Set Of Images Research Articles

Zigzag strip bundles and crystals II

Zigzag strip bundles are combinatorial models realizing the crystals B(∞) and the highest weight crystals B(λ) over quantum affine algebras Uq(g), and they are closely related with Nakajima monomials and Kashiwara embeddings of specific type. In this paper, we introduce new zigzag strip bundles for Uq(g), which we call reverse zigzag strip bundles in order to distinguish from the previous ones, and we give explicit 1-1 correspondences with the set of Nakajima monomials and the image of Kashiwara embedding which are different from those appeared in the study of the zigzag strip bundles. Another main result is to give different points of view about zigzag strip bundles and reverse zigzag strip bundles. Indeed, the previous 1-1 correspondences between the sets of zigzag strip bundles or reverse zigzag strip bundles, and the sets of Nakajima monomials or images of Kashiwara embeddings were determined based on the number of blocks in the columns of these strip bundles. In our work, we use the number of blocks in the rows of zigzag strip bundles and reverse zigzag strip bundles to provide characterizations of Nakajima monomials and images of Kashiwara embeddings that differ from the previous ones. That is, we give characterizations of Nakajima monomials and Kashiwara embeddings of 4 types. Further, we discuss the connection between zigzag strip bundles and reverse zigzag strip bundles.

Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)–based reconstruction: prospective, multi-reader, multi-vendor study

In this prospective, multi-reader, multi-vendor study, we evaluated the performance of a commercially available deep neural network (DNN)–based MR image reconstruction in enabling accelerated 2D fast spin-echo (FSE) knee imaging. Forty-five subjects were prospectively enrolled and randomly divided into three 3T MRIs. Conventional 2D FSE and accelerated 2D FSE sequences were acquired for each subject, and the accelerated FSE images were reconstructed and enhanced with DNN–based reconstruction software (FSE-DNN). Quantitative assessments and diagnostic performances were independently evaluated by three musculoskeletal radiologists. For statistical analyses, paired t-tests, and Pearson’s correlation were used for image quality comparison and inter-reader agreements. Accelerated FSE-DNN reduced scan times by 41.0% on average. FSE-DNN showed better SNR and CNR (p < 0.001). Overall image quality of FSE-DNN was comparable (p > 0.05), and diagnostic performances of FSE-DNN showed comparable lesion detection. Two of cartilage lesions were under-graded or over-graded (n = 2) while there was no significant difference in other image sets (n = 43). Overall inter-reader agreement between FSE-conventional and FSE-DNN showed good agreement (R2 = 0.76; p < 0.001). In conclusion, DNN-based reconstruction can be applied to accelerated knee imaging in multi-vendor MRI scanners, with reduced scan time and comparable image quality. This study suggests the potential for DNN-accelerated knee MRI in clinical practice.

A Sub-Second Method for SAR Image Registration Based on Hierarchical Episodic Control

For Synthetic Aperture Radar (SAR) image registration, successive processes following feature extraction are required by both the traditional feature-based method and the deep learning method. Among these processes, the feature matching process—whose time and space complexity are related to the number of feature points extracted from sensed and reference images, as well as the dimension of feature descriptors—proves to be particularly time consuming. Additionally, the successive processes introduce data sharing and memory occupancy issues, requiring an elaborate design to prevent memory leaks. To address these challenges, this paper introduces the OptionEM-based reinforcement learning framework to achieve end-to-end SAR image registration. This framework outputs registered images directly without requiring feature matching and the calculation of the transformation matrix, leading to significant processing time savings. The Transformer architecture is employed to learn image features, while a correlation network is introduced to learn the correlation and transformation matrix between image pairs. Reinforcement learning, as a decision process, can dynamically correct errors, making it more-efficient and -robust compared to supervised learning mechanisms such as deep learning. We present a hierarchical reinforcement learning framework combined with Episodic Memory to mitigate the inherent problem of invalid exploration in generalized reinforcement learning algorithms. This approach effectively combines coarse and fine registration, further enhancing training efficiency. Experiments conducted on three sets of SAR images, acquired by TerraSAR-X and Sentinel-1A, demonstrated that the proposed method’s average runtime is sub-second, achieving subpixel registration accuracy.

SynCLay: Interactive synthesis of histology images from bespoke cellular layouts

Automated synthesis of histology images has several potential applications in computational pathology. However, no existing method can generate realistic tissue images with a bespoke cellular layout or user-defined histology parameters. In this work, we propose a novel framework called SynCLay (Synthesis from Cellular Layouts) that can construct realistic and high-quality histology images from user-defined cellular layouts along with annotated cellular boundaries. Tissue image generation based on bespoke cellular layouts through the proposed framework allows users to generate different histological patterns from arbitrary topological arrangement of different types of cells (e.g., neutrophils, lymphocytes, epithelial cells and others). SynCLay generated synthetic images can be helpful in studying the role of different types of cells present in the tumor microenvironment. Additionally, they can assist in balancing the distribution of cellular counts in tissue images for designing accurate cellular composition predictors by minimizing the effects of data imbalance. We train SynCLay in an adversarial manner and integrate a nuclear segmentation and classification model in its training to refine nuclear structures and generate nuclear masks in conjunction with synthetic images. During inference, we combine the model with another parametric model for generating colon images and associated cellular counts as annotations given the grade of differentiation and cellularities (cell densities) of different cells. We assess the generated images quantitatively using the Frechet Inception Distance and report on feedback from trained pathologists who assigned realism scores to a set of images generated by the framework. The average realism score across all pathologists for synthetic images was as high as that for the real images. Moreover, with the assistance from pathologists, we showcase the ability of the generated images to accurately differentiate between benign and malignant tumors, thus reinforcing their reliability. We demonstrate that the proposed framework can be used to add new cells to a tissue images and alter cellular positions. We also show that augmenting limited real data with the synthetic data generated by our framework can significantly boost prediction performance of the cellular composition prediction task. The implementation of the proposed SynCLay framework is available at https://github.com/Srijay/SynCLay-Framework.

Semiautomatic Mapping of Center Pivot Irrigated Areas Using Sentinel-2 Images and GEOBIA Approach

Image analysis and feature extraction of remoted sensing data are significant for mapping irrigated agriculture areas as a source of information to improve water management and agricultural planning. This paper presents an image segmented base approach GEOBIA (Geographic Object-Based Image Analysis) to extract irrigated areas by Center Pivot Irrigation System (CPIS). This study suggests a semi-automated recognition of circular patterns for the mapping of irrigated regions by center pivots, using Sentinel -2 MSI images, 10 meters spatial resolution. A set of images from different seasons, humid and dry are used to maximize de CPIS’s occurrence. A multiresolution segmentation method was applied, and a large number of segment-based shape features was extracted and used as input to a feature selection procedure (shape descriptors: Area; Compactness; Circularity Factor; Length/Width; Radius of smallest enclosing ellipse; and Roundness). In addition, another shape descriptor “Circularity Factor” was developed in this research and played an important role during preliminaries classification processes. The accuracy assessment of preliminaries classifications has validated used the Circularity Factor together with the other chosen shape descriptors to reach better results to CPIS’s detection. Furthermore, 86.23% of the CPIS mapped in the classification process is in accordance with the ground truth map. This methodology can be used to map large areas in a relatively short time and provides a tool for monitoring irrigated areas.

African bovid tribe classification using transfer learning and computer vision.

Objective analytical identification methods are still a minority in the praxis of paleobiological sciences. Subjective interpretation of fossils and their modifications remains a nonreplicable expert endeavor. Identification of African bovids is a crucial element in the reconstruction of paleo-landscapes, ungulate paleoecology, and, eventually, hominin adaptation and ecosystemic reconstruction. Recent analytical efforts drawing on Fourier functional analysis and discrimination methods applied to occlusal surfaces of teeth have provided a highly accurate framework to correctly classify African bovid tribes and taxa. Artificial intelligence tools, like computer vision, have also shown their potential to be objectively more accurate in the identification of taphonomic agency than human experts. For this reason, here we implement some of the most successful computer vision methods, using transfer learning and ensemble analysis, to classify bidimensional images of African bovid teeth and show that 92% of the large testing set of images of African bovid tribes analyzed could be correctly classified. This brings an objective tool to paleoecological interpretation, where bovid identification and paleoecological interpretation can be more confidently carried out.

Machine Learning Approaches for Classification of Ultra High Carbon Steel Micrographs

The aim of this investigation is to analyze the performance of several supervised machine learning algorithms for solving the automatic classification problem of steel image microstructures. We conducted an experiment using a public-domain dataset of Ultra High Carbon Steel Micrographs (UHCSM). This image database consists of a collection of scanning electron micrographs (SEM) taken from samples of a commercial roll-mill casting with a nominal carbon of 2%. Heat treatments such as annealing, water quenching, air and furnace cooling were performed on steel samples so primary microconstituents could be found in micrographs. Each of these microconstituents defines each of the categories of classification to be accomplished by machine learning algorithms. The heat treatments brought about 4 usable classes (sets of images) of primary microconstituents: pearlite, spheroidite, proeutectoid cementite network, pearlite containing spheroidite. All labeled images are prepared to improve models' accuracy in a preprocessing stage so that the image dataset is ready for feature extraction. In order to develop classification models, we put to the test distinct machine learning approaches by working with Matlab's classification learner application where we perform automated training to search for the best classification model type, including Decision Trees, Support Vector Machines (SVM), Discriminant Analysis, Nearest Neighbors, Naive Bayes, Ensemble k-NN, and Neural Network classification. For obtaining the features of the images (feature extraction) we choose the method of Bag-of-features with 400 words for the first experiment, and 327 words by removing less important features for a second experiment. The experimented models reached very different accuracy values on training, with SVM as the best classifier which gets 91.6% accuracy. We can conclude that classic machine learning algorithms solve the classification, but an accuracy improvement can be reached by investigating deep learning techniques.

Using Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer.

Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the "Not completely responding" class and 44 patients (61.1%) belonged to the 'Completely responding' class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest ("Not completely responding" vs. "Completely responding"), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9-84.6], an accuracy (%) of 74, 74.1 [72.1-76.1], a sensitivity (%) of 71, 73.8 [68.7-78.9], and a specificity (%) of 75, 74.2 [71-77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.

Virtual Volumetric Additive Manufacturing (VirtualVAM)

AbstractTomographic volumetric additive manufacturing (VAM) produces arbitrary 3D geometries by exposure of a rotating volume of photopolymer resin to tomographically‐patterned illumination. This enables high speed, layer‐less printing of parts from a wide range of photopolymers not amenable to layer‐by‐layer processes. Since the entire geometry is produced at once over the course of a few seconds to minutes, molecular diffusion length scales become significant to the printing process. Understanding these molecular reaction and diffusion processes is imperative for advancing VAM to a usable technology. These processes are experimentally very difficult to monitor and measure. Herein, VirtualVAM ‐ a simulation framework for modeling the tomographic VAM process, is developed and experimentally validated. VirtualVAM simulates reaction, diffusion, and heat generation processes over the course of a print with single‐voxel resolution. From a few experimentally‐determined input parameters and a set of images for projection, VirtualVAM is able to generate a large spatio‐temporal data set for any given tomographic VAM print. Using VirtualVAM, a number of experimentally‐unattainable aspects of the VAM process are investigated such as single‐voxel conversion profiles, effect of molecular oxygen, and stopping time determination. VirtualVAM also enables the optimization of exposure patterns to further improve contrast between in‐part and out‐of‐part delivered dose.

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources.

Access to radiotherapy worldwide is limited. The Radiation Planning Assistant (RPA) is a fully automated, web-based tool that is being developed to offer fully automated radiotherapy treatment planning tools to clinics with limited resources. The goal is to help clinical teams scale their efforts, thus reaching more patients with cancer. The user connects to the RPA via a webpage, completes a Service Request (prescription and information about the radiotherapy targets), and uploads the patient's CT image set. The RPA offers two approaches to automated planning. In one-step planning, the system uses the Service Request and CT scan to automatically generate the necessary contours and treatment plan. In two-step planning, the user reviews and edits the automatically generated contours before the RPA continues to generate a volume-modulated arc therapy plan. The final plan is downloaded from the RPA website and imported into the user's local treatment planning system, where the dose is recalculated for the locally commissioned linac; if necessary, the plan is edited prior to approval for clinical use.

Protocol Establishment and Reliability Verification of Three-Dimensional Digital Stereophotogrammetry in Lower Eyelid Anthropometry.

Three-dimensional (3D) stereophotogrammetry has been widely used in anthropometry for both medical and esthetic purposes. However, no studies have assessed its reliability on measuring the lower eyelid by 3D imaging. This study aimed to establish a standardized 3D anthropometric protocol for lower eyelid region and validate its reliability. Fifty-eight participants (116 eyes) were recruited with mean age of 39.14 ± 11.25 years. Two sets of VECTRA 3D images were taken for each subject, and each set of images was individually measured twice by two raters. Twenty-seven landmarks were identified in the lower eyelid region, and then 19 linear, 4 curvilinear, 7 angular and 2 areal metrics were assessed for intrarater, interrater and intramethod reliability. High reliability was found in this 3D imaging-based lower eyelid anthropometry. The mean absolute difference within 2 intrarater measurement were 0.22 and 0.08 units, the technical errors measurement were 0.31 and 0.15 units, the relative errors of measurement were 0.90% and 0.31%, the relative technical errors of measurement were 1.53% and 0.64%, and the intra-group correlation coefficient was 0.99 and 0.99. The results for interrater measurement were 0.53 units, 0.59 units, 2.94%, 3.41% and 0.96, and for intramethod measurement were 0.71 units, 0.77 units, 4.12%, 4.05% and 0.95 units, respectively. 3D stereophotogrammetry is reliable for lower eyelid anthropometry. The standardized protocol can be further applied for many purposes such as lower eyelid aging evaluation, surgical related assessment and periocular rejuvenation plan. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Multi-planar low-coherence diffraction imaging

Coherent diffraction imaging (CDI) is a popular methodology for quantitative phase restoration and wavefront measurements from several desired intensity measurements that have wide applications ranging from wavefront sensing in adaptive optics to optical imaging. To overcome the problem of image quality degradation caused by the high coherence of the light source, a multi-planar low-coherent diffraction imaging (LCDI) method under low-coherence light sources was proposed and verified by measuring an U.S. Air Force (USAF) resolution test target and a nine-letter element. Negative lenses with different focal lengths were designed as filters in the image-relay system to capture multi-planar diffraction patterns at a single recording plane, and a multi-planar LCDI algorithm was used to reconstruct the test sample using a set of intensity images. Its feasibility was demonstrated experimentally using a super-radiation light-emitting diode. Considering its compact setup, easy realization, high speed, and easy operation in phase recovery, this method is effective for rapidly detecting phase and wavefront measurements with high accuracy and resolution.

QS-ADN: quasi-supervised artifact disentanglement network for low-dose CT image denoising by local similarity among unpaired data

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is expensive to obtain and cannot be perfectly simulated. Unsupervised learning utilizes unpaired data and is highly desirable for LDCT denoising. As an example, an artifact disentanglement network (ADN) relies on unpaired images and obviates the need for supervision but the results of artifact reduction are not as good as those through supervised learning. An important observation is that there is often hidden similarity among unpaired data that can be utilized. This paper introduces a new learning mode, called quasi-supervised learning, to empower ADN for LDCT image denoising. For every LDCT image, the best matched image is first found from an unpaired normal-dose CT (NDCT) dataset. Then, the matched pairs and the corresponding matching degree as prior information are used to construct and train our ADN-type network for LDCT denoising. The proposed method is different from (but compatible with) supervised and semi-supervised learning modes and can be easily implemented by modifying existing networks. The experimental results show that the method is competitive with state-of-the-art methods in terms of noise suppression and contextual fidelity. The code and working dataset are publicly available at https://github.com/ruanyuhui/ADN-QSDL.git.

Deep Learning for Fully Automatic Tumor Segmentation on Serially Acquired Dynamic Contrast-Enhanced MRI Images of Triple-Negative Breast Cancer.

Accurate tumor segmentation is required for quantitative image analyses, which are increasingly used for evaluation of tumors. We developed a fully automated and high-performance segmentation model of triple-negative breast cancer using a self-configurable deep learning framework and a large set of dynamic contrast-enhanced MRI images acquired serially over the patients' treatment course. Among all models, the top-performing one that was trained with the images across different time points of a treatment course yielded a Dice similarity coefficient of 93% and a sensitivity of 96% on baseline images. The top-performing model also produced accurate tumor size measurements, which is valuable for practical clinical applications.

Multi-modal deep fusion for bridge condition assessment

Bridge condition rating is a challenging task as it largely depends on the experience-level of the manual inspection and therefore is prone to human errors. The inspection report often consists of a collection of images and sequences of sentences (text) explaining the condition of the considered bridge. In a routine manual bridge inspection, an inspector collects a set of images and textual descriptions of bridge components and assigns an overall condition rating (ranging between 0 and 9) based on the collected information. Unfortunately, this method of bridge inspection has been shown to yield inconsistent condition ratings that correlate with inspector experience. To improve the consistency among image-text inspection data and further predict the accordant condition ratings, this study first provides a collective image-text dataset, extracted from the collection of bridge inspection reports from the Virginia Department of Transportation. Using this dataset, we have developed novel deep learning-base methods for an automatic bridge condition rating prediction based on data fusion between the textual and visual data from the collected report sets.Our proposed multi modal deep fusion approach constructs visual and textual representations for images and sentences separately using appropriate encoding functions, and then fuses representations of images and text to enhance the multi-modal prediction performance of the assigned condition ratings. Moreover, we study interpretations of the deployed deep models using saliency maps to identify parts of the image-text inputs that are essential in condition rating predictions. The findings of this study point to potential improvements by leveraging consistent image-text inspection data collection as well as leveraging the proposed deep fusion model to improve the bridge condition prediction rating from both visual and textual reports.

A novel approach to the assessment of higher-order rule learning in male mice.

Historically, the development of valid and reliable methods for assessing higher-order cognitive abilities (e.g., rule learning and transfer) has been difficult in rodent models. To date, limited evidence supports the existence of higher cognitive abilities such as rule generation and complex decision-making in mice, rats, and rabbits. To this end, we sought to develop a task that would require mice to learn and transfer a rule. We trained mice to visually discriminate a series of images (image set, six total) of increasing complexity following three stages: (1) learn a visual target, (2) learn a rule (ignore any new images around the target), and finally (3) apply this rule in abstract form to a comparable but new image set. To evaluate learning for each stage, we measured (1) days (and performance by day) to discriminate the original target at criterion, (2) days (and performance by day) to get back to criterion when images in the set were altered by the introduction of distractors (rule learning), and (3) overall days (and performance by day) to criterion when experienced versus naïve cohorts of mice were tested on the same image set (rule transfer). Twenty-seven wild-type male C57 mice were tested using Bussey-Saksida touchscreen operant conditioning boxes (Lafayette Instruments). Two comparable black-white image sets were delivered sequentially (counterbalanced for order) to two identical cohorts of mice. Results showed that all mice were able to effectively learn their initial target image and could recall it >80 d later. We also found that mice were able to quickly learn and apply a "rule" : Ignore new distractors and continue to identify their visual target embedded in more complex images. The presence of rule learning was supported because performance criterion thresholds were regained much faster than initial learning when distractors were introduced. On the other hand, mice appeared unable to transfer this rule to a new set of stimuli. This is supported because visual discrimination curves for a new image set were no better than an initial (naïve) learning by a matched cohort of mice. Overall results have important implications for phenotyping research and particularly for the modeling of complex disorders in mice.

Novel Deep Learning Segmentation Models for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients.

MR-guided adaptive radiotherapy (MRgART) improves target coverage and organ-at-risk (OAR) sparing in pancreatic cancer radiation therapy (RT). Inter-fractional changes in patients undergoing RT require time intensive re-delineation of gross tumor volume (GTV) and OARs prior to adaptive optimization. Accurate automatic segmentation has the potential to significantly improve efficiency of the adaptive workflow. We hypothesized that state-of-the-art deep learning (DL) segmentation models could adequately segment GTV and OARs in both planning and daily fractional MR scans. The study included 21 patients with pancreatic cancer treated with MRgART (10 Gy x 5 fractions). The planning MR as well as all daily MR images and registrations were collected (6 image sets per patient and a total of 126 image sets). The planning MR and fraction 1-4 image sets were used as the training set (N = 105), while the test set (N = 21) comprised images for fraction 5, to simulate the last step of incremental learning from planning to final fraction. Evaluated contours included the GTV, Small Bowel, Large Bowel, Duodenum, Left and Right Kidney, Liver, Spinal Cord, and Stomach. To mimic clinical conditions, contour accuracy was evaluated within the ring structure surrounding the PTV, inside of which daily adaptive re-contouring is applied (2 cm expansion in the cradio-caudal direction, 3 cm expansion otherwise). We evaluated three DL model architectures: SegResNet, SegResNet 2D, and SwinUNETR to autosegment GTV and OARs. The segmentation models were trained on the training set using 5-fold cross-validation (CV) and quantitatively analyzed by comparing against clinically used contours with DICE scores. Qualitative analysis was performed by a radiation oncologist using a scoring scale: 1 = perfect, 2 = minor discrepancy, 3 = moderate discrepancy, and 4 = rejected. Overall, the DL segmentations were in acceptable agreement with clinical contours. The best performing model was the SwinUNETR model with overall training DICE = 0.88±0.06, test DICE = 0.78±0.11, and qualitative score of 1.6±0.8. The agreement between the DL model and clinical segmentation for the GTV was 0.79±0.08, with a qualitative score of 2.2±0.9. The highest and lowest OAR DICE scores were for the Left Kidney (DICE = 0.93) and Small Bowel (DICE = 0.68), respectively. The highest qualitative OAR scores were for the Kidney, Liver, and Spinal Cord (score = 1.0) and the lowest qualitative score was for the Duodenum (score = 2.3) CONCLUSION: We report here the most comprehensive work on DL segmentation for pancreatic cancer MRgART, including quantitative and clinically-pertinent qualitative evaluations of 126 image sets and 3 DL architectures. Our data show good quantitative agreement between DL and clinical contours, and acceptable clinician evaluations for the majority of GTVs and OARs. The current work has great potential to significantly reduce a major bottleneck in the MRgART workflow for pancreatic cancer patients.

Contrast-Free Super-Resolution Power Doppler (CS-PD) Based on Deep Neural Networks.

Super-resolution ultrasound microvessel imaging based on ultrasound localization microscopy (ULM) is an emerging imaging modality that is capable of resolving micrometer-scaled vessels deep into tissue. In practice, ULM is limited by the need for contrast injection, long data acquisition, and computationally expensive postprocessing times. In this study, we present a contrast-free super-resolution power Doppler (CS-PD) technique that uses deep networks to achieve super-resolution with short data acquisition. The training dataset is comprised of spatiotemporal ultrafast ultrasound signals acquired from in vivo mouse brains, while the testing dataset includes in vivo mouse brain, chicken embryo chorioallantoic membrane (CAM), and healthy human subjects. The in vivo mouse imaging studies demonstrate that CS-PD could achieve an approximate twofold improvement in spatial resolution when compared with conventional power Doppler. In addition, the microvascular images generated by CS-PD showed good agreement with the corresponding ULM images as indicated by a structural similarity index of 0.7837 and a peak signal-to-noise ratio (PSNR) of 25.52. Moreover, CS-PD was able to preserve the temporal profile of the blood flow (e.g., pulsatility) that is similar to conventional power Doppler. Finally, the generalizability of CS-PD was demonstrated on testing data of different tissues using different imaging settings. The fast inference time of the proposed deep neural network also allows CS-PD to be implemented for real-time imaging. These features of CS-PD offer a practical, fast, and robust microvascular imaging solution for many preclinical and clinical applications of Doppler ultrasound.

The Theoretical Role for Radiotherapy in Patients with Diffuse Large B-Cell Lymphoma: A Secondary Analysis of a Prospective Randomized Controlled Trial.

The role of radiotherapy (RT) for diffuse large B-cell lymphoma (DLBCL) is unclear. In patients treated with upfront chemotherapy for DLBCL, indications for RT are often considered to be bulky (7.5 cm +) or extranodal disease. This is thought to improve outcomes through improvement in local control. Many trials call into question the actual benefit of RT. Alliance/CALGB 50303 was a randomized phase III trial comparing two chemotherapy regimens for the treatment for DLBCL in which no patients were to receive RT. Our objective was to assess the theoretical impact of RT by assessing outcomes of trial patients. This secondary analysis was performed using PET/CT images and data from the NCTN/NCORP Data Archive of the National Cancer Institute. Data were originally collected on the Alliance/CALGB 50303 (NCT00118209) clinical trial. Of the 524 registered patients, data and images for 155 patients were available. Two investigators measured the largest sites of nodal involvement on PET/CT and the average was calculated-the largest was used to determine bulky disease. Bulk was defined as nodal disease with maximum diameter greater than or equal to the threshold. Thresholds (in cm) examined included: 5, 6, 7, 7.5, 8, 9, and 10. PFS was estimated for patients with versus without bulky disease and compared using the log-rank test. Of the 155 evaluable pre-treatment PET/CT image sets, 135 patients had measurable nodal disease. Fifteen patients who did not complete treatment per protocol and four patients with mediastinal B-cell lymphoma were excluded. Of the 116 analyzed patients, 45% had stage IV disease, 88% had an ECOG performance status of 0-1, and one had double-hit lymphoma. IPI was 0-2 in 62% and 3-5 in 38%. Chemotherapy was R-CHOP in 61 and DA-R-EPOCH in 55. Best response was CR in 84 patients (73%), PR in 30 (26%) and SD in 1 (1%). The median follow-up was 5 years and 32 PFS events were observed. Bulky disease was associated with elevated LDH at diagnosis (using 7.5 cm threshold: LDH elevated in 72% with bulky disease v. 40% with non-bulky, p< 0.01) and more frequent use of pegfilgrastim (51% v. 31%, respectively, p = 0.04). Overall, the 5-year PFS rate was 72.3% (95% CI 64.1-81.4). Using a 7.5 cm threshold, 5-year PFS was 62.7% in patients with bulk versus 79.3% in those without (p = 0.14). There were no significant PFS differences (p>0.05) observed at any threshold. The 5-year OS was 86.4% (95% CI 80.2-93.1); no differences in OS by bulk using any threshold were observed. In this secondary analysis of a phase III randomized trial of chemotherapy alone for DLBCL, initial bulk was not shown to be significantly associated with outcomes. Prospective data comparing consolidative RT versus no RT are necessary to determine optimal treatment paradigms.

Fuzzy Transform Image Compression in the YUV Space

This research proposes a new image compression method based on the F1-transform which improves the quality of the reconstructed image without increasing the coding/decoding CPU time. The advantage of compressing color images in the YUV space is due to the fact that while the three bands Red, Green and Blue are equally perceived by the human eye, in YUV space most of the image information perceived by the human eye is contained in the Y band, as opposed to the U and V bands. Using this advantage, we construct a new color image compression algorithm based on F1-transform in which the image compression is accomplished in the YUV space, so that better-quality compressed images can be obtained without increasing the execution time. The results of tests performed on a set of color images show that our color image compression method improves the quality of the decoded images with respect to the image compression algorithms JPEG, F1-transform on the RGB color space and F-transform on the YUV color space, regardless of the selected compression rate and with comparable CPU times.