Is large improvement in efficiency of impulsive noise removal in color images still possible?

The substantial improvement in the efficiency of switching filters, intended for the removal of impulsive noise within color images is described. Numerous noisy pixel detection and replacement techniques are evaluated, where the filtering performance for color images and subsequent results are assessed using statistical reasoning. Denoising efficiency for the applied detection and interpolation techniques are assessed when the location of corrupted pixels are identified by noisy pixel detection algorithms and also in the scenario when they are already known. The results show that improvement in objective quality measures can be achieved by using more robust detection techniques, combined with novel methods of corrupted pixel restoration. A significant increase in the image denoising performance is achieved for both pixel detection and interpolation, surpassing current filtering methods especially via the application of a convolutional network. The interpolation techniques used in the image inpainting methods also significantly increased the efficiency of impulsive noise removal.

High tissue contrast image synthesis via multistage attention-GAN: Application to segmenting brain MR scans.

Magnetic resonance imaging (MRI) presents a detailed image of the internal organs via a magnetic field. Given MRI's non-invasive advantage in repeated imaging, the low-contrast MR images in the target area make segmentation of tissue a challenging problem. This study shows the potential advantages of synthetic high tissue contrast (HTC) images through image-to-image translation techniques. Mainly, we use a novel cycle generative adversarial network (Cycle-GAN), which provides a mechanism of attention to increase the contrast within the tissue. The attention block and training on HTC images are beneficial to our model to enhance tissue visibility. We use a multistage architecture to concentrate on a single tissue as a preliminary and filter out the irrelevant context in every stage in order to increase the resolution of HTC images. The multistage architecture reduces the gap between source and target domains and alleviates synthetic images' artefacts. We apply our HTC image synthesising method to two public datasets. In order to validate the effectiveness of these images we use HTC MR images in both end-to-end and two-stage segmentation structures. The experiments on three segmentation baselines on BraTS'18 demonstrate that joining the synthetic HTC images in the multimodal segmentation framework develops the average Dice similarity scores (DSCs) of 0.8%, 0.6%, and 0.5% respectively on the whole tumour (WT), tumour core (TC), and enhancing tumour (ET) while removing one real MRI channels from the segmentation pipeline. Moreover, segmentation of infant brain tissue in T1w MR slices through our framework improves DSCs approximately 1% in cerebrospinal fluid (CSF), grey matter (GM), and white matter (WM) compared to state-of-the-art segmentation techniques. The source code of synthesising HTC images is publicly available.

A practical criterion for focusing of unstained cell samples using a digital holographic microscope.

Digital holographic microscopy (DHM) is an important technique that may be used for quantitative phase imaging of unstained biological cell samples. Since the DHM technology is not commonly used in clinics or bioscience research labs, at present there is no well-accepted focusing criterion for unstained samples that users can follow while recording image plane digital holograms of cells. The usual sharpness metrics that are useful for auto-focusing of stained cells do not work well for unstained cells as there is no amplitude contrast. In this work, we report a practical method for estimating the best focus plane for unstained cells in the digital hologram domain. The method is based on an interesting observation that for the best focus plane the fringe pattern associated with individual unstained cells predominantly shows phase modulation effect in the form of bending of fringes and minimal amplitude modulation. This criterion when applied to unstained red blood cells shows that the central dip in the doughnut-like phase profile of cells is maximal in this plane. The proposed methodology is helpful for standardizing the usage of DHM technology across different users and application development efforts. LAY DESCRIPTION: Digital holographic microscopy (DHM) is slowly but steadily becoming an important microscopy modality and gaining acceptability for basic bio-science research as well as clinical usage. One of the important features of DHM is that it allows users to perform quantitative imaging of unstained transparent cells. Instead of using dyes or fluorescent labelling, DHM systems use quantitative phase as a contrast mechanism which depends on the natural refractive index variation within the cell samples. Since minimal wet lab processing is required in order to image cell samples with a DHM, cells can be imaged in their natural state. While DHM is gaining popularity among users, the imaging protocols across the labs or users need to be standardized in order to make sure that the same quantitative phase parameters are used for tasks such as quantitative phased based cell classification. One of the important operational tasks for any microscopy work is to focus the sample under study. While focusing comes naturally to users of brightfield microscopes based on image contrast, the focusing is not straightforward when samples are unstained so that they do not offer any amplitude contrast. When performing quantitative phase imaging, defocus can actually change the phase profile of the cell due to near-zone (Fresnel) diffraction effects. So unless a standardized focusing methodology is used, it will be difficult for multiple DHM users (potentially at different sites) to agree on quantitative results out of their phase images. DHM literature has prior works which perform numerical focusing of recovered complex wave-field in the hologram plane to find the best focus plane. However such methods are not user friendly and do not allow user the same focusing experience as in a brightfield microscope. The numerical focusing is therefore a reasonably good method for an optics researcher but not necessarily so for a microscopy technician looking at cell samples with a DHM system in a clinical setting. The present work provides a simple focusing criterion for unstained samples that works directly in the hologram domain. The technique is based on an interesting observation that the when an unstained cell sample is in the best-focus plane, its corresponding hologram (or fringe pattern) predominantly shows phase modulation manifested by bending of fringes at the location of the cell. This criterion can be converted into a simple numerical method as we have used to find the best-focus plane using a stack of through focus holograms. We believe that the technique can be used manually by visually observing the holograms or can be converted to an auto-focus algorithm for a motorized DHM system.

The UK Biobank imaging enhancement of 100,000 participants: rationale, data collection, management and future directions.

UK Biobank is a population-based cohort of half a million participants aged 40-69 years recruited between 2006 and 2010. In 2014, UK Biobank started the world's largest multi-modal imaging study, with the aim of re-inviting 100,000 participants to undergo brain, cardiac and abdominal magnetic resonance imaging, dual-energy X-ray absorptiometry and carotid ultrasound. The combination of large-scale multi-modal imaging with extensive phenotypic and genetic data offers an unprecedented resource for scientists to conduct health-related research. This article provides an in-depth overview of the imaging enhancement, including the data collected, how it is managed and processed, and future directions.

Denoise magnitude diffusion magnetic resonance images via variance-stabilizing transformation and optimal singular-value manipulation.

Although shown to have a great utility for a wide range of neuroscientific and clinical applications, diffusion-weighted magnetic resonance imaging (dMRI) faces a major challenge of low signal-to-noise ratio (SNR), especially when pushing the spatial resolution for improved delineation of brain's fine structure or increasing the diffusion weighting for increased angular contrast or both. Here, we introduce a comprehensive denoising framework for denoising magnitude dMRI. The framework synergistically combines the variance stabilizing transform (VST) with optimal singular value manipulation. The purpose of VST is to transform the Rician data to Gaussian-like data so that an asymptotically optimal singular value manipulation strategy tailored for Gaussian data can be used. The output of the framework is the estimated underlying diffusion signal for each voxel in the image domain. The usefulness of the proposed framework for denoising magnitude dMRI is demonstrated using both simulation and real-data experiments. Our results show that the proposed denoising framework can significantly improve SNR across the entire brain, leading to substantially enhanced performances for estimating diffusion tensor related indices and for resolving crossing fibers when compared to another competing method. More encouragingly, the proposed method when used to denoise a single average of 7 â€‹Tesla Human Connectome Project-style diffusion acquisition provided comparable performances relative to those achievable with ten averages for resolving multiple fiber populations across the brain. As such, the proposed denoising method is expected to have a great utility for high-quality, high-resolution whole-brain dMRI, desirable for many neuroscientific and clinical applications.

Acoustic biomolecules enhance hemodynamic functional ultrasound imaging of neural activity.

Hemodynamic functional ultrasound imaging (fUS) of neural activity provides a unique combination of spatial coverage, spatiotemporal resolution and compatibility with freely moving animals. However, deep and transcranial monitoring of brain activity and the imaging of dynamics in slow-flowing blood vessels remains challenging. To enhance fUS capabilities, we introduce biomolecular hemodynamic enhancers based on gas vesicles (GVs), genetically encodable ultrasound contrast agents derived from buoyant photosynthetic microorganisms. We show that intravenously infused GVs enhance ultrafast Doppler ultrasound contrast and visually-evoked hemodynamic contrast in transcranial fUS of the mouse brain. This hemodynamic contrast enhancement is smoother than that provided by conventional microbubbles, allowing GVs to more reliably amplify neuroimaging signals.

Prostate MRI technical parameters standardization: A systematic review on adherence to PI-RADSv2 acquisition protocol.

PURPOSE: The Prostate Imaging-Reporting and Data System has been developed to standardize prostate MRI in terms of acquisition, interpretation and reporting. It received a major revision in late 2014 (PI-RADSv2). Recently, doubts have been raised on imaging facilities adherence to its acquisition protocol. With this systematic review, we assessed adherence to PI-RADSv2 minimum technical specifications in literature, to achieve a better understanding of issues limiting their diffusion. METHOD: Multiple medical literature databases were extensively searched to retrieve original studies published after January 2016 performing prostate MRI. Information pertaining acquisition protocols and patient enrolment were recorded for analysis. Technical parameters were dichotomized in relation to adherence to the corresponding minimal technical requirements. RESULTS: A total of 150 studies were included for analysis. Only 5% reported every technical parameter specified in the PI-RADSv2 document requirements, none of which completely met guideline specifications. Overall, 19% were in line with PI-RADSv2 for all reported MRI acquisition parameters. The adherence was lowest for T2-weighted frequency in-plane resolution (12%), diffusion-weighted imaging field of view (40%), apparent diffusion coefficient map low b-value (27%) and dynamic contrast-enhanced imaging temporal resolution (43%). Considering its role in image interpretation, it must be highlighted that only 59% of studies reporting diffusion-weighted imaging high b-value follow recommendations. CONCLUSIONS: Adherence to PI-RADSv2 minimum technical standards is heterogeneous in the scientific community. Our findings endorse the need for greater diffusion of PI-RADSv2 guidelines to achieve protocol standardization and support the notion that some requirements might benefit from streamlining to improve clinical applicability.

Technological Advances in Endoscopic Equipment in Exotic Pet Medicine.

The aim of this article is to review some of the technological advances in endoscopy and endosurgery. The article focuses on a few key areas relevant to exotic pets, including advances in urolith management, visualization, and laparoscopic surgery.

Ungated nonenhanced radial quiescent interval slice-selective (QISS) magnetic resonance angiography of the neck: Evaluation of image quality.

BACKGROUND: Standard-of-care time-of-flight (TOF) techniques for nonenhanced magnetic resonance angiography (NEMRA) of the carotid bifurcation and other cervical arteries often provide nondiagnostic image quality due to motion and flow artifacts. PURPOSE: To perform an initial evaluation of an ungated radial quiescent-interval slice-selective (QISS) technique for NEMRA of the neck, in comparison with 2D TOF and contrast-enhanced magnetic resonance angiography (CEMRA). STUDY TYPE: Retrospective. POPULATION: Sixty patients referred for neck MR angiography. FIELD STRENGTH/SEQUENCE: Ungated radial QISS at 3T. ASSESSMENT: Three radiologists scored image quality of 18 arterial segments using a 4-point scale (1, nondiagnostic; 2, fair; 3, good; 4, excellent), and two radiologists graded proximal internal carotid stenosis using five categories (<50%, 50-69%, 70-99%, occlusion, nondiagnostic). STATISTICAL TESTS: Friedman tests with post-hoc Wilcoxon signed-rank tests; unweighted Gwet's AC1 statistic; tests for equality of proportions. RESULTS: Ungated radial QISS provided image quality that significantly exceeded 2D TOF (mean scores of 2.7 vs. 2.0, 2.7 vs. 2.2, and 2.9 vs. 2.3; P < 0.001, all comparisons), while CEMRA provided the best image quality (mean scores of 3.6, 3.7, and 3.5 for the three reviewers). Interrater agreement of image quality scores was substantial for CEMRA (AC1 = 0.70, P < 0.001), and moderate for QISS (AC1 = 0.43, P < 0.001) and TOF (AC1 = 0.41, P < 0.001). Compared with TOF, QISS NEMRA provided a significantly higher percentage of diagnostic segments for all three reviewers (91.0% vs. 71.7%, 93.5% vs. 72.9%, 95.5% vs. 85.2%; P < 0.0001) and demonstrated better agreement with CEMRA for grading of proximal internal carotid stenosis (AC1 = 0.94 vs. 0.73 for reviewer 1, P < 0.05; AC1 = 0.89 vs. 0.68 for reviewer 2, P < 0.05). DATA CONCLUSION: In this initial study, ungated radial QISS significantly outperformed 2D TOF for the evaluation of the neck arteries, with overall better image quality and more diagnostic arterial segments, and improved agreement with CEMRA for grading stenosis of the proximal internal carotid artery. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1798-1807.

Optimization of Whole-Body CT Examinations of Polytrauma Patients in Comparison with the Current Diagnostic Reference Levels. / Optimierung von Ganzkörper-CT-Untersuchungen an Polytraumatisierten anhand des Vergleichs mit den aktuellen diagnostischen Referenzwerten.

PURPOSE: Evaluation of the dose values of a polytrauma whole-body CT examination used in clinical practice with regard to the 2016 updated diagnostic reference levels and reduction of the mean exposure levels using simple optimization steps. MATERIALS AND METHODS: In each case, 100 exposure values before and after dose optimization were compared with the old and new diagnostic reference levels. The grayscale values and the signal-to-noise ratio (SNR) were determined for the lung, the aortic arch and the liver. A visual assessment of the image quality was performed by two radiologists on the basis of a Likert scale (0 - non-diagnostic, 1 - poor visualization, 2 - moderate visualization, 3 - good visualization, 4 - excellent visualization) for CT examinations both before and after optimization. RESULTS: The acquired exposure values after dose optimization were below the old and new diagnostic reference levels (1319.98 ±â€Š463.16 mGy ·â€Šcm) while the mean value of the exposure values before optimization (1774.96 ±â€Š608.78 mGy ·â€Šcm) exceeded the current diagnostic reference levels. The measured grayscale values (HU) were (before versus after optimization): lung - 833 HU vs. - 827 HU (p = 0.43), aortic arch 341 HU vs. 343 HU (p = 0.70) and liver 68 HU vs. 67 HU (p = 0.35). After dose optimization the SNR in the lung was minimally higher, while it was minimally lower in the two other regions than before the optimization. Visual assessment of the image quality showed almost identical values with 3.85 evaluation points before and 3.82 evaluation points after dose optimization (p = 0.57). CONCLUSION: Due to the updating of the diagnostic reference levels, an analysis of the own exposure values is necessary in order to be able to detect high values promptly and to initiate appropriate measures for dose reduction. Appropriate adaptation of the examination parameters with consideration of the necessary image quality allows a significant reduction of the radiation exposure in most cases, also on CT devices of older generations. KEY POINTS: · In many cases a dose reduction below the DRLs is already possible by optimizing the examination technique.. · In order to ensure a diagnostic image quality, the control of the image quality is unavoidable in a dose reduction.. · Through suitable parameter adjustments a compliance with the DRLs is also possible, using CT devices of older generation without iterative image reconstruction.. CITATION FORMAT: · Schäfer SB, Rudolph C, Kolodziej M et al. Optimization of Whole-Body CT Examinations of Polytrauma Patients in Comparison with the Current Diagnostic Reference Levels. Fortschr Röntgenstr 2019; 191: 1015 - 1025.

Referring Physicians Assess the Quality of Outpatient Diagnostic Imaging Services: Development and Psychometric Evaluation of a Questionnaire.

GOAL: In order to ensure high-quality cooperation between referring physicians and imaging services, it is important to assess the quality of imaging services as perceived by referring physicians. The present study aimed to develop and validate a questionnaire for referring physicians to assess the quality of outpatient diagnostic imaging services. MATERIALS & METHODS: The questionnaire was developed by discussing and modifying an existing instrument by the German Association of Surgeons. After qualitative pretesting, the instrument was tested with physicians referring to four outpatient diagnostic imaging services in Switzerland. The results were first assessed using descriptive statistics. The final instrument was tested for validity using the concept of known-groups validity. The hypothesis underlying this procedure was that physicians referring frequently to services estimated the quality of these services to be higher than physicians who referred less often to services. The differences in ratings were assessed using a one-sided two-sample Wilcoxon test. The final questionnaire was tested for internal consistency and reliability using Cronbach's Alpha. RESULTS: Results show a high level of satisfaction of referring physicians with the relevant services but also potential for quality improvement initiatives. The psychometric evaluation of the final questionnaire shows that it is a valid instrument, showing significant differences between the ratings of physicians referring with high and low frequency. Furthermore, the instrument proves to be consistent and reliable. CONCLUSION: The final instrument presents a valid, consistent and reliable option for assess the quality of outpatient diagnostic imaging services as perceived by referring physicians. Results can be used as a basis for quality improvement. KEY POINTS: · A newly developed questionnaire assesses the quality of outpatient diagnostic imaging services as perceived by referring physicians. The questionnaire was developed and tested in Switzerland.. · Psychometric evaluation showed the questionnaire to be a valid, consistent and reliable instrument.. · Results are of interest for imaging services as well as for initiatives encompassing several services.. CITATION FORMAT: · Jossen M, Valeri F, Heilmaier C et al. Referring Physicians Assess the Quality of Outpatient Diagnostic Imaging Services: Development and Psychometric Evaluation of a Questionnaire. Fortschr Röntgenstr 2019; 191: 725 - 731.

Decreasing Radiation Emission in Minimally Invasive Spine Surgery Using Ultra-Low-Radiation Imaging with Image Enhancement: A Prospective Cohort Study.

BACKGROUND: Visualization of the anatomy in minimally invasive surgery (MIS) of the spine is limited and dependent on radiographic imaging, leading to increased radiation exposure to patients and surgical staff. Ultra-low-radiation imaging (ULRI) with image enhancement is a novel technology that may reduce radiation in the operating room. The aim of this study was to compare radiation emission between standard-dose and ULRI fluoroscopy with image enhancement in patients undergoing MIS of the spine. METHODS: This study prospectively enrolled 60 consecutive patients who underwent lateral lumbar interbody fusion, lateral lumbar interbody fusion with percutaneous pedicle screws, or MIS transforaminal lumbar interbody fusion. Standard-dose fluoroscopy was used in 31 cases, and ULRI with image enhancement was used in 29 cases. All imaging emission and radiation doses were recorded. RESULTS: Radiation emission per level was significantly less with ULRI than with standard-dose fluoroscopy for lateral lumbar interbody fusion (36.4 mGy vs. 119.8 mGy, P < 0.001), per screw placed in lateral lumbar interbody fusion (15.4 mGy per screw vs. 47.1 mGy per screw, P < 0.001), and MIS transforaminal lumbar interbody fusion (24.4 mGy vs. 121.6 mGy, P = 0.003). These differences represented reductions in radiation emission of 69.6%, 67.3%, and 79.9%. Total radiation doses per case were also significantly decreased for the transpsoas approach by 68.8%, lateral lumbar interbody fusion with percutaneous pedicle screws by 65.8%, and MIS transforaminal lumbar interbody fusion by 81.0% (P ≤ 0.004). CONCLUSIONS: ULRI with image enhancement has the capacity to significantly decrease radiation emission in minimally invasive procedures without compromising visualization of anatomy or procedure safety.

How transparent film applied on dermatologic imaging devices in order to prevent infections affects image quality?

BACKGROUND: In the clinical practice, transparent films are used as sterile interfaces in in vivo dermatologic imaging in order to prevent the transmissions of infections. However, in our experience, the use of a transparent film can alter skin images. Our study aimed to compare the optical quality of a series of different plastic films used as interfaces in order to understand if some might be more suitable for imaging. MATERIALS AND METHODS: We tested the optical properties of 11 different protective transparent films that are marketed in France with a transparency meter and a spectrophotometer. RESULTS: Transmission, minimal diffusion, amount of gray, and contrast were obtained for each transparent film. Transmission ranged from 93.24% to 96.88% (mean 95.36; standard deviation SD 1.02), minimal diffusion from 88.28% to 123.87% (mean 101.04; standard deviation SD 10.02) and contrast from 11.01 to 15.88 (mean 13.93 and SD 1.3). For some films, the transmission was lower at lower wavelengths. CONCLUSION: All tested films had excellent optical properties. However, some of them had better optical qualities and seemed more suitable for their use in dermatologic imaging.

Unique Gadolinium Enhancement Pattern in Spinal Dural Arteriovenous Fistulas.

Importance: Spinal dural arteriovenous fistula (sDAVF) is often misdiagnosed as an inflammatory or a neoplastic myelopathy, often because of intraparenchymal gadolinium enhancement on magnetic resonance imaging (MRI); proper early diagnosis is important because deficits are reversible and a delay in treatment is associated with permanent morbidity. Tortuous flow voids on MRI are not universally present; thus, recognition of a unique gadolinium enhancement pattern may also aid in the early recognition and treatment of sDAVF. Objective: To describe a unique pattern of spinal cord gadolinium enhancement on MRI in sDAVF. Design, Setting, and Participants: This retrospective evaluation included pretreatment MRIs from 80 patients referred to the Mayo Clinic, Rochester, Minnesota, from January 1, 1997, through December 31, 2017, with a confirmed diagnosis of sDAVF and a control group of 144 patients with alternative confirmed myelopathy diagnoses. All participants underwent a neurologic evaluation at the Mayo Clinic. Main Outcomes and Measures: Evidence of at least 1 focal geographic nonenhancing area within a long segment of intense holocord gadolinium enhancement (termed the missing-piece sign) on MRI. Results: Of 51 patients with an sDAVF and a pretreatment MRI with gadolinium enhancement, 44 (86%) had intraparenchymal contrast enhancement, and 19 of these patients (43%) displayed the characteristic missing-piece sign. Of these 19 patients, symptom onset occurred at a median age of 67 years (range, 27-80 years); 15 patients were men. Progressive myelopathy features affecting the lower extremities occurred during a median of 33 months (range, 1-84 months). Eleven patients (58%) received an alternative diagnosis before confirmation of sDAVF. Tortuous flow voids were present on T2-weighted MRI in 13 of 19 patients. More than 1 digital subtraction angiogram was required for 5 patients to confirm the diagnosis. The missing-piece sign was not seen in any patients from the control group. Conclusions and Relevance: This unique gadolinium enhancement pattern in sDAVF was not found in a large control group of patients with other myelopathy. Identifying the missing-piece sign on MRI could potentially result in earlier time to angiography with improved outcomes for patients with an sDAVF.

Methylene blue MMX® tablets for chromoendoscopy. Bioavailability, colon staining and safety in healthy volunteers undergoing a full colonoscopy.

Methylene blue-MMX® tablets are proposed as an aid for detection and visualisation of adenomas and carcinomas in patients undergoing colonoscopy, by improving their detection rate and highlighting the presence of the intestinal dysplastic lesions. Single total doses of 100 and 200 mg were administered to healthy volunteers undergoing a bowel cleansing preparation and a full colonoscopy to investigate the colonic staining. The pharmacokinetics of methylene blue and the safety after exposure to the tablets were also investigated. With 200 mg, the best staining, assessed as the sum of acceptable and good staining, was achieved in the ascending colon and rectosigmoid (75% subjects each), the transverse and the descending colon (approximately 63% each). Absence of staining or overstaining were reported for no colonic region of interest in any subject. Similar results were observed in the 100 mg dose group. Methylene blue blood concentrations reached a peak (Cmax) in a median time (Tmax) of 12 h with 100 mg and 16 h with 200 mg. AUC0-t was 10.7 ±â€¯6.7 µg/mLxh after 100 mg and 25.2 ±â€¯7.4 µg/mLxh after 200 mg. Half-life ranged between 9 and 22 h after the lower dose and between 6 and 26 h after the higher dose. The cumulative urinary excretion was about 28% after 100 mg and about 39% after 200 mg up to 60 h post-dose. The overall frequency of adverse events after single dose of the test product administered along with a bowel cleansing preparation was 39%, but only one was related to the test product: abnormal transaminases. The most frequent adverse event was a transient polyuria (17%). One serious adverse event (gastrointestinal haemorrhage) led the subject to study discontinuation and hospitalisation and another subject withdrew the study due to one adverse event (haematemesis). Either event was not related to methylene blue.

Evaluation of photoshop based image analysis in cytologic diagnosis of pleural fluid in comparison with conventional modalities.

BACKGROUND: The aim of this study is to investigate and compare the results of digital image analysis in pleural effusion cytology samples with conventional modalities. MATERIALS AND METHODS: In this cross-sectional study, 53 pleural fluid cytology smears from Qaem hospital pathology department, located in Mashhad, Iran were investigated. Prior to digital analysis, all specimens were evaluated by two pathologists and categorized into three groups as: benign, suspicious, and malignant. Using an Olympus microscope and Olympus DP3 digital camera, digital images from cytology slides were captured. Appropriate images (n = 130) were separately imported to Adobe Photoshop CS5 and parameters including area and perimeter, circularity, Gray Value mean, integrated density, and nucleus to cytoplasm area ratio were analyzed. RESULTS: Gray Value mean, nucleus to cytoplasm area ratio, and circularity showed the best sensitivity and specificity rates as well as significant differences between all groups. Also, nucleus area and perimeter showed a significant relation between suspicious and malignant groups with benign group. Whereas, there was no such difference between suspicious and malignant groups. CONCLUSION: We concluded that digital image analysis is welcomed in the field of research on pleural fluid smears as it can provide quantitative data to apply various comparisons and reduce interobserver variation which could assist pathologists to achieve a more accurate diagnosis.

Multi-radial LBP Features as a Tool for Rapid Glomerular Detection and Assessment in Whole Slide Histopathology Images.

We demonstrate a simple and effective automated method for the localization of glomeruli in large (~1 gigapixel) histopathological whole-slide images (WSIs) of thin renal tissue sections and biopsies, using an adaptation of the well-known local binary patterns (LBP) image feature vector to train a support vector machine (SVM) model. Our method offers high precision (>90%) and reasonable recall (>70%) for glomeruli from WSIs, is readily adaptable to glomeruli from multiple species, including mouse, rat, and human, and is robust to diverse slide staining methods. Using 5 Intel(R) Core(TM) i7-4790 CPUs with 40 GB RAM, our method typically requires ~15 sec for training and ~2 min to extract glomeruli reproducibly from a WSI. Deploying a deep convolutional neural network trained for glomerular recognition in tandem with the SVM suffices to reduce false positives to below 3%. We also apply our LBP-based descriptor to successfully detect pathologic changes in a mouse model of diabetic nephropathy. We envision potential clinical and laboratory applications for this approach in the study and diagnosis of glomerular disease, and as a means of greatly accelerating the construction of feature sets to fuel deep learning studies into tissue structure and pathology.

Automated coronary artery tree segmentation in X-ray angiography using improved Hessian based enhancement and statistical region merging.

BACKGROUND AND OBJECTIVE: Coronary artery segmentation is a fundamental step for a computer-aided diagnosis system to be developed to assist cardiothoracic radiologists in detecting coronary artery diseases. Manual delineation of the vasculature becomes tedious or even impossible with a large number of images acquired in the daily life clinic. A new computerized image-based segmentation method is presented for automatically extracting coronary arteries from angiography images. METHODS: A combination of a multiscale-based adaptive Hessian-based enhancement method and a statistical region merging technique provides a simple and effective way to improve the complex vessel structures as well as thin vessel delineation which often missed by other segmentation methods. The methodology was validated on 100 patients who underwent diagnostic coronary angiography. The segmentation performance was assessed via both qualitative and quantitative evaluations. RESULTS: Quantitative evaluation shows that our method is able to identify coronary artery trees with an accuracy of 93% and outperforms other segmentation methods in terms of two widely used segmentation metrics of mean absolute difference and dice similarity coefficient. CONCLUSIONS: The comparison to the manual segmentations from three human observers suggests that the presented automated segmentation method is potential to be used in an image-based computerized analysis system for early detection of coronary artery disease.

Comparative evaluation of image quality among different detector configurations using area detector computed tomography.

The 320-detector row computed tomography (CT) system, i.e., the area detector CT (ADCT), can perform helical scanning with detector configurations of 4-, 16-, 32-, 64-, 80-, 100-, and 160-detector rows for routine CT examinations. This phantom study aimed to compare the quality of images obtained using helical scan mode with different detector configurations. The image quality was measured using modulation transfer function (MTF) and noise power spectrum (NPS). The system performance function (SP), based on the pre-whitening theorem, was calculated as MTF2/NPS, and compared between configurations. Five detector configurations, i.e., 0.5 × 16 mm (16 row), 0.5 × 64 mm (64 row), 0.5 × 80 mm (80 row), 0.5 × 100 mm (100 row), and 0.5 × 160 mm (160 row), were compared using a constant volume CT dose index (CTDIvol) of 25 mGy, simulating the scan of an adult abdomen, and with a constant effective mAs value. The MTF was measured using the wire method, and the NPS was measured from images of a 20-cm diameter phantom with uniform content. The SP of 80-row configuration was the best, for the constant CTDIvol, followed by the 64-, 160-, 16-, and 100-row configurations. The decrease in the rate of the 100- and 160-row configurations from the 80-row configuration was approximately 30%. For the constant effective mAs, the SPs of the 100-row and 160-row configurations were significantly lower, compared with the other three detector configurations. The 80- and 64-row configurations were adequate in cases that required dose efficiency rather than scan speed.