1
|
Kafali SG, Shih SF, Li X, Kim GHJ, Kelly T, Chowdhury S, Loong S, Moretz J, Barnes SR, Li Z, Wu HH. Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs. MAGMA (NEW YORK, N.Y.) 2024; 37:491-506. [PMID: 38300360 DOI: 10.1007/s10334-023-01146-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 12/18/2023] [Accepted: 12/27/2023] [Indexed: 02/02/2024]
Abstract
OBJECTIVE Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis. DISCUSSION ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.
Collapse
Affiliation(s)
- Sevgi Gokce Kafali
- Department of Radiological Sciences, University of California, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA
- Department of Bioengineering, University of California, Los Angeles, CA, USA
| | - Shu-Fu Shih
- Department of Radiological Sciences, University of California, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA
- Department of Bioengineering, University of California, Los Angeles, CA, USA
| | - Xinzhou Li
- Department of Radiological Sciences, University of California, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA
| | - Grace Hyun J Kim
- Department of Radiological Sciences, University of California, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA
| | - Tristan Kelly
- Department of Physiological Science, University of California, Los Angeles, CA, USA
| | - Shilpy Chowdhury
- Department of Radiology, Loma Linda University Medical Center, Loma Linda, CA, USA
| | - Spencer Loong
- Department of Psychology, Loma Linda University School of Behavioral Health, Loma Linda, CA, USA
| | - Jeremy Moretz
- Department of Neuroradiology, Loma Linda University Medical Center, Loma Linda, CA, USA
| | - Samuel R Barnes
- Department of Radiology, Loma Linda University Medical Center, Loma Linda, CA, USA
| | - Zhaoping Li
- Department of Medicine, University of California, Los Angeles, CA, USA
| | - Holden H Wu
- Department of Radiological Sciences, University of California, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA.
- Department of Bioengineering, University of California, Los Angeles, CA, USA.
| |
Collapse
|
3
|
Bouazizi K, Zarai M, Noufaily A, Prigent M, Dietenbeck T, Bollache E, Nguyen T, Della Valle V, Blondiaux E, Clément K, Aron-Wisnewsky J, Andreelli F, Redheuil A, Kachenoura N. Associations of aortic stiffness and intra-aortic flow parameters with epicardial adipose tissue in patients with type-2 diabetes. FRONTIERS IN CLINICAL DIABETES AND HEALTHCARE 2023; 4:1106342. [PMID: 37304050 PMCID: PMC10250660 DOI: 10.3389/fcdhc.2023.1106342] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Accepted: 05/09/2023] [Indexed: 06/13/2023]
Abstract
Background It has been shown that increased aortic stiffness is related to type-2 diabetes (T2D) which is considered as a risk factor for cardiovascular disease. Among other risk factors is epicardial adipose tissue (EAT) which is increased in T2D and is a relevant biomarker of metabolic severity and adverse outcome. Purpose To assess aortic flow parameters in T2D patients as compared to healthy individuals and to evaluate their associations with EAT accumulation as an index of cardiometabolic severity in T2D patients. Materials and methods Thirty-six T2D patients as well as 29 healthy controls matched by age and sex were included in this study. Participants had cardiac and aortic MRI exams at 1.5 T. Imaging sequences included cine SSFP for left ventricle (LV) function and EAT assessment and aortic cine and phase-contrast imaging for strain and flow parameters quantification. Results In this study, we found LV phenotype to be characterized by concentric remodeling with decreased stroke volume index despite global LV mass within a normal range. EAT was increased in T2D patients compared to controls (p<0.0001). Moreover, EAT, a biomarker of metabolic severity, was negatively correlated to ascending aortic (AA) distensibility (p=0.048) and positively to the normalized backward flow volume (p=0.001). These relationships remained significant after further adjustment for age, sex and central mean blood pressure. In a multivariate model, presence/absence of T2D and AA normalized backward flow (BF) to forward flow (FF) volumes ratio are both significant and independent correlates of EAT. Conclusion In our study, aortic stiffness as depicted by an increased backward flow volume and decreased distensibility seems to be related to EAT volume in T2D patients. This observation should be confirmed in the future on a larger population while considering additional biomarkers specific to inflammation and using a longitudinal prospective study design.
Collapse
Affiliation(s)
- Khaoula Bouazizi
- Laboratoire d’Imagerie Biomédicale (LIB), Sorbonne Université, Institut National de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Paris, France
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| | - Mohamed Zarai
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| | - Abdallah Noufaily
- Unité d’Imagerie Cardiovasculaire et Thoracique (ICT), Pitié-Salpêtrière Hospital, Paris, France
| | - Mikaël Prigent
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| | - Thomas Dietenbeck
- Laboratoire d’Imagerie Biomédicale (LIB), Sorbonne Université, Institut National de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Paris, France
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| | - Emilie Bollache
- Laboratoire d’Imagerie Biomédicale (LIB), Sorbonne Université, Institut National de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Paris, France
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| | - Toan Nguyen
- Assistance Publique Hôpitaux de Paris, Radiology Department, Armand-Trousseau Hospital, Paris, France
| | - Valéria Della Valle
- Assistance Publique Hôpitaux de Paris, Radiology Department, Armand-Trousseau Hospital, Paris, France
| | - Eléonore Blondiaux
- Assistance Publique Hôpitaux de Paris, Radiology Department, Armand-Trousseau Hospital, Paris, France
| | - Karine Clément
- Sorbonne Université, INSERM, Nutrition and Obesities; approches systémiques (NutriOmique), Pitié-Salpêtrière Hospital, Nutrition Department, Paris, France
- Assistance Publique Hôpitaux de Paris, Nutrition Department, Centre de Recherche en Nutrition Humaine (CRNH) Ile-de-France, Pitié-Salpêtrière Hospital, Paris, France
| | - Judith Aron-Wisnewsky
- Sorbonne Université, INSERM, Nutrition and Obesities; approches systémiques (NutriOmique), Pitié-Salpêtrière Hospital, Nutrition Department, Paris, France
- Assistance Publique Hôpitaux de Paris, Nutrition Department, Centre de Recherche en Nutrition Humaine (CRNH) Ile-de-France, Pitié-Salpêtrière Hospital, Paris, France
| | - Fabrizio Andreelli
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
- Assistance Publique Hôpitaux de Paris, Diabetology Department, Pitié-Salpêtrière Hospital, Paris, France
| | - Alban Redheuil
- Laboratoire d’Imagerie Biomédicale (LIB), Sorbonne Université, Institut National de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Paris, France
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
- Unité d’Imagerie Cardiovasculaire et Thoracique (ICT), Pitié-Salpêtrière Hospital, Paris, France
| | - Nadjia Kachenoura
- Laboratoire d’Imagerie Biomédicale (LIB), Sorbonne Université, Institut National de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Paris, France
- ICAN Imaging, Institute of Cardiometabolism and Nutrition (ICAN), Paris, France
| |
Collapse
|
4
|
Laredo M, Lamy J, Bouazizi-Verdier K, Gueda M, Giron A, Gallo A, Cluzel P, Gandjbakhch E, Redheuil A, Kachenoura N. Feasibility of a New Regional Myocardial Strain Parameter for the Detection of Wall Motion Abnormalities in Arrhythmogenic Right Ventricular Cardiomyopathy. Radiol Cardiothorac Imaging 2023; 5:e220160. [PMID: 36860830 PMCID: PMC9969209 DOI: 10.1148/ryct.220160] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2022] [Revised: 01/05/2023] [Accepted: 01/12/2023] [Indexed: 02/18/2023]
Abstract
Purpose To evaluate a cardiac MRI feature tracking (FT)-derived parameter that combines right ventricular (RV) longitudinal and radial motions in detecting arrhythmogenic right ventricular cardiomyopathy (ARVC). Materials and Methods Patients with ARVC (n = 47; median age, 46 [IQR, 30-52] years; 31 men) were compared with controls (n = 39; median age, 46 [IQR, 33-53] years; 23 men) and separated into two groups based on fulfillment of major structural 2020 International criteria. Cine data from 1.5-T cardiac MRI examinations were analyzed using FT, resulting in conventional strain parameters and a novel composite index named the longitudinal-to-radial strain loop (LRSL). Receiver operating characteristic (ROC) analysis was used to assess diagnostic performance of RV parameters. Results Volumetric parameters differed significantly between patients in the major structural criteria group and controls but not between patients in the no major structural criteria group and controls. Patients in the major structural criteria group had significantly lower magnitudes of all FT parameters than controls, including RV basal longitudinal strain, radial motion fraction, circumferential strain, and LRSL (-15.6% ± 6.4 vs -26.7% ± 13.9; -9.6% ± 4.89 vs -13.8% ± 4.7; -6.9% ± 4.6 vs -10.1% ± 3.8; and 217.0 ± 128.9 versus 618.6 ± 356.3, respectively). Only LRSL differed between patients in the no major structural criteria group and controls (359.5 ± 195.8 vs 618.6 ± 356.3; P < .0001). Parameters with the highest area under the ROC curve values for discriminating patients in the no major structural criteria group from controls were LRSL, RV ejection fraction, and RV basal longitudinal strain (0.75, 0.70, and 0.61, respectively). Conclusion A new parameter combining RV longitudinal and radial motions showed good diagnostic performance in ARVC, even in patients without major structural abnormalities.Keywords: Arrhythmogenic Right Ventricular Dysplasia, Strain, Wall Motion Abnormalities, Right Ventricle, MRI, Inherited Cardiomyopathy Supplemental material is available for this article. © RSNA, 2023.
Collapse
|
5
|
Phan F, Boussouar S, Lucidarme O, Zarai M, Salem JE, Kachenoura N, Bouazizi K, Charpentier E, Niati Y, Bekkaoui H, Amoura Z, Mathian A, Benveniste O, Cacoub P, Allenbach Y, Saadoun D, Lacorte JM, Fourati S, Laroche S, Hartemann A, Bourron O, Andreelli F, Redheuil A. Cardiac adipose tissue volume and IL-6 level at admission are complementary predictors of severity and short-term mortality in COVID-19 diabetic patients. Cardiovasc Diabetol 2021; 20:165. [PMID: 34384426 PMCID: PMC8358546 DOI: 10.1186/s12933-021-01327-1] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/07/2021] [Accepted: 06/29/2021] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND COVID-19 diabetic adults are at increased risk of severe forms irrespective of obesity. In patients with type-II diabetes, fat distribution is characterized by visceral and ectopic adipose tissues expansion, resulting in systemic inflammation, which may play a role in driving the COVID-19 cytokine storm. Our aim was to determine if cardiac adipose tissue, combined to interleukin-6 levels, could predict adverse short-term outcomes, death and ICU requirement, in COVID-19 diabetic patients during the 21 days after admission. METHODS Eighty one consecutive patients with type-II diabetes admitted for COVID-19 were included. Interleukin-6 measurement and chest computed tomography with total cardiac adipose tissue index (CATi) measurement were performed at admission. The primary outcome was death during the 21 days following admission while intensive care requirement with or without early death (ICU-R) defined the secondary endpoint. Associations of CATi and IL-6 and threshold values to predict the primary and secondary endpoints were determined. RESULTS Of the enrolled patients (median age 66 years [IQR: 59-74]), 73% male, median body mass index (BMI) 27 kg/m2 [IQR: 24-31]) 20 patients had died from COVID-19, 20 required intensive care and 41 were in conventional care at day 21 after admission. Increased CATi and IL-6 levels were both significantly related to increased early mortality (respectively OR = 6.15, p = 0.002; OR = 18.2, p < 0.0001) and ICU-R (respectively OR = 3.27, p = 0.01; OR = 4.86, p = 0.002). These associations remained significant independently of age, sex, BMI as well as troponin-T level and pulmonary lesion extension in CT. We combined CATi and IL-6 levels as a multiplicative interaction score (CATi*IL-6). The cut-point for this score was ≥ 6386 with a sensitivity of 0.90 and a specificity of 0.87 (AUC = 0.88) and an OR of 59.6 for early mortality (p < 0.0001). CONCLUSIONS Cardiac adipose tissue index and IL-6 determination at admission could help physicians to better identify diabetic patients with a potentially severe and lethal short term course irrespective of obesity. Diabetic patients with high CATi at admission, a fortiori associated with high IL-6 levels could be a relevant target population to promptly initiate anti-inflammatory therapies.
Collapse
Affiliation(s)
- Franck Phan
- Sorbonne Université, Paris, France.,Assistance Publique-Hôpitaux de Paris (APHP), Diabetology Department, La Pitié Salpêtrière-Charles Foix University Hospital, Paris, France.,Centre de Recherche des Cordeliers, INSERM, UMR_S 1138, Paris 06, France.,Institute of Cardiometabolism and Nutrition ICAN, Paris, France
| | - Samia Boussouar
- Cardiovascular and Thoracic Imaging Unit, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (APHP), Sorbonne Université, Paris, France.,Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France.,Service d'imagerie Spécialisée et d'urgence SISU, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris, Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Paris, France
| | - Olivier Lucidarme
- Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France.,Service d'imagerie Spécialisée et d'urgence SISU, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris, Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Paris, France
| | - Mohamed Zarai
- Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France
| | - Joe-Elie Salem
- Department of Pharmacology, CIC-1901, INSERM, Sorbonne Université, Assistance Publique-Hôpitaux de Paris (APHP), Paris, France
| | - Nadjia Kachenoura
- Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France
| | - Khaoula Bouazizi
- Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France
| | - Etienne Charpentier
- Cardiovascular and Thoracic Imaging Unit, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (APHP), Sorbonne Université, Paris, France.,Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France.,Service d'imagerie Spécialisée et d'urgence SISU, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris, Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Paris, France
| | - Yasmine Niati
- Cardiovascular and Thoracic Imaging Unit, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (APHP), Sorbonne Université, Paris, France
| | - Hasnae Bekkaoui
- Cardiovascular and Thoracic Imaging Unit, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (APHP), Sorbonne Université, Paris, France
| | - Zahir Amoura
- Service de Médecine Interne 2, Centre National de Référence Maladies Systémiques Rares et Histiocytoses, Institut e3M, Hôpital de La Pitié-Salpêtrière, AP-HP, Sorbonne Université, 75013, Paris, France
| | - Alexis Mathian
- Service de Médecine Interne 2, Centre National de Référence Maladies Systémiques Rares et Histiocytoses, Institut e3M, Hôpital de La Pitié-Salpêtrière, AP-HP, Sorbonne Université, 75013, Paris, France
| | - Olivier Benveniste
- Département de Médecine Interne et Immunologie Clinique, Hôpital Pitié-Salpêtrière, Sorbonne Université, AP-HP, Paris, France
| | - Patrice Cacoub
- Département de Médecine Interne et Immunologie Clinique, Hôpital Pitié-Salpêtrière, Sorbonne Université, AP-HP, Paris, France
| | - Yves Allenbach
- Département de Médecine Interne et Immunologie Clinique, Hôpital Pitié-Salpêtrière, Sorbonne Université, AP-HP, Paris, France
| | - David Saadoun
- Département de Médecine Interne et Immunologie Clinique, Hôpital Pitié-Salpêtrière, Sorbonne Université, AP-HP, Paris, France
| | - Jean-Marc Lacorte
- Department of Endocrine and Oncologic Biochemistry, Inserm, UMR_S 1166, Research Institute of Cardiovascular Disease, Metabolism and Nutrition, Paris, France
| | - Salma Fourati
- Department of Endocrine and Oncologic Biochemistry, Inserm, UMR_S 1166, Research Institute of Cardiovascular Disease, Metabolism and Nutrition, Paris, France
| | - Suzanne Laroche
- Sorbonne Université, Paris, France.,Assistance Publique-Hôpitaux de Paris (APHP), Diabetology Department, La Pitié Salpêtrière-Charles Foix University Hospital, Paris, France
| | - Agnes Hartemann
- Sorbonne Université, Paris, France.,Assistance Publique-Hôpitaux de Paris (APHP), Diabetology Department, La Pitié Salpêtrière-Charles Foix University Hospital, Paris, France.,Centre de Recherche des Cordeliers, INSERM, UMR_S 1138, Paris 06, France.,Institute of Cardiometabolism and Nutrition ICAN, Paris, France
| | - Olivier Bourron
- Sorbonne Université, Paris, France.,Assistance Publique-Hôpitaux de Paris (APHP), Diabetology Department, La Pitié Salpêtrière-Charles Foix University Hospital, Paris, France.,Centre de Recherche des Cordeliers, INSERM, UMR_S 1138, Paris 06, France.,Institute of Cardiometabolism and Nutrition ICAN, Paris, France
| | - Fabrizio Andreelli
- Sorbonne Université, Paris, France.,Assistance Publique-Hôpitaux de Paris (APHP), Diabetology Department, La Pitié Salpêtrière-Charles Foix University Hospital, Paris, France.,Nutrition and Obesities: Systemic Approaches (NutriOmics) Research Unit, Sorbonne Université, INSERM, UMRS U1269, Paris, France
| | - Alban Redheuil
- Cardiovascular and Thoracic Imaging Unit, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris (APHP), Sorbonne Université, Paris, France. .,Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, Paris, France. .,Service d'imagerie Spécialisée et d'urgence SISU, Hôpital Pitié Salpêtrière, Assistance Publique-Hôpitaux de Paris, Laboratoire d'Imagerie Biomédicale, Sorbonne Université, INSERM, CNRS, Paris, France.
| | | |
Collapse
|