Classical Image Research Articles

In-situ quality monitoring during embedded bioprinting using integrated microscopy and classical computer vision.

Despite significant advances in bioprinting technology, current hardware platforms lack the capability for process monitoring and quality control. This limitation hampers the translation of the technology into industrial GMP-compliant manufacturing settings. As a key step towards a solution, we developed a novel bioprinting platform integrating a high-resolution camera for in-situ monitoring of extrusion outcomes during embedded bioprinting. Leveraging classical computer vision and image analysis techniques, we then created a custom software module for assessing print quality. This module enables quantitative comparison of printer outputs to input points of the CAD model's 2D projections, measuring area and positional accuracy. To showcase the platform's capabilities, we then investigated compatibility with various bioinks, dyes, and support bath materials for both 2D and 3D print path trajectories. In addition, we performed a detailed study on how the rheological properties of granular support hydrogels impact print quality during embedded bioprinting, illustrating a practical application of the platform. Our results demonstrated that lower viscosity, faster thixotropy recovery, and smaller particle sizes significantly enhance print fidelity. This novel bioprinting platform, equipped with integrated process monitoring, holds great potential for establishing auditable and more reproducible biofabrication processes for industrial applications.

An Overview of Quantum Circuit Design Focusing on Compression and Representation

Quantum image computing has attracted attention due to its vast storage capacity and faster image data processing, leveraging unique properties such as parallelism, superposition, and entanglement, surpassing classical computers. Although classical computing power has grown substantially over the last decade, its rate of improvement has slowed, struggling to meet the demands of massive datasets. Several approaches have emerged for encoding and compressing classical images on quantum processors. However, a significant limitation is the complexity of preparing the quantum state, which translates pixel coordinates into corresponding quantum circuits. Current approaches for representing large-scale images require higher quantum resources, such as qubits and connection gates, presenting significant hurdles. This article aims to overview the pixel intensity and state preparation circuits requiring fewer quantum resources and explore effective compression techniques for medium and high-resolution images. It also conducts a comprehensive study of quantum image representation and compression techniques, categorizing methods by grayscale and color image types and evaluating their strengths and weaknesses. Moreover, the efficacy of each model’s compression can guide future research toward efficient circuit designs for medium- to high-resolution images. Furthermore, it is a valuable reference for advancing quantum image processing research by providing a systematic framework for evaluating quantum image compression and representation algorithms.

Effectiveness of Hybrid Quantum-Classical and Quanvolutional Neural Networks for image classification

The article focuses on studying the effectiveness of two different Hybrid Neural Networks (HNNs) architectures for solving real-world image classification problems. The first approach investigated in the research is a hybridization technique that allows creation of HNN based on a classical neural network by replacing a number of hidden layers of the neural network with a variational quantum circuit, which allows to reduce the complexity of the classical part of the neural network and move part of computations to a quantum device. The second approach is a hybridization technique based on utilizing quanvolutional operations for image processing as the first quantum convolutional layer of the hybrid neural network, thus building a Quanvolutional Neural Network (QNN). QNN leverages quantum phenomena to facilitate feature extraction, enabling the model to achieve higher accuracy metrics than its classical counterpart. The effectiveness of both architectures was tested on several image classification problems. The first one is a classical image classification problem of CIFAR10 images classification, widely used as a benchmark for various imagery-related tasks. Another problem used for the effectiveness study is the problem of geospatial data analysis. The second problem represents a real-world use case where quantum computing utilization can be very fruitful in the future. For studying the effectiveness, several models were assembled: HNN with a quantum device that replaces one of the hidden layers of the neural network, QNN based on quanvolutional operation and utilizes VGG-16 architecture as a classical part of the model, and also an unmodified VGG-16 was used as a reference model. Experiments were conducted to measure the models' key efficiency metrics: maximal accuracy, complexity of a quantum part of the model and complexity of a classical part of the model. The results of the research indicated the feasibility of both approaches for solving both proposed image classification problems. Results were analyzed to outline the advantages and disadvantages of every approach in terms of selected key metrics. Experiments showed that QNN architectures proved to be a feasible and effective solution for critical practical tasks requiring higher levels of model prediction accuracy and, simultaneously, can tolerate higher processing time and significantly increased costs due to a high number of quantum operations required. Also, the results of the experiments indicated that HNN architectures proved to be a feasible solution for time-critical practical tasks that require higher processing speed and can tolerate slightly decreased accuracy of model predictions.

Breast Cancer Image Classification Based on Attention Mechanisms

Convolutional neural networks have been frequently utilized in computer-aided diagnosis (CAD). Breast cancer image classification is one of the vital applications of CAD. The purpose of this study was to explore the role of attention mechanism in breast cancer image classification. Specifically, this study introduces attention mechanism into the classical image classification deep learning network and constructs a new breast cancer image classification model. Test results indicate that convolutional neural networks perform better in classification when an attention mechanism is added, and they also perform better in terms of training loss and accuracy.

Adnexal masses: a compendium of established radiological signs.

Adnexal masses are frequently encountered in general practice. Whether employing CT, US, or MRI, imaging plays a pivotal role in guiding appropriate treatment for patients with adnexal masses, potentially minimizing the need for surgery in benign cases and expediting the management of those with suspected malignancy. Accurately distinguishing benign from malignant adnexal masses can be challenging due to the confined pelvic space and the proximity of organs, making it difficult to determine their organ of origin or to distinguish tissue characteristics and imaging features. Radiologists have identified a myriad of classic adnexal imaging signs that are pathognomonic of certain diagnoses. Often named analogously to familiar objects, such as the "boba sign," familiarity with these signs can contribute to an accurate diagnosis, avoiding additional imaging tests. This pictorial review is a compendium of known radiological signs of adnexal pathologies, reiterating their role in making an accurate diagnosis, and guiding the next steps in management.

The Impact of Metrics in Mechanical Imaging

ABSTRACTOptical flow (OF) is an alternative technique to the more classical digital image correlation (DIC) methods, able to measure the motion between two images. It is a pixel‐wise method, in the sense that the displacement is defined at each pixel and its computation does not require overpixel grids. This paper examines the impact on the identified strain field, the main quantity of interest for solid mechanics, of the metrics used to quantify the conservation of the OF and to impose the regularity of the displacement. The Charbonnier and Lorentzian loss functions are inspected in this work. A new regularization approach is used to locally vary the Tikhonov parameter using a mask in order to preserve the discontinuities and encourage the appearance of local phenomena while smoothing the computed fields elsewhere. Finally, an open‐source GPU‐accelerated python code has been implemented.

A Novel Objective Method for Steel Degradation Rate Evaluation.

This article introduces a novel approach for assessing microstructure, particularly its degradation after extended operation. The authors focus on creep processes in power plant components, highlighting the importance of diagnostics in this field. This article emphasizes the value of combining traditional microstructure observation techniques with image analysis. A non-destructive method of evaluating microstructure parameters (matrix replicas) is presented, and its accuracy is evaluated against the conventional destructive method. The assessment utilizes quantitative data derived from classical stereological principles and image analysis. Parameters like mean chord length, relative surface area, mean cross-sectional area, and mean equivalent diameter are compared for replica and metallographic specimens. The results show that the replica method accurately reproduces the microstructure. In their conclusions, the authors highlight the importance of developing visual methods alongside the application of artificial intelligence while indicating the challenges in achieving this goal.

Echocardiography in acute pulmonary embolism – what do we have?

Pulmonary thromboembolism (PE) related mortality worldwide is decreasing due to current therapeutic advances. However, PE remains the third leading cause of death in developed countries and its incidence is increasing. Timely diagnosis and appropriate therapeutic measures are extremely important in clinical practice. Echocardiography (EchoCG) remains a preferred imaging technique at the bedside for both primary diagnosis and individual patient risk determination, and provides invaluable information regarding general hemodynamics in emergency situations. The development of the methodology in recent years adds new parameters to the classic image of the patient with PE. In this review, modern approaches for risk stratification of patients with PE by means of echocardiography and the role of echocardiography in the diagnosis of the disease are considered.

From Greek Original to Modern Pastiche: the Reformulation of the Classical Statue in Contemporary Art

From the late 1960s onwards, Italian sculptors, especially those associated with the Arte Povera movement, have frequently made overt references to ancient art. Their work may be an exact replica of an antique statue, but more often the artist makes significant formal changes with regard to medium and provides the work with a different title. The present article discusses sculptures of Michelangelo Pistoletto, Giulio Paolini and Mario Ceroli, as well as some by the English sculptor Edward Allington, and touches upon the Danish artist Christian Lemmerz. When referring to earlier art, the contemporary artist often makes use of the multiple, in this way questioning the concept of the original and unique work of art. The Romans also made serial productions of Greek statues, ans sometimes it is difficult to tell whether an ancient statue is a so-called “Greek original” or a so-called “Roman copy”. In fact some sculptures, like the Laocoön, do not fit into either category. It is argued here that the Roman attitude towards originality is to a certain extent comparable to that of contemporary artists. But while the Roman artists stressed the cultural continuatio, the contemporary of classical images lay bare the distance between past and present.

Deep learning in classical x-ray ghost imaging for dose reduction

Deep learning in classical x-ray ghost imaging for dose reduction

Image Processing Technique for Enhanced Combustion Efficiency of Wood Pellets

The combustion efficiency of wood pellets is partly affected by their average length. The ISO 17829 standard defines the methodology for assessing the average length of sample pellets, but the method does not always lead to representative data. Furthermore, a standard analysis is time-consuming as it requires manual measurement of the pellets using a caliper. This paper, whilst evaluating the effect of pellet length on combustion efficiency, proposes a pending-patented dimensional image processing method (DIP) for assessing pellet length. DIP allows the dimensional data of grouped and stacked pellets to be obtained by exploiting the shadows produced by pellets when exposed to a light source, assuming that different-sized pellets produce different shadows. Thus, the proposed method allows for the extraction of dimensional information from non-distinct objects, overcoming the reliance of classical image processing methods on object distance for effective segmentation. Combustion tests, carried out using pellets varying only in length, confirmed the influence of length on combustion efficiency. Shorter pellets, compared to longer ones, significantly reduced CO emissions by up to 94% (mg/MJ). However, they exhibited a higher fuel mass consumption rate (kg/h), with an increase of up to 22.8% compared to the longest sample. In addition, longer pellets produced fewer but larger shadows than shorter ones. Further studies are needed to correlate the number and size of shadows with samples’ average length so that DIP could be implemented in stoves and programmed to communicate with the control unit and automatically optimize the setting in order to improve combustion efficiency.

Efficient MPS representations and quantum circuits from the Fourier modes of classical image data

Machine learning tasks are an exciting application for quantum computers, as it has been proven that they can learn certain problems more efficiently than classical ones. Applying quantum machine learning algorithms to classical data can have many important applications, as qubits allow for dealing with exponentially more data than classical bits. However, preparing the corresponding quantum states usually requires an exponential number of gates and therefore may ruin any potential quantum speedups. Here, we show that classical data with a sufficiently quickly decaying Fourier spectrum after being mapped to a quantum state can be well-approximated by states with a small Schmidt rank (i.e., matrix-product states) and we derive explicit error bounds. These approximated states can, in turn, be prepared on a quantum computer with a linear number of nearest-neighbor two-qubit gates. We confirm our results numerically on a set of 1024×1024-pixel images taken from the `Imagenette' and DIV2K datasets. Additionally, we consider different variational circuit ansätze and demonstrate numerically that one-dimensional sequential circuits achieve the same compression quality as more powerful ansätze.

Development of a Python Software for the Cardiovascular System Segmentation such as Arteries and Left Ventricle

J. Festas, L.C. Sousa, S.S. Siusa, S.I.S. PintoCardiovascular diseases (CVDs) are the leading cause of death globally, accounting for approximately 17.9 million deaths annually, with coronary artery disease (CAD) as a major contributor. CAD results from the build-up of atherosclerotic plaques, reducing myocardial perfusion and leading to conditions like angina and myocardial infarctions, severely affecting the left ventricle’s function. Advanced diagnostic tools are being developed to enhance the segmentation of cardiovascular structures, improving diagnostic accuracy and treatment outcomes.Accurate segmentation is crucial for analyzing coronary behavior via Computed Tomography Angiography (CTA), a non-invasive alternative to coronary angiography, and for planning surgical interventions. Furthermore, the models retrieved after segmentation can be enlarged simulating hyperemia for further hemodynamic simulations. Similarly, segmenting the left ventricle in dynamic CT scans is vital for assessing cardiac health through measurements like ventricular volume and ejection fraction.However, manual segmentation is time-consuming and suffers from variability, which can lead to significant diagnostic errors [1]. As such, there is a pressing need for more automated tools that enhance accuracy while reducing manual labor.Most common advancements are in the realms of deep learning. These have propelled automated medical image segmentation, achieving results with high efficiency and reliability [2]; however, these require extensive data sets and high variability. In scenarios where such datasets are limited or exhibit low variance, these models risk developing biases or failing to achieve accurate results in cases that are very different then the norm of the training dataset.To mitigate these risks, we are developing a Python-based semi-automatic algorithm that relies on existing open-source libraries, enhancing them with custom developments tailored to our specific needs, while relying on technician input to enhance classical image processing, ensuring adaptability to varied clinical conditions. We are testing this tool with patient data, with results that are very promising: segmentation similarity results of around 85%. We plan to release it as open-source software, encouraging a community-driven approach for continuous improvement and adaptation to clinical needs.The initial tests allows to believe this tool can be a robust and accurate software that can be used in hospital or for investigation purposes. The semi-automatic nature allows for user input and post processing tailoring of the segmentation.[1] Tavakoli, V. et al. (2013) A survey of shaped-based registration and segmentation techniques for cardiac images. Computer Vision and Image Understanding 117, no. 9: 966-989.[2] Litjens, G. et al. (2017) A survey on deep learning in medical image analysis. Medical Image Analysis 42: 60-88.

Metasurface polarization optics: From classical to quantum

Metasurface polarization optics, manipulating polarization using metasurfaces composed of subwavelength anisotropic nanostructure array, has enabled a lot of innovative integrated strategies for versatile and on-demand polarization generation, modulation, and detection. Compared with conventional bulky optical elements for polarization control, metasurface polarization optics provides a feasible platform in a subwavelength scale to build ultra-compact and multifunctional polarization devices, greatly shrinking the size of the whole polarized optical system and network. Here, we review the recent progresses of metasurface polarization optics in both classical and quantum regimes, including uniform and spatially varying polarization-manipulating devices. Basic polarization optical elements such as meta-waveplate, meta-polarizer, and resonant meta-devices with polarization singularities provide compact means to generate and modulate uniform polarization beams. Spatial-varying polarization manipulation by employing the pixelation feature of metasurfaces, leading to advanced diffraction and imaging functionalities, such as vectorial holography, classic and quantum polarization imaging, quantum polarization entanglement, quantum interference, and modulation. Substituting conventional polarization optics, metasurface approaches pave the way for on-chip classic or quantum information processing, flourishing advanced applications in displaying, communication, imaging, and computing.

Feature Extraction and Classification of Retinal Images Using Sobel Segmentation and Linear SVC

Eye diseases such as Diabetic Retinopathy, Cataract, and Glaucoma are significant causes of visual impairment and blindness worldwide. Early detection and accurate diagnosis are crucial for effective treatment and management of these conditions. This study aimed to develop a machine learning model for the automated classification of retinal images into four categories: Normal, Diabetic Retinopathy, Cataract, and Glaucoma. The dataset, sourced from Kaggle, comprised approximately 1000 images per class, which were pre-processed using Sobel segmentation to enhance relevant features. Hu Moments were employed for feature extraction due to their invariance to scale, rotation, and translation. The classification was performed using a Linear Support Vector Classifier (SVC), and the model's performance was evaluated through 5-fold cross-validation. The average performance metrics were 44.34% for accuracy, 48.26% for precision, 44.34% for recall, and 41.76% for F1-score. These results indicate that while Sobel segmentation and Hu Moments effectively highlight and capture essential features of retinal images, the Linear SVC classifier's performance is moderate, suggesting the need for more advanced classifiers. The study's findings contribute to the ongoing research in automated eye disease diagnosis by demonstrating the strengths and limitations of classical image processing and machine learning techniques. Future research should focus on exploring more sophisticated models, such as convolutional neural networks, and addressing dataset imbalances to enhance classification accuracy and reliability. This study underscores the potential for automated diagnostic tools in clinical settings but also highlights the necessity for further optimization to achieve practical applicability.

SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration

Deep learning has emerged as a strong alternative for classical iterative methods for de- formable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular classical image registration methods enforce the useful inductive biases of symmetricity, inverse consistency, and topology preservation by construction. However, while many deep learning registration methods encourage these properties via loss functions, no earlier methods enforce all of them by construction. Here, we propose a novel registration architecture based on extracting multi-resolution feature representations which is by construction symmetric, inverse consistent, and topology pre- serving. We also develop an implicit layer for memory efficient inversion of the deformation fields. Our method achieves state-of-the-art registration accuracy on three datasets. The code is available at <a href='https://github.com/honkamj/SITReg'>https://github.com/honkamj/SITReg</a>

Permutation-equivariant quantum convolutional neural networks

Abstract The Symmetric group S n manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. Subgroups of S n arise, among many other contexts, to describe label symmetry of classical images with respect to spatial transformations, such as reflection or rotation. Equipped with the formalism of geometric quantum machine learning, in this study we propose the architectures of equivariant quantum convolutional neural networks (EQCNNs) adherent to S n and its subgroups. We demonstrate that a careful choice of pixel-to-qubit embedding order can facilitate easy construction of EQCNNs for small subgroups of S n . Our novel EQCNN architecture corresponding to the full permutation group S n is built by applying all possible QCNNs with equal probability, which can also be conceptualized as a dropout strategy in quantum neural networks. For subgroups of S n , our numerical results using MNIST datasets show better classification accuracy than non-equivariant QCNNs. The S n -equivariant QCNN architecture shows significantly improved training and test performance than non-equivariant QCNN for classification of connected and non-connected graphs. When trained with sufficiently large number of data, the S n -equivariant QCNN shows better average performance compared to S n -equivariant QNN . These results contribute towards building powerful quantum machine learning architectures in permutation-symmetric systems.

Imaging Brain Tissue with Quantum Light at Low Power.

Light-induced tissue damage is a crucial limitation for traditional microscopy of the living brain, underscoring the need for new techniques that minimize exposure of samples to light. Here, we tested the hypothesis that quantum light, i.e., entangled photons, could detect brain structures at a lower excitation energy. In a proof of principle, we show microscopic images of fixed brain tissue in the hippocampus area created by fluorescence selective excitation in the process of entangled two-photon absorption in a scanning microscope. Quantum-enhanced entangled two-photon microscopy (TPM) had brain imaging capabilities at an unprecedented low excitation intensity of ∼3.6 × 107 photons/s, orders of magnitude lower than the excitation level for the classical two-photon fluorescence image obtained in the same microscope. The extremely low light probe intensity demonstrated in entangled TPM is of critical importance in the investigation of neural activity to minimize heating and photobleaching during repetitive imaging. It may have important functional implications in optogenetic technology, removing unintended heating and accumulated photodamage effects. This technology also opens avenues in spatially resolved brain tissue investigations with quantum light, providing new capabilities in local spectroscopy.

Fractal Image Decompression via Non-affine Contractions

In this study, considering the well-known fractal image compression, we introduce the image decompression method through non-affine contraction mappings. To achieve this, we convert affine contraction mappings into non-affine contraction mappings using Lipschitz continuous functions, subject to certain assumptions. Our expectation is to obtain decompressed images of superior quality compared to the classical fractal image compression method. We also apply our method for audio decompression. At the end, we illustrate the proposed method with some examples.

Accuracy of the Image Interpretation Capability of ChatGPT-4 Vision in Analysis of Hess Screen and Visual Field Abnormalities.

OpenAI, the owner of ChatGPT, publicly released the GPT-4 Vision in September 2023. This multimedia chatbot has the capability to receive and analyze various images presented to it by the user. We assessed the accuracy of its interpretation of 2 of the images commonly used in neuro-ophthalmology, namely Hess screen and automated visual field images. We separately uploaded typical images of 5 abnormal Hess screen charts related to third, fourth, and sixth cranial nerve palsy, Brown syndrome, and inferior orbital wall fracture with entrapment of the inferior rectus muscle. Likewise, 5 classic images of automated visual field grayscale maps related to lesions of the optic nerve, the chiasma, the optic tract, the optic radiations, and the occipital lobe were presented. The chatbot was instructed to select the best option among the 5 choices presented in each question. The GPT-4 Vision was able to select the right choice in 2/5 questions on Hess screens and 3/5 of the visual field questions. Despite selection of the correct option, qualitative evaluation of GPT-4 responses revealed flawed analysis of certain aspects of some image findings, such as the side of involvement or the misinterpretation of the physiologic blind spot as a central scotoma. The performance of GPT-4 Vision in the interpretation of abnormalities of Hess screen and visual field involvement was highly variable, even with simple typical cases of classic disorders. As the chatbot's image recognition is currently evolving, its capacity to accurately interpret ophthalmologic images is still limited at this time.