CERMEP-IDB-MRXFDG: a database of 37 normal adult human brain [18F]FDG PET, T1 and FLAIR MRI, and CT images available for research

Mérida, Inès; Jung, Julien; Bouvard, Sandrine; Bars, Didier Le; Lancelot, Sophie; Lavenne, F.; Bouillot, Caroline; Redouté, Jérôme; Hammers, Alexander; Costes, Nicolas

doi:10.1186/s13550-021-00830-6

Cited by 29 publications

(26 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used an open, multi-vendor [General Electrics, Philips and Siemens 3T magnetic resonance imaging (MRI) scanners] brain MRI database, Calgary-Campinas ( 32 ), using 173 T1-weighted (T1w) 3D volumes (1 mm 3 voxels) from subjects with an average age of 53.4 ± 7.3 years (range 29–80, 50% women). Additionally, we used the publicly available database CERMEP-IDB-MRXFDG ( 33 ) which includes T1w MRI (Siemens 1.5T MRI) 3D volumes from 37 subjects (average age 38.11 ± 11.36 years; range 23–65, 54% women). It also includes 37 PET and computed tomography (CT) images from a Siemens Biograph mCT64, which we used to estimate a range of realistic FDG uptake values in brain PET as explained below.…”

Section: Methodsmentioning

confidence: 99%

“…We created GT-HQ [ 18 F]FDG PET by assigning activities to the nine labels of the numerical brain phantoms. Activities were derived from the distribution of normal [ 18 F]FDG PET values from the CERMEP-iDB-MRXFDG database ( 33 ) after partial volume correction according to the Geometric Transfer Matrix (GTM) method ( 21 ).…”

Section: Methodsmentioning

confidence: 99%

“…A total of 10 different brain activity distribution were generated for each anatomical brain model, resulting in 2100 (10 × 210) GT-HQ PETs. As a first step, WM activity was randomly chosen according to the observed distribution in ( 33 ). Activity ratios between cerebral GM and WM were then selected as 1.2, 1.8, 2.4, 3.0, 3.6, 4.2, 4.8, 5.4, 6.0, 6.6.…”

Section: Methodsmentioning

confidence: 99%

“…Activity ratios between cerebral GM and WM were then selected as 1.2, 1.8, 2.4, 3.0, 3.6, 4.2, 4.8, 5.4, 6.0, 6.6. Activities assigned to CSF, soft tissue and basal ganglia were randomly chosen according to the observed distribution in Mérida et al ( 33 ). Cerebellum GM activity was set to 80% of the cerebrum.…”

Section: Methodsmentioning

confidence: 99%

Section: Medical Image Datamentioning

confidence: 99%

See 4 more Smart Citations

PET image enhancement using artificial intelligence for better characterization of epilepsy lesions

et al. 2022

Self Cite

View full text Add to dashboard Cite

Introduction[18F]fluorodeoxyglucose ([18F]FDG) brain PET is used clinically to detect small areas of decreased uptake associated with epileptogenic lesions, e.g., Focal Cortical Dysplasias (FCD) but its performance is limited due to spatial resolution and low contrast. We aimed to develop a deep learning-based PET image enhancement method using simulated PET to improve lesion visualization.MethodsWe created 210 numerical brain phantoms (MRI segmented into 9 regions) and assigned 10 different plausible activity values (e.g., GM/WM ratios) resulting in 2100 ground truth high quality (GT-HQ) PET phantoms. With a validated Monte-Carlo PET simulator, we then created 2100 simulated standard quality (S-SQ) [18F]FDG scans. We trained a ResNet on 80% of this dataset (10% used for validation) to learn the mapping between S-SQ and GT-HQ PET, outputting a predicted HQ (P-HQ) PET. For the remaining 10%, we assessed Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Squared Error (RMSE) against GT-HQ PET. For GM and WM, we computed recovery coefficients (RC) and coefficient of variation (COV). We also created lesioned GT-HQ phantoms, S-SQ PET and P-HQ PET with simulated small hypometabolic lesions characteristic of FCDs. We evaluated lesion detectability on S-SQ and P-HQ PET both visually and measuring the Relative Lesion Activity (RLA, measured activity in the reduced-activity ROI over the standard-activity ROI). Lastly, we applied our previously trained ResNet on 10 clinical epilepsy PETs to predict the corresponding HQ-PET and assessed image quality and confidence metrics.ResultsCompared to S-SQ PET, P-HQ PET improved PNSR, SSIM and RMSE; significatively improved GM RCs (from 0.29 ± 0.03 to 0.79 ± 0.04) and WM RCs (from 0.49 ± 0.03 to 1 ± 0.05); mean COVs were not statistically different. Visual lesion detection improved from 38 to 75%, with average RLA decreasing from 0.83 ± 0.08 to 0.67 ± 0.14. Visual quality of P-HQ clinical PET improved as well as reader confidence.ConclusionP-HQ PET showed improved image quality compared to S-SQ PET across several objective quantitative metrics and increased detectability of simulated lesions. In addition, the model generalized to clinical data. Further evaluation is required to study generalization of our method and to assess clinical performance in larger cohorts.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Medical Image Datamentioning

confidence: 99%

See 3 more Smart Citations

PET image enhancement using artificial intelligence for better characterization of epilepsy lesions

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Deep‐learning predicted PET can be subtracted from the true clinical fluorodeoxyglucose PET co‐registered to MRI to identify the epileptogenic zone in focal epilepsy

Flaus,

Jung,

Ostrowky‐Coste

et al. 2023

Epilepsia Open

Self Cite

View full text Add to dashboard Cite

ObjectiveNormal interictal [18F]FDG‐PET can be predicted from the corresponding T1w MRI with Generative Adversarial Networks (GANs). A technique we call SIPCOM (Subtraction Interictal PET Co‐registered to MRI) can then be used to compare epilepsy patients’ predicted and clinical PET. We assessed the ability of SIPCOM to identify the Resection Zone (RZ) in patients with drug‐resistant epilepsy (DRE) with reference to visual and Statistical Parametric Mapping (SPM) analysis.MethodsPatients with complete pre‐surgical work‐up and subsequent SEEG and cortectomy were included. RZ localisation, the reference region, was assigned to one of eighteen anatomical brain regions. SIPCOM was implemented using healthy controls to train a GAN. To compare, the clinical PET coregistered to MRI was visually assessed by two trained readers, and a standard SPM analysis was performed.ResultsTwenty patients aged 17 to 50 (32±7.8) years were included, 14 (70%) with temporal lobe epilepsy (TLE). Eight (40%) were MRI‐negative. After surgery, fourteen patients (70%) had a good outcome (Engel I‐II). RZ localisation rate was 60% with SIPCOM vs. 35% using SPM (p=0.015) and vs. 85% using visual analysis (p=0.54). Results were similar for Engel I‐II patients, the RZ localisation rate was 64% with SIPCOM vs 36% with SPM. With SIPCOM localisation was correct in 67% in MRI‐positive vs. 50% in MRI‐negative patients, and 64% in TLE vs. 43% in extra‐TLE. The average number of false‐positive clusters was 2.2±1.3 using SIPCOM vs. 2.3±3.1 using SPM. All RZs localised with SPM were correctly localised with SIPCOM. In one case, PET and MRI were visually reported as negative, but both SIPCOM and SPM localised the RZ.SignificanceSIPCOM performed better than the reference computer‐assisted method (SPM) for RZ detection in a group of operated DRE patients. SIPCOM's impact on epilepsy management needs to be prospectively validated.

show abstract

Advances in nanoprobes for molecular MRI of Alzheimer's disease

Parekh,

Badachhape,

Tanifum

et al. 2024

WIREs Nanomed Nanobiotechnol

View full text Add to dashboard Cite

Alzheimer's disease is the most common cause of dementia and a leading cause of mortality in the elderly population. Diagnosis of Alzheimer's disease has traditionally relied on evaluation of clinical symptoms for cognitive impairment with a definitive diagnosis requiring post‐mortem demonstration of neuropathology. However, advances in disease pathogenesis have revealed that patients exhibit Alzheimer's disease pathology several decades before the manifestation of clinical symptoms. Magnetic resonance imaging (MRI) plays an important role in the management of patients with Alzheimer's disease. The clinical availability of molecular MRI (mMRI) contrast agents can revolutionize the diagnosis of Alzheimer's disease. In this article, we review advances in nanoparticle contrast agents, also referred to as nanoprobes, for mMRI of Alzheimer's disease.This article is categorized under: Diagnostic Tools > In Vivo Nanodiagnostics and Imaging Therapeutic Approaches and Drug Discovery > Nanomedicine for Neurological Disease

show abstract

CERMEP-IDB-MRXFDG: a database of 37 normal adult human brain [18F]FDG PET, T1 and FLAIR MRI, and CT images available for research

Cited by 29 publications

References 42 publications

PET image enhancement using artificial intelligence for better characterization of epilepsy lesions

PET image enhancement using artificial intelligence for better characterization of epilepsy lesions

Deep‐learning predicted PET can be subtracted from the true clinical fluorodeoxyglucose PET co‐registered to MRI to identify the epileptogenic zone in focal epilepsy

Advances in nanoprobes for molecular MRI of Alzheimer's disease

Contact Info

Product

Resources

About