ABSTRACT
Strain represents the quantification of regional tissue deformation within a given area. Myocardial strain has demonstrated considerable utility as an indicator for the assessment of cardiac function. Notably, it exhibits greater sensitivity in detecting subtle myocardial abnormalities compared to conventional cardiac function indices, like left ventricle ejection fraction (LVEF). Nonetheless, the estimation of strain poses considerable challenges due to the necessity for precise tracking of myocardial motion throughout the complete cardiac cycle. This study introduces a novel deep learning-based pipeline, designed to automatically and accurately estimate myocardial strain from three-dimensional (3D) cine-MR images. Consequently, our investigation presents a comprehensive pipeline for the precise quantification of local and global myocardial strain. This pipeline incorporates a supervised Convolutional Neural Network (CNN) for accurate segmentation of the cardiac muscle and an unsupervised CNN for robust left ventricle motion tracking, enabling the estimation of strain in both artificial phantoms and real cine-MR images. Our investigation involved a comprehensive comparison of our findings with those obtained from two commonly utilized commercial software in this field. This analysis encompassed the examination of both intra- and inter-user variability. The proposed pipeline exhibited demonstrable reliability and reduced divergence levels when compared to alternative systems. Additionally, our approach is entirely independent of previous user data, effectively eliminating any potential user bias that could influence the strain analyses.
Subject(s)
Deep Learning , Reproducibility of Results , Magnetic Resonance Imaging, Cine/methods , Heart/diagnostic imaging , Heart Ventricles/diagnostic imagingABSTRACT
OBJECTIVES: This study investigated whether intramyocardial bone marrow-derived hematopoietic progenitor cells (BMCs) increase coronary flow reserve (CFR) in ischemic myocardial regions where direct revascularization was unsuitable. BACKGROUND: Patients with diffuse coronary artery disease frequently undergo incomplete myocardial revascularization, which increases their risk for future adverse cardiovascular outcomes. The residual regional ischemia related to both untreated epicardial lesions and small vessel disease usually contributes to the disease burden. METHODS: The MiHeart/IHD study randomized patients with diffuse coronary artery disease undergoing incomplete coronary artery bypass grafting to receive BMCs or placebo in ischemic myocardial regions. After the procedure, 78 patients underwent cardiovascular magnetic resonance (CMR) at 1, 6, and 12 months and were included in this cardiac magnetic resonance substudy with perfusion quantification. Segments were classified as target (injected), adjacent (surrounding the injection site), and remote from injection site. RESULTS: Of 1,248 segments, 269 were target (22%), 397 (32%) adjacent, and 582 (46%) remote. The target had significantly lower CFR at baseline (1.40 ± 0.79 vs 1.64 ± 0.89 in adjacent and 1.79 ± 0.79 in remote; both P < 0.05). BMCs significantly increased CFR in target and adjacent segments at 6 and 12 months compared with placebo. In target regions, there was a progressive treatment effect (27.1% at 6 months, P = 0.037, 42.2% at 12 months, P = 0.001). In the adjacent segments, CFR increased by 21.8% (P = 0.023) at 6 months, which persisted until 12 months (22.6%; P = 0.022). Remote segments in both the BMC and placebo groups experienced similar improvements in CFR (not significant at 12 months compared with baseline). CONCLUSIONS: BMCs, injected in severely ischemic regions unsuitable for direct revascularization, led to the largest CFR improvements, which progressed up to 12 months, compared with smaller but persistent CFR changes in adjacent and no improvement in remote segments.
Subject(s)
Coronary Artery Disease , Fractional Flow Reserve, Myocardial , Bone Marrow Cells , Coronary Artery Disease/diagnostic imaging , Coronary Artery Disease/therapy , Humans , Magnetic Resonance Spectroscopy , Myocardium , Perfusion , Predictive Value of TestsABSTRACT
Radiomics using rectal MRI radiomics has emerged as a promising approach in predicting pathological complete response. In this study, we present a typical pipeline of a radiomics analysis and review recent studies, exploring applications, development of radiomics methodologies and model construction in pCR prediction. Finally, we will offer our opinion about the future and discuss the next steps of rectal MRI radiomics for predicting pCR.
Subject(s)
Rectal Neoplasms , Chemoradiotherapy , Humans , Magnetic Resonance Imaging , Neoadjuvant Therapy , Rectal Neoplasms/diagnostic imaging , Retrospective StudiesABSTRACT
OBJECTIVES: To investigate whether quantitative textural features, extracted from pretreatment MRI, can predict sustained complete response to radiofrequency ablation (RFA) in patients with hepatocellular carcinoma (HCC). METHODS: In this IRB-approved study, patients were selected from a maintained six-year database of consecutive patients who underwent both pretreatment MRI imaging with a probable or definitive imaging diagnosis of HCC (LI-RADS 4 or 5) and loco-regional treatment with RFA. An experienced radiologist manually segmented the hepatic nodules in MRI arterial and equilibrium phases to obtain the volume of interest (VOI) for extraction of 107 quantitative textural features, including shape and first- and second-order features. Statistical analysis was performed to evaluate associations between textural features and complete response. RESULTS: The study consisted of 34 patients with 51 treated hepatic nodules. Sustained complete response was achieved by 6 patients (4 with single nodule and 2 with multiple nodules). Of the 107 features from the arterial and equilibrium phases, 20 (18%) and 25 (23%) achieved AUC >0.7, respectively. The three best performing features were found in the equilibrium phase: Dependence Non-Uniformity Normalized and Dependence Variance (both GLDM class, with AUC of 0.78 and 0.76, respectively) and Maximum Probability (GLCM class, AUC of 0.76). CONCLUSIONS: This pilot study demonstrates that a radiomic analysis of pre-treatment MRI might be useful in identifying patients with HCC who are most likely to have a sustained complete response to RFA. Second-order features (GLDM and GLCM) extracted from equilibrium phase obtained highest discriminatory performance.
Subject(s)
Carcinoma, Hepatocellular , Catheter Ablation , Liver Neoplasms , Radiofrequency Ablation , Carcinoma, Hepatocellular/diagnostic imaging , Carcinoma, Hepatocellular/surgery , Humans , Liver Neoplasms/diagnostic imaging , Liver Neoplasms/surgery , Magnetic Resonance Imaging , Pilot Projects , Retrospective StudiesABSTRACT
OBJECTIVES: To investigate whether quantitative textural features, extracted from pretreatment MRI, can predict sustained complete response to radiofrequency ablation (RFA) in patients with hepatocellular carcinoma (HCC). METHODS: In this IRB-approved study, patients were selected from a maintained six-year database of consecutive patients who underwent both pretreatment MRI imaging with a probable or definitive imaging diagnosis of HCC (LI-RADS 4 or 5) and loco-regional treatment with RFA. An experienced radiologist manually segmented the hepatic nodules in MRI arterial and equilibrium phases to obtain the volume of interest (VOI) for extraction of 107 quantitative textural features, including shape and first- and second-order features. Statistical analysis was performed to evaluate associations between textural features and complete response. RESULTS: The study consisted of 34 patients with 51 treated hepatic nodules. Sustained complete response was achieved by 6 patients (4 with single nodule and 2 with multiple nodules). Of the 107 features from the arterial and equilibrium phases, 20 (18%) and 25 (23%) achieved AUC >0.7, respectively. The three best performing features were found in the equilibrium phase: Dependence Non-Uniformity Normalized and Dependence Variance (both GLDM class, with AUC of 0.78 and 0.76, respectively) and Maximum Probability (GLCM class, AUC of 0.76). CONCLUSIONS: This pilot study demonstrates that a radiomic analysis of pre-treatment MRI might be useful in identifying patients with HCC who are most likely to have a sustained complete response to RFA. Second-order features (GLDM and GLCM) extracted from equilibrium phase obtained highest discriminatory performance.
Subject(s)
Humans , Catheter Ablation , Carcinoma, Hepatocellular/surgery , Carcinoma, Hepatocellular/diagnostic imaging , Radiofrequency Ablation , Liver Neoplasms/surgery , Liver Neoplasms/diagnostic imaging , Magnetic Resonance Imaging , Pilot Projects , Retrospective StudiesABSTRACT
OBJECTIVE: Qualitative and quantitative image analysis between Iopamidol-370 and Ioversol-320 in stents´ evaluation by coronary computed tomography angiography (CTA). METHODS: Sixty-five patients with low-risk stable angina undergoing stent follow-up with coronary CTA were assigned to Iopamidol I-370 (n = 33) or Ioversol I-320 (n = 32) in this prospective, double-blind, non-inferiority, randomized trial. Stent lumen image quality was graded by 5-point Likert Scale. Lumen mean attenuation was measured at native coronary segments: pre-stent, post-stent, distal segments and at coronary plaques. Lumen attenuation increase (LAI) ratio was calculated for all stents. Heart rate (HR) variation, premature heart beats (PHB), heat sensation (HS), blooming and beam hardening were also assessed. RESULTS: Image quality was similar between groups, with no significant difference (Likert score 4.48 ± 0.75 vs 4.54 ± 0.65, p = 0.5). There were similarities in LAI ratio between I-370 and I-320 (0.39 ± 0.42 vs 0.48 ± 0.44 HU, p = 0.08). Regarding lumen mean attenuation at native coronary segments, a significant difference was observed, with I-320 presenting lower values, including contrast mean attenuation in distal segments. After statistical multivariate analysis, three variables correlated with stent image quality: 1) stent diameter, 2) HR variation and 3) stent lumen LAI ratio. CONCLUSIONS: There was no significant difference between Iopamidol-370 mgI ml-1 and Ioversol-320 mgI ml-1 contrasts regarding overall stent lumen image quality, which was mainly influenced by stent diameter, HR and LAI ratio.Advances in knowledge:Coronary CTA allows adequate stents' visualization and image quality is influenced by stent diameter, HR variation and LAI ratio.Stents' image quality showed no difference between different concentration contrasts (I-370 vs. I-320); however, higher concentration contrasts may provide an improved overall visualization, especially regarding coronary distal segments.
Subject(s)
Angina, Stable/diagnostic imaging , Computed Tomography Angiography/methods , Contrast Media , Coronary Angiography/methods , Iopamidol , Stents , Triiodobenzoic Acids , Angina, Stable/therapy , Artifacts , Cardiac Complexes, Premature , Computed Tomography Angiography/adverse effects , Computed Tomography Angiography/standards , Coronary Angiography/adverse effects , Coronary Angiography/standards , Double-Blind Method , Female , Heart Rate , Humans , Male , Middle Aged , Multivariate Analysis , Prohibitins , Prospective Studies , Stents/statistics & numerical dataABSTRACT
AIMS: To investigate the association between pericoronary adipose tissue (PCAT) computed tomography (CT) attenuation derived from coronary computed tomography angiography (CTA) and coronary flow reserve (CFR) by positron emission tomography (PET) in patients with suspected coronary artery disease (CAD). METHODS AND RESULTS: PCAT CT attenuation was measured in proximal segments of all major epicardial coronary vessels of 105 patients with suspected CAD. We evaluated the relationship between PCAT CT attenuation and other quantitative/qualitative CT-derived anatomic parameters with CFR by PET. Overall, the mean age was 60 ± 12 years and 93% had intermediate pre-test probability of obstructive CAD. Obstructive CAD (≥50% stenosis) was detected in 37 (35.2%) patients and impaired CFR (<2.0) in 32 (30.5%) patients. On a per-vessel analysis (315 vessels), obstructive CAD, non-calcified plaque volume, and PCAT CT attenuation were independently associated with CFR. In patients with coronary calcium score (CCS) <100, those with high-PCAT CT attenuation presented significantly lower CFR values than those with low-PCAT CT attenuation (2.47 ± 0.95 vs. 3.13 ± 0.89, P = 0.003). Among those without obstructive CAD, CFR was significantly lower in patients with high-PCAT CT attenuation (2.51 ± 0.95 vs. 3.02 ± 0.84, P = 0.021). CONCLUSION: Coronary perivascular inflammation by CTA was independently associated with downstream myocardial perfusion by PET. In patients with low CCS or without obstructive CAD, CFR was lower in the presence of higher perivascular inflammation. PCAT CT attenuation might help identifying myocardial ischaemia particularly among patients who are traditionally considered non-high risk for future cardiovascular events.
Subject(s)
Coronary Artery Disease , Aged , Computed Tomography Angiography , Coronary Angiography , Coronary Artery Disease/diagnostic imaging , Humans , Inflammation/diagnostic imaging , Middle Aged , PerfusionABSTRACT
Radiomics is a new field in medical imaging with the potential of changing medical practice. Radiomics is characterized by the extraction of several quantitative imaging features which are not visible to the naked eye from conventional imaging modalities, and its correlation with specific relevant clinical endpoints, such as pathology, therapeutic response, and survival. Several studies have evaluated the use of radiomics in patients with hepatocellular carcinoma (HCC) with encouraging results, particularly in the pretreatment prediction of tumor biological characteristics, risk of recurrence, and survival. In spite of this, there are limitations and challenges to be overcome before the implementation of radiomics into clinical routine. In this article, we will review the concepts of radiomics and their current potential applications in patients with HCC. It is important that the multidisciplinary team involved in the treatment of patients with HCC be aware of the basic principles, benefits, and limitations of radiomics in order to achieve a balanced interpretation of the results toward a personalized medicine.