Imaging Problems Research Articles

Comment on 'A PET reconstruction formulation that enforces non-negativity in projection space for bias reduction in Y-90 imaging'.

We read with great interest the paper by Limet al(2018Phys. Med. Biol.63035042) on bias reduction in Y-90 PET imaging. In particular, they proposed a new formulation of the tomographic reconstruction problem that enforces non-negativity in projection space as opposed to image space. We comment on the algorithm they derived from this formulation and bring some clarifications on the constraint that this algorithm respects.

Ensemble Based Estimation of Wet Refractivity Indices Using a Functional Model Approach

AbstractThe estimation of the wet refractivity indices is crucial for applications like weather predictions or improving the accuracy of real‐time positioning techniques. Traditionally, solving the inverse tomography problem to estimate these atmospheric parameters has been challenging due to its ill‐posed nature and high computational demands, necessitating additional constraints. To overcome these challenges, the data assimilation method is proposed here to integrate Global Navigation Satellite System (GNSS) observations into a background model. In this study, the Ensemble Kalman Filter (EnKF) was served as the assimilation core to reduce the computational load and to enable the epoch‐wise estimation of wet refractivity indices. The Global Pressure and Temperature 3 (GPT3w) model was utilized as the background, and wet refractivity indices at each epoch were transformed into B‐spline coefficients, representing state vector parameters. Subsequently, GNSS derived zenith wet delay (ZWD) values were integrated into the model using the EnKF method. The study's region encompassed the western parts of Europe and incorporated approximately 893 GNSS stations. Evaluation spanned from 1 January 2017 to 31 December 2017. The estimated wet refractivity indices from the proposed method were compared with observations from 16 existing radiosonde stations, radio occultation data, and ZWD values from the 47 selected GNSS test stations. Additionally, calculated ZWD values, resulting from the integration of wet refractivity indices, were compared to the ZWD values from 47 test stations in the study region. The numerical results demonstrated that the proposed method achieved a root mean square error value of approximately 2.6 ppm, which was nearly 49% and 18% lower than that of the considered empirical and numerical atmospheric models, respectively.

A virtual anti-scatter grid for multi-energy photon counting detector systems

Photon-counting (PC) systems are the next technological generation of medical computed tomography (CT) imaging and is being worked on by all major system providers. CT devices that are based on PC detectors enable multi-energy data collection. The information-content of this data can be used to obtain more detailed patient data, which improves the quality of reconstructions, compared to conventional detector systems. However, PC CT systems are subject to radiation scatter as just as any other imaging systems is. Conventionally anti-scatter grids (ASG) are used to reduce the scatter effect. These are however an imperfect solution, especially for PC detectors. In this work, a software-based scatter correction method, thus a virtual ASG is proposed. The method is tailoring a new statistical model in the measurement space and combining it with the statistical inversion method called Markov chain Monte Carlo (MCMC). The method can recover the measurement data from dense projections. We present the method on simulated data of a single photon emission computed tomography (SPECT) problem for which only under-sampled data is available. However, our approach can in principle be generalised to CT, PC-CT, Positron emission tomography (PET), radiotherapy, or even digital radiography problems. The results show that the proposed model performs similarly as physical ASGs and for cases where ASGs are not possible. The model further offers a significant improvement in the quality of the reconstruction image compared to the image reconstruction from original under-sampled data.

Better than the Total Variation Regularization

The total variation (TV) regularization is popular in iterative image reconstruction when the piecewise-constant nature of the image is encouraged. As a matter of fact, the TV regularization is not strong enough to enforce the piecewise- constant appearance. This paper suggests a different regularization function that is able to discourage some smooth transitions in the image and to encourage the piecewise-constant behavior. This new regularization function involves a Gaussian function. We use the limited-angle tomography problem to illustrate the effectiveness of this new regularization function. The limited-angle tomography situation considered in this paper uses a scanning angular range of 40°. For two-dimensional parallel-beam imaging, the required angular range is supposed to be 180°.

From Love to Hate: The Catholic Church in Poland in the Public Opinion

Poland is a country that is still considered Catholic. Faced with a series of image problems of the Catholic Church, this opinion is being increasingly revised. People, especially young people, are increasingly turning away from this centuries-old institution in search of their moral principles. The percentage of Catholics in Poland is decreasing. The author of the study decided to find out: (1) What do Poles think of the Catholic Church today?; (2) How do they evaluate the various areas of activity of the Catholic Church in Poland?; (3) Is there a predominant opinion in Polish society about the necessity of separation of state and church?; (4) What political consequences does this have? These questions are answered through desk research analysis of reports by the Public Opinion Research Centre and statistical analysis of the author’s quantitative survey conducted after the 2023 parliamentary elections in Poland. The survey results indicate that various areas of activity of the Catholic Church in Poland are evaluated in different ways. The respondents are most critical of the Church’s influence on political authorities and the problem of solving the issue of paedophilia among the clergy. The results of the survey confirm that Law and Justice voters are the people who have the highest opinion of the Catholic Church in Poland and are closely associated with Christian values.

Convergence of Peaceman-Rachford splitting method with Bregman distance for three-block nonconvex nonseparable optimization

Abstract It is of strong theoretical significance and application prospects to explore three-block nonconvex optimization with nonseparable structure, which are often modeled for many problems in machine learning, statistics, and image and signal processing. In this article, by combining the Bregman distance and Peaceman-Rachford splitting method, we propose a novel three-block Bregman Peaceman-Rachford splitting method (3-BPRSM). Under a general assumption, global convergence is presented via optimality conditions. Furthermore, we prove strong convergence when the augmented Lagrange function satisfies Kurdyka-Łojasiewicz property. In addition, if the association function possessing the Kurdyka-Łojasiewicz property exhibits a distinctive structure, then linear and sublinear convergence rate of 3-BPRSM can be guaranteed. Finally, a preliminary numerical experiment demonstrates the effectiveness.

A microlocal and visual comparison of 2D Kirchhoff migration formulas in seismic imaging*

Abstract The term Kirchhoff migration refers to a collection of approximate linearized inversion formulas for solving the inverse problem of seismic tomography which entails reconstructing the Earth’s subsurface from reflected wave fields. A number of such formulas exists, the first dating from the 1950 s. As far as we know, these formulas have not yet been mathematically compared with respect to their imaging properties. This shortcoming is to be alleviated by the present work: we systematically discuss the advantages and disadvantages of the formulas in 2D from a microlocal point of view. To this end we consider the corresponding imaging operators in an unified framework as pseudodifferential or Fourier integral operators. Numerical examples illustrate the theoretical insights and allow a visual comparison of the different formulas.

SimpliScopeX: Enhanced Deep Learning Model for Identification of Microscopic Image of Simplicia Fragments of Medicinal Plant Leaves

As the "Back to Nature" trend progresses, people are switching from chemical medicine to herbal medicine or traditional medicine derived from nature. One form of traditional medicine is the simplicia of medicinal plant leaves. The authenticity of dried simplicia powder of medicinal plants can be determined through a microscopic test by looking at the identifier fragments. However, this remains difficult for humans to identify due to the need for more information on standard references. The dataset from microscopic images of simplicia fragments of medicinal plant leaves still needs to be improved. In addition, manual matching of microscopic test results with standard reference books requires quite a long time. It allows for human error, so it is necessary to apply artificial intelligence that can assist researchers in quickly and accurately predicting the species of medicinal plants and their fragments based on microscopic images. Deep learning performance has shown promising results in computer vision in recent years. Inspired by sophisticated deep learning techniques, the proposed work presents a deep learning method to identify and classify images of microscopic fragments of simple medicinal plants and their enhanced fragments using data augmentation techniques, modified EfficientNetB0 architecture, and the use of the ReduceLROnPlateau function in the training process, which is referred to as "SimpliScopeX". The SimpliScopeX model can also automatically extract microscopic image features of simplicia fragments of medicinal plant leaves. Experimental results using the new dataset show that our proposed model can produce the highest accuracy value of 80.25% for the test data for microscopic image problems of medicinal leaf simplicia. The implications of this research are petrified in the pharmaceutical world in fast and accurate microscopic identification.

Microlensing and event rate of static spherically symmetric wormhole

The study focuses on the impact of microlensing in modern cosmology and introduces a new framework for the static spherically symmetrical wormhole in terms of the radial equation of state. Following a standard procedure, the study calculates the lensing equation, magnification, and event rate based on the radial equation of state. The analysis highlights that the image problem of the light source is complex. Furthermore, the study suggests that larger values for the throat radius of the wormhole and the radial equation of state lead to higher event rates. Additionally, it is proposed that the event rate of a wormhole will be larger compared to that of a black hole, provided their masses and distances from the light source and observer are comparable. This study offers the potential to distinguish between a wormhole and a black hole under similar conditions.

Learning a Single Network for Robust Medical Image Segmentation With Noisy Labels.

Robust segmenting with noisy labels is an important problem in medical imaging due to the difficulty of acquiring high-quality annotations. Despite the enormous success of recent developments, these developments still require multiple networks to construct their frameworks and focus on limited application scenarios, which leads to inflexibility in practical applications. They also do not explicitly consider the coarse boundary label problem, which results in sub-optimal results. To overcome these challenges, we propose a novel Simultaneous Edge Alignment and Memory-Assisted Learning (SEAMAL) framework for noisy-label robust segmentation. It achieves single-network robust learning, which is applicable for both 2D and 3D segmentation, in both Set-HQ-knowable and Set-HQ-agnostic scenarios. Specifically, to achieve single-model noise robustness, we design a Memory-assisted Selection and Correction module (MSC) that utilizes predictive history consistency from the Prediction Memory Bank to distinguish between reliable and non-reliable labels pixel-wisely, and that updates the reliable ones at the superpixel level. To overcome the coarse boundary label problem, which is common in practice, and to better utilize shape-relevant information at the boundary, we propose an Edge Detection Branch (EDB) that explicitly learns the boundary via an edge detection layer with only slight additional computational cost, and we improve the sharpness and precision of the boundary with a thinning loss. Extensive experiments verify that SEAMAL outperforms previous works significantly.

Truncated Newton full waveform inversion method for the human brain imaging

Abstract It has been shown that full-waveform inversion (FWI) method can be a competitive alternative for medical imaging problems. It offers high-resolution results while delivering the advantages of being fast, safe, portable, and affordable, compared to magnetic resonance imaging (MRI) and x-ray computed tomography. However, to the best of our knowledge, FWI applications in medical imaging only use the first-order derivative information. In this case, the high parameter contrasts between different tissues of human body and multi-scatterings problems may lead FWI to local minima. Thus, we present a competitive truncated Newton method for high-resolution imaging of the human brain. This truncated Newton method, based on the efficient linear solver MINRES-QLP, can make full use of multiple scattering wavefield information. Compared with the truncated Newton method based on conjugate gradient, the MINRES-QLP iterative method presents various advantages when solving linear systems, such as the capacity to handle both non-singular and singular systems, less computational cost, and efficiency even for ill-conditioned systems. Numerical experiments for imaging the brain with and without the skull are conducted. Numerical results indicate that, compared with the truncated Newton method based on conjugate gradient, the truncated Newton method based on MINRES-QLP exhibits computational efficiency while maintaining the same level of accuracy.

A Study of Classroom Behavior Recognition Incorporating Super-Resolution and Target Detection.

With the development of educational technology, machine learning and deep learning provide technical support for traditional classroom observation assessment. However, in real classroom scenarios, the technique faces challenges such as lack of clarity of raw images, complexity of datasets, multi-target detection errors, and complexity of character interactions. Based on the above problems, a student classroom behavior recognition network incorporating super-resolution and target detection is proposed. To cope with the problem of unclear original images in the classroom scenario, SRGAN (Super Resolution Generative Adversarial Network for Images) is used to improve the image resolution and thus the recognition accuracy. To address the dataset complexity and multi-targeting problems, feature extraction is optimized, and multi-scale feature recognition is enhanced by introducing AKConv and LASK attention mechanisms into the Backbone module of the YOLOv8s algorithm. To improve the character interaction complexity problem, the CBAM attention mechanism is integrated to enhance the recognition of important feature channels and spatial regions. Experiments show that it can detect six behaviors of students-raising their hands, reading, writing, playing on their cell phones, looking down, and leaning on the table-in high-definition images. And the accuracy and robustness of this network is verified. Compared with small-object detection algorithms such as Faster R-CNN, YOLOv5, and YOLOv8s, this network demonstrates good detection performance on low-resolution small objects, complex datasets with numerous targets, occlusion, and overlapping students.

Investigating the missing-wedge problem in small-angle X-ray scattering tensor tomography across real and reciprocal space.

Small-angle-scattering tensor tomography is a technique for studying anisotropic nanostructures of millimetre-sized samples in a volume-resolved manner. It requires the acquisition of data through repeated tomographic rotations about an axis which is subjected to a series of tilts. The tilt that can be achieved with a typical setup is geometrically constrained, which leads to limits in the set of directions from which the different parts of the reciprocal space map can be probed. Here, we characterize the impact of this limitation on reconstructions in terms of the missing wedge problem of tomography, by treating the problem of tensor tomography as the reconstruction of a three-dimensional field of functions on the unit sphere, represented by a grid of Gaussian radial basis functions. We then devise an acquisition scheme to obtain complete data by remounting the sample, which we apply to a sample of human trabecular bone. Performing tensor tomographic reconstructions of limited data sets as well as the complete data set, we further investigate and validate the missing wedge problem by investigating reconstruction errors due to data incompleteness across both real and reciprocal space. Finally, we carry out an analysis of orientations and derived scalar quantities, to quantify the impact of this missing wedge problem on a typical tensor tomographic analysis. We conclude that the effects of data incompleteness are consistent with the predicted impact of the missing wedge problem, and that the impact on tensor tomographic analysis is appreciable but limited, especially if precautions are taken. In particular, there is only limited impact on the means and relative anisotropies of the reconstructed reciprocal space maps.

Noise Resilience in Dermoscopic Image Segmentation: Comparing Deep Learning Architectures for Enhanced Accuracy

Skin diseases and lesions can be ambiguous to recognize due to the similarity of lesions and enhanced imaging features. In this study, we compared three cutting-edge deep learning frameworks for dermoscopic segmentation: U-Net, SegAN, and MultiResUNet. We used a dermoscopic dataset including detailed lesion annotations with segmentation masks to help train and evaluate models on the precise localization of melanomas. SegAN is a special type of Generative Adversarial Network (GAN) that introduces a new architecture by adding generator and discriminator steps. U-Net has become a common strategy in segmentation to encode and decode image features for limited data. MultiResUNet is a U-Net-based architecture that overcomes the insufficient data problem in medical imaging by extracting contextual details. We trained the three frameworks on colored images after preprocessing. We added incremental Gaussian noise to measure the robustness of segmentation performance. We evaluated the frameworks using the following parameters: accuracy, sensitivity, specificity, Dice and Jaccard coefficients. Our accuracy results show that SegAN (92%) and MultiResUNet (92%) both outperform U-Net (86%), which is a well-known segmentation framework for skin lesion analysis. MultiResUNet sensitivity (96%) outperforms the methods in the challenge leaderboard. These results suggest that SegAN and MultiResUNet are more resistant techniques against noise in dermoscopic segmentation.

Re-envisioning vocational education: critical discourse analysis of a government publicity campaign in Hong Kong

PurposeVocational education in Hong Kong suffers from an image problem. Stakeholders often perceive it as a second-best option for those who fail to advance in academic education. In 2016, to promote vocational education, the Hong Kong government launched a publicity campaign and rebranded vocational education and training (VET) as vocational and professional education and training (VPET). This study critically analyzes the new discourse crafted by this campaign and assesses its potential to change VPET’s status.Design/methodology/approachThis study applies critical discourse analysis to the set of television public service advertisements produced as part of the government publicity campaign.FindingsThe messaging of the publicity campaign consists of two major discursive strategies. One stresses the ability to find self-fulfillment through VPET. The other stresses the academic ability and middle-class status of VPET students as well as the non-manual and high-end career opportunities for graduates. While the first strategy offers a new basis on which to value VPET, the second recreates assumptions about the value of academic achievement and what constitutes respectable employment, even as it attempts to challenge stereotypes. It reinforces that the ultimate goal of education is financial gain and social status. It overlooks other values of education and the potential value of VPET in enhancing individual choice and agency.Research limitations/implicationsDiscourse analysis does not provide information about audience perceptions and interpretations.Social implicationsThe government could consider reframing their messaging in terms of the diverse values and experiences of VPET students. Highlighting the values that VPET students themselves see in their education provides alternative discourses that can better challenge hegemonic ideas.Originality/valueTo the best of our knowledge, this is the first discourse analysis of the government’s publicity campaign to promote VPET.

Body image discontentment among head and neck cancer patients in Visakhapatnam district: An empirical study

Head and neck cancers, which comprise tumours of the oral cavity, throat, nasal cavity, and thyroid, pose substantial physical and psychological issues. These tumours frequently require harsh therapies such as surgery, radiation therapy, and chemotherapy, which can result in apparent changes in appearance and physical function. As a result, patients are frequently subjected to body image distress, low self-esteem, and overall unhealthy psychological well-being. This study aims to investigate head and neck cancer patients' self-perceptions and body image problems, with an emphasis on feelings of self-consciousness, physical attractiveness, and general body dissatisfaction amongst head and neck cancer out patients undergoing treatment in HCG cancer hospital in Visakhapatnam. This study was conducted on 50 head and neck cancer outpatients undergoing treatment at an oncology centre Healthcare Global Enterprises ltd (HCG) hospital Visakhapatnam during the period of (May 2023 to June 2023) who were willing to participate in the study and were 20 years of age and above. An interview schedule was prepared by the researcher and administered to the patients comprising section A (questions pertaining to the demographic and clinical details of the patient), section B (modified 6 item Body Image Scale). Majority of the patients were male (62%) while female constituted 38% with the majority aged between 20- 39 years (61%) and the most common cancer being that of oral cavity (58%). The findings reveal a sizable proportion of respondents reporting feeling self-conscious and less physically attractive as a result of their sickness or treatment. Many individuals are dissatisfied with their appearance and overall body image, with a significant percentage reporting that these issues interfere with their social relationships and sense of wholeness. These findings highlight the need of addressing psychological and emotional support in the treatment and care of head and neck cancer patients. Integrating mental health and body image counselling into cancer treatment programmes has the potential to greatly improve patients' overall well-being and quality of life.

Confocal structured illumination microscopy for improving the signal-to-noise ratio and depth of fluorescent optical section imaging

Light scattering from the sample is an unavoidable problem in fluorescence imaging. Compared with laser scanning confocal scanning microscopy, although optical-sectioning structured illumination microscopy (OS-SIM) has the advantages of fast imaging speed and low phototoxicity, it faces the challenge of removing the scattering fluorescent noise particularly when imaging thick and densely labeled sampling. To improve the imaging performance of OS-SIM, we introduce the concept of confocal imaging to OS-SIM and propose confocal structured illumination microscopy (CSIM). CSIM exploits the principle of dual imaging to reconstruct a dual image from each camera pixel. The scattered fluorescent noise and the unscattered fluorescent signal recorded by the camera pixel are separated in the reconstructed dual image. By extracting the unscattered fluorescent signal from each dual image based on the conjugate relationship between the camera and the spatial light modulator, we can eliminate the scattered fluorescent noise and reconstruct a confocal image. We have built the theoretical framework of CSIM. Experimental results of fluorescent optical-sectioning demonstrate that CSIM achieves a superior performance in eliminating scattered fluorescent noise and in extending imaging depth compared with existing OS-SIM. CSIM is expected to broaden the application range of OS-SIM.

How Data Infrastructure Deals with Bias Problems in Medical Imaging.

The paper discusses biases in medical imaging analysis, particularly focusing on the challenges posed by the development of machine learning algorithms and generative models. It introduces a taxonomy of bias problems and addresses them through a data infrastructure initiative: the PADME (Platform for Analytics and Distributed Machine-Learning for Enterprises), which is a part of the National Research Data Infrastructure for Personal Health Data (NFDI4Health) project. The PADME facilitates the structuring and sharing of health data while ensuring privacy and adherence to FAIR principles. The paper presents experimental results that show that generative methods can be effective in data augmentation. Complying with PADME infrastructure, this work proposes a solution framework to deal with bias in the different data stations and preserve privacy when transferring images. It highlights the importance of standardized data infrastructure in mitigating biases and promoting FAIR, reusable, and privacy-preserving research environments in healthcare.

Multitasking optimization for the imaging problem in electrical capacitance tomography

Electrical capacitance tomography excels in measuring multiphase flows, but it faces challenges in reconstructing high-accuracy images. To tap into the potential of this measurement technique, we model the image reconstruction problem as a bilevel multitasking optimization problem, aiming to enhance imaging quality via effective knowledge transfer and integration across various tasks. This new imaging model consists of a target optimization problem and an auxiliary optimization problem, facilitating knowledge transfer and fusion between tasks. We design a new algorithm to solve the target optimization problem and integrate it with an autoencoder used for the cross-task knowledge transfer, forming a new multitasking optimizer to solve this proposed bilevel multitasking optimization imaging model. The extreme learning machine is developed for the prediction of learnable prior images by introducing a novel bilevel optimization framework that enables concurrent parameter selection and model training. A novel nested algorithm, designed to efficiently address optimization problems structured hierarchically, is developed to solve the training model. Evaluation results show that the new imaging algorithm outperforms popular imaging methods in terms of reconstruction accuracy and robustness, while also demonstrating stable performance. This proposed imaging algorithm achieves cross-task knowledge transfer and fusion, integrates measurement physics and machine learning, mines and integrates effective image priors, adaptively learns model parameters, alleviates the ill-posed property of the image reconstruction problem, increase the automation of the model, and improves imaging quality, robustness and performance stability, which provides a comprehensive solution to mitigate challenges in imaging.

Auto-weighted Bayesian Physics-Informed Neural Networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution

Auto-weighted Bayesian Physics-Informed Neural Networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution