Automated assessment of task-based performance of digital mammography and tomosynthesis systems using an anthropomorphic breast phantom and deep learning-based scoring.

Purpose: Conventional metrics used for assessing digital mammography (DM) and digital breast tomosynthesis (DBT) image quality, including noise, spatial resolution, and detective quantum efficiency, do not necessarily predict how well the system will perform in a clinical task. A number of existing phantom-based methods have their own limitations, such as unrealistic uniform backgrounds, subjective scoring using humans, and regular signal patterns unrepresentative of common clinical findings. We attempted to address this problem with a realistic breast phantom with random hydroxyapatite microcalcifications and semi-automated deep learning-based image scoring. Our goal was to develop a methodology for objective task-based assessment of image quality for tomosynthesis and DM systems, which includes an anthropomorphic phantom, a detection task (microcalcification clusters), and automated performance evaluation using a convolutional neural network. Approach: Experimental 2D and pseudo-3D mammograms of an anthropomorphic inkjet-printed breast phantom with inserted microcalcification clusters were collected on clinical mammography systems to train a signal-present/signal-absent image classifier based on Resnet-18 architecture. In a separate validation study using simulations, this Resnet-18 classifier was shown to approach the performance of an ideal observer. Microcalcification detection performance was evaluated as a function of four dose levels using receiver operating characteristic (ROC) analysis [i.e., area under the ROC curve (AUC)]. To demonstrate the use of this evaluation approach for assessing different technologies, the method was applied to two different mammography systems, as well as to mammograms with re-binned pixels emulating a lower-resolution X-ray detector. Results: Microcalcification detectability, as assessed by the deep learning classifier, was observed to vary with the exposure incident on the breast phantom for both DM and tomosynthesis. At full dose, experimental AUC was 0.96 (for DM) and 0.95 (for DBT), whereas at half dose, it dropped to 0.85 and 0.71, respectively. AUC performance on DM was significantly decreased with an effective larger pixel size obtained with re-binning. The task-based assessment approach also showed the superiority of a newer mammography system compared with an older system. Conclusions: An objective task-based methodology for assessing the image quality of mammography and tomosynthesis systems is proposed. Possible uses for this tool could be quality control, acceptance, and constancy testing, assessing the safety and effectiveness of new technology for regulatory submissions, and system optimization. The results from this study showed that the proposed evaluation method using a deep learning model observer can track differences in microcalcification signal detectability with varied exposure conditions.

Evaluating Machine Learning-Based MRI Reconstruction Using Digital Image Quality Phantoms.

Quantitative and objective evaluation tools are essential for assessing the performance of machine learning (ML)-based magnetic resonance imaging (MRI) reconstruction methods. However, the commonly used fidelity metrics, such as mean squared error (MSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR), often fail to capture fundamental and clinically relevant MR image quality aspects. To address this, we propose evaluation of ML-based MRI reconstruction using digital image quality phantoms and automated evaluation methods. Our phantoms are based upon the American College of Radiology (ACR) large physical phantom but created in k-space to simulate their MR images, and they can vary in object size, signal-to-noise ratio, resolution, and image contrast. Our evaluation pipeline incorporates evaluation metrics of geometric accuracy, intensity uniformity, percentage ghosting, sharpness, signal-to-noise ratio, resolution, and low-contrast detectability. We demonstrate the utility of our proposed pipeline by assessing an example ML-based reconstruction model across various training and testing scenarios. The performance results indicate that training data acquired with a lower undersampling factor and coils of larger anatomical coverage yield a better performing model. The comprehensive and standardized pipeline introduced in this study can help to facilitate a better understanding of the performance and guide future development and advancement of ML-based reconstruction algorithms.

Evaluating the Quality of Serial EM Sections with Deep Learning.

Automated image acquisition can significantly improve the throughput of serial section scanning electron microscopy (ssSEM). However, image quality can vary from image to image depending on autofocusing and beam stigmation. Automatically evaluating the quality of images is, therefore, important for efficiently generating high-quality serial section scanning electron microscopy (ssSEM) datasets. We tested several convolutional neural networks for their ability to reproduce user-generated evaluations of ssSEM image quality. We found that a modification of ResNet-50 that we term quality evaluation Network (QEN) reliably predicts user-generated quality scores. Running QEN in parallel to ssSEM image acquisition therefore allows users to quickly identify imaging problems and flag images for retaking. We have publicly shared the Python code for evaluating images with QEN, the code for training QEN, and the training dataset.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images.

Purpose: The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Approach: Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. Results: The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Conclusions: Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

Daily dose evaluation based on corrected CBCTs for breast cancer patients: accuracy of dose and complication risk assessment.

OBJECTIVES: The goal of this study is to validate different CBCT correction methods to select the superior method that can be used for dose evaluation in breast cancer patients with large anatomical changes treated with photon irradiation. MATERIALS AND METHOD: Seventy-six breast cancer patients treated with a partial VMAT photon technique (70% conformal, 30% VMAT) were included in this study. All patients showed at least a 5 mm variation (swelling or shrinkage) of the breast on the CBCT compared to the planning-CT (pCT) and had a repeat-CT (rCT) for dose evaluation acquired within 3 days of this CBCT. The original CBCT was corrected using four methods: (1) HU-override correction (CBCTHU), (2) analytical correction and conversion (CBCTCC), (3) deep learning (DL) correction (CTDL) and (4) virtual correction (CTV). Image quality evaluation consisted of calculating the mean absolute error (MAE) and mean error (ME) within the whole breast clinical target volume (CTV) and the field of view of the CBCT minus 2 cm (CBCT-ROI) with respect to the rCT. The dose was calculated on all image sets using the clinical treatment plan for dose and gamma passing rate analysis. RESULTS: The MAE of the CBCT-ROI was below 66 HU for all corrected CBCTs, except for the CBCTHU with a MAE of 142 HU. No significant dose differences were observed in the CTV regions in the CBCTCC, CTDL and CTv. Only the CBCTHU deviated significantly (p < 0.01) resulting in 1.7% (± 1.1%) average dose deviation. Gamma passing rates were > 95% for 2%/2 mm for all corrected CBCTs. CONCLUSION: The analytical correction and conversion, deep learning correction and virtual correction methods can be applied for an accurate CBCT correction that can be used for dose evaluation during the course of photon radiotherapy of breast cancer patients.

Ideal-Observer Computation with anthropomorphic phantoms using Markov chain Monte Carlo.

In medical imaging, it is widely recognized that image quality should be objectively evaluated based on performance in clinical tasks. To evaluate performance in signal-detection tasks, the ideal observer (IO) is optimal but also challenging to compute in clinically realistic settings. Markov Chain Monte Carlo (MCMC)-based strategies have demonstrated the ability to compute the IO using pre-computed projections of an anatomical database. To evaluate image quality in clinically realistic scenarios, the observer performance should be measured for a realistic patient distribution. This implies that the anatomical database should also be derived from a realistic population. In this manuscript, we propose to advance the MCMC-based approach towards achieving these goals. We then use the proposed approach to study the effect of anatomical database size on IO computation for the task of detecting perfusion defects in simulated myocardial perfusion SPECT images. Our preliminary results provide evidence that the size of the anatomical database affects the computation of the IO.

Relationship between the visual evaluation of pathology visibility and the physical measure of low contrast detail detectability in neonatal chest radiography.

INTRODUCTION: The detectability of low contrast detail (LCD) is a method used to assess image quality (IQ) in neonatal radiography; however, there is a lack of data on the relationship between LCD detectability and visual IQ. The study aims at investigating the relationship between the LCD detectability and visual IQ and pathology visibility (PV). METHODS: Several acquisition parameters were employed to obtain a group of images from a neonatal Gammex chest phantom. Three observers applied relative visual grading analysis (VGA) for assessing the IQ and PV. A simulated pneumothorax visibility (PNV) and simulated hyaline membrane disease visibility (HMV) represented PV. Next, a CDRAD 2.0 phantom was radiographed utilising the same acquisition protocols, and several paired images were obtained. With the use of CDRAD analyser software, the detectability of LCD was assessed and expressed by an image quality figure inverse (IQFiinv) metric. The correlation between the IQFinv and each of IQ, PNV and HMV was examined. RESULTS: The physical measure (IQFinv) and the visual assessment of IQ were shown to be strongly correlated (r = 0.95; p < 0.001). Using Pearson's correlation, the IQFinv, PNV, and HMV were found to be strongly correlated (r = 0.94; p < 0.001) and (r = 0.92; p < 0.001), correspondingly. CONCLUSION: Results of the study show that physical measures of LCD detectability utilising the CDRAD 2.0 phantom is strongly corelated with visual IQ and PV (PNV and HMV) and can be used to evaluate IQ when undertaking neonatal chest radiography (CXR). IMPLICATIONS FOR PRACTICE: This study establishes the feasibility of utilising the physical measure (IQFinv) and the CDRAD 2.0 phantom in routine quality assurance and neonatal CXR optimisation studies.

Multiresolution residual deep neural network for improving pelvic CBCT image quality.

PURPOSE: Cone-beam computed tomography (CBCT) is frequently used for accurate image-guided radiation therapy. However, the poor CBCT image quality prevents its further clinical use. Thus, it is important to improve the HU accuracy and structure preservation of CBCT images. METHODS: In this study, we proposed a novel method to generate synthetic CT (sCT) images from CBCT images. A multiresolution residual deep neural network (RDNN) was adopted for image regression from CBCT images to planning CT (pCT) images. At the coarse level, RDNN was first trained with a large amount of lower resolution images, which can make the network focus on coarse information and prevent overfitting problems. More fine information was obtained gradually by fine-tuning the coarse model using fewer number of higher resolution images. Our model was optimized by using aligned pCT and CBCT image pairs of a particular body region of 153 prostate cancer patients treated in our hospital (120 for training and 33 for testing). Five-fold cross-validation was used to tune the hyperparameters and the testing data were used to evaluate the performance of the final models. RESULTS: The mean absolute error (MAE) between CBCT and pCT on the testing data was 352.56 HU, while the MAE between the sCT and pCT images was 52.18 HU for our proposed multiresolution RDNN model, which reduced the MAE by 85.20% (p < 0.01). In addition, the average structural similarity index measure between the sCT and CBCT was 19.64% (p = 0.01) higher than that of pCT and CBCT. CONCLUSIONS: The sCT images generated using our proposed multiresolution RDNN have higher HU accuracy and structural fidelity, which may promote the further applications of CBCT images in the clinic for structure segmentation, dose calculation, and adaptive radiotherapy planning.

Comparison of lung image quality between CT Ark and Brilliance 64 CT during COVID-19.

AIM: This study is to compare the lung image quality between shelter hospital CT (CT Ark) and ordinary CT scans (Brilliance 64) scans. METHODS: The patients who received scans with CT Ark or Brilliance 64 CT were enrolled. Their lung images were divided into two groups according to the scanner. The objective evaluation methods of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were used. The subjective evaluation methods including the evaluation of the fine structure under the lung window and the evaluation of the general structure under the mediastinum window were compared. Kappa method was used to assess the reliability of the subjective evaluation. The subjective evaluation results were analyzed using the Wilcoxon rank sum test. SNR and CNR were tested using independent sample t tests. RESULTS: There was no statistical difference in somatotype of enrolled subjects. The Kappa value between the two observers was between 0.68 and 0.81, indicating good consistency. For subjective evaluation results, the rank sum test P value of fine structure evaluation and general structure evaluation by the two observers was ≥ 0.05. For objective evaluation results, SNR and CNR between the two CT scanners were significantly different (P<0.05). Notably, the absolute values ​​of SNR and CNR of the CT Ark were larger than Brilliance 64 CT scanner. CONCLUSION: CT Ark is fully capable of scanning the lungs of the COVID-19 patients during the epidemic in the shelter hospital.

Impact of novel deep learning image reconstruction algorithm on diagnosis of contrast-enhanced liver computed tomography imaging: Comparing to adaptive statistical iterative reconstruction algorithm.

OBJECTIVE: To assess clinical application of applying deep learning image reconstruction (DLIR) algorithm to contrast-enhanced portal venous phase liver computed tomography (CT) for improving image quality and lesions detection rate compared with using adaptive statistical iterative reconstruction (ASIR-V) algorithm under routine dose. METHODS: The raw data from 42 consecutive patients who underwent contrast-enhanced portal venous phase liver CT were reconstructed using three strength levels of DLIRs (low [DL-L]; medium [DL-M]; high [DL-H]) and two levels of ASIR-V (30%[AV-30]; 70%[AV-70]). Objective image parameters, including noise, signal-to-noise (SNR), and the contrast-to-noise ratio (CNR) relative to muscle, as well as subjective parameters, including noise, artifact, hepatic vein-clarity, index lesion-clarity, and overall scores were compared pairwise. For the lesions detection rate, the five reconstructions in patients who underwent subsequent contrast-enhanced magnetic resonance imaging (MRI) examinations were compared. RESULTS: For objective parameters, DL-H exhibited superior image quality of lower noise and higher SNR than AV-30 and AV-70 (all P < 0.05). CNR was not statistically different between AV-70, DL-M, and DL-H (all P > 0.05). In both objective and subjective parameters, only image noise was statistically reduced as the strength of DLIR increased compared with ASIR-V (all P < 0.05). Regarding the lesions detection rate, a total of 45 lesions were detected by MRI examination and all five reconstructions exhibited similar lesion-detection rate (25/45, 55.6%). CONCLUSION: Compared with AV-30 and AV 70, DLIR leads to better image quality with equal lesion detection rate for liver CT imaging under routine dose.

Evaluation of 360° Image Projection Formats; Comparing Format Conversion Distortion Using Objective Quality Metrics.

Currently available 360° cameras normally capture several images covering a scene in all directions around a shooting point. The captured images are spherical in nature and are mapped to a two-dimensional plane using various projection methods. Many projection formats have been proposed for 360° videos. However, standards for a quality assessment of 360° images are limited. In this paper, various projection formats are compared to explore the problem of distortion caused by a mapping operation, which has been a considerable challenge in recent approaches. The performances of various projection formats, including equi-rectangular, equal-area, cylindrical, cube-map, and their modified versions, are evaluated based on the conversion causing the least amount of distortion when the format is changed. The evaluation is conducted using sample images selected based on several attributes that determine the perceptual image quality. The evaluation results based on the objective quality metrics have proved that the hybrid equi-angular cube-map format is the most appropriate solution as a common format in 360° image services for where format conversions are frequently demanded. This study presents findings ranking these formats that are useful for identifying the best image format for a future standard.

Validation of a candidate instrument to assess image quality in digital mammography using ROC analysis.

PURPOSE: To validate a candidate instrument, to be used by different professionals to assess image quality in digital mammography (DM), against detection performance results. METHODS: A receiver operating characteristics (ROC) study was conducted to assess the detection performance in DM images with four different image quality levels due to different quality issues. Fourteen expert breast radiologists from five countries assessed a set of 80 DM cases, containing 60 lesions (40 cancers, 20 benign findings) and 20 normal cases. A visual grading analysis (VGA) study using a previously-described candidate instrument was conducted to evaluate a subset of 25 of the images used in the ROC study. Eight radiologists that had participated in the ROC study, and seven expert breast-imaging physicists, evaluated this subset. The VGA score (VGAS) and the ROC and visual grading characteristics (VGC) areas under the curve (AUCROC and AUCVGC) were compared. RESULTS: No large differences in image quality among the four levels were detected by either ROC or VGA studies. However, the ranking of the four levels was consistent: level 1 (partial AUCROC: 0.070, VGAS: 6.77) performed better than levels 2 (0.066, 6.15), 3 (0.061, 5.82), and 4 (0.062, 5.37). Similarity between radiologists' and physicists' assessments was found (average VGAS difference of 10 %). CONCLUSIONS: The results from the candidate instrument were found to correlate with those from ROC analysis, when used by either observer group. Therefore, it may be used by different professionals, such as radiologists, radiographers, and physicists, to assess clinically-relevant image quality variations in DM.

Development and content validity evaluation of a candidate instrument to assess image quality in digital mammography: A mixed-method study.

PURPOSE: To develop a candidate instrument to assess image quality in digital mammography, by identifying clinically relevant features in images that are affected by lower image quality. METHODS: Interviews with fifteen expert breast radiologists from five countries were conducted and analysed by using adapted directed content analysis. During these interviews, 45 mammographic cases, containing 44 lesions (30 cancers, 14 benign findings), and 5 normal cases, were shown with varying image quality. The interviews were performed to identify the structures from breast tissue and lesions relevant for image interpretation, and to investigate how image quality affected the visibility of those structures. The interview findings were used to develop tentative items, which were evaluated in terms of wording, understandability, and ambiguity with expert breast radiologists. The relevance of the tentative items was evaluated using the content validity index (CVI) and modified kappa index (k*). RESULTS: Twelve content areas, representing the content of image quality in digital mammography, emerged from the interviews and were converted into 29 tentative items. Fourteen of these items demonstrated excellent CVI ≥ 0.78 (k* > 0.74), one showed good CVI < 0.78 (0.60 ≤ k* ≤ 0.74), while fourteen were of fair or poor CVI < 0.78 (k* ≤ 0.59). In total, nine items were deleted and five were revised or combined resulting in 18 items. CONCLUSIONS: By following a mixed-method methodology, a candidate instrument was developed that may be used to characterise the clinically-relevant impact that image quality variations can have on digital mammography.

Image quality evaluation of in-treatment four-dimensional cone-beam computed tomography in volumetric-modulated arc therapy for stereotactic body radiation therapy.

In this study, the image quality of in-treatment four-dimensional cone-beam computed tomography (In-4D-CBCT) obtained with various prescription doses (PDs) were quantitatively evaluated in volumetric-modulated arc therapy (VMAT) for stereotactic body radiation therapy (SBRT) of the lungs and liver. To assess image quality, we used a dynamic thorax phantom and three-dimensional (3D) abdominal phantom; In-4D-CBCT images were acquired with various PDs (from 5 to 12 Gy). The In-4D-CBCT with various PDs were compared with the reference images (pre-4D-CBCT). The image quality was evaluated using the signal-to-noise ratio (SNR), the contrast-to-noise ratio (CNR), and the Dice similarity coefficient (DSC). The fiducial marker positions with various PDs were compared with those of the reference images. For the dynamic thorax phantom, the difference between pre- and In-4D-CBCT in terms of SNR and CNR decreased, as the PD increased from 6 to 12 Gy. The median DSC ranged from 0.7 to 0.74, and showed good similarity. For the 3D abdominal phantom, the difference between pre- and In-4D-CBCT in terms of SNR and CNR decreased as the PD increased from 5 to 6 Gy; conversely, it increased as the PD increased from 7 to 8 Gy. The fiducial marker positions were within 1.0 mm for all PDs. We concluded that the image quality of In-4D-CBCT degraded compared with the reference image; however, it was sufficiently accurate for assessing the intra-fractional tumor position in VMAT for SBRT of the lungs and liver both in terms of the target volume similarity and accuracy of the fiducial marker position.

Is It Better to Enter a Volume CT Dose Index Value before or after Scan Range Adjustment for Radiation Dose Optimization of Pediatric Cardiothoracic CT with Tube Current Modulation?

Objective: To determine whether the body size-adapted volume computed tomography (CT) dose index (CTDvol) in pediatric cardiothoracic CT with tube current modulation is better to be entered before or after scan range adjustment for radiation dose optimization. Materials and Methods: In 83 patients, cardiothoracic CT with tube current modulation was performed with the body size-adapted CTDIvol entered after (group 1, n = 42) or before (group 2, n = 41) scan range adjustment. Patient-related, radiation dose, and image quality parameters were compared and correlated between the two groups. Results: The CTDIvol after the CT scan in group 1 was significantly higher than that in group 2 (1.7 ± 0.1 mGy vs. 1.4 ± 0.3 mGy; p < 0.0001). Image noise (4.6 ± 0.5 Hounsfield units [HU] vs. 4.5 ± 0.7 HU) and image quality (1.5 ± 0.6 vs. 1.5 ± 0.6) showed no significant differences between the two (p > 0.05). In both groups, all patient-related parameters, except body density, showed positive correlations (r = 0.49-0.94; p < 0.01) with the CTDIvol before and after the CT scan. The CTDIvol after CT scan showed modest positive correlation (r = 0.49; p ≤ 0.001) with image noise in group 1 but no significant correlation (p > 0.05) in group 2. Conclusion: In pediatric cardiothoracic CT with tube current modulation, the CTDIvol entered before scan range adjustment provides a significant dose reduction (18%) with comparable image quality compared with that entered after scan range adjustment.

Quantitative Image Quality and Histogram-Based Evaluations of an Iterative Reconstruction Algorithm at Low-to-Ultralow Radiation Dose Levels: A Phantom Study in Chest CT.

Objective: To describe the quantitative image quality and histogram-based evaluation of an iterative reconstruction (IR) algorithm in chest computed tomography (CT) scans at low-to-ultralow CT radiation dose levels. Materials and Methods: In an adult anthropomorphic phantom, chest CT scans were performed with 128-section dual-source CT at 70, 80, 100, 120, and 140 kVp, and the reference (3.4 mGy in volume CT Dose Index [CTDIvol]), 30%-, 60%-, and 90%-reduced radiation dose levels (2.4, 1.4, and 0.3 mGy). The CT images were reconstructed by using filtered back projection (FBP) algorithms and IR algorithm with strengths 1, 3, and 5. Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were statistically compared between different dose levels, tube voltages, and reconstruction algorithms. Moreover, histograms of subtraction images before and after standardization in x- and y-axes were visually compared. Results: Compared with FBP images, IR images with strengths 1, 3, and 5 demonstrated image noise reduction up to 49.1%, SNR increase up to 100.7%, and CNR increase up to 67.3%. Noteworthy image quality degradations on IR images including a 184.9% increase in image noise, 63.0% decrease in SNR, and 51.3% decrease in CNR, and were shown between 60% and 90% reduced levels of radiation dose (p < 0.0001). Subtraction histograms between FBP and IR images showed progressively increased dispersion with increased IR strength and increased dose reduction. After standardization, the histograms appeared deviated and ragged between FBP images and IR images with strength 3 or 5, but almost normally-distributed between FBP images and IR images with strength 1. Conclusion: The IR algorithm may be used to save radiation doses without substantial image quality degradation in chest CT scanning of the adult anthropomorphic phantom, down to approximately 1.4 mGy in CTDIvol (60% reduced dose).

Background Registration-Based Adaptive Noise Filtering of LWIR/MWIR Imaging Sensors for UAV Applications.

Unmanned aerial vehicles (UAVs) are equipped with optical systems including an infrared (IR) camera such as electro-optical IR (EO/IR), target acquisition and designation sights (TADS), or forward looking IR (FLIR). However, images obtained from IR cameras are subject to noise such as dead pixels, lines, and fixed pattern noise. Nonuniformity correction (NUC) is a widely employed method to reduce noise in IR images, but it has limitations in removing noise that occurs during operation. Methods have been proposed to overcome the limitations of the NUC method, such as two-point correction (TPC) and scene-based NUC (SBNUC). However, these methods still suffer from unfixed pattern noise. In this paper, a background registration-based adaptive noise filtering (BRANF) method is proposed to overcome the limitations of conventional methods. The proposed BRANF method utilizes background registration processing and robust principle component analysis (RPCA). In addition, image quality verification methods are proposed that can measure the noise filtering performance quantitatively without ground truth images. Experiments were performed for performance verification with middle wave infrared (MWIR) and long wave infrared (LWIR) images obtained from practical military optical systems. As a result, it is found that the image quality improvement rate of BRANF is 30% higher than that of conventional NUC.

Development of a myocardial phantom and analysis system toward the standardization of myocardial SPECT image across institutions.

OBJECTIVE: We developed a novel myocardial phantom and analysis program to standardize using a quantitative index to objectively evaluate the image quality. We aimed to reveal whether our proposed phantom and analysis program are suitable for image standardization. METHODS: An evaluation system of myocardial image based on technical grounds (EMIT) phantom was developed to standardize the image quality of myocardial SPECT and was constructed with the lung and myocardium in the thorax phantom; the myocardial phantom included five normal areas and eight defective areas with four defects in size (5, 10, 15, and 20 mm) and four defects in thickness (10, 7.5, 5, and 2.5 mm). Therefore, this phantom was appropriate to simultaneously simulate eight different defects and normal myocardium. The %rate value, calculated using the region of interest method, and the %count value, calculated from the profile method, were automatically analyzed to evaluate myocardial defects. The phantom was validated using difference in count levels and filter parameters compared with those in previously reported models. RESULTS: The average %count of eight defects by 0.3, 0.4, 0.5, and 0.6 cycles/cm were 56.8, 47.4, 44.3, and 43.4 %, respectively, whereas the %count for 0.3 cycles/cm was significantly higher than that for 0.5 and 0.6 cycles/cm. The uniformity between full- and half-time images was 16.5 ± 4.2 and 18.7 ± 5.5 % for integral uniformity and 3.4 ± 1.2 and 3.4 ± 1.3 % for differential uniformity, respectively, revealing a significant difference in integral uniformity between the two acquisition times. Visual differences in defects were evident in full-time images between 0.30 and 0.50 cycles/cm, and defect detectability of the myocardial image at 0.30 cycles/cm was poor. Normal myocardial thickness widened in comparison with images at 0.50 cycles/cm. Compared with full-time myocardial image at the same cut-off frequency, the half-time myocardial image demonstrated inhomogeneous distribution and thickness of the normal myocardium. CONCLUSION: We developed a new phantom and program to standard image quality among multicenter for myocardial SPECT. The EMIT phantom and quantitative indices were useful for evaluating image quality. The physical characteristics of the image quality, including defects and uniformity, were properly measured by this method.

Metal artifact reduction and image quality evaluation of lumbar spine CT images using metal sinogram segmentation.

Metal artifacts often appear in the images of computed tomography (CT) imaging. In the case of lumbar spine CT images, artifacts disturb the images of critical organs. These artifacts can affect the diagnosis, treatment, and follow up care of the patient. One approach to metal artifact reduction is the sinogram completion method. A mixed-variable thresholding (MixVT) technique to identify the suitable metal sinogram is proposed. This technique consists of four steps: 1) identify the metal objects in the image by using k-mean clustering with the soft cluster assignment, 2) transform the image by separating it into two sinograms, one of which is the sinogram of the metal object, with the surrounding tissue shown in the second sinogram. The boundary of the metal sinogram is then found by the MixVT technique, 3) estimate the new value of the missing data in the metal sinogram by linear interpolation from the surrounding tissue sinogram, 4) reconstruct a modified sinogram by using filtered back-projection and complete the image by adding back the image of the metal object into the reconstructed image to form the complete image. The quantitative and clinical image quality evaluation of our proposed technique demonstrated a significant improvement in image clarity and detail, which enhances the effectiveness of diagnosis and treatment.

Referenceless image quality evaluation for whole slide imaging.

OBJECTIVE: The image quality in whole slide imaging (WSI) is one of the most important issues for the practical use of WSI scanners. In this paper, we proposed an image quality evaluation method for scanned slide images in which no reference image is required. METHODS: While most of the conventional methods for no-reference evaluation only deal with one image degradation at a time, the proposed method is capable of assessing both blur and noise by using an evaluation index which is calculated using the sharpness and noise information of the images in a given training data set by linear regression analysis. The linear regression coefficients can be determined in two ways depending on the purpose of the evaluation. For objective quality evaluation, the coefficients are determined using a reference image with mean square error as the objective value in the analysis. On the other hand, for subjective quality evaluation, the subjective scores given by human observers are used as the objective values in the analysis. The predictive linear regression models for the objective and subjective image quality evaluations, which were constructed using training images, were then used on test data wherein the calculated objective values are construed as the evaluation indices. RESULTS: The results of our experiments confirmed the effectiveness of the proposed image quality evaluation method in both objective and subjective image quality measurements. Finally, we demonstrated the application of the proposed evaluation method to the WSI image quality assessment and automatic rescanning in the WSI scanner.