ABSTRACT
OBJECTIVES: This study aims to assess the effectiveness of super-resolution deep-learning-based reconstruction (SR-DLR), which leverages k-space data, on the image quality of lumbar spine magnetic resonance (MR) bone imaging using a 3D multi-echo in-phase sequence. MATERIALS AND METHODS: In this retrospective study, 29 patients who underwent lumbar spine MRI, including an MR bone imaging sequence between January and April 2023, were analyzed. Images were reconstructed with and without SR-DLR (Matrix sizes: 960 × 960 and 320 × 320, respectively). The signal-to-noise ratio (SNR) of the vertebral body and spinal canal and the contrast and contrast-to-noise ratio (CNR) between the vertebral body and spinal canal were quantitatively evaluated. Furthermore, the slope at half-peak points of the profile curve drawn across the posterior border of the vertebral body was calculated. Two radiologists independently assessed image noise, contrast, artifacts, sharpness, and overall image quality of both image types using a 4-point scale. Interobserver agreement was evaluated using weighted kappa coefficients, and quantitative and qualitative scores were compared via the Wilcoxon signed-rank test. RESULTS: SNRs of the vertebral body and spinal canal were notably improved in images with SR-DLR (p < 0.001). Contrast and CNR were significantly enhanced with SR-DLR compared to those without SR-DLR (p = 0.023 and p = 0.022, respectively). The slope of the profile curve at half-peak points across the posterior border of the vertebral body and spinal canal was markedly higher with SR-DLR (p < 0.001). Qualitative scores (noise: p < 0.001, contrast: p < 0.001, artifact p = 0.042, sharpness: p < 0.001, overall image quality: p < 0.001) were superior in images with SR-DLR compared to those without. Kappa analysis indicated moderate to good agreement (noise: κ = 0.56, contrast: κ = 0.51, artifact: κ = 0.46, sharpness: κ = 0.76, overall image quality: κ = 0.44). CONCLUSION: SR-DLR, which is based on k-space data, has the potential to enhance the image quality of lumbar spine MR bone imaging utilizing a 3D gradient echo in-phase sequence. CLINICAL RELEVANCE STATEMENT: The application of SR-DLR can lead to improvements in lumbar spine MR bone imaging quality.
Subject(s)
Deep Learning , Lumbar Vertebrae , Magnetic Resonance Imaging , Humans , Female , Lumbar Vertebrae/diagnostic imaging , Male , Retrospective Studies , Middle Aged , Magnetic Resonance Imaging/methods , Aged , Adult , Signal-To-Noise Ratio , Imaging, Three-Dimensional/methods , Aged, 80 and over , Spinal Diseases/diagnostic imagingABSTRACT
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.
ABSTRACT
The study aimed to compare the performance of photon-counting detector computed tomography (PCD CT) with high-resolution (HR)-plaque kernel with that of the energy-integrating detector CT (EID CT) in terms of the visualization of the lumen size and the in-stent stenotic portion at different coronary vessel angles. The lumen sizes in PCD CT and EID CT images were 2.13 and 1.80 mm at 0°, 2.20 and 1.77 mm at 45°, and 2.27 mm and 1.67 mm at 90°, respectively. The lumen sizes in PCD CT with HR-plaque kernel were wider than those in EID CT. The mean degree of the in-stent stenotic portion at 50% was 69.7% for PCD CT and 90.4% for EID CT. PCD CT images with HR-plaque kernel enable improved visualization of lumen size and accurate measurements of the in-stent stenotic portion compared to conventional EID CT images regardless of the stent direction.
ABSTRACT
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.
ABSTRACT
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.
ABSTRACT
To assess the diagnostic performance of unenhanced electrocardiogram (ECG)-gated cardiac computed tomography (CT) for detecting myocardial edema, using MRI T2 mapping as the reference standard. This retrospective study protocol was approved by our institutional review board, which waived the requirement for written informed consent. Between December 2017 to February 2019, consecutive patients who had undergone T2 mapping for myocardial tissue characterization were identified. We excluded patients who did not undergo unenhanced ECG-gated cardiac CT within 3 months from MRI T2 mapping or who had poor CT image quality. All patients underwent unenhanced ECG-gated cardiac CT with an axial scan using a third-generation, 320â ×â 0.5 mm detector-row CT unit. Two radiologists together drew regions of interest (ROIs) in the interventricular septum on the unenhanced ECG-gated cardiac CT images. Using T2 mapping as the reference standard, the diagnostic performance of unenhanced cardiac CT for detecting myocardial edema was evaluated by using the area under the receiver operating characteristic curve with sensitivity and specificity. Youden index was used to find an optimal sensitivity-specificity cutoff point. A cardiovascular radiologist independently performed the measurements, and interobserver reliability was assessed using intraclass correlation coefficients for CT value measurements. A P value of <.05 was considered statistically significant. We included 257 patients who had undergone MRI T2 mapping. Of the 257 patients, 35 patients underwent unenhanced ECG-gated cardiac CT. One patient was excluded from the study because of poor CT image quality. Finally, 34 patients (23 men; age 64.7â ±â 14.6 years) comprised our study group. Using T2 mapping, we identified myocardial edema in 19 patients. Mean CT and T2 values for 34 patients were 46.3â ±â 2.7 Hounsfield unit and 49.0â ±â 4.9 ms, respectively. Mean CT values moderately correlated with mean T2 values (Rhoâ =â -0.41; Pâ <â .05). Mean CT values provided a sensitivity of 63.2% and a specificity of 93.3% for detecting myocardial edema, with a cutoff value of ≤45.0 Hounsfield unit (area under the receiver operating characteristic curveâ =â 0.77; Pâ <â .01). Inter-observer reproducibility in measuring mean CT values was excellent (intraclass correlation coefficientâ =â 0.93; [95% confidence interval: 0.86, 0.96]). Myocardial edema could be detected by CT value of myocardium in unenhanced ECG-gated cardiac CT.
Subject(s)
Electrocardiography , Tomography, X-Ray Computed , Humans , Male , Female , Middle Aged , Retrospective Studies , Electrocardiography/methods , Tomography, X-Ray Computed/methods , Aged , Magnetic Resonance Imaging/methods , Sensitivity and Specificity , Reproducibility of Results , Edema/diagnostic imaging , Edema, Cardiac/diagnostic imaging , Cardiac-Gated Imaging Techniques/methods , ROC Curve , AdultABSTRACT
OBJECTIVE: The purpose of this study was to evaluate the usefulness of the injection pressure-to-injection rate (IPIR) ratio for the early detection of contrast extravasation at the venipuncture site during contrast-enhanced computed tomography. METHODS: We retrospectively enrolled 57,528 patients who underwent contrast-enhanced computed tomography examinations in a single hospital. The power injector recorded the contrast injection pressure at 0.25-second intervals. We constructed logistic regression models using the IPIR ratio as the independent variable and extravasation occurrence as the dependent variable (IPIR ratio models) at 1, 2, 3, 4, 5, and 6 seconds after the start of contrast administration. Univariate logistic regression models in which injection pressure is used as an independent variable (injection pressure models) were also constructed as a reference baseline. The performance of the models was evaluated with the area under the receiver operating characteristic curves. RESULTS: Of the 57,528 cases, 46,022 were assigned to the training group and 11,506 were assigned to the test group, which included 112 extravasation cases (0.24%) in the training group and 28 (0.24%) in the test group. The area under the receiver operating characteristic curves for the IPIR ratio models and injection pressure models were 0.555 versus 0.563 at t = 1 (P = 0.270), 0.712 versus 0.678 at t = 2 (P = 0.305), 0.758 versus 0.693 at t = 3 (P = 0.032), 0.776 versus 0.688 at t = 4 (P = 0.005), 0.810 versus 0.699 at t = 5 (P = 0.002), and 0.811 versus 0.706 at t = 6 (P = 0.002). CONCLUSIONS: The IPIR ratio models perform better in detecting contrast extravasation at 3 to 6 seconds after the start of contrast administration than injection pressure models.
ABSTRACT
BACKGROUND: Follow-up is recommended for an asymptomatic unilocular hepatic cystic lesion without wall-thickness and nodular components. A few liver cystic lesions represent biliary cystic neoplasms, which are difficult to differentiate from simple cysts with benign mural nodules on imaging alone. CASE PRESENTATION: An 84-year-old woman with a history of simple liver cyst diagnosed one year prior was admitted for evaluation of a developed mural nodule in the cystic lesion. She had no specific symptoms and no abnormalities in blood tests except for carcinoembryonic antigen (5.0 ng/mL) and carbohydrate antigen (43.5 U/mL) levels. Contrast-enhanced computed tomography revealed a well-defined, low-attenuation lesion without a septum that had enlarged from 41 to 47 mm. No dilation of the bile duct was observed. A gradually enhancing mural nodule, 14 mm in diameter, was confirmed. MRI revealed a uniform water-intense cystic lesion with a mural nodule. This was followed by T2-enhanced imaging showing peripheral hypointensity and central hyperintensity. Enhanced ultrasonography revealed an enhanced nodule with a distinct artery within it. A needle biopsy of the wall nodule or aspiration of intracystic fluid was not performed to avoid tumor cell spillage. The possibility of a neoplastic cystic tumor could not be ruled out, so a partial hepatectomy was performed with adequate margins. Pathologically, the cystic lesion contained a black 5 mm nodule consisting of a thin, whitish fibrous wall and dilated vessels lined by CD31 and CD34 positive endothelial cells. The final diagnosis was a rare cavernous hemangioma within a simple liver cyst. CONCLUSIONS: Cavernous hemangiomas mimicking well-enhanced mural nodules can arise from simple liver cysts. In less malignant cases, laparoscopic biopsy or percutaneous targeted biopsy of the mural nodules, together with needle ablation, may be recommended to avoid unnecessary surgery.
ABSTRACT
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.
Subject(s)
Adrenal Gland Neoplasms , Carcinoma, Hepatocellular , Liver Neoplasms , Magnetic Resonance Imaging , Sensitivity and Specificity , Tomography, X-Ray Computed , Humans , Liver Neoplasms/diagnostic imaging , Male , Female , Carcinoma, Hepatocellular/diagnostic imaging , Retrospective Studies , Aged , Magnetic Resonance Imaging/methods , Adrenal Gland Neoplasms/diagnostic imaging , Tomography, X-Ray Computed/methods , Diagnosis, Differential , Middle Aged , Adenoma/diagnostic imaging , Contrast MediaABSTRACT
Hepatic artery pseudoaneurysms have been reported to occur in approximately 1% of cases after metal stenting for malignant biliary obstruction. In contrast, only a few cases have been reported as complications after plastic stenting for benign biliary disease. We report a 61-year-old man with cholangitis who presented with a rare complication of hemobilia after implantation of 7 Fr double pigtail plastic biliary stents. No bleeding was observed approximately one month after biliary stent tube removal. Contrast-enhanced CT scan revealed a circularly enhanced lesion (5 mm in diameter) in the arterial phase at the tip of the previously inserted plastic bile duct stent. Color Doppler ultrasonography enhanced the lesion and detected arterial blood flow inside. He was diagnosed with a hepatic artery pseudoaneurysm. However, he had no risk factors such as prolonged catheterization, severe cholangitis, liver abscess, or long-term steroid use. Superselective transarterial embolization using two metal microcoils was successfully completed without damage to the surrounding liver parenchyma. If hemobilia is suspected after insertion of a plastic bile duct stent, immediate monitoring using contrast-enhanced computed tomography or Doppler ultrasonography is recommended.
Subject(s)
Aneurysm, False , Cholangitis , Hemobilia , Male , Humans , Middle Aged , Aneurysm, False/diagnostic imaging , Aneurysm, False/etiology , Aneurysm, False/therapy , Hemobilia/therapy , Hemobilia/complications , Hepatic Artery/diagnostic imaging , Hepatic Artery/pathology , Incidence , Cholangitis/complications , Stents/adverse effectsABSTRACT
OBJECTIVE: The aim of this study was to assess the utility of the combined use of 3D wheel sampling and deep learning-based reconstruction (DLR) for intracranial high-resolution (HR)-time-of-flight (TOF)-magnetic resonance angiography (MRA) at 3 T. METHODS: This prospective study enrolled 20 patients who underwent head MRI at 3 T, including TOF-MRA. We used 3D wheel sampling called "fast 3D" and DLR for HR-TOF-MRA (spatial resolution, 0.39 × 0.59 × 0.5 mm3) in addition to conventional MRA (spatial resolution, 0.39 × 0.89 × 1 mm3). We compared contrast and contrast-to-noise ratio between the blood vessels (basilar artery and anterior cerebral artery) and brain parenchyma, full width at half maximum in the P3 segment of the posterior cerebral artery among 3 protocols. Two board-certified radiologists evaluated noise, contrast, sharpness, artifact, and overall image quality of 3 protocols. RESULTS: The contrast and contrast-to-noise ratio of fast 3D-HR-MRA with DLR are comparable or higher than those of conventional MRA and fast 3D-HR-MRA without DLR. The full width at half maximum was significantly lower in fast 3D-MRA with and without DLR than in conventional MRA (P = 0.006, P < 0.001). In qualitative evaluation, fast 3D-MRA with DLR had significantly higher sharpness and overall image quality than conventional MRA and fast 3D-MRA without DLR (sharpness: P = 0.021, P = 0.001; overall image quality: P = 0.029, P < 0.001). CONCLUSIONS: The combination of 3D wheel sampling and DLR can improve visualization of arteries in intracranial TOF-MRA.
ABSTRACT
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.
Subject(s)
Amyloidosis , Cardiomyopathies , Humans , Prealbumin , Cardiomyopathies/diagnostic imaging , Technetium Tc 99m Pyrophosphate , Retrospective Studies , Stroke Volume , Ventricular Function, Left , Amyloidosis/diagnostic imaging , Magnetic Resonance Imaging , Edema , BiomarkersABSTRACT
PURPOSE: In this preliminary study, we aimed to evaluate the potential of the generative pre-trained transformer (GPT) series for generating radiology reports from concise imaging findings and compare its performance with radiologist-generated reports. METHODS: This retrospective study involved 28 patients who underwent computed tomography (CT) scans and had a diagnosed disease with typical imaging findings. Radiology reports were generated using GPT-2, GPT-3.5, and GPT-4 based on the patient's age, gender, disease site, and imaging findings. We calculated the top-1, top-5 accuracy, and mean average precision (MAP) of differential diagnoses for GPT-2, GPT-3.5, GPT-4, and radiologists. Two board-certified radiologists evaluated the grammar and readability, image findings, impression, differential diagnosis, and overall quality of all reports using a 4-point scale. RESULTS: Top-1 and Top-5 accuracies for the different diagnoses were highest for radiologists, followed by GPT-4, GPT-3.5, and GPT-2, in that order (Top-1: 1.00, 0.54, 0.54, and 0.21, respectively; Top-5: 1.00, 0.96, 0.89, and 0.54, respectively). There were no significant differences in qualitative scores about grammar and readability, image findings, and overall quality between radiologists and GPT-3.5 or GPT-4 (p > 0.05). However, qualitative scores of the GPT series in impression and differential diagnosis scores were significantly lower than those of radiologists (p < 0.05). CONCLUSIONS: Our preliminary study suggests that GPT-3.5 and GPT-4 have the possibility to generate radiology reports with high readability and reasonable image findings from very short keywords; however, concerns persist regarding the accuracy of impressions and differential diagnoses, thereby requiring verification by radiologists.
Subject(s)
Radiology , Humans , Retrospective Studies , Radiography , Tomography, X-Ray Computed , RadiologistsABSTRACT
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.
Subject(s)
Amyloidosis , Troponin T , Humans , Stroke Volume , Retrospective Studies , Magnetic Resonance Imaging, Cine/methods , Ventricular Function, Left , Myocardium/pathology , Magnetic Resonance Imaging , Amyloidosis/diagnostic imaging , Biomarkers , Predictive Value of TestsABSTRACT
PURPOSE: This study aimed to predict contrast effects in cardiac computed tomography (CT) from CT localizer radiographs using a deep learning (DL) model and to compare the prediction performance of the DL model with that of conventional models based on patients' physical size. METHODS: This retrospective study included 473 (256 men and 217 women) cardiac CT scans between May 2014 and August 2017. We developed and evaluated DL models that predict milligrams of iodine per enhancement of the aorta from CT localizer radiographs. To assess the model performance, we calculated and compared Pearson correlation coefficient ( r ) between the actual iodine dose that was necessary to obtain a contrast effect of 1 HU (iodine dose per contrast effect [IDCE]) and IDCE predicted by DL, body weight, lean body weight, and body surface area of patients. RESULTS: The model was tested on 52 cases for the male group (mean [SD] age, 63.7 ± 11.4) and 44 cases for the female group (mean [SD] age, 69.8 ± 11.6). Correlation coefficients between the actual and predicted IDCE were 0.607 for the male group and 0.412 for the female group, which were higher than the correlation coefficients between the actual IDCE and body weight (0.539 for male, 0.290 for female), lean body weight (0.563 for male, 0.352 for female), and body surface area (0.587 for male, 0.349 for female). CONCLUSIONS: The performance for predicting contrast effects by analyzing CT localizer radiographs with the DL model was at least comparable with conventional methods using the patient's body size, notwithstanding that no additional measurements other than CT localizer radiographs were required.
Subject(s)
Deep Learning , Iodine , Humans , Male , Female , Middle Aged , Aged , Aged, 80 and over , Retrospective Studies , Feasibility Studies , Tomography, X-Ray Computed/methods , Contrast Media , Body WeightABSTRACT
PURPOSE: The aim of this study is to assess the effect of super-resolution deep learning-based reconstruction (SR-DLR), which uses k-space properties, on image quality of intracranial time-of-flight (TOF) magnetic resonance angiography (MRA) at 3 T. METHODS: This retrospective study involved 35 patients who underwent intracranial TOF-MRA using a 3-T MRI system with SR-DLR based on k-space properties in October and November 2022. We reconstructed MRA with SR-DLR (matrix = 1008 × 1008) and MRA without SR-DLR (matrix = 336 × 336). We measured the signal-to-noise ratio (SNR), contrast, and contrast-to-noise ratio (CNR) in the basilar artery (BA) and the anterior cerebral artery (ACA) and the sharpness of the posterior cerebral artery (PCA) using the slope of the signal intensity profile curve at the half-peak points. Two radiologists evaluated image noise, artifacts, contrast, sharpness, and overall image quality of the two image types using a 4-point scale. We compared quantitative and qualitative scores between images with and without SR-DLR using the Wilcoxon signed-rank test. RESULTS: The SNRs, contrasts, and CNRs were all significantly higher in images with SR-DLR than those without SR-DLR (p < 0.001). The slope was significantly greater in images with SR-DLR than those without SR-DLR (p < 0.001). The qualitative scores in MRAs with SR-DLR were all significantly higher than MRAs without SR-DLR (p < 0.001). CONCLUSION: SR-DLR with k-space properties can offer the benefits of increased spatial resolution without the associated drawbacks of longer scan times and reduced SNR and CNR in intracranial MRA.
Subject(s)
Deep Learning , Magnetic Resonance Angiography , Humans , Magnetic Resonance Angiography/methods , Retrospective Studies , Magnetic Resonance Imaging , Signal-To-Noise Ratio , Radiographic Image Interpretation, Computer-Assisted/methodsABSTRACT
PURPOSE: The purpose of this study is to evaluate the influence of super-resolution deep learning-based reconstruction (SR-DLR), which utilizes k-space data, on the quality of images and the quantitation of the apparent diffusion coefficient (ADC) for diffusion-weighted images (DWI) in brain magnetic resonance imaging (MRI). METHODS: A retrospective analysis was performed on 34 patients who had undergone DWI using a 3 T MRI system with SR-DLR reconstruction based on k-space data in August 2022. DWI was reconstructed with SR-DLR (Matrix = 684 × 684) and without SR-DLR (Matrix = 228 × 228). Measurements were made of the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) in white matter (WM) and grey matter (GM), and the full width at half maximum (FWHM) of the septum pellucidum. Two radiologists assessed image noise, contrast, artifacts, blur, and the overall quality of three image types using a four-point scale. Quantitative and qualitative scores between images with and without SR-DLR were compared using the Wilcoxon signed-rank test. RESULTS: Images with SR-DLR showed significantly higher SNRs and CNRs than those without SR-DLR (p < 0.001). No statistically significant variances were found in the apparent diffusion coefficients (ADCs) in WM and GM between images with and without SR-DLR (ADC in WM, p = 0.945; ADC in GM, p = 0.235). Moreover, the FWHM without SR-DLR was notably lower compared to that with SR-DLR (p < 0.001). CONCLUSION: SR-DLR has the potential to augment the quality of DWI in DL MRI scans without significantly impacting ADC quantitation.
ABSTRACT
BACKGROUND: Multiple bilateral lung metastases secondary to hepatocellular carcinoma (HCC) are mainly treated with molecular therapy. Atezolizumab plus bevacizumab can provide excellent long-term survival for patients with a good response. CASE REPORT: A 67-year-old woman underwent right hepatectomy for a primary solitary HCC, 11 cm in diameter, after portal embolization. After 2 years, she developed bilateral lung metastases with >100 nodules, <1 cm in size. She had no viral hepatitis or liver cirrhosis, and the Child-Pugh Grade was A (5 points). Lenvatinib (12 mg daily) was administered as a first-line treatment and continued for 18 months. The best response was stable disease (SD). Subsequently, intravenous atezolizumab (1,200 mg) plus bevacizumab (15 mg/kg) was administered once every three weeks. The best response was SD, which continued for 26 months. After that, cabozantinib treatment was initiated and discontinued after one cycle. Subsequently, dual immune checkpoint inhibitor treatment (durvalumab + tremelimumab) was administered. She has had multiple, but lung-only, metastases over four years. She has been well as an outpatient with the Child-Pugh Grade of A and a performance status of 0. CONCLUSION: Even if atezolizumab plus bevacizumab does not induce a good response, a durable SD could prolong survival in patients with metastatic HCC while maintaining liver function and a good quality-of-life.
Subject(s)
Carcinoma, Hepatocellular , Liver Neoplasms , Lung Neoplasms , Female , Humans , Aged , Carcinoma, Hepatocellular/drug therapy , Bevacizumab , Liver Neoplasms/drug therapy , Lung Neoplasms/drug therapyABSTRACT
OBJECTIVES: To evaluate the effect of super-resolution deep-learning-based reconstruction (SR-DLR) on the image quality of coronary CT angiography (CCTA). METHODS: Forty-one patients who underwent CCTA using a 320-row scanner were retrospectively included. Images were reconstructed with hybrid (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning-based reconstruction (NR-DLR), and SR-DLR algorithms. For each image series, image noise, and contrast-to-noise ratio (CNR) at the left main trunk, right coronary artery, left anterior descending artery, and left circumflex artery were quantified. Blooming artifacts from calcified plaques were measured. Image sharpness, noise magnitude, noise texture, edge smoothness, overall quality, and delineation of the coronary wall, calcified and noncalcified plaques, cardiac muscle, and valves were subjectively ranked on a 4-point scale (1, worst; 4, best). The quantitative parameters and subjective scores were compared among the four reconstructions. Task-based image quality was assessed with a physical evaluation phantom. The detectability index for the objects simulating the coronary lumen, calcified plaques, and noncalcified plaques was calculated from the noise power spectrum (NPS) and task-based transfer function (TTF). RESULTS: SR-DLR yielded significantly lower image noise and blooming artifacts with higher CNR than HIR, MBIR, and NR-DLR (all p < 0.001). The best subjective scores for all the evaluation criteria were attained with SR-DLR, with significant differences from all other reconstructions (p < 0.001). In the phantom study, SR-DLR provided the highest NPS average frequency, TTF50%, and detectability for all task objects. CONCLUSION: SR-DLR considerably improved the subjective and objective image qualities and object detectability of CCTA relative to HIR, MBIR, and NR-DLR algorithms. CLINICAL RELEVANCE STATEMENT: The novel SR-DLR algorithm has the potential to facilitate accurate assessment of coronary artery disease on CCTA by providing excellent image quality in terms of spatial resolution, noise characteristics, and object detectability. KEY POINTS: ⢠SR-DLR designed for CCTA improved image sharpness, noise property, and delineation of cardiac structures with reduced blooming artifacts from calcified plaques relative to HIR, MBIR, and NR-DLR. ⢠In the task-based image-quality assessments, SR-DLR yielded better spatial resolution, noise property, and detectability for objects simulating the coronary lumen, coronary calcifications, and noncalcified plaques than other reconstruction techniques. ⢠The image reconstruction times of SR-DLR were shorter than those of MBIR, potentially serving as a novel standard-of-care reconstruction technique for CCTA performed on a 320-row CT scanner.