Phantom studies demonstrated superior resolution and noise properties for the Sharp and UHR modes relative to the standard Macro mode and patient images demonstrated the potential benefit of these scan modes for clinical practice.
Purpose This work aims to develop a new framework of image quality assessment using deep learning-based model observer (DL-MO) and to validate it in a low-contrast lesion detection task that involves CT images with patient anatomical background. Methods The DL-MO was developed using the transfer learning strategy to incorporate a pretrained deep convolutional neural network (CNN), a partial least square regression discriminant analysis (PLS-DA) model and an internal noise component. The CNN was previously trained to achieve the state-of-the-art classification accuracy over a natural image database. The earlier layers of the CNN were used as a deep feature extractor, with the assumption that similarity exists between the CNN and the human visual system. The PLSR model was used to further engineer the deep feature for the lesion detection task in CT images. The internal noise component was incorporated to model the inefficiency and variability of human observer (HO) performance, and to generate the ultimate DL-MO test statistics. Seven abdominal CT exams were retrospectively collected from the same type of CT scanners. To compare DL-MO with HO, 12 experimental conditions with varying lesion size, lesion contrast, radiation dose, and reconstruction types were generated, each condition with 154 trials. CT images of a real liver metastatic lesion were numerically modified to generate lesion models with four lesion sizes (5, 7, 9, and 11 mm) and three contrast levels (15, 20, and 25 HU). The lesions were inserted into patient liver images using a projection-based method. A validated noise insertion tool was used to synthesize CT exams with 50% and 25% of routine radiation dose level. CT images were reconstructed using the weighted filtered back projection algorithm and an iterative reconstruction algorithm. Four medical physicists performed a two-alternative forced choice (2AFC) detection task (with multislice scrolling viewing mode) on patient images across the 12 experimental conditions. DL-MO was operated on the same datasets. Statistical analyses were performed to evaluate the correlation and agreement between DL-MO and HO. Results A statistically significant positive correlation was observed between DL-MO and HO for the 2AFC low-contrast detection task that involves patient liver background. The corresponding Pearson product moment correlation coefficient was 0.986 [95% confidence interval (0.950, 0.996)]. Bland–Altman agreement analysis did not indicate statistically significant differences. Conclusions The proposed DL-MO is highly correlated with HO in a low-contrast detection task that involves realistic patient liver background. This study demonstrated the potential of the proposed DL-MO to assess image quality directly based on patient images in realistic, clinically relevant CT tasks.
Objective: The aims of this study were to investigate the feasibility of using a universal abdominal acquisition protocol on a photon-counting detector computed tomography (PCD-CT) system and to compare its performance to that of single-energy (SE) and dual-energy (DE) CT using energy-integrating detectors (EIDs). Methods: Iodine inserts of various concentrations and sizes were embedded into different sizes of adult abdominal phantoms. Phantoms were scanned on a research PCD-CT and a clinical EID-CT with SE and DE modes. Virtual monoenergetic images (VMIs) were generated from PCD-CTand DE mode of EID-CT. For each image type and phantom size, contrast-to-noise ratio (CNR) was measured for each iodine insert and the area under the receiver operating characteristic curve (AUC) for iodine detectability was calculated using a channelized Hotelling observer. The optimal energy (in kiloelectrovolt) of VMIs was determined separately as the one with highest CNR and the one with the highest AUC. The PCD-CT VMIs at the optimal energy were then compared with DE VMIs and SE images in terms of CNR and AUC. Results: Virtual monoenergetic image at 50 keV had both the highest CNR and highest AUC for PCD-CT and DECT. For 1.0 mg I/mL iodine and 35 cm phantom, the CNRs of 50 keV VMIs from PCD-CT (2.01 ± 0.67) and DE (1.96 ± 0.52) were significantly higher (P < 0.001, Wilcoxon signed-rank test) than SE images (1.11 ± 0.35). The AUC of PCD-CT (0.98 ± 0.01) was comparable to SE (0.98 ± 0.01), and both were slightly lower than DE (0.99 ± 0.01, P < 0.01, Wilcoxon signed-rank test). A similar trend was observed for other phantom sizes and iodine concentrations. Conclusions: Virtual monoenergetic images at a fixed energy from a universal acquisition protocol on PCD-CT demonstrated higher iodine CNR and comparable iodine detectability than SECT images, and similar performance compared with DE VMIs.
Purpose To develop a convolutional neural network (CNN) that can directly estimate material density distribution from multi‐energy computed tomography (CT) images without performing conventional material decomposition. Methods The proposed CNN (denoted as Incept‐net) followed the general framework of encoder–decoder network, with an assumption that local image information was sufficient for modeling the nonlinear physical process of multi‐energy CT. Incept‐net was implemented with a customized loss function, including an in‐house‐designed image‐gradient‐correlation (IGC) regularizer to improve edge preservation. The network consisted of two types of customized multibranch modules exploiting multiscale feature representation to improve the robustness over local image noise and artifacts. Inserts with various densities of different materials [hydroxyapatite (HA), iodine, a blood–iodine mixture, and fat] were scanned using a research photon‐counting detector (PCD) CT with two energy thresholds and multiple radiation dose levels. The network was trained using phantom image patches only, and tested with different‐configurations of full field‐of‐view phantom and in vivo porcine images. Furthermore, the nominal mass densities of insert materials were used as the labels in CNN training, which potentially provided an implicit mass conservation constraint. The Incept‐net performance was evaluated in terms of image noise, detail preservation, and quantitative accuracy. Its performance was also compared to common material decomposition algorithms including least‐square‐based material decomposition (LS‐MD), total‐variation regularized material decomposition (TV‐MD), and U‐net‐based method. Results Incept‐net improved accuracy of the predicted mass density of basis materials compared with the U‐net, TV‐MD, and LS‐MD: the mean absolute error (MAE) of iodine was 0.66, 1.0, 1.33, and 1.57 mgI/cc for Incept‐net, U‐net, TV‐MD, and LS‐MD, respectively, across all iodine‐present inserts (2.0–24.0 mgI/cc). With the LS‐MD as the baseline, Incept‐net and U‐net achieved comparable noise reduction (both around 95%), both higher than TV‐MD (85%). The proposed IGC regularizer effectively helped both Incept‐net and U‐net to reduce image artifact. Incept‐net closely conserved the total mass densities (i.e., mass conservation constraint) in porcine images, which heuristically validated the quantitative accuracy of its outputs in anatomical background. In general, Incept‐net performance was less dependent on radiation dose levels than the two conventional methods; with approximately 40% less parameters, the Incept‐net achieved relatively improved performance than the comparator U‐net, indicating that performance gain by Incept‐net was not achieved by simply increasing network learning capacity. Conclusion Incept‐net demonstrated superior qualitative image appearance, quantitative accuracy, and lower noise than the conventional methods and less sensitive to dose change. Incept‐net generalized and performed well with unseen image structures and d...
The basic helix-loop-helix transcription factor activating enhancer‑binding protein (AP)-4 has been found to be involved in tumor biology. However, the role of AP-4 in non-small cell lung cancer (NSCLC) has yet to be elucidated. The present study aimed to investigate the role of AP-4 expression in NSCLC. AP-4 expression as analyzed using quantitative polymerase chain reaction and western blot analyses of 42 fresh NSCLC samples and matched adjacent noncancerous tissues. Immunohistochemistry was performed to assess the clinical significance of AP-4 expression in tumor tissues of NSCLC patients (n=240) and matched adjacent noncancerous tissues. The correlation between AP-4 expression, clinicopathological features and clinical outcome were investigated. AP-4 expression was found to be increased in the NSCLC samples at the gene and protein levels compared with the matched adjacent noncancerous tissues. Immunohistochemistry revealed that the positive expression rates of AP-4 in the 240 NSCLC samples and the matched adjacent noncancerous tissues were 48.3 and 5.8%, respectively. Positive AP-4 expression was found to be significantly associated with the tumor, nodes and metastasis stage and nodal status. Furthermore, patients with NSCLC tumors expressing AP-4 were observed to have a poorer prognosis than those without AP-4 expression. Multivariate analysis revealed that AP-4 expression was an independent prognostic marker (hazard ratio, 2.543; 95% confidence interval, 1.18-5.016; P=0.016) in NSCLC. Thus, positive AP-4 expression may be a potential prognostic marker for NSCLC.
Purpose: Task-based image quality assessment using model observers (MOs) is an effective approach to radiation dose and scanning protocol optimization in computed tomography (CT) imaging, once the correlation between MOs and radiologists can be established in well-defined clinically relevant tasks. Conventional MO studies were typically simplified to detection, classification, or localization tasks using tissue-mimicking phantoms, as traditional MOs cannot be readily used in complex anatomical background. However, anatomical variability can affect human diagnostic performance.Approach: To address this challenge, we developed a deep-learning-based MO (DL-MO) for localization tasks and validated in a lung nodule detection task, using previously validated projection-based lesion-/noise-insertion techniques. The DL-MO performance was compared with 4 radiologist readers over 12 experimental conditions, involving varying radiation dose levels, nodule sizes, nodule types, and reconstruction types. Each condition consisted of 100 trials (i.e., 30 images per trial) generated from a patient cohort of 50 cases. DL-MO was trained using small image volume-of-interests extracted across the entire volume of training cases. For each testing trial, the nodule searching of DL-MO was confined to a 3-mm thick volume to improve computational efficiency, and radiologist readers were tasked to review the entire volume.Results: A strong correlation between DL-MO and human readers was observed (Pearson's correlation coefficient: 0.980 with a 95% confidence interval of [0.924, 0.994]). The averaged performance bias between DL-MO and human readers was 0.57%. Conclusion:The experimental results indicated the potential of using the proposed DL-MO for diagnostic image quality assessment in realistic chest CT tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.