Search

In this paper, we propose a novel contour search algorithm (CSA) for image processing. Its efficacy is evaluated through a comparative analysis with established techniques such as Canny Edge and Snakes: Active contour models, utilizing infrared thermography (IRT) images. Based on the new CSA, we investigate the influence of different pulse shapes on the IRT post-processing methodology, particularly focusing on the thermal shock response spectrum (TSRS), using two different heat sources: xenon flash lamps and a laser. Moreover, this allows for a more precise quantitative comparison of the TSRS with existing IRT post-processing techniques, including pulse phase thermography and thermal signal reconstruction, concerning the detection of defects in composite materials, particularly in carbon fiber-reinforced polymer. A quantitative comparison was performed using the Tanimoto criterion and signal-to-noise ratio. A more detailed analysis is conducted to identify inherent limitations and potential benefits of the new TSRS methodology. We further investigate and experimentally confirm our previous finding on the qualitative correlation between the one-dimensional thermal N-layer model and test data from the TSRS optimization process for defect determination. This correlation can eliminate the time-consuming optimization step, making TSRS a more attractive alternative to common IRT methods and enhancing the quantitative description of defects. [ABSTRACT FROM AUTHOR]

Objective. This study presents a universal phantom for positron emission tomography (PET) that allows arbitrary static and dynamic activity distributions of various complexities to be generated using a single PET acquisition.Approach. We collected a high-statistics dataset (with a total of 22.4 × 109prompt coincidences and an event density of 2.75 × 106events mm-3) by raster-scanning a single plane with a22Na point source mounted on a robotic arm in the field-of-view of the uEXPLORER PET/CT scanner. The source position was determined from the reconstructed dynamic frames. Uniquely, true coincidences were separated from scattered and random events based on the distance between their line-of-response and the known source location. Finally, we randomly sampled the dataset to generate the desired activity distributions modeling several different phantoms.Main results. Overall, the target and the reconstructed phantom images had good agreement. The analysis of a simple geometric distribution showed high quantitative accuracy of the phantom, with mean error of

Computer-assisted diagnosis (CAD) plays a key role in cancer diagnosis or screening. Whereas, current CAD performs poorly on whole slide image (WSI) analysis, and thus fails to generalize well. This research aims to develop an automatic classification system to distinguish between different types of carcinomas. Obtaining rich deep features in multi-class classification while achieving high accuracy is still a challenging problem. The detection and classification of cancerous cells in WSI are quite challenging due to the misclassification of normal lumps and cancerous cells. This is due to cluttering, occlusion, and irregular cell distribution. Researchers in the past mostly obtained the hand-crafted features while neglecting the above-mentioned challenges which led to a reduction of the classification accuracy. To mitigate this problem we proposed an efficient dual attention-based network (CytoNet). The proposed network is composed of two main modules (i) Efficient-Net and (ii) Dual Attention Module (DAM). Efficient-Net is capable of obtaining higher accuracy and enhancing efficiency as compared to existing Convolutional Neural Networks (CNNs). It is also useful to obtain the most generic features as it has been trained on ImageNet. Whereas DAM is very robust in obtaining attention and targeted features while negating the background. In this way, the combination of an efficient and attention module is useful to obtain the robust, and intrinsic features to obtain comparable performance. Further, we evaluated the proposed network on two well-known datasets (i) Our generated thyroid dataset (ii) Mendeley Cervical dataset (Hussain in Data Brief, 2019) with enhanced performance compared to their counterparts. CytoNet demonstrated a 99% accuracy rate on the thyroid dataset in comparison to its counterpart. The precision, recall, and F1-score values achieved on the Mendeley Cervical dataset are 0.992, 0.985, and 0.977, respectively. The code implementation is available on GitHub. https://github.com/naveedilyas/CytoNet-An-Efficient-Dual-Attention-based-Automatic-Prediction-of-Cancer-Sub-types-in-Cytol.

The human face plays a central role in emotions and social communication. The emotional and somatic motor networks generate facial behaviors, but whether facial behaviors have representations in the structural anatomy of the human brain is unknown. We coded 16 facial behaviors in 55 healthy older adults who viewed five videos that elicited emotions and examined whether individual differences in facial behavior were related to regional variation in gray matter volume. Voxel-based morphometry analyses revealed that greater emotional facial behavior during the disgust trial (i.e. greater brow furrowing and eye tightening as well as nose wrinkling and upper lip raising) and the amusement trial (i.e. greater smiling and eye tightening) was associated with larger gray matter volume in midcingulate cortex, supplementary motor area, and precentral gyrus, areas spanning both the emotional and somatic motor networks. When measured across trials, however, these facial behaviors (and others) only related to gray matter volume in the precentral gyrus, a somatic motor network hub. These findings suggest that the emotional and somatic motor networks store structural representations of facial behavior and that the midcingulate cortex is critical for generating the predictable movements in the face that arise during emotions.

Explainability of convolutional neural networks (CNNs) is integral for their adoption into radiological practice. Commonly used attribution methods localize image areas important for CNN prediction but do not characterize relevant imaging features underlying these areas, acting as a barrier to the adoption of CNNs for clinical use. We therefore propose Semantic Exploration and Explainability using a Style-based Generative Adversarial Autoencoder Network (SEE-GAAN), an explainability framework that uses latent space manipulation to generate a sequence of synthetic images that semantically visualizes how clinical and CNN features manifest within medical images. Visual analysis of changes in these sequences then facilitates the interpretation of features, thereby improving explainability. SEE-GAAN was first developed on a cohort of 26,664 chest radiographs across 15,409 patients from our institution. SEE-GAAN sequences were then generated across several clinical features and CNN predictions of NT-pro B-type natriuretic peptide (BNPP) as a proxy for acute heart failure. Radiological interpretations indicated SEE-GAAN sequences captured relevant changes in anatomical and pathological morphology associated with clinical and CNN predictions and clarified ambiguous areas highlighted by commonly used attribution methods. Our study demonstrates SEE-GAAN can facilitate our understanding of clinical features for imaging biomarker exploration and improve CNN transparency over commonly used explainability methods.

Early stages of Alzheimer's disease (AD) are associated with volume reductions in specific subregions of the medial temporal lobe (MTL). Using a manual segmentation method-the Olsen-Amaral-Palombo (OAP) protocol-previous work in healthy older adults showed that reductions in grey matter volumes in MTL subregions were associated with lower scores on the Montreal Cognitive Assessment (MoCA), suggesting atrophy may occur prior to diagnosis of mild cognitive impairment, a condition that often progresses to AD. However, current "gold standard" manual segmentation methods are labour intensive and time consuming. Here, we examined the utility of Automatic Segmentation of Hippocampal Subfields (ASHS) to detect volumetric differences in MTL subregions of healthy older adults who varied in cognitive status as determined by the MoCA. We trained ASHS on the OAP protocol to create the ASHS-OAP atlas and then examined how well automated segmentation replicated manual segmentation. Volumetric measures obtained from the ASHS-OAP atlas were also contrasted against those from the ASHS-PMC atlas, a widely used atlas provided by the ASHS team. The pattern of volumetric results was similar between the ASHS-OAP atlas and manual segmentation for anterolateral entorhinal cortex and perirhinal cortex, suggesting that ASHS-OAP is a viable alternative to current manual segmentation methods for detecting group differences based on cognitive status. Although ASHS-OAP and ASHS-PMC produced varying volumes for most regions of interest, they both identified early signs of neurodegeneration in CA2/CA3/DG and identified marginal differences in entorhinal cortex. Our findings highlight the utility of automated segmentation methods but still underscore the need for a unified and harmonized MTL segmentation atlas.

Inquiries into properties of brain structure and function have progressed due to developments in magnetic resonance imaging (MRI). To sustain progress in investigating and quantifying neuroanatomical details in vivo, the reliability and validity of brain measurements are paramount. Quality control (QC) is a set of procedures for mitigating errors and ensuring the validity and reliability of brain measurements. Despite its importance, there is little guidance on best QC practices and reporting procedures. The study of hippocampal subfields in vivo is a critical case for QC because of their small size, inter-dependent boundary definitions, and common artifacts in the MRI data used for subfield measurements. We addressed this gap by surveying the broader scientific community studying hippocampal subfields on their views and approaches to QC. We received responses from 37 investigators spanning 10 countries, covering different career stages, and studying both healthy and pathological development and aging. In this sample, 81% of researchers considered QC to be very important or important, and 19% viewed it as fairly important. Despite this, only 46% of researchers reported on their QC processes in prior publications. In many instances, lack of reporting appeared due to ambiguous guidance on relevant details and guidance for reporting, rather than absence of QC. Here, we provide recommendations for correcting errors to maximize reliability and minimize bias. We also summarize threats to segmentation accuracy, review common QC methods, and make recommendations for best practices and reporting in publications. Implementing the recommended QC practices will collectively improve inferences to the larger population, as well as have implications for clinical practice and public health.

We proposed an end-to-end deep learning convolutional neural network (DCNN) for region-of-interest based multi-parameter quantification (RMQ-Net) to accelerate quantitative ultrashort echo time (UTE) MRI of the knee joint with automatic multi-tissue segmentation and relaxometry mapping. The study involved UTE-based T1 (UTE-T1) and Adiabatic T1ρ (UTE-AdiabT1ρ) mapping of the knee joint of 65 human subjects, including 20 normal controls, 29 with doubtful-minimal osteoarthritis (OA), and 16 with moderate-severe OA. Comparison studies were performed on UTE-T1 and UTE-AdiabT1ρ measurements using 100%, 43%, 26%, and 18% UTE MRI data as the inputs and the effects on the prediction quality of the RMQ-Net. The RMQ-net was modified and retrained accordingly with different combinations of inputs. Both ROI-based and voxel-based Pearson correlation analyses were performed. High Pearson correlation coefficients were achieved between the RMQ-Net predicted UTE-T1 and UTE-AdiabT1ρ results and the ground truth for segmented cartilage with acceleration factors ranging from 2.3 to 5.7. With an acceleration factor of 5.7, the Pearson r-value achieved 0.908 (ROI-based) and 0.945 (voxel-based) for UTE-T1, and 0.733 (ROI-based) and 0.895 (voxel-based) for UTE-AdiabT1ρ, correspondingly. The results demonstrated that RMQ-net can significantly accelerate quantitative UTE imaging with automated segmentation of articular cartilage in the knee joint.

PURPOSE: CT Hounsfield Units (HUs) are converted to electron density using a calibration curve obtained from physical measurements of an electron density phantom. HU values assigned to an MRI-derived synthetic computed tomography (sCT) may present a different relationship with electron density compared to CT HU. Correct assignment of sCT HU values is critical for accurate dose calculation and delivery. The goals of this work were to develop a sCT calibration curve using patient data acquired on a clinically commissioned CT scanner and assess for CyberKnife- and volumetric modulated arc therapy (VMAT)-based MR-only treatment planning of prostate SBRT. METHODS: Same-day CT and MRI simulation in the treatment position were performed on 10 patients treated with SBRT to the prostate. Dixon in-phase and out-of-phase MRIs were acquired on a 3T scanner using a 3D T1-weighted gradient-echo sequence to generate sCTs using a commercial sCT algorithm. CT and sCT datasets were co-registered and HU values compared using mean absolute error (MAE). An optimized HU-to-density calibration curve was created based on average HU values across an institutional patient database for each of the four sCT tissue types. Clinical CyberKnife and VMAT treatment plans were generated on each patient CT and recomputed onto corresponding sCTs. Dose distributions computed using CT and sCT were compared using gamma criteria and dose-volume-histograms. RESULTS: For the optimized calibration curve, HU values were -96, 37, 204, and 1170 and relative electron densities were 0.95, 1.04, 1.1, and 1.7 for adipose, soft tissue, inner bone, and outer bone, respectively. The proposed sCT protocol produced total MAE of 94 ± 20HU. Gamma values mean ± std (min-max) were 98.9% ± 0.9% (97.1%-100%) and 97.7% ± 1.3% (95.3%-99.3%) for VMAT and CyberKnife plans, respectively. CONCLUSION: MRI-derived sCT using the proposed approach shows excellent dosimetric agreement with conventional CT simulation, demonstrating the feasibility of MRI-derived sCT for prostate SBRT treatment planning.

Slow motion is a popular video editing tool used to enhance short-form videos (e.g., reels, stories, GIFs), which are commonly found in media entertainment and marketing communications. This research shows that slow motion increases the virality (e.g., likes, votes, views) of short-form videos and boosts brand liking, choice, and willingness to pay. The effect occurs because slow motion enhances the hedonic component of the viewing experience via processing fluency. By documenting how the success of slow motion is subject to moderators, this work shows marketers, entertainment producers, and everyday people how to use slow motion more effectively. Across a large-scale field data set and six experiments, the authors highlight that slow motion is especially effective when applied to short-form videos that are inherently pleasant and that involve complex movements that are difficult to perceive at regular speed. However, even simple movements benefit from slow motion when content creators zoom in on subtle movements to increase complexity. Moreover, slow motion is more effective when viewers engage in less elaborate processing. Finally, the authors show that the perceived disfluency of fast-motion editing is effective at boosting brand evaluations when viewers desire excitement. [ABSTRACT FROM AUTHOR]

Smart machine tools must be able to recognise the materials they interact with, in order to independently decide on what actions to be taken whenever needed. The purpose of this research is to offer a generic method to automate material identification and classification task utilising image processing and machine learning techniques so as to improve the cognitive capabilities of machine tools. A dataset of four material surfaces; Copper, Aluminium, Stainless Steel, and Bronze is generated and the RGB data are extracted. These colour channels are utilised as input features to train the machine learning algorithms. Convolutional Neural Network (CNN) and other classification methods like Support Vector Machine (SVM), Decision Trees, and k-Nearest Neighbour are also used to classify material images based on the generated dataset. A unique generalised technique, based on CNN, has been proposed to accurately recognise and categorise round surfaced materials during machining. The accuracy achieved by the classifier has reached 100% during training and testing. Test images are used to confirm the proposed methodology's capability to distinguish between materials based on various illumination environments and camera positions. [ABSTRACT FROM AUTHOR]

Image-based deformation estimation is an important tool used in a variety of engineering problems, including crack propagation, fracture, and fatigue failure. These tools have been important in biomechanics research where measuring in vitro and in vivo tissue deformations are important for evaluating tissue health and disease progression. However, accurately measuring tissue deformation in vivo is particularly challenging due to limited image signal-to-noise ratio. Therefore, we created a novel deep-learning approach for measuring deformation from a sequence of images collected in vivo called StrainNet. Utilizing a training dataset that incorporates image artifacts, StrainNet was designed to maximize performance in challenging, in vivo settings. Artificially generated image sequences of human flexor tendons undergoing known deformations were used to compare benchmark StrainNet against two conventional image-based strain measurement techniques. StrainNet outperformed the traditional techniques by nearly 90%. High-frequency ultrasound imaging was then used to acquire images of the flexor tendons engaged during contraction. Only StrainNet was able to track tissue deformations under the in vivo test conditions. Findings revealed strong correlations between tendon deformation and applied forces, highlighting the potential for StrainNet to be a valuable tool for assessing rehabilitation strategies or disease progression. Additionally, by using real-world data to train our model, StrainNet was able to generalize and reveal important relationships between the effort exerted by the participant and tendon mechanics. Overall, StrainNet demonstrated the effectiveness of using deep learning for image-based strain analysis in vivo.

We present a new method to measure sub-microcurie activities of photon-emitting radionuclides in organs and lesions of small animals in vivo. Our technique, named the collimator-less likelihood fit, combines a very high sensitivity collimatorless detector with a Monte Carlo-based likelihood fit in order to estimate the activities in previously segmented regions of interest along with their uncertainties. This is done directly from the photon projections in our collimatorless detector and from the region of interest segmentation provided by an x-ray computed tomography scan. We have extensively validated our approach with 225Ac experimentally in spherical phantoms and mouse phantoms, and also numerically with simulations of a realistic mouse anatomy. Our method yields statistically unbiased results with uncertainties smaller than 20% for activities as low as ~111Bq (3nCi) and for exposures under 30 minutes. We demonstrate that our method yields more robust recovery coefficients when compared to SPECT imaging with a commercial pre-clinical scanner, specially at very low activities. Thus, our technique is complementary to traditional SPECT/CT imaging since it provides a more accurate and precise organ and tumor dosimetry, with a more limited spatial information. Finally, our technique is specially significant in extremely low-activity scenarios when SPECT/CT imaging is simply not viable.

SIGNIFICANCE: Spatial frequency domain imaging (SFDI) applies patterned near-infrared illumination to quantify the optical properties of subsurface tissue. The periocular region is unique due to its complex ocular adnexal anatomy. Although SFDI has been successfully applied to relatively flat in vivo tissues, regions that have significant height variations and curvature may result in optical property inaccuracies. AIM: We characterize the geometric impact of the periocular region on SFDI imaging reliability. APPROACH: SFDI was employed to measure the reduced scattering coefficient ( μ s ) and absorption coefficient ( μ a ) of the periocular region in a cast facial tissue-simulating phantom by capturing images along regions of interest (ROIs): inferior temporal quadrant (ITQ), inferior nasal quadrant (INQ), superior temporal quadrant (STQ), central eyelid margin (CEM), rostral lateral nasal bridge (RLNB), and forehead (FH). The phantom was placed on a chin rest and imaged nine times from an en face or side profile position, and the flat back of the phantom was measured 15 times. RESULTS: The measured μ a and μ s of a cast facial phantom are accurate when comparing the ITQ, INQ, STQ, and FH to its flat posterior surface. Paired t tests of ITQ, INQ, STQ, and FH μ a and μ s concluded that there is not enough evidence to suggest that imaging orientation impacted the measurement accuracy. Regions of extreme topographical variation, i.e., CEM and RLNB, did exhibit differences in measured optical properties. CONCLUSIONS: We are the first to evaluate the geometric implications of wide-field imaging along the periocular region using a solid tissue-simulating facial phantom. Results suggest that the ITQ, INQ, STQ, and FH of a generalized face have minimal impact on the SFDI measurement accuracy. Areas with heightened topographic variation exhibit measurement variability. Device and facial positioning do not appear to bias measurements. These findings confirm the need to carefully select ROIs when measuring optical properties along the periocular region.

The dry mass and the orientation of biomolecules can be imaged without a label by measuring their permittivity tensor (PT), which describes how biomolecules affect the phase and polarization of light. Three-dimensional (3D) imaging of PT has been challenging. We present a label-free computational microscopy technique, PT imaging (PTI), for the 3D measurement of PT. PTI encodes the invisible PT into images using oblique illumination, polarization-sensitive detection and volumetric sampling. PT is decoded from the data with a vectorial imaging model and a multi-channel inverse algorithm, assuming uniaxial symmetry in each voxel. We demonstrate high-resolution imaging of PT of isotropic beads, anisotropic glass targets, mouse brain tissue, infected cells and histology slides. PTI outperforms previous label-free imaging techniques such as vector tomography, ptychography and light-field imaging in resolving the 3D orientation and symmetry of organelles, cells and tissue. We provide open-source software and modular hardware to enable the adoption of the method.

SIGNIFICANCE: Information about the spatial organization of fibers within a nerve is crucial to our understanding of nerve anatomy and its response to neuromodulation therapies. A serial block-face microscopy method [three-dimensional microscopy with ultraviolet surface excitation (3D-MUSE)] has been developed to image nerves over extended depths ex vivo. To routinely visualize and track nerve fibers in these datasets, a dedicated and customizable software tool is required. AIM: Our objective was to develop custom software that includes image processing and visualization methods to perform microscopic tractography along the length of a peripheral nerve sample. APPROACH: We modified common computer vision algorithms (optic flow and structure tensor) to track groups of peripheral nerve fibers along the length of the nerve. Interactive streamline visualization and manual editing tools are provided. Optionally, deep learning segmentation of fascicles (fiber bundles) can be applied to constrain the tracts from inadvertently crossing into the epineurium. As an example, we performed tractography on vagus and tibial nerve datasets and assessed accuracy by comparing the resulting nerve tracts with segmentations of fascicles as they split and merge with each other in the nerve sample stack. RESULTS: We found that a normalized Dice overlap ( Dice norm ) metric had a mean value above 0.75 across several millimeters along the nerve. We also found that the tractograms were robust to changes in certain image properties (e.g., downsampling in-plane and out-of-plane), which resulted in only a 2% to 9% change to the mean Dice norm values. In a vagus nerve sample, tractography allowed us to readily identify that subsets of fibers from four distinct fascicles merge into a single fascicle as we move ∼ 5    mm along the nerves length. CONCLUSIONS: Overall, we demonstrated the feasibility of performing automated microscopic tractography on 3D-MUSE datasets of peripheral nerves. The software should be applicable to other imaging approaches. The code is available at https://github.com/ckolluru/NerveTracker.

PurposeHigh quality scan prescription that optimally covers the area of interest with scan planes aligned to relevant anatomical structures is crucial for error-free radiologic interpretation. The goal of this project was to develop a machine learning pipeline for oblique scan prescription that could be trained on localizer images and metadata from previously acquired MR exams.MethodsA novel Multislice Rotational Region-based Convolutional Neural Network (MS-R2CNN) architecture was developed. Based on this architecture, models for automated prescription sagittal lumbar spine acquisitions from axial, sagittal, and coronal localizer slices were trained. The automated prescription pipeline was integrated with the scanner console software and evaluated in experiments with healthy volunteers (N = 3) and patients with lower-back pain (N = 20).ResultsExperiments in healthy volunteers demonstrated high accuracy of automated prescription in all subjects. There was good agreement between alignment and coverage of manual and automated prescriptions, as well as consistent views of the lumbar spine at different positions of the subjects within the scanner bore. In patients with lower-back pain, the generated prescription was applied in 18 cases (90% of the total number). None of the cases required major adjustment, while in 11 cases (55%) there were minor manual adjustments to the generated prescription.ConclusionsThis study demonstrates the ability of oriented object detection-based models to be trained to prescribe oblique lumbar spine MRI acquisitions without the need of manual annotation or feature engineering and the feasibility of using machine learning-based pipelines on the scanner for automated prescription of MRI acquisitions.

In finishing simulations, achieving accurate results can be challenging due to the minimal amount of material removal and the limited measurement range of surface micro-topography instruments. To overcome these limitations, a novel high-fidelity modeling method combining image mosaic and wavelet decomposition technologies is proposed in this paper. We achieve the stitching of narrow field and high pixel micro morphology images through four steps: image feature extraction, overlapped feature matching, feature fusion, and stitching effect evaluation. On this basis, the wavelet decomposition method is employed to separate detection signals based on their respective frequencies, allowing the establishment of a datum plane and a roughness surface. The point cloud model undergoes a transformation into a continuous geometric model via the Poisson reconstruction algorithm. In the case study, four sample images of an aluminum alloy sheet after barrel finishing were collected using the ZeGage Plus optical profiler. Each image has an actual size of 834.37 μm × 834.37 μm. Subsequently, a comparison was carried out between the physical and simulation experiments. The results clearly indicate that the proposed method has the potential to enhance the accuracy of the finishing simulation by over 30%. The error between the resulting model and the actual surface of the part can be controlled within 1 μm.

PURPOSE: This study enhances Meibomian gland (MG) infrared image analysis in dry eye (DE) research through artificial intelligence (AI). It is comprised of two main stages: automated eyelid detection and tarsal plate segmentation to standardize meibography image analysis. The goal is to address limitations of existing assessment methods, bridge the curated and real-world dataset gap, and standardize MG image analysis. METHODS: The approach involves a two-stage process: automated eyelid detection and tarsal plate segmentation. In the first stage, an AI model trained on curated data identifies relevant eyelid areas in non-curated datasets. The second stage refines the eyelid area in meibography images, enabling precise comparisons between normal and DE subjects. This approach also includes specular reflection removal and tarsal plate mask refinement. RESULTS: The methodology achieved a promising instance-wise accuracy of 80.8% for distinguishing meibography images from 399 DE and 235 non-DE subjects. By integrating diverse datasets and refining the area of interest, this approach enhances meibography feature extraction accuracy. Dimension reduction through Uniform Manifold Approximation and Projection (UMAP) allows feature visualization, revealing distinct clusters for DE and non-DE phenotypes. CONCLUSIONS: The AI-driven methodology presented here quantifies and classifies meibography image features and standardizes the analysis process. By bootstrapping the model from curated datasets, this methodology addresses real-world dataset challenges to enhance the accuracy of meibography image feature extraction. TRANSLATIONAL RELEVANCE: The study presents a standardized method for meibography image analysis. This method could serve as a valuable tool in facilitating more targeted investigations into MG characteristics.

Positron emission tomography (PET) is a widely utilized medical imaging modality that uses positron-emitting radiotracers to visualize biochemical processes in a living body. The spatiotemporal distribution of a radiotracer is estimated by detecting the coincidence photon pairs generated through positron annihilations. In human tissue, about 40% of the positrons form positroniums prior to the annihilation. The lifetime of these positroniums is influenced by the microenvironment in the tissue and could provide valuable information for better understanding of disease progression and treatment response. Currently, there are few methods available for reconstructing high-resolution lifetime images in practical applications. This paper presents an efficient statistical image reconstruction method for positronium lifetime imaging (PLI). We also analyze the random triple-coincidence events in PLI and propose a correction method for random events, which is essential for real applications. Both simulation and experimental studies demonstrate that the proposed method can produce lifetime images with high numerical accuracy, low variance, and resolution comparable to that of the activity images generated by a PET scanner with currently available time-of-flight resolution.

Evaluation of 3D bone morphology of the glenohumeral joint is necessary for pre-surgical planning. Zero echo time (ZTE) magnetic resonance imaging (MRI) provides excellent bone contrast and can potentially be used in place of computed tomography. Segmentation of shoulder anatomy, particularly humeral head and acetabulum, is needed for detailed assessment of each anatomy and for pre-surgical preparation. In this study we compared performance of two popular deep learning models based on Google's DeepLab and U-Net to perform automated segmentation on ZTE MRI of human shoulders. Axial ZTE images of normal shoulders (n=31) acquired at 3-Tesla were annotated for training with a DeepLab and 2D U-Net, and the trained model was validated with testing data (n=13). While both models showed visually satisfactory results for segmenting the humeral bone, U-Net slightly over-estimated while DeepLab under-estimated the segmented area compared to the ground truth. Testing accuracy quantified by Dice score was significantly higher (p

Dynamic PET allows quantification of physiological parameters through tracer kinetic modeling. For dynamic imaging of brain or head and neck cancer on conventional PET scanners with a short axial field of view, the image-derived input function (ID-IF) from intracranial blood vessels such as the carotid artery (CA) suffers from severe partial volume effects. Alternatively, optimization-derived input function (OD-IF) by the simultaneous estimation (SIME) method does not rely on an ID-IF but derives the input function directly from the data. However, the optimization problem is often highly ill-posed. We proposed a new method that combines the ideas of OD-IF and ID-IF together through a kernel framework. While evaluation of such a method is challenging in human subjects, we used the uEXPLORER total-body PET system that covers major blood pools to provide a reference for validation.MethodsThe conventional SIME approach estimates an input function using a joint estimation together with kinetic parameters by fitting time activity curves from multiple regions of interests (ROIs). The input function is commonly parameterized with a highly nonlinear model which is difficult to estimate. The proposed kernel SIME method exploits the CA ID-IF as a priori information via a kernel representation to stabilize the SIME approach. The unknown parameters are linear and thus easier to estimate. The proposed method was evaluated using 18F-fluorodeoxyglucose studies with both computer simulations and 20 human-subject scans acquired on the uEXPLORER scanner. The effect of the number of ROIs on kernel SIME was also explored.ResultsThe estimated OD-IF by kernel SIME showed a good match with the reference input function and provided more accurate estimation of kinetic parameters for both simulation and human-subject data. The kernel SIME led to the highest correlation coefficient (R = 0.97) and the lowest mean absolute error (MAE = 10.5 %) compared to using the CA ID-IF (R = 0.86, MAE = 108.2 %) and conventional SIME (R = 0.57, MAE = 78.7 %) in the human-subject evaluation. Adding more ROIs improved the overall performance of the kernel SIME method.ConclusionThe proposed kernel SIME method shows promise to provide an accurate estimation of the blood input function and kinetic parameters for brain PET parametric imaging.

Flatbed scanners are commonly used for root analysis, but typical manual segmentation methods are time-consuming and prone to errors, especially in large-scale, multi-plant studies. Furthermore, the complex nature of root structures combined with noisy backgrounds in images complicates automated analysis. Addressing these challenges, this article introduces RhizoNet, a deep learning-based workflow to semantically segment plant root scans. Utilizing a sophisticated Residual U-Net architecture, RhizoNet enhances prediction accuracy and employs a convex hull operation for delineation of the primary root component. Its main objective is to accurately segment root biomass and monitor its growth over time. RhizoNet processes color scans of plants grown in a hydroponic system known as EcoFAB, subjected to specific nutritional treatments. The root detection model using RhizoNet demonstrates strong generalization in the validation tests of all experiments despite variable treatments. The main contributions are the standardization of root segmentation and phenotyping, systematic and accelerated analysis of thousands of images, significantly aiding in the precise assessment of root growth dynamics under varying plant conditions, and offering a path toward self-driving labs.

The scanning electron microscope (SEM) recordings of dynamic nano-electromechanical systems (NEMS) are difficult to analyze due to the noise caused by low frame rate, insufficient resolution, and blurriness induced by applied electric potentials. Here, we develop an image processing platform enhanced by the physics of the underlying system to track the motion of buckling NEMS structures in the presence of high noise levels. The algorithm is composed of an image filter, two data filters, and a nonlinear regression model, which utilizes the expected form of the physical solution. The method was applied to the recordings of a NEMS beam about 150 nm wide, undergoing intra- and inter-well post-buckling states with a transition rate of approximately 0.5 Hz. The algorithm can track the dynamical motion of the NEMS and capture the dependency of deflection amplitude on the compressive force on the beam. With the help of the proposed algorithm, the transition from inter-well to intra-well motion is clearly resolved for buckling NEMS imaged under SEM. [ABSTRACT FROM AUTHOR]

Meningiomas are the most common primary intracranial tumors and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on brain MRI for diagnosis, treatment planning, and longitudinal treatment monitoring. However, automated, objective, and quantitative tools for non-invasive assessment of meningiomas on multi-sequence MR images are not available. Here we present the BraTS Pre-operative Meningioma Dataset, as the largest multi-institutional expert annotated multilabel meningioma multi-sequence MR image dataset to date. This dataset includes 1,141 multi-sequence MR images from six sites, each with four structural MRI sequences (T2-, T2/FLAIR-, pre-contrast T1-, and post-contrast T1-weighted) accompanied by expert manually refined segmentations of three distinct meningioma sub-compartments: enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Basic demographic data are provided including age at time of initial imaging, sex, and CNS WHO grade. The goal of releasing this dataset is to facilitate the development of automated computational methods for meningioma segmentation and expedite their incorporation into clinical practice, ultimately targeting improvement in the care of meningioma patients.

The lungs are supplied by both the pulmonary arteries carrying deoxygenated blood originating from the right ventricle and the bronchial arteries carrying oxygenated blood downstream from the left ventricle. However, this effect of dual blood supply has never been investigated using PET, partially because the temporal resolution of conventional dynamic PET scans is limited. The advent of PET scanners with a long axial field of view, such as the uEXPLORER total-body PET/CT system, permits dynamic imaging with high temporal resolution (HTR). In this work, we modeled the dual-blood input function (DBIF) and studied its impact on the kinetic quantification of normal lung tissue and lung tumors using HTR dynamic PET imaging. Methods: Thirteen healthy subjects and 6 cancer subjects with lung tumors underwent a dynamic 18F-FDG scan with the uEXPLORER for 1 h. Data were reconstructed into dynamic frames of 1 s in the early phase. Regional time-activity curves of lung tissue and tumors were analyzed using a 2-tissue compartmental model with 3 different input functions: the right ventricle input function, left ventricle input function, and proposed DBIF, all with time delay and dispersion corrections. These models were compared for time-activity curve fitting quality using the corrected Akaike information criterion and for differentiating lung tumors from lung tissue using the Mann-Whitney U test. Voxelwise multiparametric images by the DBIF model were further generated to verify the regional kinetic analysis. Results: The effect of dual blood supply was pronounced in the high-temporal-resolution time-activity curves of lung tumors. The DBIF model achieved better time-activity curve fitting than the other 2 single-input models according to the corrected Akaike information criterion. The estimated fraction of left ventricle input was low in normal lung tissue of healthy subjects but much higher in lung tumors (∼0.04 vs. ∼0.3, P < 0.0003). The DBIF model also showed better robustness in the difference in 18F-FDG net influx rate [Formula: see text] and delivery rate [Formula: see text] between lung tumors and normal lung tissue. Multiparametric imaging with the DBIF model further confirmed the differences in tracer kinetics between normal lung tissue and lung tumors. Conclusion: The effect of dual blood supply in the lungs was demonstrated using HTR dynamic imaging and compartmental modeling with the proposed DBIF model. The effect was small in lung tissue but nonnegligible in lung tumors. HTR dynamic imaging with total-body PET can offer a sensitive tool for investigating lung diseases.

BACKGROUND: Global shortages of iodinated contrast media (ICM) during COVID-19 pandemic forced the imaging community to use ICM more strategically in CT exams. PURPOSE: The purpose of this work is to provide a quantitative framework for preserving iodine CNR while reducing ICM dosage by either lowering kV in single-energy CT (SECT) or using lower energy virtual monochromatic images (VMI) from dual-energy CT (DECT) in a phantom study. MATERIALS AND METHODS: In SECT study, phantoms with effective diameters of 9.7, 15.9, 21.1, and 28.5 cm were scanned on SECT scanners of two different manufacturers at a range of tube voltages. Statistical based iterative reconstruction and deep learning reconstruction were used. In DECT study, phantoms with effective diameters of 20, 29.5, 34.6, and 39.7 cm were scanned on DECT scanners from three different manufacturers. VMIs were created from 40 to 140 keV. ICM reduction by lowering kV levels for SECT or switching from SECT to DECT was calculated based on the linear relationship between iodine CNR and its concentration under different scanning conditions. RESULTS: On SECT scanner A, while matching CNR at 120 kV, ICM reductions of 21%, 58%, and 72% were achieved at 100, 80, and 70 kV, respectively. On SECT scanner B, 27% and 80% ICM reduction was obtained at 80 and 100 kV. On the Fast-kV switch DECT, with CNR matched at 120 kV, ICM reductions were 35%, 30%, 23%, and 15% with VMIs at 40, 50, 60, and 68 keV, respectively. On the dual-source DECT, ICM reductions were 52%, 48%, 42%, 33%, and 22% with VMIs at 40, 50, 60, 70, and 80 keV. On the dual-layer DECT, ICM reductions were 74%, 62%, 45%, and 22% with VMIs at 40, 50, 60, and 70 keV. CONCLUSIONS: Our work provided a quantitative baseline for other institutions to further optimize their scanning protocols to reduce the use of ICM.

BackgroundWhole brain delineation (WBD) is utilized in neuroimaging analysis for data preprocessing and deriving whole brain image metrics. Current automated WBD techniques for analysis of preclinical brain MRI data show limited accuracy when images present with significant neuropathology and anatomical deformations, such as that resulting from organophosphate intoxication (OPI) and Alzheimer's Disease (AD), and inadequate generalizability.MethodsA modified 2D U-Net framework was employed for WBD of MRI rodent brains, consisting of 27 convolutional layers, batch normalization, two dropout layers and data augmentation, after training parameter optimization. A total of 265 T2-weighted 7.0 T MRI scans were utilized for the study, including 125 scans of an OPI rat model for neural network training. For testing and validation, 20 OPI rat scans and 120 scans of an AD rat model were utilized. U-Net performance was evaluated using Dice coefficients (DC) and Hausdorff distances (HD) between the U-Net-generated and manually segmented WBDs.ResultsThe U-Net achieved a DC (median[range]) of 0.984[0.936-0.990] and HD of 1.69[1.01-6.78] mm for OPI rat model scans, and a DC (mean[range]) of 0.975[0.898-0.991] and HD of 1.49[0.86-3.89] for the AD rat model scans.Comparison with existing methodsThe proposed approach is fully automated and robust across two rat strains and longitudinal brain changes with a computational speed of 8 seconds/scan, overcoming limitations of manual segmentation.ConclusionsThe modified 2D U-Net provided a fully automated, efficient, and generalizable segmentation approach that achieved high accuracy across two disparate rat models of neurological diseases.

Despite much progress, image processing remains a significant bottleneck for high-throughput analysis of microscopy data. One popular platform for single-cell time-lapse imaging is the mother machine, which enables long-term tracking of microbial cells under precisely controlled growth conditions. While several mother machine image analysis pipelines have been developed in the past several years, adoption by a non-expert audience remains a challenge. To fill this gap, we implemented our own software, MM3, as a plugin for the multidimensional image viewer napari. napari-MM3 is a complete and modular image analysis pipeline for mother machine data, which takes advantage of the high-level interactivity of napari. Here, we give an overview of napari-MM3 and test it against several well-designed and widely used image analysis pipelines, including BACMMAN and DeLTA. Researchers often analyze mother machine data with custom scripts using varied image analysis methods, but a quantitative comparison of the output of different pipelines has been lacking. To this end, we show that key single-cell physiological parameter correlations and distributions are robust to the choice of analysis method. However, we also find that small changes in thresholding parameters can systematically alter parameters extracted from single-cell imaging experiments. Moreover, we explicitly show that in deep learning-based segmentation, what you put is what you get (WYPIWYG) - that is, pixel-level variation in training data for cell segmentation can propagate to the model output and bias spatial and temporal measurements. Finally, while the primary purpose of this work is to introduce the image analysis software that we have developed over the last decade in our lab, we also provide information for those who want to implement mother machine-based high-throughput imaging and analysis methods in their research.

Quantitative PET attenuation correction (AC) for cardiac PET/CT and PET/MR is a challenging problem. We propose and evaluate an AC approach that uses coincidences from a relatively weak and physically fixed sparse external source, in combination with that from the patient, to reconstruct μ -maps based on physics principles alone. The low 30 cm3 volume of the source makes it easy to fill and place, and the method does not use prior image data or attenuation map assumptions. Our supplemental transmission aided maximum likelihood reconstruction of attenuation and activity (sTX-MLAA) algorithm contains an attenuation map update that maximizes the likelihood of terms representing coincidences originating from tracer in the patient and a weighted expression of counts segmented from the external source alone. Both external source and patient scatter and randoms are fully corrected. We evaluated performance of sTX-MLAA compared to reference standard CT-based AC with FDG PET/CT phantom studies; including modeling a patient with myocardial inflammation. Through an ROI analysis we measured ≤ 5 % bias in activity concentrations for PET images generated with sTX-MLAA and a TX source strength ≥ 12.7 MBq, relative to CT-AC. PET background variability (from noise and sparse sampling) was substantially reduced with sTX-MLAA compared to using counts segmented from the transmission source alone for AC. Results suggest that sTX-MLAA will enable quantitative PET during cardiac PET/CT and PET/MR of human patients.

The short association fibers or U-fibers travel in the superficial white matter (SWM) beneath the cortical layer. While the U-fibers play a crucial role in various brain disorders, there is a lack of effective tools to reconstruct their highly curved trajectory from diffusion MRI (dMRI). In this work, we propose a novel surface-based framework for the probabilistic tracking of fibers on the triangular mesh representation of the SWM. By deriving a closed-form solution to transform the spherical harmonics (SPHARM) coefficients of 3D fiber orientation distributions (FODs) to local coordinate systems on each triangle, we develop a novel approach to project the FODs onto the tangent space of the SWM. After that, we utilize parallel transport to realize the intrinsic propagation of streamlines on SWM following probabilistically sampled fiber directions. Our intrinsic and surface-based method eliminates the need to perform the necessary but challenging sharp turns in 3D compared with conventional volume-based tractography methods. Using data from the Human Connectome Project (HCP), we performed quantitative comparisons to demonstrate the proposed algorithm can more effectively reconstruct the U-fibers connecting the precentral and postcentral gyrus than previous methods. Quantitative validations were then performed on post-mortem MRIs to show the reconstructed U-fibers from our method more faithfully follow the SWM than volume-based tractography. Finally, we applied our algorithm to study the parietal U-fiber connectivity changes in autosomal dominant Alzheimers disease (ADAD) patients and successfully detected significant associations between U-fiber connectivity and disease severity.