RESUMO
OBJECTIVES: To compare the diagnostic performance of conventional non-contrast CT, dual-energy spectral CT, and chemical-shift MRI (CS-MRI) in discriminating lipid-poor adenomas (> 10-HU on non-contrast CT) from non-adenomas. METHODS: A total of 110 patients (69 men; 41 women; mean age 66.5 ± 13.4 years) with 80 lipid-poor adenomas and 30 non-adenomas who underwent non-contrast dual-layer spectral CT and CS-MRI were retrospectively identified. For each lesion, non-contrast attenuation on conventional 120-kVp images, ΔHU-index ([attenuation difference between virtual monoenergetic 140-keV and 40-keV images]/conventional attenuation × 100), and signal intensity index (SI-index) were quantified. Each parameter was compared between adenomas and non-adenomas using the Mann-Whitney U-test. The area under the receiver operating characteristic curve (AUC) and sensitivity to achieve > 95% specificity for adenoma diagnosis were determined. RESULTS: Conventional non-contrast attenuation was lower in adenomas than in non-adenomas (22.4 ± 8.6 HU vs 32.8 ± 48.5 HU), whereas ΔHU-index (148.0 ± 103.2 vs 19.4 ± 25.8) and SI-index (41.6 ± 19.6 vs 4.2 ± 10.2) were higher in adenomas (all, p < 0.001). ΔHU-index showed superior performance to conventional non-contrast attenuation (AUC: 0.919 [95% CI: 0.852-0.963] vs 0.791 [95% CI: 0.703-0.863]; sensitivity: 75.0% [60/80] vs 27.5% [22/80], both p < 0.001), and near equivalent to SI-index (AUC: 0.952 [95% CI: 0.894-0.984], sensitivity 85.0% [68/80], both p > 0.05). Both the ΔHU-index and SI-index provided a sensitivity of 96.0% (48/50) for hypoattenuating adenomas (≤ 25 HU). For hyperattenuating (> 25 HU) adenomas, SI-index showed higher sensitivity than ΔHU-index (66.7% [20/30] vs 40.0% [12/30], p = 0.022). CONCLUSIONS: Non-contrast spectral CT and CS-MRI outperformed conventional non-contrast CT in distinguishing lipid-poor adenomas from non-adenomas. While CS-MRI demonstrated superior sensitivity for adenomas measuring > 25 HU, non-contrast spectral CT provided high discriminative values for adenomas measuring ≤ 25 HU. CLINICAL RELEVANCE STATEMENT: Spectral attenuation analysis improves the diagnostic performance of non-contrast CT in discriminating lipid-poor adrenal adenomas, potentially serving as an alternative to CS-MRI and obviating the necessity for additional diagnostic workup in indeterminate adrenal incidentalomas, particularly for lesions measuring ≤ 25 HU. KEY POINTS: Incidental adrenal lesion detection has increased as abdominal CT use has become more frequent. Non-contrast spectral CT and CS-MRI differentiated lipid-poor adenomas from non-adenomas better than conventional non-contrast CT. For lesions measuring ≤ 25 HU, spectral CT may obviate the need for additional evaluation.
RESUMO
This study aimed to evaluate the impact of radiation dose and focal spot size on the image quality of super-resolution deep-learning reconstruction (SR-DLR) in comparison with iterative reconstruction (IR) and normal-resolution DLR (NR-DLR) algorithms for cardiac CT. Catphan-700 phantom was scanned on a 320-row scanner at six radiation doses (small and large focal spots at 1.4-4.3 and 5.8-8.8 mGy, respectively). Images were reconstructed using hybrid-IR, model-based-IR, NR-DLR, and SR-DLR algorithms. Noise properties were evaluated through plotting noise power spectrum (NPS). Spatial resolution was quantified with task-based transfer function (TTF); Polystyrene, Delrin, and Bone-50% inserts were used for low-, intermediate, and high-contrast spatial resolution. The detectability index (d') was calculated. Image noise, noise texture, edge sharpness of low- and intermediate-contrast objects, delineation of fine high-contrast objects, and overall quality of four reconstructions were visually ranked. Results indicated that among four reconstructions, SR-DLR yielded the lowest noise magnitude and NPS peak, as well as the highest average NPS frequency, TTF50%, d' values, and visual rank at each radiation dose. For all reconstructions, the intermediate- to high-contrast spatial resolution was maximized at 4.3 mGy, while the lowest noise magnitude and highest d' were attained at 8.8 mGy. SR-DLR at 4.3 mGy exhibited superior noise performance, intermediate- to high-contrast spatial resolution, d' values, and visual rank compared to the other reconstructions at 8.8 mGy. Therefore, SR-DLR may yield superior diagnostic image quality and facilitate radiation dose reduction compared to the other reconstructions, particularly when combined with small focal spot scanning.
RESUMO
OBJECTIVES: To investigate the feasibility of low-radiation dose and low iodinated contrast medium (ICM) dose protocol combining low-tube voltage and deep-learning reconstruction (DLR) algorithm in thin-slice abdominal CT. METHODS: This prospective study included 148 patients who underwent contrast-enhanced abdominal CT with either 120-kVp (600 mgL/kg, n = 74) or 80-kVp protocol (360 mgL/kg, n = 74). The 120-kVp images were reconstructed using hybrid iterative reconstruction (HIR) (120-kVp-HIR), while 80-kVp images were reconstructed using HIR (80-kVp-HIR) and DLR (80-kVp-DLR) with 0.5 mm thickness. Size-specific dose estimate (SSDE) and iodine dose were compared between protocols. Image noise, CT attenuation, and contrast-to-noise ratio (CNR) were quantified. Noise power spectrum (NPS) and edge rise slope (ERS) were used to evaluate noise texture and edge sharpness, respectively. The subjective image quality was rated on a 4-point scale. RESULTS: SSDE and iodine doses of 80-kVp were 40.4% (8.1 ± 0.9 vs. 13.6 ± 2.7 mGy) and 36.3% (21.2 ± 3.9 vs. 33.3 ± 4.3 gL) lower, respectively, than those of 120-kVp (both, p < 0.001). CT attenuation of vessels and solid organs was higher in 80-kVp than in 120-kVp images (all, p < 0.001). Image noise of 80-kVp-HIR and 80-kVp-DLR was higher and lower, respectively than that of 120-kVp-HIR (both p < 0.001). The highest CNR and subjective scores were attained in 80-kVp-DLR (all, p < 0.001). There were no significant differences in average NPS frequency and ERS between 120-kVp-HIR and 80-kVp-DLR (p ≥ 0.38). CONCLUSION: Compared with the 120-kVp-HIR protocol, the combined use of 80-kVp and DLR techniques yielded superior subjective and objective image quality with reduced radiation and ICM doses at thin-section abdominal CT. CLINICAL RELEVANCE STATEMENT: Scanning at low-tube voltage (80-kVp) combined with the deep-learning reconstruction algorithm may enhance diagnostic efficiency and patient safety by improving image quality and reducing radiation and contrast doses of thin-slice abdominal CT. KEY POINTS: Reducing radiation and iodine doses is desirable; however, contrast and noise degradation can be detrimental. The 80-kVp scan with the deep-learning reconstruction technique provided better images with lower radiation and contrast doses. This technique may be efficient for improving diagnostic confidence and patient safety in thin-slice abdominal CT.
RESUMO
PURPOSE: To evaluate the diagnostic performance of multiphase hepatic CT parameters (non-contrast attenuation, absolute and relative washout ratios [APW and RPW, respectively], and relative enhancement ratio [RER]) and chemical-shift MRI (CS-MRI) for discriminating lipid-poor adrenal adenomas (with non-contrast CT attenuation > 10 HU) from metastases in patients with hepatocellular carcinoma (HCC). METHODS: This retrospective study included HCC patients with lipid-poor adrenal lesions who underwent multiphase hepatic CT between January 2010 and December 2021. For each adrenal lesion, non-contrast attenuation, APW, RPW, RER, and signal-intensity index (SI-index) were measured. Each parameter was compared between adenomas and metastases. The area under the receiver operating characteristic curves (AUCs) and sensitivities to achieve 100% specificity for adenoma diagnoses were determined. RESULTS: 104 HCC patients (78 men; mean age, 71.8 ± 9.6 years) with 63 adenomas and 48 metastases were identified; CS-MRI was performed in 66 patients with 49 adenomas and 21 metastases within one year of CT. Lipid-poor adenomas showed lower non-contrast attenuation (22.9 ± 7.1 vs. 37.9 ± 9.4 HU) and higher APW (40.5% ± 12.8% vs. 23.7% ± 17.4%), RPW (30.0% ± 10.2% vs. 12.4% ± 9.6%), RER (329% ± 152% vs. 111% ± 43.0%), and SI-index (43.3 ± 20.7 vs. 10.8 ± 13.4) than HCC metastases (all p < .001). AUC for non-contrast attenuation, APW, RPW, RER, and SI-index were 0.894, 0.786, 0.904, 0.969, and 0.902, respectively. The sensitivities to achieve 100% specificity were 7.9%, 25.4%, 30.2%, 63.5%, and 24.5%, respectively. Combined RER and APW achieved the highest sensitivity of 73.0%. CONCLUSION: Multiphase hepatic CT allows for better discrimination between lipid-poor adrenal adenomas and metastases relative to CS-MRI, especially when combined with RER and washout parameters.
Assuntos
Neoplasias das Glândulas Suprarrenais , Carcinoma Hepatocelular , Neoplasias Hepáticas , Imageamento por Ressonância Magnética , Sensibilidade e Especificidade , Tomografia Computadorizada por Raios X , Humanos , Neoplasias Hepáticas/diagnóstico por imagem , Masculino , Feminino , Carcinoma Hepatocelular/diagnóstico por imagem , Estudos Retrospectivos , Idoso , Imageamento por Ressonância Magnética/métodos , Neoplasias das Glândulas Suprarrenais/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Diagnóstico Diferencial , Pessoa de Meia-Idade , Adenoma/diagnóstico por imagem , Meios de ContrasteRESUMO
PURPOSE: We aimed to evaluate the effect of deep learning-based reconstruction (DLR) on high-spatial-resolution three-dimensional T2-weighted fast asymmetric spin-echo (HR-3D T2-FASE) imaging in the preoperative evaluation of cerebellopontine angle (CPA) tumors. METHODS: This study included 13 consecutive patients who underwent preoperative HR-3D T2-FASE imaging using a 3 T MRI scanner. The reconstruction voxel size of HR-3D T2-FASE imaging was 0.23 × 0.23 × 0.5 mm. The contrast-to-noise ratios (CNRs) of the structures were compared between HR-3D T2-FASE images with and without DLR. The observers' preferences based on four categories on the tumor side on HR-3D T2-FASE images were evaluated. The facial nerve in relation to the tumor on HR-3D T2-FASE images was assessed with reference to intraoperative findings. RESULTS: The mean CNR between the tumor and trigeminal nerve and between the cerebrospinal fluid and trigeminal nerve was significantly higher for DLR images than non-DLR-based images (14.3 ± 8.9 vs. 12.0 ± 7.6, and 66.4 ± 12.0 vs. 53.9 ± 8.5, P < 0.001, respectively). The observer's preference for the depiction and delineation of the tumor, cranial nerves, vessels, and location relation on DLR HR-3D T2FASE images was superior to that on non-DLR HR-3D T2FASE images in 7 (54%), 6 (46%), 6 (46%), and 6 (46%) of 13 cases, respectively. The facial nerves around the tumor on HR-3D T2-FASE images were visualized accurately in five (38%) cases with DLR and in four (31%) without DLR. CONCLUSION: DLR HR-3D T2-FASE imaging is useful for the preoperative assessment of CPA tumors.
Assuntos
Aprendizado Profundo , Imageamento Tridimensional , Imageamento por Ressonância Magnética , Cuidados Pré-Operatórios , Humanos , Feminino , Masculino , Pessoa de Meia-Idade , Adulto , Imageamento Tridimensional/métodos , Imageamento por Ressonância Magnética/métodos , Cuidados Pré-Operatórios/métodos , Idoso , Ângulo Cerebelopontino/diagnóstico por imagem , Ângulo Cerebelopontino/cirurgia , Neoplasias Cerebelares/diagnóstico por imagem , Neoplasias Cerebelares/cirurgia , Interpretação de Imagem Assistida por Computador/métodos , Estudos Retrospectivos , Neuroma Acústico/diagnóstico por imagem , Neuroma Acústico/cirurgiaRESUMO
RATIONALE AND OBJECTIVES: This study aimed to assess the utility of cardiac magnetic resonance imaging (MRI) T1 and T2 mapping as quantitative imaging biomarkers in transthyretin amyloid cardiomyopathy (ATTR-CM). MATERIALS AND METHODS: This study retrospectively evaluated 74 patients with confirmed wild-type ATTR-CM who underwent cardiac MRI, 99mTc-labeled pyrophosphate (99mTc-PYP) scintigraphy, and echocardiography. We assessed the quantitative disease parameters, for example, left ventricular ejection fraction (LVEF), and global longitudinal strain (GLS) by echocardiography, native T1, extracellular volume fraction (ECV), and native T2 value by cardiac MRI, heart-to-contralateral ratio (H/CL) by 99mTc-PYP, and high-sensitive cardiac troponin T. Myocardial native T2 of ≥50 ms was defined as myocardial edema. Correlations between the disease's quantitative parameters were evaluated, and the ECV was compared to other parameters in ATTR-CM with/without myocardial edema. RESULTS: ECV in all patients with ATTR-CM revealed a strong correlation with native T1 (r = 0.62), a moderate correlation with hs-TnT (r = 0.59), LVEF (r = -0.48), GLS (r = 0.58), and H/CL (r = 0.48). Correlations between ECV and other quantitative parameters decreased in ATTR-CM with myocardial edema except for H/CL. Meanwhile, the correlations increased in ATTR-CM without myocardial edema. CONCLUSION: The presence of myocardial edema affected the interpretation of ECV assessment, although ECV can be a comprehensive imaging biomarker for ATTR-CM. ECV showed a significant correlation with various quantitative disease parameters and can be a reliable disease monitoring marker in patients with ATTR-CM when myocardial edema was excluded.
Assuntos
Amiloidose , Cardiomiopatias , Humanos , Pré-Albumina , Cardiomiopatias/diagnóstico por imagem , Pirofosfato de Tecnécio Tc 99m , Estudos Retrospectivos , Volume Sistólico , Função Ventricular Esquerda , Amiloidose/diagnóstico por imagem , Imageamento por Ressonância Magnética , Edema , BiomarcadoresRESUMO
This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist's perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.
Assuntos
Neoplasias , Radioterapia (Especialidade) , Radioterapia Guiada por Imagem , Humanos , Inteligência Artificial , Planejamento da Radioterapia Assistida por Computador/métodos , Neoplasias/radioterapia , Radioterapia (Especialidade)/métodosRESUMO
OBJECTIVES: Myocardial extracellular volume (ECV) on computed tomography (CT), an alternative to cardiac magnetic resonance (CMR), has significant practical clinical advantages. However, the consistency between ECVs quantified via CT and CMR in cardiac amyloidosis (CA) has not been investigated sufficiently. Therefore, the current study investigated the application of CT-ECV in CA with CMR-ECV as the reference standard. METHODS: We retrospectively evaluated 31 patients with CA who underwent cardiac CT and CMR. Pearson correlation analysis was performed to investigate correlations between CT-ECV and CMR-ECV at each segment. Further, correlations between ECV and clinical parameters were assessed. RESULTS: There were no significant differences in the mean global ECVs between CT scan and CMR (51.3% ± 10.2% vs 50.0% ± 10.5%). CT-ECV was correlated with CMR-ECV at the septal (r = 0.88), lateral (r = 0.80), inferior (r = 0.79), anterior (r = 0.77) segments, and global (r = 0.87). In both CT and CMR, the ECV had a weak to strong correlation with high-sensitivity cardiac troponin T level, a moderate correlation with global longitudinal strain, and an inverse correlation with left ventricular ejection fraction. Further, the septal ECV and global ECV had a slightly higher correlation with the clinical parameters. CONCLUSIONS: Cardiac CT can quantify myocardial ECV and yield results comparable to CMR in patients with CA. Moreover, a significant correlation between CT-ECV and clinical parameters was observed. Thus, CT-ECV can be an imaging biomarker and alternative to CMR-ECV. CLINICAL RELEVANCE STATEMENT: Cardiac CT can quantify myocardial ECV and yield results comparable to CMR in patients with CA, and CT-ECV can be used clinically as an imaging biomarker and alternative to CMR-ECV. KEY POINTS: ⢠A significant correlation was found between CT myocardial extracellular volume and cardiac MR myocardial extracellular volume in patients with cardiac amyloidosis. ⢠In CT and cardiac MR, the myocardial extracellular volume correlated well with high-sensitivity cardiac troponin T level, global longitudinal strain, and left ventricular ejection fraction. ⢠CT myocardial extracellular volume can be an imaging biomarker and alternative to cardiac MR myocardial extracellular volume.
Assuntos
Amiloidose , Troponina T , Humanos , Volume Sistólico , Estudos Retrospectivos , Imagem Cinética por Ressonância Magnética/métodos , Função Ventricular Esquerda , Miocárdio/patologia , Imageamento por Ressonância Magnética , Amiloidose/diagnóstico por imagem , Biomarcadores , Valor Preditivo dos TestesRESUMO
The radiopharmaceutical 2-[fluorine-18]fluoro-2-deoxy-D-glucose (FDG) has been dominantly used in positron emission tomography (PET) scans for over 20 years, and due to its vast utility its applications have expanded and are continuing to expand into oncology, neurology, cardiology, and infectious/inflammatory diseases. More recently, the addition of artificial intelligence (AI) has enhanced nuclear medicine diagnosis and imaging with FDG-PET, and new radiopharmaceuticals such as prostate-specific membrane antigen (PSMA) and fibroblast activation protein inhibitor (FAPI) have emerged. Nuclear medicine therapy using agents such as [177Lu]-dotatate surpasses conventional treatments in terms of efficacy and side effects. This article reviews recently established evidence of FDG and non-FDG drugs and anticipates the future trajectory of nuclear medicine.
RESUMO
Purpose: To evaluate the diagnostic performance of myocardium-to-lumen R1 (1/T1) ratio on postcontrast T1 maps for the detection of cardiac amyloidosis in a large patient sample. Materials and Methods: This retrospective study included consecutive patients who underwent MRI-derived extracellular volume fraction (MRI ECV) analysis between March 2017 and July 2021 because of known or suspected heart failure or cardiomyopathy. Pre- and postcontrast T1 maps were generated using the modified Look-Locker inversion recovery sequence. Diagnostic performances of MRI ECV and myocardium-to-lumen R1 ratio on postcontrast T1 maps (a simplified index not requiring a native T1 map and hematocrit level data) for detecting cardiac amyloidosis were evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results: Of 352 patients (mean age, 63 years ± 16 [SD]; 235 men), 136 had cardiac amyloidosis. MRI ECV showed 89.0% (121 of 136; 95% CI: 82%, 94%) sensitivity and 98.6% (213 of 216; 95% CI: 96%, 100%) specificity for helping detect cardiac amyloidosis (cutoff value of 40% [AUC, 0.99 {95% CI: 0.97, 1.00}; P < .001]). Postcontrast myocardium-to-lumen R1 ratio showed 92.6% (126 of 136; 95% CI: 89%, 96%) sensitivity and 93.1% (201 of 216; 95% CI: 89%, 96%) specificity (cutoff value of 0.84 [AUC, 0.98 {95% CI: 0.95, 0.99}; P < .001]). There was no evidence of a difference in AUCs for each parameter (P = .10). Conclusion: Postcontrast myocardium-to-lumen R1 ratio showed excellent diagnostic performance comparable to that of MRI ECV in the detection of cardiac amyloidosis.Keywords: MR Imaging, Cardiac, Heart, Cardiomyopathies Supplemental material is available for this article. © RSNA, 2023.
RESUMO
This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.
Assuntos
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Inteligência Artificial , Carcinoma Hepatocelular/diagnóstico por imagem , Tomografia Computadorizada por Raios X , Neoplasias Hepáticas/diagnóstico por imagemRESUMO
To compare the radiation dose and diagnostic ability of the 100-kVp protocol, based on the contrast noise ratio (CNR) index, during coronary artery bypass graft (CABG) vessels with those of the 120-kVp protocol. For the 120-kVp scans (150 patients), the targeted image level was set at 25 Hounsfield units (HU) (CNR120 = iodine contrast/25 HU). For the 100-kVp scans (150 patients), the targeted noise level was set at 30 HU to obtain the same CNR as in the 120-kVp scans (i.e. using 1.2-fold higher iodine contrast, CNR100 = 1.2 × iodine contrast/(1.2 × 25 HU) = CNR120). We compared the CNRs, radiation doses, detection of CABG vessels and visualisation scores of the scans acquired at 120 and 100 kVp, respectively. At the same CNR, the 100-kVp protocol may help reduce the radiation dose by â30% compared with the 120-kVp protocol, without degradation of diagnostic ability during CABG.
Assuntos
Angiografia por Tomografia Computadorizada , Redução da Medicação , Humanos , Angiografia por Tomografia Computadorizada/métodos , Doses de Radiação , Tomografia Computadorizada por Raios X/métodos , Ponte de Artéria Coronária , Meios de Contraste , Interpretação de Imagem Radiográfica Assistida por Computador , Angiografia Coronária/métodosRESUMO
OBJECTIVES: To evaluate the image quality of deep learning-based reconstruction (DLR), model-based (MBIR), and hybrid iterative reconstruction (HIR) algorithms for lower-dose (LD) unenhanced head CT and compare it with those of standard-dose (STD) HIR images. METHODS: This retrospective study included 114 patients who underwent unenhanced head CT using the STD (n = 57) or LD (n = 57) protocol on a 320-row CT. STD images were reconstructed with HIR; LD images were reconstructed with HIR (LD-HIR), MBIR (LD-MBIR), and DLR (LD-DLR). The image noise, gray and white matter (GM-WM) contrast, and contrast-to-noise ratio (CNR) at the basal ganglia and posterior fossa levels were quantified. The noise magnitude, noise texture, GM-WM contrast, image sharpness, streak artifact, and subjective acceptability were independently scored by three radiologists (1 = worst, 5 = best). The lesion conspicuity of LD-HIR, LD-MBIR, and LD-DLR was ranked through side-by-side assessments (1 = worst, 3 = best). Reconstruction times of three algorithms were measured. RESULTS: The effective dose of LD was 25% lower than that of STD. Lower image noise, higher GM-WM contrast, and higher CNR were observed in LD-DLR and LD-MBIR than those in STD (all, p ≤ 0.035). Compared with STD, the noise texture, image sharpness, and subjective acceptability were inferior for LD-MBIR and superior for LD-DLR (all, p < 0.001). The lesion conspicuity of LD-DLR (2.9 ± 0.2) was higher than that of HIR (1.2 ± 0.3) and MBIR (1.8 ± 0.4) (all, p < 0.001). Reconstruction times of HIR, MBIR, and DLR were 11 ± 1, 319 ± 17, and 24 ± 1 s, respectively. CONCLUSION: DLR can enhance the image quality of head CT while preserving low radiation dose level and short reconstruction time. KEY POINTS: ⢠For unenhanced head CT, DLR reduced the image noise and improved the GM-WM contrast and lesion delineation without sacrificing the natural noise texture and image sharpness relative to HIR. ⢠The subjective and objective image quality of DLR was better than that of HIR even at 25% reduced dose without considerably increasing the image reconstruction times (24 s vs. 11 s). ⢠Despite the strong noise reduction and improved GM-WM contrast performance, MBIR degraded the noise texture, sharpness, and subjective acceptance with prolonged reconstruction times relative to HIR, potentially hampering its feasibility.
Assuntos
Interpretação de Imagem Radiográfica Assistida por Computador , Tomografia Computadorizada por Raios X , Humanos , Algoritmos , Aprendizado Profundo , Doses de Radiação , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodos , Cabeça/diagnóstico por imagemRESUMO
The application of machine learning (ML) and deep learning (DL) in radiology has expanded exponentially. In recent years, an extremely large number of studies have reported about the hepatobiliary domain. Its applications range from differential diagnosis to the diagnosis of tumor invasion and prediction of treatment response and prognosis. Moreover, it has been utilized to improve the image quality of DL reconstruction. However, most clinicians are not familiar with ML and DL, and previous studies about these concepts are relatively challenging to understand. In this review article, we aimed to explain the concepts behind ML and DL and to summarize recent achievements in their use in the hepatobiliary region.
Assuntos
Aprendizado Profundo , Radiologia , Inteligência Artificial , Aprendizado de Máquina , Radiologia/métodos , Imageamento por Ressonância MagnéticaRESUMO
RATIONALE AND OBJECTIVES: To evaluate the performance of a machine learning method to differentiate malignant from benign soft tissue tumors based on textural features on multiparametric magnetic resonance imaging (mpMRI). MATERIALS AND METHODS: We enrolled 163 patients with soft tissue tumors whose diagnosis was pathologically proven (71 malignant, 92 benign). All patients underwent mpMRI. Twelve histographic and textural parameters were assessed on T1-weighted imaging (T1WI), T2-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced T1WI imaging. We compared mean signals of all sequences from the malignant and benign tumors using Welch's t-test. Prediction models were developed via a machine learning technique (support vector machine) using textural features of each sequence, clinical information (sex + age + tumor size), and the combined model incorporating all features. Areas under the receiver operating characteristic curves (AUCs) of these models were calculated using fivefold cross validation. RESULTS: The diagnostic ability of clinical information model (AUC 0.85) was not inferior to the model with textural features of each sequence (AUC 0.79-0.84). The combined model showed the highest diagnostic ability (AUC 0.89). The AUC of the combined model (0.89) was comparable to those of two board-certified radiologists (0.89 and 0.87). CONCLUSIONS: Machine learning methods based on textural features on mpMRI and clinical information offer adequate diagnostic performance to differentiate between malignant and benign soft tissue tumors.
Assuntos
Neoplasias Encefálicas , Neoplasias de Tecidos Moles , Humanos , Estudos Retrospectivos , Imageamento por Ressonância Magnética/métodos , Neoplasias de Tecidos Moles/diagnóstico por imagem , Aprendizado de Máquina , Imagem de Difusão por Ressonância Magnética/métodosRESUMO
Background Large studies on the diagnostic performance of CT-derived myocardial extracellular volume fraction (ECV) for detecting cardiac amyloidosis are lacking. A simple and practical index as a surrogate for CT ECV would be clinically useful. Purpose To compare the diagnostic performances between CT-derived myocardial ECV and myocardium-to-lumen signal ratio for the detection of cardiac amyloidosis in a large patient sample. Materials and Methods This retrospective study included patients who underwent CT ECV analysis because of suspected heart failure or cardiomyopathy between January 2018 and July 2021. CT ECV was quantified using routine pre-transcatheter aortic valve replacement planning cardiac CT, pre-atrial fibrillation ablation planning cardiac CT, or coronary CT angiography with the addition of unenhanced and delayed phase cardiac CT scans. The diagnostic performances of CT ECV and myocardium-to-lumen signal ratio in delayed phase cardiac CT (a simplified index not requiring unenhanced CT and hematocrit) for detecting cardiac amyloidosis were evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results Of 552 patients (mean age, 69 years ± 14 [SD]; 295 men), 41 had cardiac amyloidosis. The sensitivity of CT ECV for amyloidosis was 90% (37 of 41 patients [95% CI: 77, 97]), with a specificity of 92% (472 of 511 patients [95% CI: 90, 95]) and optimal ECV cutoff value of 37% (AUC, 0.97 [95% CI: 0.96, 0.99]). The sensitivity of myocardium-to-lumen signal ratio was 88% (36 of 41 patients [95% CI: 74, 96]), with a specificity of 92% (469 of 511 patients [95% CI: 89, 94]) and optimal myocardium-to-lumen signal ratio cutoff value of 0.87 (AUC, 0.96 [95% CI: 0.94, 0.97]; P = .27 for comparison with ECV). Conclusion CT-derived myocardial extracellular volume fraction and myocardium-to-lumen signal ratio showed comparable and excellent diagnostic performance in detecting cardiac amyloidosis in a large patient sample. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Williams in this issue.
Assuntos
Amiloidose , Cardiomiopatias , Masculino , Humanos , Idoso , Estudos Retrospectivos , Miocárdio , Amiloidose/diagnóstico por imagem , Cardiomiopatias/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Valor Preditivo dos Testes , Imagem Cinética por Ressonância Magnética/métodosRESUMO
OBJECTIVE: To investigate the features associated with rapid growth of vestibular schwannoma using radiomics analysis on magnetic resonance imaging (MRI) together with clinical factors. METHODS: From August 2005 to February 2019, 67 patients with vestibular schwannoma underwent contrast-enhanced T1-weighted MRI at least twice as part of their diagnosis. After excluding 3 cases with an extremely short follow-up period of 15 days or less, 64 patients were finally enrolled in this study. Ninety-three texture features were extracted from the tumor image data using 3D Slicer software (http://www.slicer.org/). We determined the texture features that significantly affected maximal tumor diameter growth of more than 2 mm/year using Random Forest and Bounty. We also analyzed age and tumor size as clinical factors. We calculated the areas under the curve (AUCs) using receiver operating characteristic analysis for prediction models using texture, clinical, and mixed factors by Random Forest and 5-fold cross-validation. RESULTS: Two texture features, low minimum signal and high inverse difference moment normalized (Idmn), were significantly associated with rapid growth of vestibular schwannoma. The mixed model of texture features and clinical factors offered the highest AUC (0.69), followed by the pure texture (0.67), and pure clinical (0.63) models. The minimum signal was the most important variable followed by tumor size, Idmn, and age. CONCLUSIONS: Our radiomics analysis found that texture features were significantly associated with the rapid growth of vestibular schwannoma in contrast-enhanced T1-weighted images. The mixed model offered a higher diagnostic performance than the pure texture or clinical models.
Assuntos
Neuroma Acústico , Área Sob a Curva , Humanos , Imageamento por Ressonância Magnética/métodos , Neuroma Acústico/diagnóstico por imagem , Curva ROC , Estudos Retrospectivos , Fatores de RiscoRESUMO
PURPOSE: This clinical and phantom study aimed to evaluate the impact of deep learning-based reconstruction (DLR) on image quality and its radiation dose optimization capability for multiphase hepatic CT relative to hybrid iterative reconstruction (HIR). METHODS: Task-based image quality was assessed with a physical evaluation phantom; the high- and low-contrast detectability of HIR and DLR images were computed from the noise power spectrum and task-based transfer function at five different size-specific dose estimate (SSDE) values in the range 5.3 to 18.0-mGy. For the clinical study, images of 73 patients who had undergone multiphase hepatic CT under both standard-dose (STD) and lower-dose (LD) examination protocols within a time interval of about four-months on average, were retrospectively examined. STD images were reconstructed with HIR, while LD with HIR (LD-HIR) and DLR (LD-DLR). SSDE, quantitative image noise, and contrast-to-noise ratio (CNR) were compared between protocols. The noise magnitude, noise texture, streak artifact, image sharpness, interface smoothness, and overall image quality were subjectively rated by two independent radiologists. RESULTS: In phantom study, the high- and low-contrast detectability of DLR images obtained at 5.3-mGy and 7.3-mGy, respectively, were slightly higher than those obtained with HIR at the STD protocol dose (18.0-mGy). In clinical study, LD-DLR yielded lower image noise, higher CNR, and higher subjective scores for all evaluation criteria than STD (all, p ≤ 0.05), despite having 52.8% lower SSDE (8.0 ± 2.5 vs. 16.8 ± 3.4-mGy). CONCLUSIONS: DLR improved the subjective and objective image quality of multiphase hepatic CT compared with HIR techniques, even at approximately half the radiation dose.
Assuntos
Aprendizado Profundo , Infecções Sexualmente Transmissíveis , Algoritmos , Humanos , Doses de Radiação , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodosRESUMO
PURPOSE: To compare the effects of tube voltage and iodinated concentration on increasing the iodinated radiation dose in computed tomography (CT). MATERIAL AND METHODS: Water and iodinated materials were inserted in an anthropomorphic thorax phantom. Helical CT scans were performed with tube voltages of 80 and 120 kV. Monte Carlo simulation of radiation doses in CT images was used to study the radiation dose profiles. The radiation doses at different iodine to water ratios in images were calculated from cumulative radiation doses for iodine and water at each iodine concentration, tube voltage, and peripheral/central location. A radiation dose ratio from 80 to 120 kV was calculated from cumulative radiation doses at the same iodine concentration. RESULTS: The iodinated radiation doses with small and large phantoms were 1.56-2.04 and 1.61-1.82 times higher at 80 kV and 1.55-2.23 and 1.22-1.79 times higher at 120 kV than those in water. In the central portion, the iodinated radiation dose ratio decreased by 1.14-0.75 and 1.20-0.93 times at 80 kV and 1.29-1.23 and 1.17-1.23 times at 120 kV with increasing iodinated concentrations. In the peripheral portion, the iodinated radiation dose was slightly higher for 80 kV than for 120 kV. In the central portion, the ratio decreased with increasing iodinated concentration. CONCLUSION: The increase in iodinated radiation dose caused by photoelectric absorption was greater with increased iodine load than with lower tube voltage.
Assuntos
Iodo , Tomografia Computadorizada por Raios X , Meios de Contraste , Método de Monte Carlo , Imagens de Fantasmas , Doses de Radiação , Tomografia Computadorizada por Raios X/métodosRESUMO
BACKGROUND. Deep learning-based reconstruction (DLR) may facilitate CT radiation dose reduction, but a paucity of literature has compared lower-dose DLR images with standard-dose iterative reconstruction (IR) images or explored application of DLR to low-tube-voltage scanning in children. OBJECTIVE. The purpose of this study was to assess whether DLR can be used to reduce radiation dose while maintaining diagnostic image quality in comparison with hybrid IR (HIR) and model-based IR (MBIR) for low-tube-voltage pediatric CT. METHODS. This retrospective study included children 6 years old or younger who underwent contrast-enhanced 80-kVp CT with a standard-dose or lower-dose protocol. Standard images were reconstructed with HIR, and lower-dose images were reconstructed with HIR, MBIR, and DLR. Size-specific dose estimate (SSDE) was calculated for both protocols. Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were quantified. Two radiologists independently evaluated noise magnitude, noise texture, streak artifact, edge sharpness, and overall quality. Interreader agreement was assessed, and mean values were calculated. To evaluate task-based object detection performance, a phantom was imaged with 80-kVp CT at six doses (SSDE, 0.6-5.3 mGy). Detectability index (d') was calculated from the noise power spectrum and task-based transfer function. Reconstruction methods were compared. RESULTS. Sixty-five children (mean age, 25.0 ± 25.2 months) who underwent CT with standard- (n = 31) or lower-dose (n = 34) protocol were included. SSDE was 54% lower for the lower-dose than for the standard-dose group (1.9 ± 0.4 vs 4.1 ± 0.8 mGy). Lower-dose DLR and MBIR yielded lower image noise and higher SNR and CNR than standard-dose HIR (p < .05). Interobserver agreement on subjective features ranged from a kappa coefficient of 0.68 to 0.78. The readers subjectively scored noise texture, edge sharpness, and overall quality lower for lower-dose MBIR than for standard-dose HIR (p < .001), though higher for lower-dose DLR than for standard-dose HIR (p < .001). In the phantom, DLR provided higher d' than HIR and MBIR at each dose. Object detectability was greater for 2.0-mGy DLR than for 4.0-mGy HIR for low-contrast (3.67 vs 3.57) and high-contrast (1.20 vs 1.04) objects. CONCLUSION. Compared with IR algorithms, DLR results in substantial dose reduction with preserved or even improved image quality for low-tube-voltage pediatric CT. CLINICAL IMPACT. Use of DLR at 80 kVp allows greater dose reduction for pediatric CT than do current IR techniques.