scispace - formally typeset
Search or ask a question

Showing papers in "Journal of medical imaging in 2015"


Journal ArticleDOI
TL;DR: Improvement on the prediction performance by combining genomics and radiomics data was not found to be statistically significant, most likely due to the small sample size of 91 cancer cases with 38 radiomic features and 144 genomic features.
Abstract: Genomic and radiomic imaging profiles of invasive breast carcinomas from The Cancer Genome Atlas and The Cancer Imaging Archive were integrated and a comprehensive analysis was conducted to predict clinical outcomes using the radiogenomic features. Variable selection via LASSO and logistic regression were used to select the most-predictive radiogenomic features for the clinical phenotypes, including pathological stage, lymph node metastasis, and status of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Cross-validation with receiver operating characteristic (ROC) analysis was performed and the area under the ROC curve (AUC) was employed as the prediction metric. Higher AUCs were obtained in the prediction of pathological stage, ER, and PR status than for lymph node metastasis and HER2 status. Overall, the prediction performances by genomics alone, radiomics alone, and combined radiogenomics features showed statistically significant correlations with clinical outcomes; however, improvement on the prediction performance by combining genomics and radiomics data was not found to be statistically significant, most likely due to the small sample size of 91 cancer cases with 38 radiomic features and 144 genomic features.

126 citations


Journal ArticleDOI
TL;DR: In this paper, the effects of stochastic image acquisition noise on heterogeneity metrics such as textural features are poorly understood and a simulation study was performed by generating 50 statistically independent PET images of the NEMA IQ phantom with realistic noise and resolution properties.
Abstract: Image heterogeneity metrics such as textural features are an active area of research for evaluating clinical outcomes with positron emission tomography (PET) imaging and other modalities. However, the effects of stochastic image acquisition noise on these metrics are poorly understood. We performed a simulation study by generating 50 statistically independent PET images of the NEMA IQ phantom with realistic noise and resolution properties. Heterogeneity metrics based on gray-level intensity histograms, co-occurrence matrices, neighborhood difference matrices, and zone size matrices were evaluated within regions of interest surrounding the lesions. The impact of stochastic variability was evaluated with percent difference from the mean of the 50 realizations, coefficient of variation and estimated sample size for clinical trials. Additionally, sensitivity studies were performed to simulate the effects of patient size and image reconstruction method on the quantitative performance of these metrics. Complex trends in variability were revealed as a function of textural feature, lesion size, patient size, and reconstruction parameters. In conclusion, the sensitivity of PET textural features to normal stochastic image variation and imaging parameters can be large and is feature-dependent. Standards are needed to ensure that prospective studies that incorporate textural features are properly designed to measure true effects that may impact clinical outcomes.

118 citations


Journal ArticleDOI
TL;DR: A segmentation framework for fully automatic segmentation of knee MRI that combines multiatlas rigid registration with voxel classification and was trained on manual segmentations with varying configurations of bones, cartilages, and menisci demonstrated precision and accuracy comparable to manual segmentation.
Abstract: Clinical studies including thousands of magnetic resonance imaging (MRI) scans offer potential for pathogenesis research in osteoarthritis. However, comprehensive quantification of all bone, cartilage, and meniscus compartments is challenging. We propose a segmentation framework for fully automatic segmentation of knee MRI. The framework combines multiatlas rigid registration with voxel classification and was trained on manual segmentations with varying configurations of bones, cartilages, and menisci. The validation included high- and low-field knee MRI cohorts from the Center for Clinical and Basic Research, the osteoarthritis initiative (QAI), and the segmentation of knee images10 (SKI10) challenge. In total, 1907 knee MRIs were segmented during the evaluation. No segmentations were excluded. Our resulting OAI cartilage volume scores are available upon request. The precision and accuracy performances matched manual reader re-segmentation well. The cartilage volume scan-rescan precision was 4.9% (RMS CV). The Dice volume overlaps in the medial/lateral tibial/femoral cartilage compartments were 0.80 to 0.87. The correlations with volumes from independent methods were between 0.90 and 0.96 on the OAI scans. Thus, the framework demonstrated precision and accuracy comparable to manual segmentations. Finally, our method placed second for cartilage segmentation in the SKI10 challenge. The comprehensive validation suggested that automatic segmentation is appropriate for cohorts with thousands of scans.

101 citations


Journal ArticleDOI
TL;DR: A robust automated algorithm for computer detection of coronary artery lesions by machine learning techniques that shows promising results in the automated detection of obstructive and nonobstructive lesions from CTA.
Abstract: Visual identification of coronary arterial lesion from three-dimensional coronary computed tomography angiography (CTA) remains challenging. We aimed to develop a robust automated algorithm for computer detection of coronary artery lesions by machine learning techniques. A structured learning technique is proposed to detect all coronary arterial lesions with stenosis ≥25%. Our algorithm consists of two stages: (1) two independent base decisions indicating the existence of lesions in each arterial segment and (b) the final decision made by combining the base decisions. One of the base decisions is the support vector machine (SVM) based learning algorithm, which divides each artery into small volume patches and integrates several quantitative geometric and shape features for arterial lesions in each small volume patch by SVM algorithm. The other base decision is the formula-based analytic method. The final decision in the first stage applies SVM-based decision fusion to combine the two base decisions in the second stage. The proposed algorithm was applied to 42 CTA patient datasets, acquired with dual-source CT, where 21 datasets had 45 lesions with stenosis ≥25%. Visual identification of lesions with stenosis ≥25% by three expert readers, using consensus reading, was considered as a reference standard. Our method performed with high sensitivity (93%), specificity (95%), and accuracy (94%), with receiver operator characteristic area under the curve of 0.94. The proposed algorithm shows promising results in the automated detection of obstructive and nonobstructive lesions from CTA.

69 citations


Journal ArticleDOI
TL;DR: Challenges, in the context of medical imaging, are valuable in that they allow for a direct comparison of different algorithms designed for a specific radiologic task, with all algorithms abiding by the same set of rules, operating on a common set of images, and being evaluated with a uniform performance assessment paradigm.
Abstract: Challenges, in the context of medical imaging, are valuable in that they allow for a direct comparison of different algorithms designed for a specific radiologic task, with all algorithms abiding by the same set of rules, operating on a common set of images, and being evaluated with a uniform performance assessment paradigm. The variability of system performance based on database composition and subtlety, definition of “truth,” and scoring metric is well-known;1–3 challenges serve to level the differences across these various dimensions. The medical imaging community has hosted a number of successful thoracic imaging challenges that have spanned a wide range of tasks,4,5 including lung nodule detection,6 lung nodule change, vessel segmentation,7 and vessel tree extraction.8 Each challenge presents its own unique set of circumstances and considerations; however, important common themes exist. Future challenge organizers (and participants) could benefit from an open discussion of successes achieved, pitfalls encountered, and lessons learned from each completed challenge.

55 citations


Journal ArticleDOI
TL;DR: Investigation of the utility of obtaining “core samples” of regions in CT volume scans for extraction of radiomic features concludes that certain features such as intensity and texture features are robust to segmentation.
Abstract: The purpose of this study is to investigate the utility of obtaining "core samples" of regions in CT volume scans for extraction of radiomic features. We asked four readers to outline tumors in three representative slices from each phase of multiphasic liver CT images taken from 29 patients (1128 segmentations) with hepatocellular carcinoma. Core samples were obtained by automatically tracing the maximal circle inscribed in the outlines. Image features describing the intensity, texture, shape, and margin were used to describe the segmented lesion. We calculated the intraclass correlation between the features extracted from the readers' segmentations and their core samples to characterize robustness to segmentation between readers, and between human-based segmentation and core sampling. We conclude that despite the high interreader variability in manually delineating the tumor (average overlap of 43% across all readers), certain features such as intensity and texture features are robust to segmentation. More importantly, this same subset of features can be obtained from the core samples, providing as much information as detailed segmentation while being simpler and faster to obtain.

54 citations


Journal ArticleDOI
TL;DR: Results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support the hypothesis: the pulmonary parenchema is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.
Abstract: Current computer-aided diagnosis (CAD) models for determining pulmonary nodule malignancy characterize nodule shape, density, and border in computed tomography (CT) data. Analyzing the lung parenchyma surrounding the nodule has been minimally explored. We hypothesize that improved nodule classification is achievable by including features quantified from the surrounding lung tissue. To explore this hypothesis, we have developed expanded quantitative CT feature extraction techniques, including volumetric Laws texture energy measures for the parenchyma and nodule, border descriptors using ray-casting and rubber-band straightening, histogram features characterizing densities, and global lung measurements. Using stepwise forward selection and leave-one-case-out cross-validation, a neural network was used for classification. When applied to 50 nodules (22 malignant and 28 benign) from high-resolution CT scans, 52 features (8 nodule, 39 parenchymal, and 5 global) were statistically significant. Nodule-only features yielded an area under the ROC curve of 0.918 (including nodule size) and 0.872 (excluding nodule size). Performance was improved through inclusion of parenchymal (0.938) and global features (0.932). These results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support our hypothesis: the pulmonary parenchyma is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.

53 citations


Journal ArticleDOI
TL;DR: A fast and accurate method for automatic segmentation of mandible in panoramic x-rays using a modified Canny edge detector accompanied by morphological operators and the best-matched template from the atlas of mandibles is presented.
Abstract: As the panoramic x-ray is the most common extraoral radiography in dentistry, segmentation of its anatomical structures facilitates diagnosis and registration of dental records. This study presents a fast and accurate method for automatic segmentation of mandible in panoramic x-rays. In the proposed four-step algorithm, a superior border is extracted through horizontal integral projections. A modified Canny edge detector accompanied by morphological operators extracts the inferior border of the mandible body. The exterior borders of ramuses are extracted through a contour tracing method based on the average model of mandible. The best-matched template is fetched from the atlas of mandibles to complete the contour of left and right processes. The algorithm was tested on a set of 95 panoramic x-rays. Evaluating the results against manual segmentations of three expert dentists showed that the method is robust. It achieved an average performance of [Formula: see text] in Dice similarity, specificity, and sensitivity.

52 citations


Journal ArticleDOI
TL;DR: This work proposes a more global framework to generate arteriovenous trees in retinal images, given a vessel segmentation, by generating an overconnected vessel network, named the vessel potential connectivity map (VPCM), consisting of vessel segments and the potential connectivity between them.
Abstract: While many approaches exist to segment retinal vessels in fundus photographs, only a limited number focus on the construction and disambiguation of arterial and venous trees. Previous approaches are local and/or greedy in nature, making them susceptible to errors or limiting their applicability to large vessels. We propose a more global framework to generate arteriovenous trees in retinal images, given a vessel segmentation. In particular, our approach consists of three stages. The first stage is to generate an overconnected vessel network, named the vessel potential connectivity map (VPCM), consisting of vessel segments and the potential connectivity between them. The second stage is to disambiguate the VPCM into multiple anatomical trees, using a graph-based metaheuristic algorithm. The third stage is to classify these trees into arterial or venous (A/V) trees. We evaluated our approach with a ground truth built based on a public database, showing a pixel-wise classification accuracy of 88.15% using a manual vessel segmentation as input, and 86.11% using an automatic vessel segmentation as input.

41 citations


Journal ArticleDOI
TL;DR: It is suggested that these spatial habitat diversity features are associated with these clinical characteristics and could be a useful prognostic tool for magnetic resonance imaging studies of patients with GBM.
Abstract: We analyzed the spatial diversity of tumor habitats, regions with distinctly different intensity characteristics of a tumor, using various measurements of habitat diversity within tumor regions. These features were then used for investigating the association with a 12-month survival status in glioblastoma (GBM) patients and for the identification of epidermal growth factor receptor (EGFR)-driven tumors. T1 postcontrast and T2 fluid attenuated inversion recovery images from 65 GBM patients were analyzed in this study. A total of 36 spatial diversity features were obtained based on pixel abundances within regions of interest. Performance in both the classification tasks was assessed using receiver operating characteristic (ROC) analysis. For association with 12-month overall survival, area under the ROC curve was 0.74 with confidence intervals [0.630 to 0.858]. The sensitivity and specificity at the optimal operating point ([Formula: see text]) on the ROC were 0.59 and 0.75, respectively. For the identification of EGFR-driven tumors, the area under the ROC curve (AUC) was 0.85 with confidence intervals [0.750 to 0.945]. The sensitivity and specificity at the optimal operating point ([Formula: see text]) on the ROC were 0.76 and 0.83, respectively. Our findings suggest that these spatial habitat diversity features are associated with these clinical characteristics and could be a useful prognostic tool for magnetic resonance imaging studies of patients with GBM.

38 citations


Journal ArticleDOI
TL;DR: A flexible multipurpose nonlinear microscopic imaging system based on a femtosecond excitation source and a photonic crystal fiber with multiple miniaturized time-correlated single-photon counting detectors that perfectly matches the needs for the clinical investigation of human skin in vivo.
Abstract: We report on a flexible multipurpose nonlinear microscopic imaging system based on a femtosecond excitation source and a photonic crystal fiber with multiple miniaturized time-correlated single-photon counting detectors. The system provides the simultaneous acquisition of e.g., two-photon autofluorescence, second-harmonic generation, and coherent anti-Stokes Raman scattering images. Its flexible scan head permits ex vivo biological imaging with subcellular resolution such as rapid biopsy examination during surgery as well as imaging on small as well as large animals. Above all, such an arrangement perfectly matches the needs for the clinical investigation of human skin in vivo where knowledge about the distribution of endogenous fluorophores, second-harmonic generation–active collagen as well as nonfluorescent lipids is of high interest.

Journal ArticleDOI
TL;DR: An imaging-genomic pipeline to derive three-dimensional intra-tumor heterogeneity features from contrast-enhanced CT images and correlates them with gene mutation status is presented and shows that the model can predict BAP1 mutation status with a high degree of sensitivity and specificity.
Abstract: This paper presents an imaging-genomic pipeline to derive three-dimensional intra-tumor heterogeneity features from contrast-enhanced CT images and correlates them with gene mutation status. The pipeline has been demonstrated using CT scans of patients with clear cell renal cell carcinoma (ccRCC) from The Cancer Genome Atlas. About 15% of ccRCC cases reported have BRCA1-associated protein 1 (BAP1) gene alterations that are associated with high tumor grade and poor prognosis. We hypothesized that BAP1 mutation status can be detected using computationally derived image features. The molecular data pertaining to gene mutation status were obtained from the cBioPortal. Correlation of the image features with gene mutation status was assessed using the Mann-Whitney-Wilcoxon rank-sum test. We also used the random forests classifier in the Waikato Environment for Knowledge Analysis software to assess the predictive ability of the computationally derived image features to discriminate cases with BAP1 mutations for ccRCC. Receiver operating characteristics were obtained using a leave-one-out-cross-validation procedure. Our results show that our model can predict BAP1 mutation status with a high degree of sensitivity and specificity. This framework demonstrates a methodology for noninvasive disease biomarker detection from contrast-enhanced CT images.

Journal ArticleDOI
TL;DR: The first in-tissue needle-based OCT imaging and three-dimensional optical attenuation analysis of prostate tissue that indicates a correlation with pathology is described and may contribute to the current challenge of prostate imaging and the rising interest in focal therapy for reduction of side effects occurring with current therapies.
Abstract: The objective of this study is to demonstrate the feasibility of needle-based optical coherence tomography (OCT) and functional analysis of OCT data along the full pullback trajectory of the OCT measurement in the prostate, correlated with pathology. OCT images were recorded using a commercially available C7-XR™ OCT Intravascular Imaging System interfaced to a C7 Dragonfly™ intravascular 0.9-mm-diameter imaging probe. A computer program was constructed for automated image attenuation analysis. First, calibration of the OCT system for both the point spread function and the system roll-off was achieved by measurement of the OCT signal attenuation from an extremely weakly scattering medium (Intralipid® 0.0005 volume%). Second, the data were arranged in 31 radial wedges (pie slices) per circular segments consisting of 16 A-scans per wedge and 5 axial B-scans, resulting in an average A-scan per wedge. Third, the decay of the OCT signal is analyzed over 50 pixels ([Formula: see text]) in depth, starting from the first found maximum data point. Fourth, for visualization, the data were grouped with a corresponding color representing a specific [Formula: see text] range according to their attenuation coefficient. Finally, the analyses were compared to histopathology. To ensure that each single use sterile imaging probe is comparable to the measurements of the other imaging probes, the probe-to-probe variations were analyzed by measuring attenuation coefficients of 0.03, 6.5, 11.4, 17, and 22.7 volume% Intralipid®. Experiments were repeated five times per probe for four probes. Inter- and intraprobe variation in the measured attenuation of Intralipid samples with scattering properties similar to that of the prostate was [Formula: see text] of the mean values. Mean attenuation coefficients in the prostate were [Formula: see text] for parts of the tissue that were classified as benign (SD: [Formula: see text], minimum: [Formula: see text], maximum: [Formula: see text]) and [Formula: see text] for parts of tissue that were classified as malignant (SD: [Formula: see text], minimum: [Formula: see text], maximum: [Formula: see text]). In benign areas, the tissue looked homogeneous, whereas in malignant areas, small glandular structures were seen. However, not all areas in which a high attenuation coefficient became apparent corresponded to areas of prostate cancer. This paper describes the first in-tissue needle-based OCT imaging and three-dimensional optical attenuation analysis of prostate tissue that indicates a correlation with pathology. Fully automated attenuation coefficient analysis was performed at 1300 nm over the full pullback. Correlation with pathology was achieved by coregistration of three-dimensional (3-D) OCT attenuation maps with 3-D pathology of the prostate. This may contribute to the current challenge of prostate imaging and the rising interest in focal therapy for reduction of side effects occurring with current therapies.

Journal ArticleDOI
TL;DR: After integration into the clinical workflow, this decision support system has the potential to support earlier salvage for patients with recurrence and fewer investigations of benign RILI.
Abstract: Benign radiation-induced lung injury (RILI) is not uncommon following stereotactic ablative radiotherapy (SABR) for lung cancer and can be difficult to differentiate from tumor recurrence on follow-up imaging. We previously showed the ability of computed tomography (CT) texture analysis to predict recurrence. The aim of this study was to evaluate and compare the accuracy of recurrence prediction using manual region-of-interest segmentation to that of a semiautomatic approach. We analyzed 22 patients treated for 24 lesions (11 recurrences, 13 RILI). Consolidative and ground-glass opacity (GGO) regions were manually delineated. The longest axial diameter of the consolidative region on each post-SABR CT image was measured. This line segment is routinely obtained as part of the clinical imaging workflow and was used as input to automatically delineate the consolidative region and subsequently derive a periconsolidative region to sample GGO tissue. Texture features were calculated, and at two to five months post-SABR, the entropy texture measure within the semiautomatic segmentations showed prediction accuracies [areas under the receiver operating characteristic curve (AUC): 0.70 to 0.73] similar to those of manual GGO segmentations (AUC: 0.64). After integration into the clinical workflow, this decision support system has the potential to support earlier salvage for patients with recurrence and fewer investigations of benign RILI.

Journal ArticleDOI
TL;DR: Challenges associated with eye tracking in volumetric imaging are particularly associated with the selection of stimulus material, the detection of events in the eye tracking data, the calculation of meaningful eye tracking parameters, and the reporting of abnormalities.
Abstract: While eye tracking research in conventional radiography has flourished over the past decades, the number of eye tracking studies that looked at multislice images lags behind. A possible reason for the lack of studies in this area might be that the eye tracking methodology used in the context of conventional radiography cannot be applied one-on-one to volumetric imaging material. Challenges associated with eye tracking in volumetric imaging are particularly associated with the selection of stimulus material, the detection of events in the eye tracking data, the calculation of meaningful eye tracking parameters, and the reporting of abnormalities. However, all of these challenges can be addressed in the design of the experiment. If this is done, eye tracking studies using volumetric imaging material offer almost unlimited opportunity for perception research and are highly relevant as the number of volumetric images that are acquired and interpreted is rising.

Journal ArticleDOI
TL;DR: The images obtained clinically in real time using the dental SS-OCT system are suitable for the assessment of natural subsurface lesions and their surface layer, providing comparable images to a laboratory high-resolution μCT without the use of x-ray.
Abstract: A technology to characterize early enamel lesions is needed in dentistry. Optical coherence tomography (OCT) is a noninvasive method that provides high-resolution cross-sectional images. The aim of this study is to compare OCT with microfocus x-ray computed tomography (μCT) for assessment of natural enamel lesions in vitro. Ten human teeth with visible white spot-like changes on the enamel smooth surface and no cavitation (ICDAS code 2) were subjected to imaging by μCT (SMX-100CT, Shimadzu) and 1300-nm swept-source OCT (Dental SS-OCT, Panasonic Health Care). In μCT, the lesions appeared as radiolucent dark areas, while in SS-OCT, they appeared as areas of increased signal intensity beneath the surface. An SS-OCT attenuation coefficient based on Beer–Lambert law could discriminate lesions from sound enamel. Lesion depth ranged from 175 to 606 μm in SS-OCT. A correlation between μCT and SS-OCT was found regarding lesion depth (R=0.81, p<0.001) and also surface layer thickness (R=0.76, p<0.005). The images obtained clinically in real time using the dental SS-OCT system are suitable for the assessment of natural subsurface lesions and their surface layer, providing comparable images to a laboratory high-resolution μCT without the use of x-ray.

Journal ArticleDOI
TL;DR: Clinical significant variation in relative CBV measures based on the software used, but minimal interoperator variation is revealed, and it is recommended against using specific relativeCBV measurement thresholds for GBM progression determination unless the same software or processing algorithm is used.
Abstract: Determining whether glioblastoma multiforme (GBM) is progressing despite treatment is challenging due to the pseudoprogression phenomenon seen on conventional MRIs, but relative cerebral blood volume (CBV) has been shown to be helpful. As CBV’s calculation from perfusion-weighted images is not standardized, we investigated whether there were differences between three FDA-cleared software packages in their CBV output values and subsequent performance regarding predicting survival/progression. Forty-five postradiation therapy GBM cases were retrospectively identified as having indeterminate MRI findings of progression versus pseudoprogression. The dynamic susceptibility contrast MR images were processed with different software and three different relative CBV metrics based on the abnormally enhancing regions were computed. The intersoftware intraclass correlation coefficients were 0.8 and below, depending on the metric used. No statistically significant difference in progression determination performance was found between the software packages, but performance was better for the cohort imaged at 3.0 T versus those imaged at 1.5 T for many relative CBV metric and classification criteria combinations. The results revealed clinically significant variation in relative CBV measures based on the software used, but minimal interoperator variation. We recommend against using specific relative CBV measurement thresholds for GBM progression determination unless the same software or processing algorithm is used.

Journal ArticleDOI
TL;DR: In this paper, the optical properties of calcified, fibrotic, and lipid atherosclerotic plaques from in vivo coronary artery intravascular optical coherence tomography clinical pullbacks were estimated.
Abstract: We developed robust, three-dimensional methods, as opposed to traditional A-line analysis, for estimating the optical properties of calcified, fibrotic, and lipid atherosclerotic plaques from in vivo coronary artery intravascular optical coherence tomography clinical pullbacks. We estimated attenuation μt and backscattered intensity I0 from small volumes of interest annotated by experts in 35 pullbacks. Some results were as follows: noise reduction filtering was desirable, parallel line (PL) methods outperformed individual line methods, root mean square error was the best goodness-of-fit, and α-trimmed PL (α-T-PL) was the best overall method. Estimates of μt were calcified (3.84±0.95 mm−1), fibrotic (2.15±1.08 mm−1), and lipid (9.99±2.37 mm−1), similar to those in the literature, and tissue classification from optical properties alone was promising.

Journal ArticleDOI
TL;DR: A fully automated supervised pixel classification approach for segmenting GA, including uni- and multifocal patches in fundus autofluorescene (FAF) images, including region-wise intensity measures, gray-level co-occurrence matrix measures, and Gaussian filter banks is developed.
Abstract: Geographic atrophy (GA) is a manifestation of the advanced or late stage of age-related macular degeneration (AMD). AMD is the leading cause of blindness in people over the age of 65 in the western world. The purpose of this study is to develop a fully automated supervised pixel classification approach for segmenting GA, including uni- and multifocal patches in fundus autofluorescene (FAF) images. The image features include region-wise intensity measures, gray-level co-occurrence matrix measures, and Gaussian filter banks. A [Formula: see text]-nearest-neighbor pixel classifier is applied to obtain a GA probability map, representing the likelihood that the image pixel belongs to GA. Sixteen randomly chosen FAF images were obtained from 16 subjects with GA. The algorithm-defined GA regions are compared with manual delineation performed by a certified image reading center grader. Eight-fold cross-validation is applied to evaluate the algorithm performance. The mean overlap ratio (OR), area correlation (Pearson's [Formula: see text]), accuracy (ACC), true positive rate (TPR), specificity (SPC), positive predictive value (PPV), and false discovery rate (FDR) between the algorithm- and manually defined GA regions are [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively.

Journal ArticleDOI
TL;DR: An automated brain densitometric method that divides CT scans of the brain into ASPECTS regions using atlas-based segmentation could be used as a supplementary tool to assist manual scoring in patients with acute ischemic stroke.
Abstract: The Alberta Stroke Program Early CT score (ASPECTS) scoring method is frequently used for quan- tifying early ischemic changes (EICs) in patients with acute ischemic stroke in clinical studies. Varying interob- server agreement has been reported, however, with limited agreement. Therefore, our goal was to develop and evaluate an automated brain densitometric method. It divides CT scans of the brain into ASPECTS regions using atlas-based segmentation. EICs are quantified by comparing the brain density between contralateral sides. This method was optimized and validated using CT data from 10 and 63 patients, respectively. The automated method was validated against manual ASPECTS, stroke severity at baseline and clinical outcome after 7 to 10 days (NIH Stroke Scale, NIHSS) and 3 months (modified Rankin Scale). Manual and automated ASPECTS showed similar and statistically significant correlations with baseline NIHSS (R ¼ −0.399 and −0.277, respectively) and with follow-up mRS (R ¼ −0.256 and −0.272), except for the follow-up NIHSS. Agreement between automated and consensus ASPECTS reading was similar to the interobserver agreement of manual ASPECTS (differences <1 point in 73% of cases). The automated ASPECTS method could, therefore, be used as a supplementary tool to assist manual scoring.©TheAuthors.PublishedbySPIEunderaCreativeCommonsAttribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. (DOI:

Journal ArticleDOI
TL;DR: It is demonstrated that teaching a search pattern to trainees improves their ability to identify nodules and decreases the number of perceptual errors in nodule identification, and it is suggested that the knowledge of medical image perception may be used to develop rational tools for the education of healthcare trainees.
Abstract: The goal of this research is to demonstrate that teaching healthcare trainees a formal search or scan pattern for evaluation of the lungs improves their ability to identify pulmonary nodules on chest radiographs (CXRs). A group of physician assistant trainees were randomly assigned to control and experimental groups. Each group was shown two sets of CXRs, each set with a nodule prevalence of approximately 50%. The experimental group received search pattern training between case sets, whereas the control group did not. Both groups were asked to mark nodules when present and indicate their diagnostic confidence. Subject performance at nodule detection was quantified using changes in area under the localization receiver operating characteristic curve ([Formula: see text]). There was no significant improvement in performance between case sets for the control group. There was a significant improvement in subject performance after training for the experimental group, [Formula: see text], [Formula: see text]. These results demonstrate that teaching a search pattern to trainees improves their ability to identify nodules and decreases the number of perceptual errors in nodule identification, and suggest that our knowledge of medical image perception may be used to develop rational tools for the education of healthcare trainees.

Journal ArticleDOI
TL;DR: An experimental L-shell XFCT imaging system consisting of a miniature x-ray tube and two spectrometers, a silicon drift detector (SDD), and a CdTe detector placed at ±120 deg with respect to the excitation beam is built to demonstrate the feasibility and assess its achievable sensitivity.
Abstract: Thanks to the current advances in nanoscience, molecular biochemistry, and x-ray detector technology, x-ray fluorescence computed tomography (XFCT) has been considered for molecular imaging of probes containing high atomic number elements, such as gold nanoparticles. The commonly used XFCT imaging performed with K-shell x rays appears to have insufficient imaging sensitivity to detect the low gold concentrations observed in small animal studies. Low energy fluorescence L-shell x rays have exhibited higher signal-to-background ratio and appeared as a promising XFCT mode with greatly enhanced sensitivity. The aim of this work was to experimentally demonstrate the feasibility of L-shell XFCT imaging and to assess its achievable sensitivity. We built an experimental L-shell XFCT imaging system consisting of a miniature x-ray tube and two spectrometers, a silicon drift detector (SDD), and a CdTe detector placed at [Formula: see text] with respect to the excitation beam. We imaged a 28-mm-diameter water phantom with 4-mm-diameter Eppendorf tubes containing gold solutions with concentrations of 0.06 to 0.1% Au. While all Au vials were detectable in the SDD L-shell XFCT image, none of the vials were visible in the CdTe L-shell XFCT image. The detectability limit of the presented L-shell XFCT SDD imaging setup was 0.007% Au, a concentration observed in small animal studies.

Journal ArticleDOI
TL;DR: The classification of non melanoma skin cancers is automated using machine learning approach and the model is built to predict the type of disease accurately using support vector machine and its variants.
Abstract: Skin cancer is the growth of uncontrolled abnormal skin cells. There are two main types of skin cancers such as Melanoma and Non-Melanoma. The main objective of this research work is to focus on Non-Melanoma skin cancers and classify the types of it.The classification of non melanoma skin cancers is automated using machine learning approach and the model is built to predict the type of disease accurately using support vector machine and its variants. Various experiments have been carried out with skin lesion images and the results are analyzed.

Journal ArticleDOI
TL;DR: The results suggest that a low- frequencies element effectively provides depth resolved images of the whole vessel and its adjacent tissue, and a high-frequency element visualizes detailed structure near the surface of the lumen wall in the presence of blood within theLumen.
Abstract: A dual-element needle transducer for intravascular ultrasound imaging has been developed. A low-frequency element and a high-frequency element were integrated into one device to obtain images which conveyed both low- and high-frequency information from a single scan. The low-frequency element with a center frequency of 48 MHz was fabricated from the single crystal form of lead magnesium niobate-lead titanate solid solution with two matching layers (MLs) and the high frequency element with a center frequency of 152 MHz was fabricated from lithium niobate with one ML. The measured axial and lateral resolutions were 27 and 122 μm, respectively, for the low-frequency element, and 14 and 40 μm, respectively, for the high-frequency element. The performance of the dual-element needle transducer was validated by imaging a tissue-mimicking phantom with lesion-mimicking area, and ex vivo rabbit aortas in water and rabbit whole blood. The results suggest that a low-frequency element effectively provides depth resolved images of the whole vessel and its adjacent tissue, and a high-frequency element visualizes detailed structure near the surface of the lumen wall in the presence of blood within the lumen. The advantages of a dual-element approach for intravascular imaging are also discussed.

Journal ArticleDOI
TL;DR: A spatial domain-based channelized Hotelling observer model is presented to calculate the detectability index (DI) of different sized disks and compare the performance of different imaging conditions and angiography systems.
Abstract: Evaluation of flat-panel angiography equipment through conventional image quality metrics is limited by the scope of standard spatial-domain image quality metric(s), such as contrast-to-noise ratio and spatial resolution, or by restricted access to appropriate data to calculate Fourier domain measurements, such as modulation transfer function, noise power spectrum, and detective quantum efficiency. Observer models have been shown capable of overcoming these limitations and are able to comprehensively evaluate medical-imaging systems. We present a spatial domain-based channelized Hotelling observer model to calculate the detectability index (DI) of our different sized disks and compare the performance of different imaging conditions and angiography systems. When appropriate, changes in DIs were compared to expectations based on the classical Rose model of signal detection to assess linearity of the model with quantum signal-to-noise ratio (SNR) theory. For these experiments, the estimated uncertainty of the DIs was less than 3%, allowing for precise comparison of imaging systems or conditions. For most experimental variables, DI changes were linear with expectations based on quantum SNR theory. DIs calculated for the smallest objects demonstrated nonlinearity with quantum SNR theory due to system blur. Two angiography systems with different detector element sizes were shown to perform similarly across the majority of the detection tasks.

Journal ArticleDOI
TL;DR: Inversion of data leads to electrical conductivity distribution images for the thoracic spinal column which are the first of their kind to correctly distinguish such basic features as size and depth of spinal canal, as well as size, depth, and spacing of transverse spinal processes.
Abstract: Previously, magnetic induction tomography (MIT) has been considered for noncontact imaging of human tissue electrical properties. Commonly, multiple coils are used, with any one serving as the source while others detect eddy currents generated in the specimen. Here, imaging of low conductivity objects is shown feasible with a single coil acting simultaneously as source and detector, provided that the coil is repeatedly relocated while collecting coil loss data. To enable such “scanning,” an analytical coil loss formula is derived in the quasistatic limit for a single coil consisting of several concentric circular wire loops, all within a common plane. Conductivity may vary arbitrarily in space, whereas permittivity and permeability are treated as uniform. The analytical form is used to build an algorithm for imaging electrical conductivity in human tissues. A practical device operating at 12.5 MHz is described and used in a clinical trial that “scans” the region between the scapulae while collecting coil loss data. Inversion of data leads to electrical conductivity distribution images for the thoracic spinal column which are the first of their kind to correctly distinguish such basic features as size and depth of spinal canal, as well as size, depth, and spacing of transverse spinal processes.

Journal ArticleDOI
TL;DR: An analytical framework is presented for evaluating the equivalence of parenchymal texture features across different full-field digital mammography systems using a physical breast phantom and certain features, such as edge enhancement, tend to be more robust to intergenerational differences between detectors of a single vendor than to intervendor differences.
Abstract: An analytical framework is presented for evaluating the equivalence of parenchymal texture features across different full-field digital mammography (FFDM) systems using a physical breast phantom. Phantom images (FOR PROCESSING) are acquired from three FFDM systems using their automated exposure control setting. A panel of texture features, including gray-level histogram, co-occurrence, run length, and structural descriptors, are extracted. To identify features that are robust across imaging systems, a series of equivalence tests are performed on the feature distributions, in which the extent of their intersystem variation is compared to their intrasystem variation via the Hodges–Lehmann test statistic. Overall, histogram and structural features tend to be most robust across all systems, and certain features, such as edge enhancement, tend to be more robust to intergenerational differences between detectors of a single vendor than to intervendor differences. Texture features extracted from larger regions of interest (i.e., 63 pixels 2 ) and with a larger offset length (i.e., 7 pixels ), when applicable, also appear to be more robust across imaging systems. This framework and observations from our experiments may benefit applications utilizing mammographic texture analysis on images acquired in multivendor settings, such as in multicenter studies of computer-aided detection and breast cancer risk assessment.


Journal ArticleDOI
TL;DR: The purpose of this work is to determine the optimal beam quality for material decomposition in two head imaging cases: nonenhanced imaging and K-edge imaging, and to develop a photon-counting spectral detector for CT applications.
Abstract: Head computed tomography (CT) plays an important role in the comprehensive evaluation of acutestroke. Photon-counting spectral detectors, as promising candidates for use in the next generation of x ...

Journal ArticleDOI
TL;DR: A fully automated method for detection and segmentation of liver metastases in serial computed tomography (CT) examinations and the segmentation performance, matching rate, and RECIST assessment results hence appear promising.
Abstract: This paper presents a fully automated method for detection and segmentation of liver metastases in serial computed tomography (CT) examinations. Our method uses a given two-dimensional baseline segmentation mask for identifying the lesion location in the follow-up CT and locating surrounding tissues, using nonrigid image registration and template matching, in order to reduce the search area for segmentation. Adaptive region growing and mean-shift clustering are used to obtain the lesion segmentation. Our database contains 127 cases from the CT abdomen unit at Sheba Medical Center. Development of the methodology was conducted using 22 of the cases, and testing was conducted on the remaining 105 cases. Results show that 94 of the 105 lesions were detected, for an overall matching rate of 90% making the correct RECIST 1.1 assessment in 88% of the cases. The average Dice index was [Formula: see text], the average sensitivity was [Formula: see text], and the positive predictive value was [Formula: see text]. In 92% of the rated cases, the results were classified by the radiologists as acceptable or better. The segmentation performance, matching rate, and RECIST assessment results hence appear promising.