1
|
Nakajo M, Hirahara D, Jinguji M, Ojima S, Hirahara M, Tani A, Takumi K, Kamimura K, Ohishi M, Yoshiura T. Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis. Jpn J Radiol 2024; 42:744-752. [PMID: 38491333 PMCID: PMC11217075 DOI: 10.1007/s11604-024-01546-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 02/05/2024] [Indexed: 03/18/2024]
Abstract
OBJECTIVES To investigate the usefulness of machine learning (ML) models using pretreatment 18F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS). MATERIALS AND METHODS This retrospective study included 47 patients with CS who underwent 18F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 18F-FDG-PET-based radiomic features and the visibility of right ventricle 18F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances. RESULTS Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm. CONCLUSION ML analyses using 18F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Megumi Jinguji
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Satoko Ojima
- Department of Cardiovascular Medicine and Hypertension, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Mitsuho Hirahara
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Koji Takumi
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Kiyohisa Kamimura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Mitsuru Ohishi
- Department of Cardiovascular Medicine and Hypertension, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
2
|
Kaneko K, Nagao M, Yamamoto A, Sakai A, Sakai S. Linking cardiac and extracardiac sarcoidosis and their clinical outcome: 18F-FDG PET/CT analysis in patients with systemic cardiac sarcoidosis. Ann Nucl Med 2023:10.1007/s12149-023-01844-x. [PMID: 37119390 DOI: 10.1007/s12149-023-01844-x] [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: 03/07/2023] [Accepted: 04/24/2023] [Indexed: 05/01/2023]
Abstract
OBJECTIVE To clarify the link between cardiac sarcoidosis (CS) and extra-CS (ECS) in systemic CS (SCS) patients in terms of extent and clinical outcome by serial FDG-PET/CT. METHODS Thirty-five SCS patients treated for > 2 years were enrolled in this study. In the overall analysis, patient-based comparisons of the complete resolution (CR) and recurrence rate between CS and ECS lesions were performed. Then, subgroup analyses were performed according to the extent (mono- vs. multi-organ ECS group) and clinical outcome (stable vs. unstable ECS group) of ECS. Pre-treatment cardiac FDG uptake was compared between the mono- and multi-organ ECS groups. The rates of CR, recurrence, and major adverse cardiac events (MACE) were compared between the two groups. RESULTS The CR rate was significantly higher in CS than ECS lesions [77.1% (27/35) vs. 48.5% (17/35), p = 0.01], whereas recurrence rates were similar between CS and ECS [40.7% (11/27) vs. 58.8% (10/17)]. Both the mono- and multi-organ ECS groups showed similar SUVmax, cardiac metabolic volume, and cardiac metabolic activity in the pre-treatment condition. The CR rates were similar between the mono- and multi-organ ECS groups [71.4% (15/21) vs. 85.7% (12/14)], but the recurrence rate was significantly lower in the multi-organ ECS group [60.0% (9/15) vs. 16.7% (2/12), p = 0.02]. The CR [71.4% (5/7) vs. 78.6% (22/28)] and recurrence rates [60.0% (3/5) vs. 36.3% (8/22)] were not significantly different between the stable and unstable ECS groups. The occurrence of MACE was also not significantly different between the mono- and multi-organ ECS groups [19.0% (4/21) vs. 28.6% (4/14)] or between the stable and unstable ECS groups [42.9% (3/7) vs. 17.8% (5/28)]. CONCLUSIONS CS lesions respond to treatment better than ECS lesions, and the extent and clinical outcome of ECS lesion are not linked with those of CS lesions.
Collapse
Affiliation(s)
- Koichiro Kaneko
- Department of Diagnostic Imaging and Nuclear Medicine, Tokyo Women's Medical University, 8-1, Kawada-Cho, Shinjuku-Ku, Tokyo, 162-8666, Japan.
| | - Michinobu Nagao
- Department of Diagnostic Imaging and Nuclear Medicine, Tokyo Women's Medical University, 8-1, Kawada-Cho, Shinjuku-Ku, Tokyo, 162-8666, Japan
| | - Atsushi Yamamoto
- Department of Diagnostic Imaging and Nuclear Medicine, Tokyo Women's Medical University, 8-1, Kawada-Cho, Shinjuku-Ku, Tokyo, 162-8666, Japan
| | - Akiko Sakai
- Department of Cardiology, Tokyo Women's Medical University, 8-1, Kawada-Cho, Shinjuku-Ku, Tokyo, 162-8666, Japan
| | - Shuji Sakai
- Department of Diagnostic Imaging and Nuclear Medicine, Tokyo Women's Medical University, 8-1, Kawada-Cho, Shinjuku-Ku, Tokyo, 162-8666, Japan
| |
Collapse
|
3
|
Wang C, Ma Y, Liu Y, Li L, Cui C, Qin H, Zhao Z, Li C, Ju W, Chen M, Li D, Zhou W. Texture analysis of SPECT myocardial perfusion provides prognostic value for dilated cardiomyopathy. J Nucl Cardiol 2023; 30:504-515. [PMID: 35676551 DOI: 10.1007/s12350-022-03006-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2022] [Accepted: 05/03/2022] [Indexed: 11/27/2022]
Abstract
BACKGROUND Texture analysis (TA) has demonstrated clinical values in extracting information, quantifying inhomogeneity, evaluating treatment outcomes, and predicting long-term prognosis for cardiac diseases. The aim of this study was to explore whether TA of SPECT myocardial perfusion could contribute to improving the prognosis of dilated cardiomyopathy (DCM) patients. METHODS Eighty-eight patients were recruited in our study between 2009 and 2020 who were diagnosed with DCM and underwent single-photon emission tomography myocardial perfusion imaging (SPECT MPI). Forty TA features were obtained from quantitative analysis of SPECT imaging in subjects with myocardial perfusion at rest. All patients were divided into two groups: the all-cause death group and the survival group. The prognostic value of texture parameters was assessed by Cox regression and Kaplan-Meier analysis. RESULTS Twenty-five all-cause deaths (28.4%) were observed during the follow-up (39.2±28.7 months). Compared with the survival group, NT-proBNP and total perfusion deficit (TPD) were higher and left ventricular ejection fraction (LVEF) was lower in the all-cause death group. In addition, 26 out of 40 texture parameters were significantly different between the two groups. Univariate Cox regression analysis revealed that NT-proBNP, LVEF, and 25 texture parameters were significantly associated with all-cause death. The multivariate Cox regression analysis showed that low gray-level emphasis (LGLE) (P = 0.010, HR = 4.698, 95% CI 1.457-15.145) and long-run low gray-level emphasis (LRLGE) (P =0.002, HR = 6.085, 95% CI 1.906-19.422) were independent predictors of the survival outcome. When added to clinical parameters, LVEF, TPD, and TA parameters, including LGLE and LRLGE, were incrementally associated with all-cause death (global chi-square statistic of 26.246 vs. 33.521; P = 0.028, global chi-square statistic of 26.246 vs. 34.711; P = 0.004). CONCLUSION TA based on gated SPECT MPI could discover independent prognostic predictors of all-cause death in medically treated patients with DCM. Moreover, TA parameters, including LGLE and LRLGE, independent of the total perfusion deficit of the cardiac myocardium, appeared to provide incremental prognostic value for DCM patients.
Collapse
Affiliation(s)
- Cheng Wang
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Ying Ma
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Yanyun Liu
- Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Shaanxi, 710126, China
| | - Longxi Li
- School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, China
| | - Chang Cui
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Huiyuan Qin
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Zhongqiang Zhao
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Chunxiang Li
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Weizhu Ju
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Minglong Chen
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China
| | - Dianfu Li
- Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, 300 Guangzhou Road, Nanjing, 210029, China.
| | - Weihua Zhou
- Department of Applied Computing, Michigan Technological University, 1400 Townsend Dr, Houghton, MI, 49931, USA.
- Center for Biocomputing and Digital Health, Institute of Computing and Cybersystems, and Health Research Institute, Michigan Technological University, Houghton, USA.
| |
Collapse
|
4
|
Wang B, Xu Y, Wan P, Shao S, Zhang F, Shao X, Wang J, Wang Y. Right Atrial Fluorodeoxyglucose Uptake Is a Risk Factor for Stroke and Improves Prediction of Stroke Above the CHA2DS2-VASc Score in Patients With Atrial Fibrillation. Front Cardiovasc Med 2022; 9:862000. [PMID: 35872918 PMCID: PMC9304590 DOI: 10.3389/fcvm.2022.862000] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2022] [Accepted: 06/15/2022] [Indexed: 11/13/2022] Open
Abstract
BackgroundAtrial fibrillation (AF) is a common arrhythmia, and its most severe and dreaded complication is stroke. The CHA2DS2-VASc score is currently recommended for stroke risk assessment in AF. We aimed to explore the relationship between atrial FDG uptake and stroke and whether atrial FDG uptake could provide incremental value above the CHA2DS2-VAS score to predict stroke in AF by 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT).Materials and MethodsFrom September 2017 to December 2020, we retrospectively enrolled 230 patients (115 with AF and 115 without AF as the non-AF group, matched for the date of PET/CT examination and the basic characteristics of the patient) who underwent 18F-FDG PET/CT due to tumor screening or preoperative staging after prolonged fasting and followed up for at least 12 months from the date of PET/CT examination; the endpoint event is the occurrence of stroke. We visually and quantitatively analyzed 18F-FDG uptake in the right and left atria (RA/LA), right and left atrial appendage (RAA/LAA), right and left ventricle (RV/LV), and collected clinical features. In addition, according to the endpoint event (stroke), the enrolled population was divided into the stroke group and non-stroke group, and relevant clinical features and atrial FDG uptake indicators of the two groups were analyzed. Univariate and multivariate Cox regression analyzes were used to analyze the risk factors of stroke events. The Kaplan–Meier survival curve of atrial FDG uptake was drawn, and the log-rank method was used to compare the differences in the survival curves of the two groups. Receiver operating characteristic (ROC) curves were used to examine the discriminatory power of atrial FDG uptake in predicting stroke and determine whether the addition of atrial FDG uptake improves predictive value beyond the CHA2DS2-VASc score for stroke.ResultsIn the AF group, more than half of patients had RA FDG uptake and one-fifth had LA FDG uptake, while one patient had RA FDG uptake and two patients had LA FDG uptake in the non-AF group. In quantitative analysis, the maximum standardized uptake value (SUVmax) of the RA and LA in the AF group was significantly higher than that of the non-AF group (all P < 0.001). We followed up the patients for 28 ± 10 months, and finally, 31 patients had stroke. In the stroke group, atrial fibrillation, RA SUVmax, RAA SUVmax, LAA SUVmax, age ≥ 75 years, and left atrial dilation were significantly higher than those of the non-stroke group (all P < 0.05). Multivariate Cox regression analysis showed that high RA SUVmax (RA SUVmax ≥ 2.62) was an independent risk factor for stroke (HR = 4.264, 95% CI 1.368–13.293, P = 0.012). By using the log-rank test, patients with high RA SUVmax had a significantly higher incidence of stroke compared with patients with low RA SUVmax (P < 0.001). Addition of high RA SUVmax to the CHA2DS2-VASc score could predict stroke more effectively, with a larger AUC 0.790 (P < 0.001).ConclusionThis study found a significant correlation between atrial FDG uptake and AF, especially in RA. Meanwhile, RA FDG uptake is an independent risk factor for stroke, and patients with high RA SUVmax have a significantly higher risk of stroke. Moreover, RA FDG uptake improves prediction of stroke above the CHA2DS2-VASc score in patients with AF.
Collapse
Affiliation(s)
- Bing Wang
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
| | - Yiduo Xu
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
| | - Peng Wan
- Department of Cardiology, The Third Affiliated Hospital of Soochow University, Changzhou, China
| | - Shan Shao
- Department of Cardiology, The Third Affiliated Hospital of Soochow University, Changzhou, China
| | - Feifei Zhang
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
| | - Xiaoliang Shao
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
| | - Jianfeng Wang
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
| | - Yuetao Wang
- Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Changzhou, China
- Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, Changzhou, China
- *Correspondence: Yuetao Wang,
| |
Collapse
|
5
|
Manabe O, Oyama-Manabe N, Aikawa T, Tsuneta S, Tamaki N. Advances in Diagnostic Imaging for Cardiac Sarcoidosis. J Clin Med 2021; 10:jcm10245808. [PMID: 34945105 PMCID: PMC8704832 DOI: 10.3390/jcm10245808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2021] [Revised: 12/05/2021] [Accepted: 12/09/2021] [Indexed: 11/16/2022] Open
Abstract
Sarcoidosis is a systemic granulomatous disease of unknown etiology, and its clinical presentation depends on the affected organ. Cardiac sarcoidosis (CS) is one of the leading causes of death among patients with sarcoidosis. The clinical manifestations of CS are heterogeneous, and range from asymptomatic to life-threatening arrhythmias and progressive heart failure due to the extent and location of granulomatous inflammation in the myocardium. Advances in imaging techniques have played a pivotal role in the evaluation of CS because histological diagnoses obtained by myocardial biopsy tend to have lower sensitivity. The diagnosis of CS is challenging, and several approaches, notably those using positron emission tomography and cardiac magnetic resonance imaging (MRI), have been reported. Delayed-enhanced computed tomography (CT) may also be used for diagnosing CS in patients with MRI-incompatible devices and allows acceptable evaluation of myocardial hyperenhancement in such patients. This article reviews the advances in imaging techniques for the evaluation of CS.
Collapse
Affiliation(s)
- Osamu Manabe
- Department of Radiology, Jichi Medical University Saitama Medical Center, Saitama 330-8503, Japan; (O.M.); (T.A.)
| | - Noriko Oyama-Manabe
- Department of Radiology, Jichi Medical University Saitama Medical Center, Saitama 330-8503, Japan; (O.M.); (T.A.)
- Correspondence: ; Tel.: +81-48-647-2111
| | - Tadao Aikawa
- Department of Radiology, Jichi Medical University Saitama Medical Center, Saitama 330-8503, Japan; (O.M.); (T.A.)
| | - Satonori Tsuneta
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, Sapporo 060-8648, Japan;
| | - Nagara Tamaki
- Department of Radiology, Kyoto Prefectural University of Medicine, Kyoto 602-8566, Japan;
| |
Collapse
|
6
|
Kobayashi Y, Sato T, Nagai T, Hirata K, Tsuneta S, Kato Y, Komoriyama H, Kamiya K, Konishi T, Omote K, Ohira H, Kudo K, Konno S, Anzai T. Association of high serum soluble interleukin 2 receptor levels with risk of adverse events in cardiac sarcoidosis. ESC Heart Fail 2021; 8:5282-5292. [PMID: 34514715 PMCID: PMC8712796 DOI: 10.1002/ehf2.13614] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2021] [Revised: 08/25/2021] [Accepted: 09/01/2021] [Indexed: 12/17/2022] Open
Abstract
Aims Although soluble interleukin 2 receptor (sIL‐2R) is a potentially useful biomarker in the diagnosis and evaluation of disease severity in patients with sarcoidosis, its prognostic implication in patients with cardiac sarcoidosis (CS) is unclear. We sought to investigate whether sIL‐2R was associated with clinical outcomes and to clarify the relationship between sIL‐2R levels and disease activity in patients with CS. Methods and results We examined 83 consecutive patients with CS in our hospital who had available serum sIL‐2R data between May 2003 and February 2020. The primary outcome was a composite of advanced atrioventricular block, ventricular tachycardia or ventricular fibrillation, heart failure hospitalization, and all‐cause death. Inflammatory activity in the myocardium and lymph nodes was assessed by 18F‐fluorideoxyglucose positron emission tomography/computed tomography. During a median follow‐up period of 2.96 (IQR 2.24–4.27) years, the primary outcome occurred in 24 patients (29%). Higher serum sIL‐2R levels (>538 U/mL, the median) were significantly related to increased incidence of primary outcome (P = 0.037). Multivariable Cox regression analysis showed that a higher sIL‐2R was independently associated with an increased subsequent risk of adverse events (HR 3.71, 95% CI 1.63–8.44, P = 0.002), even after adjustment for significant covariates. sIL‐2R levels were significantly correlated to inflammatory activity in lymph nodes (r = 0.346, P = 0.003) but not the myocardium (r = 0.131, P = 0.27). Conclusions Increased sIL‐2R is associated with worse long‐term clinical outcomes accompanied by increased systemic inflammatory activity in CS patients.
Collapse
Affiliation(s)
- Yuta Kobayashi
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Takuma Sato
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Toshiyuki Nagai
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Kenji Hirata
- Department of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Satonori Tsuneta
- Department of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Yoshiya Kato
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Hirokazu Komoriyama
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Kiwamu Kamiya
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Takao Konishi
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Kazunori Omote
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| | - Hiroshi Ohira
- Department of Respiratory Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Kohsuke Kudo
- Department of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Satoshi Konno
- Department of Respiratory Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Toshihisa Anzai
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo, Hokkaido, 060-8638, Japan
| |
Collapse
|
7
|
Tana C, Mantini C, Donatiello I, Mucci L, Tana M, Ricci F, Cipollone F, Giamberardino MA. Clinical Features and Diagnosis of Cardiac Sarcoidosis. J Clin Med 2021; 10:1941. [PMID: 34062709 PMCID: PMC8124502 DOI: 10.3390/jcm10091941] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2021] [Revised: 04/09/2021] [Accepted: 04/13/2021] [Indexed: 12/12/2022] Open
Abstract
Cardiac sarcoidosis (CS) is an unusual, but potentially harmful, manifestation of systemic sarcoidosis (SA), a chronic disease characterized by organ involvement from noncaseating and nonnecrotizing granulomas. Lungs and intrathoracic lymph nodes are usually the sites that are most frequently affected, but no organ is spared and CS can affect a variable portion of SA patients, up to 25% from post-mortem studies. The cardiovascular involvement is usually associated with a bad prognosis and is responsible for the major cause of death and complications, particularly in African American patients. Furthermore, the diagnosis is often complicated by the occurrence of non-specific clinical manifestations, which can mimic the effect of more common heart disorders, and imaging and biopsies are the most valid approach to avoid misdiagnosis. This narrative review summarizes the main clinical features of CS and imaging findings, particularly of CMR and 18-Fluorodeoxyglucose Positron Emission Tomography (18F-FDG PET) that can give the best cost/benefit ratio in terms of the diagnostic approach. Imaging can be very useful in replacing the endomyocardial biopsy in selected cases, to avoid unnecessary, and potentially dangerous, invasive maneuvers.
Collapse
Affiliation(s)
- Claudio Tana
- COVID-19 Medicine Unit and Geriatrics Clinic, SS Annunziata Hospital of Chieti, 66100 Chieti, Italy; (F.C.); (M.A.G.)
| | - Cesare Mantini
- Department of Neuroscience, Imaging and Clinical Sciences, Institute of Radiology, “SS Annunziata” Hospital, “G. d’Annunzio” University, 66100 Chieti, Italy; (C.M.); (F.R.)
| | - Iginio Donatiello
- Internal Medicine Unit, University Hospital of Salerno, 84121 Salerno, Italy;
| | - Luciano Mucci
- Internal Medicine Unit, Hospital of Fano, Azienda Ospedaliera Ospedali Riuniti Marche, 61032 Fano, Italy;
| | - Marco Tana
- 2nd Medicine Unit and Department of Vascular Medicine and Cardiovascular Ultrasound, SS Annunziata Hospital of Chieti, 66100 Chieti, Italy;
| | - Fabrizio Ricci
- Department of Neuroscience, Imaging and Clinical Sciences, Institute of Radiology, “SS Annunziata” Hospital, “G. d’Annunzio” University, 66100 Chieti, Italy; (C.M.); (F.R.)
| | - Francesco Cipollone
- COVID-19 Medicine Unit and Geriatrics Clinic, SS Annunziata Hospital of Chieti, 66100 Chieti, Italy; (F.C.); (M.A.G.)
- Department of Medicine and Science of Aging, and CAST, G D’Annunzio University of Chieti, 66100 Chieti, Italy;
| | - Maria Adele Giamberardino
- COVID-19 Medicine Unit and Geriatrics Clinic, SS Annunziata Hospital of Chieti, 66100 Chieti, Italy; (F.C.); (M.A.G.)
| |
Collapse
|
8
|
Josselyn N, MacLean MT, Jean C, Fuchs B, Moon BF, Hwuang E, Iyer SK, Litt H, Han Y, Kaghazchi F, Bravo PE, Witschey WR. Classification of Myocardial 18F-FDG PET Uptake Patterns Using Deep Learning. Radiol Artif Intell 2021; 3:e200148. [PMID: 34350405 DOI: 10.1148/ryai.2021200148] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2020] [Revised: 02/17/2021] [Accepted: 03/11/2021] [Indexed: 11/11/2022]
Abstract
Purpose To perform automated myocardial segmentation and uptake classification from whole-body fluorine 18 fluorodeoxyglucose (FDG) PET. Materials and Methods In this retrospective study, consecutive patients who underwent FDG PET imaging for oncologic indications were included (July-August 2018). The left ventricle (LV) on whole-body FDG PET images was manually segmented and classified as showing no myocardial uptake, diffuse uptake, or partial uptake. A total of 609 patients (mean age, 64 years ± 14 [standard deviation]; 309 women) were included and split between training (60%, 365 patients), validation (20%, 122 patients), and testing (20%, 122 patients) datasets. Two sequential neural networks were developed to automatically segment the LV and classify the myocardial uptake pattern using segmentation and classification training data provided by human experts. Linear regression was performed to correlate findings from human experts and deep learning. Classification performance was evaluated using receiver operating characteristic (ROC) analysis. Results There was moderate agreement of uptake pattern between experts and deep learning (as a fraction of correctly categorized images) with 78% (36 of 46) for no uptake, 71% (34 of 48) for diffuse uptake, and 71% (20 of 28) for partial uptake. There was no bias in LV volume for partial or diffuse uptake categories (P = .56); however, deep learning underestimated LV volumes in the no uptake category. There was good correlation for LV volume (R 2 = 0.35, b = .71). ROC analysis showed the area under the curve for classifying no uptake and diffuse uptake was high (> 0.90) but lower for partial uptake (0.77). The feasibility of a myocardial uptake index (MUI) for quantifying the degree of myocardial activity patterns was shown, and there was excellent visual agreement between MUI and uptake patterns. Conclusion Deep learning was able to segment and classify myocardial uptake patterns on FDG PET images.Keywords: PET, Heart, Computer Aided Diagnosis, Computer Application-Detection/DiagnosisSupplemental material is available for this article.©RSNA, 2021.
Collapse
Affiliation(s)
- Nicholas Josselyn
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Matthew T MacLean
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Christopher Jean
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Ben Fuchs
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Brianna F Moon
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Eileen Hwuang
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Srikant Kamesh Iyer
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Harold Litt
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Yuchi Han
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Fatemeh Kaghazchi
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Paco E Bravo
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| | - Walter R Witschey
- Departments of Radiology (N.J., M.T.M., C.J., B.F., H.L., Y.H., F.K., P.E.B., W.R.W.), Bioengineering (B.F.M., E.H., S.K.I.), and Medicine (Y.H., P.B.), Perelman School of Medicine, University of Pennsylvania, 3400 Civic Center Blvd, South Pavilion, Room 11-155, Philadelphia, PA 19104
| |
Collapse
|
9
|
Texture analysis of delayed contrast-enhanced computed tomography to diagnose cardiac sarcoidosis. Jpn J Radiol 2021; 39:442-450. [PMID: 33483941 DOI: 10.1007/s11604-020-01086-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2020] [Accepted: 12/27/2020] [Indexed: 01/09/2023]
Abstract
PURPOSE To investigate the diagnostic value of texture analysis to differentiate cardiac sarcoidosis (CS) from other non-ischemic cardiomyopathies (non-CS). MATERIALS AND METHODS Twenty CS patients and 15 non-CS patients who had undergone myocardial CT delayed enhancement (CTDE) were included. A total of 36 texture features were calculated according to the CT attenuation of CTDE. We investigated the diagnostic value to differentiate CS from non-CS. We also assessed the intra- and inter-rater reproducibility for each feature and inter-observer agreement for visual assessment. RESULTS Seven extracted features had significantly higher run length non-uniformity (RLNU) values (5.4 × 102 ± 6.2 × 102 vs. 11.2 × 102 ± 4.9 × 102, p = 0.037) and significantly lower low gray-level zone emphasis (LGZE) values (7.1 × 10-3 ± 8.6 × 10-3 vs. 18.1 × 10-3 ± 16.9 × 10-3, p = 0.017) in CS than in non-CS. Intra- and inter-rater reproducibility of RLNU and LGZE were excellent (ICCs > 0.8), while inter-observer agreement of visual assessment was poor (kappa = 0.19). The accuracies of texture analysis were 69% with RLNU and 71% with LGZE, which were better than that of visual assessment. CONCLUSION Texture analysis of CTDE could differentiate CS from non-CS with high reproducibility.
Collapse
|
10
|
Tarkin JM, Ćorović A, Wall C, Gopalan D, Rudd JH. Positron emission tomography imaging in cardiovascular disease. Heart 2020; 106:1712-1718. [PMID: 32571959 DOI: 10.1136/heartjnl-2019-315183] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/31/2020] [Revised: 05/22/2020] [Accepted: 05/26/2020] [Indexed: 01/05/2023] Open
Abstract
Positron emission tomography (PET) imaging is useful in cardiovascular disease across several areas, from assessment of myocardial perfusion and viability, to highlighting atherosclerotic plaque activity and measuring the extent of cardiac innervation in heart failure. Other important roles of PET have emerged in prosthetic valve endocarditis, implanted device infection, infiltrative cardiomyopathies, aortic stenosis and cardio-oncology. Advances in scanner technology, including hybrid PET/MRI and total body PET imaging, as well as the development of novel PET tracers and cardiac-specific postprocessing techniques using artificial intelligence will undoubtedly continue to progress the field.
Collapse
Affiliation(s)
- Jason M Tarkin
- Division of Cardiovascular Medicine, University of Cambridge, Cambridge, UK
| | - Andrej Ćorović
- Division of Cardiovascular Medicine, University of Cambridge, Cambridge, UK
| | - Christopher Wall
- Division of Cardiovascular Medicine, University of Cambridge, Cambridge, UK
| | - Deepa Gopalan
- Radiology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, Cambridgeshire, UK
| | - James Hf Rudd
- Division of Cardiovascular Medicine, University of Cambridge, Cambridge, UK
| |
Collapse
|
11
|
Naya M, Manabe O. Nuclear Medicine Image Interpretation Progress in the Assessment of Cardiac Sarcoidosis: July 2019 ASNC/JSNC Joint Session. ANNALS OF NUCLEAR CARDIOLOGY 2020; 6:49-52. [PMID: 37123489 PMCID: PMC10133950 DOI: 10.17996/anc.20-00113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/22/2019] [Revised: 12/06/2020] [Accepted: 01/28/2020] [Indexed: 05/02/2023]
Abstract
Sarcoidosis is a significant disease affecting the heart. 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is a well-validated method for identifying significant focal inflammatory sarcoid lesions. The recent progress in image interpretation in nuclear medicine improves the diagnosis and the risk stratification in patients with cardiac sarcoidosis. Especially, metabolic activity, texture analysis, phase analysis, right ventricle assessment, and digital PET/CT are promising methods to assess cardiac sarcoidosis. This review focuses on the latest data analyses and image interpretation used in nuclear medicine to assess cardiac sarcoidosis.
Collapse
Affiliation(s)
- Masanao Naya
- Department of Cardiovascular Medicine, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan
| | - Osamu Manabe
- Department of Diagnostic and Interventional Radiology, Hokkaido University Hospital, Sapporo, Japan
| |
Collapse
|