Automatic Detection of Morphologically Distinct Objects in Biomedical Images Using Second Generation Wavelets and Multiple Marked Point Process

Millimeter-wave (mmWave) communication is the rising technology for simultaneous wireless information and power transfer (SWIPT) unmanned aerial vehicle (UAV)-based relay networks for the abundant bandwidth and short wavelength. However, the secrecy performance of mmWave SWIPT UAV-based relay systems has not been investigated so far. In this paper, we consider secure transmissions of mmWave SWIPT UAV-based relay systems in the presence of multiple independent homogeneous Poisson point process (HPPP) eavesdroppers. Different from most existing works considering a free-space path loss model, the air-to-ground channels are modeled as Nakagami-m small-scale fading, and the effects of blockage to mmWave links on the ground and the 3D antenna gain model are considered. The closed-form expressions of the average achievable secrecy rate and energy coverage probability for amplify-and-forward (AF) and decode-and-forward (DF) relay protocols under power splitting (PS) SWIPT policy are derived to reveal the impact of various parameters on system performance. The simulation results show that there is the optimal UAV position to maximize the secrecy rate and the optimal position is closer to the node whose transmit power is relatively small. Furthermore, different carrier frequencies are suitable for different eavesdropping node density.

The article explores modern neural network architectures for the automatic detection and recognition of marine surface objects and obstacles of given classes throughout the full image area, applicable for execution in real or near real time on an optoelectronic vision system to au-tomate and improve the safety of civil marine navigation. A formal statement of the problem of automatic detection of objects on images is given. The state-of-the-art algorithms for detecting objects in images based on use of artificial convolutional neural networks were reviewed, their comparison was made and a reasonable choice was made in favor of the most efficient neuralnetwork architecture in terms of computational complexity to recognition accuracy. The subject area is studied, as well as publicly available databases of surface objects suitable for use in the training of algorithms using artificial neural networks. The article concluded that there is insuffi-cient labeled data for training neural network algorithms, as a result of which the authors inde-pendently collected research images and video sequences, prepared and labeled the collected data containing surface marine objects and other obstacles that represent a navigation hazard for ships. Based on the selected neural network architecture, a new neural network algorithm for automatic full-frame detection and recognition of surface objects was developed, and an artificial neural network was trained using the prepared database of images of typical objects. The resulting algorithm was tested by the authors on a validation data set, the quality of its work was estimated using various metrics, and the algorithm’s performance was measured. Conclusions are made about the necessity to expand the collected database of images of typical marine objects, further steps are proposed to improve the accuracy of the developed software and algorithmic complex and its implementation to be used in a marine optoelectronic machine vision system for automa-tion and improving the safety of civil navigation.

Object detection in hyperspectral images

In the last years, it has become very popular as well as significant to diagnose patients as less invasively as only it is possible. This becomes extremely important mainly when diagnosing adolescent patients or even babies. This paper describes the possibilities of medical diagnostics from a different point of view which is the evaluation of microscopic biomedical images of patient's body instead of examining him directly, i.e., invasively. The subject of research is human respiratory system and its diseases which are often caused or closely connected with proper function of small microscopic structures which should serve to clean one's airways. Such structures are called cilia of respiratory epithelium and can be found within nose, trachea or bronchi. The old way of diagnostic of a patient who is suspected to suffer from a disease called Primary ciliary dyskinesia (PCD), as he often undergoes serious inflammations and other breathing complications, comprises several repeated bronchoscopies which cut a small pieces of epithelium from selected parts of respiratory apparatus that are consequently observed using microscope. This is very uncomfortable and many times very hard to perform as the most affected group of patients are children under the age of three. Moreover, evaluation of microscopic samples is often imprecise because doctors assess it subjectively and the proper frequency of ciliary movement is only estimated and classified “slow” or “quick enough”, without accurate value. This paper proposes automated, much faster and much more exact ways of frequency measurements of ciliary movement based on processing and segmentation of biomedical microscopic images, which means more precise evaluation of patient's ciliary health status without such invasiveness as it is used during older methods of examination.

In real‐time, visually impaired persons face challenging issues in identifying and avoiding obstacles in their path, making it difficult to move around freely and confidently. Object detection technology benefits visually impaired persons and contains the procedure of determining several individual objects from the image and recognizing their place with bounding boxes with class labels. Both exploit typical machine learning (ML) approaches and utilize deep learning (DL) models to execute object detection methods. Recently, several researchers have leveraged DL techniques such as convolutional neural networks (CNNs) for solving object detection problems and presented various recent object detection approaches. The study presents a sine cosine optimization with DL–driven object detector (SCODL–ODC) technique for visually impaired persons. The presented SCODL–ODC technique detects and classifies the objects, which can help them navigate their environment more efficiently and avoid obstacles. To accomplish this, the proposed SCODL–ODC technique employs a YOLOv5 object detector at the initial stage to detect the objects accurately, and the SCO model performs its hyperparameter tuning process. The following step is to classify them using the deep stacked autoencoder (DSAE) model when the objects are detected. Finally, the Harris Hawks optimization (HHO) technique is used to adjust the hyperparameters of the DSAE model. The experimentation outcome of the SCODL–ODC method is examined on the object detection dataset. The investigational validation of the SCODL–ODC method portrayed a superior accuracy value of 99.31% over existing models.

Near infrared wavelength region between 0.8 and 2 μm is an attractive region for biomedical imaging due to the low loss in biomedical objects in the region. Rare-earth doped ceramic phosphors are known to emit efficient fluorescence in the same wavelength region. The authors have developed micro fluorescence bioimaging system for cellular or tissue imaging and macro one for in vivo imaging. This paper will review the materials synthesis for the near infrared fluorescence probes as well as the system development and demonstrative works. Er-doped or Yb/Er-doped ceramic phosphors were synthesized with required particle size. The phosphors were partly modified with polyethylene glycol to give dispersion and controlled interaction with the biological objects. By using the micro imaging system, nematodes, mouse tissue and M1 cells were observed by detecting 1.5 μm emission from Er doped in the ceramic phosphor. in vivo imaging with the same fluorescence scheme was also performed for the digestive organs of live mouse.

Objectives: This study aimed to determine the accuracy of deep learning (DL) in kidney detection and differentiation of luminal emptying in pediatric diuretic renography. Patients and methods: In the retrospective study, labeling was performed on 1,260 diuretic renography images of 36 children with unilateral or bilateral hydronephrosis between January 2020 and December 2020. The Tensorflow Object Detection API was used to deploy object detection models. Sensitivity, precision, and F1 score were determined for the detection of the right or left kidney as an object. Supervised training was applied for the differentiation of filled and empty renal pelvis and calyxes. Results: In 1,260 labeled renal images, the left or right kidney was detected by the machine with 94% sensitivity, 96% precision, and 95% F1 score. The accuracy for differentiation was 88% for filled renal pelvis and calyxes and 66% for empty renal pelvis and calyxes. Conclusion: The machine using DL algorithms with a large data set training may differentiate the kidney, its location, and the contrast-filled lumen. Low contrast and unclear boundaries in an empty lumen may affect the quality of annotation. The DL model used in this study could be adapted to other urinary system pathologies in medical scans.

Images in biomedical publications often convey important information related to an article's content. When referenced properly, these images aid in clinical decision support. Annotations such as text labels and symbols, as provided by medical experts, are used to highlight regions of interest within the images. These annotations, if extracted automatically, could be used in conjunction with either the image caption text or the image citations (mentions) in the articles to improve biomedical information retrieval. In the current study, automatic detection and recognition of text labels in biomedical publication images was investigated. This paper presents both image analysis and feature-based approaches to extract and recognize specific regions of interest (text labels) within images in biomedical publications. Experiments were performed on 6515 characters extracted from text labels present in 200 biomedical publication images. These images are part of the data set from ImageCLEF 2010. Automated character recognition experiments were conducted using geometry-, region-, exemplar-, and profile-based correlation features and Fourier descriptors extracted from the characters. Correct recognition as high as 92.67% was obtained with a support vector machine classifier, compared to a 75.90% correct recognition rate with a benchmark Optical Character Recognition technique.

Monitoring the 3-D cell culture process or drug responses non-destructively using Electrical Impedance Tomography (EIT) is an emerging topic in biomedical imaging. Significant efforts have been spent on developing EIT image reconstruction algorithms in order to achieve robust and high-quality cell imaging. The considerable computation time and imperfect image quality are the main issues of these conventional methods whereas the emergence of deep learning techniques point out a new direction due to its fast inferences on object detection, image segmentation and classification. In this paper, a novel deep learning architecture is proposed by adding a fully connected layer before a U-Net structure. This new architecture will first generate an initial guess of the conductivity distribution and then feed it to the following denoising model. A novel initialization strategy is also proposed to further help obtain this initial guess. The performance of the method is verified by simulation and experimental data. The results show that the proposed model outperforms the state-of-the-art EIT algorithms and can generalize well to reconstruct unseen cases consisting of human breast cancer cell pellet.

YOFIR: High precise infrared object detection algorithm based on YOLO and FasterNet

Summary The nonparametric multiplicative intensity model for simple point processes on the line is considered. By introducing a suitable topology on the space of all point process paths, a topological extension of the model is found, accommodating point processes with multiple points. In the extended model the maximum likelihood estimator is determined and shown to be interpretable in terms of a multiple point process. Finally, the maximum likelihood estimator and the Aalen estimator are compared. The results are illustrated by examples involving a model for Poisson processes, a model for censored survival data and the Cox regression model.

Chapter 2 - Parametric modeling in biomedical image synthesis

Vertex defect is a defect introduced during the physicochemical treatment phase of the microchannel plate in low-light-level (LLL) image intensifiers. It will affect the imaging quality of the product when the contrast exceeds a certain range, so it should be detected in time before delivery. Traditional detection techniques for this defect are divided into visual inspection and objective detection. High degree of uncertainty is the main drawback of the subjective method, while the existing objective detection technology has limitations in terms of detection coverage. To address the above problems, an automatic detection method for vertex defects based on spectral maximum points histogram statistics and analysis of multifilament boundary distribution patterns is proposed. First, a spatial bandpass filter is adopted to enhance visible defects in the effective area. After performing image binarization and connected component analysis, the regions corresponding to visible defects are extracted, and the processed image is generated. Then, a sliding window of equal multifilament size is utilized to scan the effective area of the processed image globally. By performing histogram statistics on the local maximum point coordinates of the spectrogram, defective image blocks can be identified using the maximum weight bin of the histogram. Subsequently, defective image blocks are restored to the processed image to obtain dense areas of vertex defects. Finally, the distribution pattern of the multifilament boundary is mathematically analyzed and defined as two constraints that can determine the effective line segment composed of vertex defects. To substantiate the performance of this method, multiple products are put into the experiment and relevant defect detection techniques are used for comparison. The experimental results indicate that our method has better detection performance than relevant objective detection methods, and can generate results consistent with the visual inspection method, while maintaining applicability to changes in image brightness, clarity, contrast, background noise, and uniformity within a certain range.

In this paper, a novel multiple objects detection and tracking approach based on support vector machine and particle filter is proposed to track players in broadcast sports video. Compared with previous work, the contributions of this paper are focused on three aspects. First, an improved particle filter called SVR particle filter is proposed as the player tracker by integrating support vector regression (SVR) into sequential Monte Carlo framework. SVR particle filter enhances the performance of classical particle filter with small sample set and improves the efficiency of tracking system. Second, support vector classification combined with playfield segmentation is employed to automatically detect the players in sports video as the initialization of tracker. Third, a unified framework for automatic object detection and tracking is proposed based on support vector machine and particle filter. The experimental results are encouraging and demonstrate that our approach is effective

This study proposes a segmentation-based approach for object detection, developed for analyzing aquatic behavior in controlled laboratory environments. The research focuses on overcoming detection challenges in long-term video recordings of bullheads housed in enclosed aquariums, where sediment drift, background instability, and partial occlusions often confound traditional tracking techniques. To address these issues, an approach based on the improved SLIC Superpixel segmentation method was proposed. The basic SLIC method was modified to incorporate multi-layer contrast features and neighborhood-based pixel uniformity checks. The proposed approach includes the following stages: preprocessing, segmentation, clustering, and post-processing. The preprocessing stage includes bilateral and median filtering, contrast and brightness normalization, and optional image upscaling to improve clarity. Subsequent background subtraction and context-aware thresholding within segmented regions help eliminate false positives caused by floating debris and occluded contours. At the clustering stage, a refined distance metric is introduced to evaluate pixel coherence in a multilayered feature space, which include LAB components, subtraction results, and histogram-equalized grayscale representations, improving segmentation accuracy. Additionally, at the post-processing stage fragmented object blobs are merged to enhance spatial continuity. Empirical validation was conducted on a dataset of bullhead video frames recorded under realistic aquatic conditions. The approach based on the improved SLIC Superpixel segmentation method demonstrated an increase in object detection accuracy of more than 6% compared to the approach based on the basic SLIC method. The modularity and simplicity of the proposed approach allow it to be easily extended to other biological objects − in particular, for the behavioral analysis of rodents − without relying on deep neural networks or computationally intensive frameworks, making it suitable for tasks in ethology, neuroscience, and precision aquaculture. Further research will be devoted to implementing the approach in real-time and advanced trajectory analysis.