Efficient Small Blob Detection Based on Local Convexity, Intensity and Shape Information

BlobCUT: A Contrastive Learning Method to Support Small Blob Detection in Medical Imaging

Medical imaging-based biomarkers derived from small objects (e.g., cell nuclei) play a crucial role in medical applications. However, detecting and segmenting small objects (a.k.a. blobs) remains a challenging task. In this research, we propose a novel 3D small blob detector called BlobCUT. BlobCUT is an unpaired image-to-image (I2I) translation model that falls under the Contrastive Unpaired Translation paradigm. It employs a blob synthesis module to generate synthetic 3D blobs with corresponding masks. This is incorporated into the iterative model training as the ground truth. The I2I translation process is designed with two constraints: (1) a convexity consistency constraint that relies on Hessian analysis to preserve the geometric properties and (2) an intensity distribution consistency constraint based on Kullback-Leibler divergence to preserve the intensity distribution of blobs. BlobCUT learns the inherent noise distribution from the target noisy blob images and performs image translation from the noisy domain to the clean domain, effectively functioning as a denoising process to support blob identification. To validate the performance of BlobCUT, we evaluate it on a 3D simulated dataset of blobs and a 3D MRI dataset of mouse kidneys. We conduct a comparative analysis involving six state-of-the-art methods. Our findings reveal that BlobCUT exhibits superior performance and training efficiency, utilizing only 56.6% of the training time required by the state-of-the-art BlobDetGAN. This underscores the effectiveness of BlobCUT in accurately segmenting small blobs while achieving notable gains in training efficiency.

Pantograph Detection Algorithm with Complex Background and External Disturbances

As an important equipment for high-speed railway (HSR) to obtain electric power from outside, the state of the pantograph will directly affect the operation safety of HSR. In order to solve the problems that the current pantograph detection method is easily affected by the environment, cannot effectively deal with the interference of external scenes, has a low accuracy rate and can hardly meet the actual operation requirements of HSR, this study proposes a pantograph detection algorithm. The algorithm mainly includes three parts: the first is to use you only look once (YOLO) V4 to detect and locate the pantograph region in real-time; the second is the blur and dirt detection algorithm for the external interference directly affecting the high-speed camera (HSC), which leads to the pantograph not being detected; the last is the complex background detection algorithm for the external complex scene "overlapping" with the pantograph when imaging, which leads to the pantograph not being recognized effectively. The dirt and blur detection algorithm combined with blob detection and improved Brenner method can accurately evaluate the dirt or blur of HSC, and the complex background detection algorithm based on grayscale and vertical projection can greatly reduce the external scene interference during HSR operation. The algorithm proposed in this study was analyzed and studied on a large number of video samples of HSR operation, and the precision on three different test samples reached 99.92%, 99.90% and 99.98%, respectively. Experimental results show that the algorithm proposed in this study has strong environmental adaptability and can effectively overcome the effects of complex background and external interference on pantograph detection, and has high practical application value.

Comparative Dissemination of Aerosol and Splatter Using Suction Device during Ultrasonic Scaling: A Pilot Study

Objective: This study compared the aerosol and splatter diameter and count numbers produced by a dental mouth prop with a suction holder device and a saliva ejector during ultrasonic scaling in a clinical setting. Methodology: Fluorescein dye was placed in the dental equipment irrigation reservoirs with a mannequin, and an ultrasonic scaler was employed. The procedures were performed three times per device. The upper and bottom board papers were placed on the laboratory platform. All processes used an ultrasonic scaler to generate aerosol and splatter. A dental mouth prop with a suction holder and a saliva ejector were also tested. Photographic analysis was used to examine the fluorescein samples, followed by image processing in Python and assessment of the diameter and count number. For device comparison, statistics were used with an independent t-test. Result: When using the dental mouth prop with a suction holder, the scaler produced aerosol particles that were maintained on the upper board paper (mean ± SD: 1080 ± 662 µm) compared to on the bottom board paper (1230 ± 1020 µm). When the saliva ejector was used, it was found that the diameter of the aerosol on the upper board paper was 900 ± 580 µm, and the diameter on the bottom board paper was 1000 ± 756 µm. Conclusion: There was a significant difference in the aerosol and splatter particle diameter and count number between the dental mouth prop with a suction holder and saliva ejector (p < 0.05). Furthermore, the results revealed that there was a statistically significant difference between the two groups on the upper and bottom board papers.

GAN Training Acceleration Using Fréchet Descriptor-Based Coreset

Generative Adversarial Networks (GANs) are a class of deep learning models being applied to image processing. GANs have demonstrated state-of-the-art performance in applications such as image generation and image-to-image translation, just to name a few. However, with this success comes the realization that the training of GANs takes a long time and is often limited by available computing resources. In this research, we propose to construct a Coreset using Fréchet Descriptor Distances (FDD-Coreset) to accelerate the training of GAN for blob identification. We first propose a Fréchet Descriptor Distance (FDD) to measure the difference between each pair of blob images based on the statistics derived from blob distribution. The Coreset is then employed using our proposed FDD metric to select samples from the entire dataset for GAN training. A 3D-simulated dataset of blobs and a 3D MRI dataset of human kidneys are studied. Using computation time and eight performance metrics, the GAN trained on the FDD-Coreset is compared against the model trained on the entire dataset and an Inception and Euclidean Distance-based Coreset (IED-Coreset). We conclude that the FDD-Coreset not only significantly reduces the training time, but also achieves higher denoising performance and maintains approximate performance of blob identification compared with training on the entire dataset.

Image analysis techniques to map pyramids, pyramid structure, glomerular distribution, and pathology in the intact human kidney from 3-D MRI

Kidney pathologies are often highly heterogeneous. To comprehensively understand kidney structure and pathology, it is critical to develop tools to map tissue microstructure in the context of the whole, intact organ. Magnetic resonance imaging (MRI) can provide a unique, three-dimensional view of the kidney and allows for measurements of multiple pathological features. Here, we developed a platform to systematically render and map gross and microstructural features of the human kidney based on three-dimensional MRI. These features include pyramid number and morphology as well as the associated medulla and cortex. In a subset of these kidneys, we also mapped individual glomeruli and glomerular volumes using cationic ferritin-enhanced MRI to report intrarenal heterogeneity in glomerular density and size. Finally, we rendered and measured regions of nephron loss due to pathology and individual glomerular volumes in each pyramidal unit. This work provides new tools to comprehensively evaluate the kidney across scales, with potential applications in anatomic and physiological research, transplant allograft evaluation, biomarker development, biopsy guidance, and therapeutic monitoring. These image rendering and analysis tools could eventually impact the field of transplantation medicine to improve longevity matching of donor allografts and recipients and reduce discard rates through the direct assessment of donor kidneys.NEW & NOTEWORTHY We report the application of cutting-edge image analysis approaches to characterize the pyramidal geometry, glomerular microstructure, and heterogeneity of the whole human kidney imaged using MRI. This work establishes a framework to improve the detection of microstructural pathology to potentially facilitate disease monitoring or transplant evaluation in the individual kidney.

Small Blob Detector Using Bi-Threshold Constrained Adaptive Scales

Recent advances in medical imaging technology bring great promises for medicine practices. Imaging biomarkers are discovered to inform disease diagnosis, prognosis, and treatment assessment. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap among the blobs. This research proposes a Bi-Threshold Constrained Adaptive Scale (BTCAS) blob detector to uncover the relationship between the U-Net threshold and the Difference of Gaussian (DoG) scale to derive a multi-threshold, multi-scale small blob detector. With lower and upper bounds on the probability thresholds from U-Net, two binarized maps of the distance are rendered between blob centers. Each blob is transformed to a DoG space with an adaptively identified local optimum scale. A Hessian convexity map is rendered using the adaptive scale, and the under-segmentation typical of the U-Net is resolved. To validate the performance of the proposed BTCAS, a 3D simulated dataset (n = 20) of blobs, a 3D MRI dataset of human kidneys and a 3D MRI dataset of mouse kidneys, are studied. BTCAS is compared against four state-of-the-art methods: HDoG, U-Net with standard thresholding, U-Net with optimal thresholding, and UH-DoG using precision, recall, F-score, Dice and IoU. We conclude that BTCAS statistically outperforms the compared detectors.

Nephron number and its determinants: a 2020 update

Studies of human nephron number have been conducted for well over a century and have uncovered a large variability in nephron number. However, the mechanisms influencing nephron endowment and loss, along with the etiology for the wide range among individuals are largely unknown. Advances in imaging technology have allowed investigators to revisit the principles of renal structure and physiology and their roles in the progression of kidney disease. Here, we will review the latest data on the influences impacting nephron number, innovations made over the last 6 years to understand and integrate renal structure and function, and new developments in the tools used to count nephrons in vivo.

Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis

Imaging biomarkers are being rapidly developed for early diagnosis and staging of disease. The development of these biomarkers requires advances in both image acquisition and analysis. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap between the blobs. The Difference of Gaussian (DoG) detector has been used to overcome these challenges in blob detection. However, the DoG detector is susceptible to over-detection and must be refined for robust, reproducible detection in a wide range of medical images. In this research, we propose a joint constraint blob detector from U-Net, a deep learning model, and Hessian analysis, to overcome these problems and identify true blobs from noisy medical images. We evaluate this approach, UH-DoG, using a public 2D fluorescent dataset for cell nucleus detection and a 3D kidney magnetic resonance imaging dataset for glomerulus detection. We then compare this approach to methods in the literature. While comparable to the other four comparing methods on recall, the UH-DoG outperforms them on both precision and F-score.

Battery Surface and Edge Defect Inspection Based on Sub-Regional Gaussian and Moving Average Filter

Detecting the defects of a battery on the surface and edge has always been difficult, especially for concave and convex ones, thereby seriously affecting its quality. Thus, sub-regional Gaussian and moving average filtering are innovatively proposed in this study considering the effect of the nonuniform background illumination of the battery edge and the difference between the edge background and the internal surface defects of the battery. The battery surface image is divided into two areas, namely, edge area W 1 and inner area W 2 . Gaussian and moving average filtering are carried out row-by-row and column-by-column in the inner area W 2 and the edge area W 1 , respectively. The algorithm is tested on 600 battery samples that mainly possess concave and convex defects. The proposed method has higher detection accuracy and lower omission detection rate than the traditional unpartitioned processing method, especially in detecting the accuracy of edge defects. The accuracy rates were approximately 20% higher than that obtained by the traditional processing algorithm. The proposed method has remarkable real-time performance that can process four 8192 × 10,240 pixel battery images per second, thereby meeting the industrial production line speed requirements while satisfying accuracy. The proposed method has been applied in actual production for defect inspection.

In vivo measurements of kidney glomerular number and size in healthy and Os/+ mice using MRI

The development of chronic kidney disease (CKD) is associated with the loss of functional nephrons. However, there are no methods to directly measure nephron number in living subjects. Thus, there are no methods to track the early stages of progressive CKD before changes in total renal function. In this work, we used cationic ferritin-enhanced magnetic resonance imaging (CFE-MRI) to enable measurements of glomerular number (N_glom) and apparent glomerular volume (aV_glom) in vivo in healthy wild-type (WT) mice (n = 4) and mice with oligosyndactylism (Os^/+; n = 4), a model of congenital renal hypoplasia leading to nephron reduction. We validated in vivo measurements of N_glom and aV_glom by high-resolution ex vivo MRI. CFE-MRI measured a mean N_glom of 12,220 ± 2,028 and 6,848 ± 1,676 (means ± SD) for WT and Os^/+ mouse kidneys in vivo, respectively. N_glom measured in all mice in vivo using CFE-MRI varied by an average 15% from N_glom measured ex vivo in the same kidney (α = 0.05, P = 0.67). To confirm that CFE-MRI can also be used to track nephron endowment longitudinally, a WT mouse was imaged three times by CFE-MRI over 2 wk. Values of N_glom measured in vivo in the same kidney varied within ~3%. Values of aV_glom calculated from CFE-MRI in vivo were significantly different (~15% on average, P < 0.01) from those measured ex vivo, warranting further investigation. This is the first report of direct measurements of N_glom and aV_glom in healthy and diseased mice in vivo.

A New Local Fractional Entropy-Based Model for Kidney MRI Image Enhancement

Kidney image enhancement is challenging due to the unpredictable quality of MRI images, as well as the nature of kidney diseases. The focus of this work is on kidney images enhancement by proposing a new Local Fractional Entropy (LFE)-based model. The proposed model estimates the probability of pixels that represent edges based on the entropy of the neighboring pixels, which results in local fractional entropy. When there is a small change in the intensity values (indicating the presence of edge in the image), the local fractional entropy gives fine image details. Similarly, when no change in intensity values is present (indicating smooth texture), the LFE does not provide fine details, based on the fact that there is no edge information. Tests were conducted on a large dataset of different, poor-quality kidney images to show that the proposed model is useful and effective. A comparative study with the classical methods, coupled with the latest enhancement methods, shows that the proposed model outperforms the existing methods.

The Hessian Blob Algorithm: Precise Particle Detection in Atomic Force Microscopy Imagery

Imaging by atomic force microscopy (AFM) offers high-resolution descriptions of many biological systems; however, regardless of resolution, conclusions drawn from AFM images are only as robust as the analysis leading to those conclusions. Vital to the analysis of biomolecules in AFM imagery is the initial detection of individual particles from large-scale images. Threshold and watershed algorithms are conventional for automatic particle detection but demand manual image preprocessing and produce particle boundaries which deform as a function of user-defined parameters, producing imprecise results subject to bias. Here, we introduce the Hessian blob to address these shortcomings. Combining a scale-space framework with measures of local image curvature, the Hessian blob formally defines particle centers and their boundaries, both to subpixel precision. Resulting particle boundaries are independent of user defined parameters, with no image preprocessing required. We demonstrate through direct comparison that the Hessian blob algorithm more accurately detects biomolecules than conventional AFM particle detection techniques. Furthermore, the algorithm proves largely insensitive to common imaging artifacts and noise, delivering a stable framework for particle analysis in AFM.

3D small structure detection in medical image using texture analysis

Small structure segmentation from medical images is a challenging problem yet has important applications. Examples are labeling cell, lesion and glomeruli for disease diagnosis, just to name a few. Though extensive research has proposed various detectors for this type of problem, most are 2D detectors. Recently, we have developed a Hessian based 3D detector to segment small structures from medical images (e.g., MRI). In our detector, two 3D geometrical features: regional blobness and flatness, in conjunction with the intensity features are fully utilized to serve the segmentation purpose. The objective of this research is to further improve the 3D detector with additions of texture features. Medical images contain rich information which can be presented as texture, the local characteristics pattern of image intensity. We hypothesize the Hessian based detector extended with the 3D texture features is expected to have improved performance in segmenting small structures. To thoroughly evaluate the contributions from the textual features, 25 synthetic images and 6 real world rat MR images are studied. It is observed the combination of intensity, blobness, and two texture features: intensity standard deviation and entropy improves performance in synthetic dataset by about 19% in F-score, and performs as well as other detectors on rat MR images.

Enclosure Transform for Interest Point Detection From Speckle Imagery

We present a fast enclosure transform (ET) to localize complex objects of interest from speckle imagery. This approach explores the spatial confinement on regional features from a sparse image feature representation. Unrelated, broken ridge features surrounding an object are organized collaboratively, giving rise to the enclosureness of the object. Three enclosure likelihood measures are constructed, consisting of the enclosure force, potential energy, and encloser count. In the transform domain, the local maxima manifest the locations of objects of interest, for which only the intrinsic dimension is known a priori. The discrete ET algorithm is computationally efficient, being on the order of O(MN) using N measuring distances across an image of M ridge pixels. It involves easy and few parameter settings. We demonstrate and assess the performance of ET on the automatic detection of the prostate locations from supra-pubic ultrasound images. ET yields superior results in terms of positive detection rate, accuracy and coverage.

MRI tools for assessment of microstructure and nephron function of the kidney

MRI can provide excellent detail of renal structure and function. Recently, novel MR contrast mechanisms and imaging tools have been developed to evaluate microscopic kidney structures including the tubules and glomeruli. Quantitative MRI can assess local tubular function and is able to determine the concentrating mechanism of the kidney noninvasively in real time. Measuring single nephron function is now a near possibility. In parallel to advancing imaging techniques for kidney microstructure is a need to carefully understand the relationship between the local source of MRI contrast and the underlying physiological change. The development of these imaging markers can impact the accurate diagnosis and treatment of kidney disease. This study reviews the novel tools to examine kidney microstructure and local function and demonstrates the application of these methods in renal pathophysiology.

Biocompatibility of ferritin-based nanoparticles as targeted MRI contrast agents

Ferritin is a naturally occurring iron storage protein, proposed as a clinically relevant nanoparticle with applications as a diagnostic and therapeutic agent. Cationic ferritin is a targeted, injectable contrast agent to measure kidney microstructure with MRI. Here, the toxicity of horse spleen ferritin is assessed as a step to clinical translation. Adult male mice received cationic, native and high dose cationic ferritin (CF, NF, or HDCF) or saline and were monitored for 3weeks. Transient weight loss occurred in the ferritin groups with no difference in renal function parameters. Ferritin-injected mice demonstrated a lower serum iron 3weeks after administration. In ferritin-injected animals pre-treated with hydrocortisone, there were no structural or weight differences in the kidneys, liver, lung, heart, or spleen. This study demonstrates a lack of significant detrimental effects of horse-derived ferritin-based nanoparticles at MRI-detectable doses, allowing further exploration of these agents in basic research and clinical diagnostics.

Automatic Nuclei Detection Based on Generalized Laplacian of Gaussian Filters

Efficient and accurate detection of cell nuclei is an important step toward automatic analysis in histopathology. In this work, we present an automatic technique based on generalized Laplacian of Gaussian (gLoG) filter for nuclei detection in digitized histological images. The proposed technique first generates a bank of gLoG kernels with different scales and orientations and then performs convolution between directional gLoG kernels and the candidate image to obtain a set of response maps. The local maxima of response maps are detected and clustered into different groups by mean-shift algorithm based on their geometrical closeness. The point which has the maximum response in each group is finally selected as the nucleus seed. Experimental results on two datasets show that the proposed technique provides a superior performance in nuclei detection compared to existing techniques.