTV was estimated as the sum of the volumes of ROIs classified as suspicious uptake. The reference TMTV was measured by two experienced readers using independent semiautomatic software. The AI-based TMTV was compared to the reference TMTV in terms of prognostic value for progression-free survival (PFS) and overall survival (OS). The AI-based TMTV was significantly correlated with the reference TMTV (ρ=0.76; p<0.001). Using the AI-based approach, an average of 24 regions per subject with increased tracer uptake were identified, and an average of 20 regions per subject were correctly identified as nonsuspicious or suspicious, yielding 85% classification accuracy, 80% sensitivity, 88% specificity, compared to the reference TMTV region. Both TMTV results were predictive of PFS (hazard ratio: 2.4 and 2.6 for AI-based and reference TMTVs, respectively; p<0.001) and OS (hazard ratio: 2.8 and 3.7 for AI-based and reference TMTVs, respectively; p<0.001). TMTV estimated fully automatically using an AI-based approach was consistent with that obtained by experts and displayed a significant prognostic value for PFS and OS in DLBCL patients. Classification of high uptake regions using deep learning for rapidly discarding physiological uptake may considerably simplify TMTV estimation, reduce observer variability and facilitate the use of TMTV as a predictive factor in DLBCL patients.
ReplierLongitudinal mouse-PET imaging: a reliable method for estimating binding parameters without a reference region or blood sampling.
European journal of nuclear medicine and molecular imaging : DOI : 10.1007/s00259-020-04755-5 En savoir plusRésumé
Longitudinal mouse PET imaging is becoming increasingly popular due to the large number of transgenic and disease models available but faces challenges. These challenges are related to the small size of the mouse brain and the limited spatial resolution of microPET scanners, along with the small blood volume making arterial blood sampling challenging and impossible for longitudinal studies. The ability to extract an input function directly from the image would be useful for quantification in longitudinal small animal studies where there is no true reference region available such as TSPO imaging.
ReplierThe Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.
Radiology : 328-338 : DOI : 10.1148/radiol.2020191145 En savoir plusRésumé
Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 See also the editorial by Kuhl and Truhn in this issue.
ReplierAnnée de publication : 2019
A downsampling strategy to assess the predictive value of radiomic features.
Scientific reports : 17869 : DOI : 10.1038/s41598-019-54190-2 En savoir plusRésumé
Many studies are devoted to the design of radiomic models for a prediction task. When no effective model is found, it is often difficult to know whether the radiomic features do not include information relevant to the task or because of insufficient data. We propose a downsampling method to answer that question when considering a classification task into two groups. Using two large patient cohorts, several experimental configurations involving different numbers of patients were created. Univariate or multivariate radiomic models were designed from each configuration. Their performance as reflected by the Youden index (YI) and Area Under the receiver operating characteristic Curve (AUC) was compared to the stable performance obtained with the highest number of patients. A downsampling method is described to predict the YI and AUC achievable with a large number of patients. Using the multivariate models involving machine learning, YI and AUC increased with the number of patients while they decreased for univariate models. The downsampling method better estimated YI and AUC obtained with the largest number of patients than the YI and AUC obtained using the number of available patients and identifies the lack of information relevant to the classification task when no such information exists.
ReplierPharmacokinetic Analysis of [18F]FAZA Dynamic PET Imaging Acquisitions for Highlighting Sacrum Tumor Profiles.
Clinical nuclear medicine : e36-e38 : DOI : 10.1097/RLU.0000000000002813 En savoir plusRésumé
A patient enrolled in a clinical trial (NCT02802969) with suspicion of chordoma underwent an [F]FAZA PET/CT, a radiolabeled nitroimidazole analog of hypoxia PET imaging. The patient’s images showed a different tumor profile compared to those observed in other hypoxic or nonhypoxic chordoma patients. The motivation for using [F]FAZA pharmacokinetic imaging was to compare this profile with histologically confirmed cases of chordoma. Through visual imaging and quantification of blood and tumor time-activity curves, we excluded the hypothesis that it was a chordoma, diagnosing a paraganglioma.
ReplierThe Dark Side of Radiomics: On the Paramount Importance of Publishing Negative Results.
Journal of nuclear medicine : official publication, Society of Nuclear Medicine : 1543-1544 : DOI : 10.2967/jnumed.119.235325 En savoir plusRésumé
ReplierPET/MRI in large-vessel vasculitis: clinical value for diagnosis and assessment of disease activity.
Scientific reports : 12388 : DOI : 10.1038/s41598-019-48709-w En savoir plusRésumé
Diagnosis of large vessel vasculitis (LVV) and evaluation of its inflammatory activity can be challenging. Our aim was to investigate the value of hybrid positron-emission tomography/magnetic resonance imaging (PET/MRI) in LVV. All consecutive patients with LVV from the Department of Internal Medicine who underwent PET/MRI were included. Three PET/MRI patterns were defined: (i) « inflammatory, » with positive PET (>liver uptake) and abnormal MRI (stenosis and/or wall thickening); (ii) « fibrous », negative PET (≤liver uptake) and abnormal MRI; and (iii) « normal ». Thirteen patients (10 female; median age: 67-years [range: 23-87]) underwent 18 PET/MRI scans. PET/MRI was performed at diagnosis (n = 4), at relapse (n = 7), or during remission (n = 7). Among the 18 scans, eight (44%) showed an inflammatory pattern and three (17%) a fibrous pattern; the other seven were normal. The distribution of the three patterns did not differ between patients with Takayasu arteritis (TA, n = 10 scans) and those with giant cell arteritis (GCA, n = 8 scans). PET/MRI findings were normal in 2/10 (20%) TA scans vs. 5/8 (62%) GCA scans (p = 0.3). Median SUV was 4.7 [2.1-8.6] vs. 2 [1.8-2.6] in patients with active disease vs. remission, respectively (p = 0.003). PET/MRI is a new hybrid imaging modality allowing comprehensive and multimodal analysis of vascular wall inflammation and the vascular lumen. This technique offers promising perspectives for the diagnosis and monitoring of LVV.
ReplierEJNMMI supplement: bringing AI and radiomics to nuclear medicine.
European journal of nuclear medicine and molecular imaging : 2627-2629 : DOI : 10.1007/s00259-019-04395-4 En savoir plusRésumé
ReplierF-FDG PET Dissemination Features in Diffuse Large B-Cell Lymphoma Are Predictive of Outcome.
Journal of nuclear medicine : official publication, Society of Nuclear Medicine : 40-45 : DOI : 10.2967/jnumed.119.229450 En savoir plusRésumé
We assessed the predictive value of new radiomic features characterizing lesion dissemination in baseline F-FDG PET and tested whether combining them with baseline metabolic tumor volume (MTV) could improve prediction of progression-free survival (PFS) and overall survival (OS) in diffuse large B-cell lymphoma (DLBCL) patients. From the LNH073B trial (NCT00498043), patients with advanced-stage DLCBL and F-FDG PET/CT images available for review were selected. MTV and several radiomic features, including the distance between the 2 lesions that were farthest apart (Dmax), were calculated. Receiver-operating-characteristic analysis was used to determine the optimal cutoff for quantitative variables, and Kaplan-Meier survival analyses were performed. With a median age of 46 y, 95 patients were enrolled, half of them treated with R-CHOP biweekly (rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone) and the other half with R-ACVBP (rituximab, doxorubicin, cyclophosphamide, vindesine, bleomycin, and prednisone), with no significant impact on outcome. Median MTV and Dmax were 375 cm and 45 cm, respectively. The median follow-up was 44 mo. High MTV and Dmax were adverse factors for PFS ( = 0.027 and = 0.0003, respectively) and for OS ( = 0.0007 and = 0.0095, respectively). In multivariate analysis, only Dmax was significantly associated with PFS ( = 0.0014) whereas both factors remained significant for OS ( = 0.037 and = 0.0029, respectively). Combining MTV (>384 cm) and Dmax (>58 cm) yielded 3 risk groups for PFS ( = 0.0003) and OS ( = 0.0011): high with 2 adverse factors (4-y PFS and OS of 50% and 53%, respectively, = 18), low with no adverse factor (94% and 97%, = 36), and an intermediate category with 1 adverse factor (73% and 88%, = 41). Combining MTV with a parameter reflecting the tumor burden dissemination further improves DLBCL patient risk stratification at staging.
ReplierCorrigendum to « Evaluation of TSPO PET imaging, a marker of glial activation, to study the neuroimmune footprints of morphine exposure and withdrawal » [Drug Alcohol Depend. 170 (2017) 43-50].
Drug and alcohol dependence : 266-268 : DOI : S0376-8716(19)30162-0 En savoir plusRésumé
ReplierValidation of A Method to Compensate Multicenter Effects Affecting CT Radiomics.
Radiology : 53-59 : DOI : 10.1148/radiol.2019182023 En savoir plusRésumé
Background Radiomics extracts features from medical images more precisely and more accurately than visual assessment. However, radiomics features are affected by CT scanner parameters such as reconstruction kernel or section thickness, thus obscuring underlying biologically important texture features. Purpose To investigate whether a compensation method could correct for the variations of radiomic feature values caused by using different CT protocols. Materials and Methods Phantom data involving 10 texture patterns and 74 patients in cohorts 1 (19 men; 42 patients; mean age, 60.4 years; September-October 2013) and 2 (16 men; 32 patients; mean age, 62.1 years; January-September 2007) scanned by using different CT protocols were retrospectively included. For any radiomic feature, the compensation approach identified a protocol-specific transformation to express all data in a common space that were devoid of protocol effects. The differences in statistical distributions between protocols were assessed by using Friedman tests before and after compensation. Principal component analyses were performed on the phantom data to evaluate the ability to distinguish between texture patterns after compensation. Results In the phantom data, the statistical distributions of features were different between protocols for all radiomic features and texture patterns (P < .05). After compensation, the protocol effect was no longer detectable (P > .05). Principal component analysis demonstrated that each texture pattern was no longer displayed as different clusters corresponding to different imaging protocols, unlike what was observed before compensation. The correction for scanner effect was confirmed in patient data with 100% (10 of 10 features for cohort 1) and 98% (87 of 89 features for cohort 2) of P values less than .05 before compensation, compared with 30% (three of 10) and 15% (13 of 89) after compensation. Conclusion Image compensation successfully realigned feature distributions computed from different CT imaging protocols and should facilitate multicenter radiomic studies. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Steiger and Sood in this issue.
ReplierAnnée de publication : 2018
Physical blood-brain barrier disruption induced by focused ultrasound does not overcome the transporter-mediated efflux of erlotinib.
Journal of controlled release : official journal of the Controlled Release Society : 210-220 : DOI : S0168-3659(18)30646-1 En savoir plusRésumé
Overcoming the efflux mediated by ATP-binding cassette (ABC) transporters at the blood-brain barrier (BBB) remains a challenge for the delivery of small molecule tyrosine kinase inhibitors (TKIs) such as erlotinib to the brain. Inhibition of ABCB1 and ABCG2 at the mouse BBB improved the BBB permeation of erlotinib but could not be achieved in humans. BBB disruption induced by focused ultrasound (FUS) was investigated as a strategy to overcome the efflux transport of erlotinib in vivo. In rats, FUS combined with microbubbles allowed for a large and spatially controlled disruption of the BBB in the left hemisphere. ABCB1/ABCG2 inhibition was performed using elacridar (10 mg/kg i.v). The brain kinetics of erlotinib was studied using C-erlotinib Positron Emission Tomography (PET) imaging in 5 groups (n = 4-5 rats per group) including a baseline group, immediately after sonication (FUS), 48 h after FUS (FUS + 48 h), elacridar (ELA) and their combination (FUS + ELA). BBB integrity was assessed using the Evan’s Blue (EB) extravasation test. Brain exposure to C-erlotinib was measured as the area under the curve (AUC) of the brain kinetics (% injected dose (%ID) versus time (min)) in volumes corresponding to the disrupted (left) and the intact (right) hemispheres, respectively. EB extravasation highlighted BBB disruption in the left hemisphere of animals of the FUS and FUS + ELA groups but not in the control and ELA groups. EB extravasation was not observed 48 h after FUS suggesting recovery of BBB integrity. Compared with the control group (AUC = 1.4 ± 0.5%ID.min), physical BBB disruption did not impact the brain kinetics of C-erlotinib in the left hemisphere (p > .05) either immediately (AUC = 1.2 ± 0.1%ID.min) or 48 h after FUS (AUC = 1.1 ± 0.3%ID.min). Elacridar similarly increased C-erlotinib brain exposure to the left hemisphere in the absence (AUC = 2.2 ± 0.5%ID.min, p < .001) and in the presence of BBB disruption (AUC = 2.1 ± 0.5%ID.min, p < .001). AUC was never significantly different from AUC (p > .05), in any of the tested conditions. BBB integrity is not the rate limiting step for erlotinib delivery to the brain which is mainly governed by ABC-mediated efflux. Efflux transport of erlotinib persisted despite BBB disruption.
ReplierInfluence of age on radiomic features in F-FDG PET in normal breast tissue and in breast cancer tumors.
Oncotarget : 30855-30868 : DOI : 10.18632/oncotarget.25762 En savoir plusRésumé
To help interpret measurements in breast tissue and breast tumors from F-FDG PET scans, we studied the influence of age in measurements of PET parameters in normal breast tissue and in a breast cancer (BC) population.
ReplierRadiomics in Nuclear Medicine Applied to Radiation Therapy: Methods, Pitfalls, and Challenges.
International journal of radiation oncology, biology, physics : 1117-1142 : DOI : S0360-3016(18)30815-0 En savoir plusRésumé
Radiomics is a recent area of research in precision medicine and is based on the extraction of a large variety of features from medical images. In the field of radiation oncology, comprehensive image analysis is crucial to personalization of treatments. A better characterization of local heterogeneity and the shape of the tumor, depicting individual cancer aggressiveness, could guide dose planning and suggest volumes in which a higher dose is needed for better tumor control. In addition, noninvasive imaging features that could predict treatment outcome from baseline scans could help the radiation oncologist to determine the best treatment strategies and to stratify patients as at low risk or high risk of recurrence. Nuclear medicine molecular imaging reflects information regarding biological processes in the tumor thanks to a wide range of radiotracers. Many studies involving F-fluorodeoxyglucose positron emission tomography suggest an added value of radiomics compared with the use of conventional PET metrics such as standardized uptake value for both tumor diagnosis and prediction of recurrence or treatment outcome. However, these promising results should not hide technical difficulties that still currently prevent the approach from being widely studied or clinically used. These difficulties mostly pertain to the variability of the imaging features as a function of the acquisition device and protocol, the robustness of the models with respect to that variability, and the interpretation of the radiomic models. Addressing the impact of the variability in acquisition and reconstruction protocols is needed, as is harmonizing the radiomic feature calculation methods, to ensure the reproducibility of studies in a multicenter context and their implementation in a clinical workflow. In this review, we explain the potential impact of positron emission tomography radiomics for radiation therapy and underline the various aspects that need to be carefully addressed to make the most of this promising approach.
ReplierLIFEx: A Freeware for Radiomic Feature Calculation in Multimodality Imaging to Accelerate Advances in the Characterization of Tumor Heterogeneity.
Cancer research : 4786-4789 : DOI : 10.1158/0008-5472.CAN-18-0125 En savoir plusRésumé
Textural and shape analysis is gaining considerable interest in medical imaging, particularly to identify parameters characterizing tumor heterogeneity and to feed radiomic models. Here, we present a free, multiplatform, and easy-to-use freeware called LIFEx, which enables the calculation of conventional, histogram-based, textural, and shape features from PET, SPECT, MR, CT, and US images, or from any combination of imaging modalities. The application does not require any programming skills and was developed for medical imaging professionals. The goal is that independent and multicenter evidence of the usefulness and limitations of radiomic features for characterization of tumor heterogeneity and subsequent patient management can be gathered. Many options are offered for interactive textural index calculation and for increasing the reproducibility among centers. The software already benefits from a large user community (more than 800 registered users), and interactions within that community are part of the development strategy. This study presents a user-friendly, multi-platform freeware to extract radiomic features from PET, SPECT, MR, CT, and US images, or any combination of imaging modalities. .
Replier- 1
- 2