Medical Imaging Modalities Research Articles

A comparative study of statistical, radiomics, and deep learning feature extraction techniques for medical image classification in optical and radiological modalities.

Feature extraction in ML plays a crucial role in transforming raw data into a more meaningful and interpretable representation. In this study, we thoroughly examined a range of feature extraction techniques and assessed their impact on the binary classification models for medical images, utilizing a diverse and rich set of medical imaging modalities. Using H&E-stained, chest X-ray, and retina OCT images, we applied methods to extract statistical, radiomics, and deep features. These features were then used to develop PCA-LDA models as the employed classifier. We evaluated the models based on two decisive metrics: latency and performance. Latency measured the time taken for feature extraction and prediction, while mean sensitivity (balanced accuracy) characterizes the model performance. Our comparative study revealed that statistical and radiomics features were less effective for medical image classification, as they showed high latency and lower performance scores. In contrast, pre-trained DL networks performed efficiently, with high sensitivity and low latency. For H&E-stained images, the statistical feature extraction took about an hour and achieved 90.8% sensitivity, while ResNet50 reduced processing time fourfold and increased sensitivity to 96.9%. For chest X-rays, radiomics features were time-intensive with 92.2% sensitivity, while ResNet50 improved sensitivity to 96% with faster extraction time. For retina OCT images, radiomics yielded a sensitivity of 91%, while DenseNet121 achieved 98.6% sensitivity in 15min. These findings underscore the superior performance of DL techniques over the statistical and radiomics features, highlighting their potential for real-world applications where accurate and rapid diagnostic decisions are essential.

Unlocking the Power of 3D Convolutional Neural Networks for COVID-19 Detection: A Comprehensive Review.

The advent of three-dimensional convolutional neural networks (3D CNNs) has revolutionized the detection and analysis of COVID-19 cases. As imaging technologies have advanced, 3D CNNs have emerged as a powerful tool for segmenting and classifying COVID-19 in medical images. These networks have demonstrated both high accuracy and rapid detection capabilities, making them crucial for effective COVID-19 diagnostics. This study offers a thorough review of various 3D CNN algorithms, evaluating their efficacy in segmenting and classifying COVID-19 across a range of medical imaging modalities. This review systematically examines recent advancements in 3D CNN methodologies. The process involved a comprehensive screening of abstracts and titles to ensure relevance, followed by a meticulous selection and analysis of research papers from academic repositories. The study evaluates these papers based on specific criteria and provides detailed insights into the network architectures and algorithms used for COVID-19 detection. The review reveals significant trends in the use of 3D CNNs for COVID-19 segmentation and classification. It highlights key findings, including the diverse range of networks employed for COVID-19 detection compared to other diseases, which predominantly utilize encoder/decoder frameworks. The study provides an in-depth analysis of these methods, discussing their strengths, limitations, and potential areas for future research. The study reviewed a total of 60 papers published across various repositories, including Springer and Elsevier. The insights from this study have implications for clinical diagnosis and treatment strategies. Despite some limitations, the accuracy and efficiency of 3D CNN algorithms underscore their potential for advancing medical image segmentation and classification. The findings suggest that 3D CNNs could significantly enhance the detection and management of COVID-19, contributing to improved healthcare outcomes.

Guided Multispectral Optoacoustic Tomography for 3D Imaging of the Murine Colon.

Multispectral optoacoustic tomography is a promising medical imaging modality that combines light and sound to provide molecular imaging information at depths of several centimeters, based on the optical absorption of endogenous chromophores, such as hemoglobin. Assessment of inflammatory bowel disease has emerged as a promising clinical application of optoacoustic tomography. In this context, preclinical studies in animal models are essential to identify novel disease-specific imaging biomarkers and understand findings from emerging clinical pilot studies, however to-date, these studies have been limited by the precise identification of the bowel wall. Herein, a transrectal-absorber guide is applied, serving as a high-contrast landmark for 3D optoacoustic tomography of the colon. This study shows that guided multispectral optoacoustic tomography is able to measure changes in blood oxygenation status over the course of acute, chemically-induced colitis in mice and correlates with standard disease activity scores. This novel approach depicts intestinal hemoglobin composition non-invasively during murine inflammation. These results underscore the potential for optoacoustic imaging in translational inflammatory bowel disease research.

ATEDU-NET: An Attention-Embedded Deep Unet for multi-disease diagnosis in chest X-ray images, breast ultrasound, and retina fundus.

In image segmentation for medical image analysis, effective upsampling is crucial for recovering spatial information lost during downsampling. This challenge becomes more pronounced when dealing with diverse medical image modalities, which can significantly impact model performance. Plain and standard skip connections, widely used in most models, often fall short of maintaining high segmentation accuracy across different modalities, because essential spatial information transferred from the encoder to the decoder is lost. Inspired by these limitations, the Attention-Embedded Deep UNet (ATEDU-Net) is presented here, an innovative framework designed and tested on diverse medical image modalities, including X-ray, breast ultrasound, and retinal fundus images. ATEDU-Net features a unique architecture that combines progressive context refinement modules (PCRM) and global context modules (GCM) within a U-shaped network structure with Convgroup blocks which facilitate the integration of convolutional operations. This allows ATEDU-Net to autonomously capture rich spatial details and crucial contextual information from input images. The GCM captures essential contextual information for informed decision-making, while the PCRM enhances feature attention, resulting in precise and robust segmentation. The experimentation and analysis demonstrate that ATEDU-Net promises to be a powerful tool for medical professionals, aiding in the early detection of chest-related diseases, accurate localization of breast tumors, and early identification of eye diseases. This, in turn, contributes significantly to the formulation of optimal therapeutic strategies, enhancing patient care and outcomes. The versatility of ATEDU-Net is further highlighted by its ability to analyze medical images across various modalities, making it well-suited for the complex task of medical image analysis in diverse clinical scenarios.

An ℓ1-plug-and-play approach for MPI using a zero shot denoiser with evaluation on the 3D open MPI dataset

Objective.Magnetic particle imaging (MPI) is an emerging medical imaging modality which has gained increasing interest in recent years. Among the benefits of MPI are its high temporal resolution, and that the technique does not expose the specimen to any kind of ionizing radiation. It is based on the non-linear response of magnetic nanoparticles to an applied magnetic field. From the electric signal measured in receive coils, the particle concentration has to be reconstructed. Due to the ill-posedness of the reconstruction problem, various regularization methods have been proposed for reconstruction ranging from early stopping methods, via classical Tikhonov regularization and iterative methods to modern machine learning approaches. In this work, we contribute to the latter class: we propose a Plug-and-Play approach based on a generic zero-shot denoiser with anℓ1-prior.Approach.We validate the reconstruction parameters of the method on a hybrid dataset and compare it with the baseline Tikhonov, ART, DIP and the previous PP-MPI, which is a Plug-and-Play method with denoiser trained on MPI-friendly data.Main results.We derive a Plug-and-Play reconstruction method based on a generic zero-shot denoiser. Addressing (hyper)parameter selection, we perform an extended parameter search on a hybrid validation dataset we produced and apply the derived parameters for reconstruction on the 3D Open MPI Dataset. We offer a quantitative and qualitative evaluation of the zero-shot Plug-and-Play approach on the 3D Open MPI dataset with the validated parameters. Moreover, we show the quality of the approach with different levels of preprocessing of the data.Significance.The proposed method employs a zero-shot denoiser which has not been trained for the MPI reconstruction task and therefore saves the cost for training. Moreover, it offers a method that can be potentially applied in future MPI contexts.

STUDI KASUS: OSTEOCHONDROMA SCAPULA DAN TIBIA FIBULA PADA REMAJA USIA 14 TAHUN

Multiple Hereditary Exostoses (MHE) is an autosomal dominant inherited genetic condition characterized by multiple exostoses (or osteochondromas). Genetic analysis had identified a certain type of mutated Exostosin genes, can potentially cause exostoses. A 14 years old boy referred to our hospital with a chronic hard palpable lump on his left back and right lower limb in the past 10 years, and was gradually increased in size. Laboratory test which consists of complete blood count, urinalysis, and renal function test were normal. A radiographic examination of the related skeleton demonstrated multiple osteochondromas of scapula and tibia fibula. As a consequence of mutations in the Exostosin 1 and Exostosin 2 genes, chondrocytes exhibiting shortened Heparan Sulfate chains are present in this region. In the later stages, these cells develop exostoses. Multiple Hereditary Exostoses may involve different bone locations and could be diagnosed using various medical imaging modalities, however plain radiography x-ray was already sufficient enough to conclude the abnormality. Sessile lesions were much more common than pedunculated in Multiple Hereditary Exostoses, however Sessile lesions bear a higher risk of malignant transformation into chondrosarcoma. Upon early detection, the prognosis for patients who have chondrosarcoma was favorable. Multiple Hereditary Exostoses is a rare bone disorder marked by the development of non-cancerous tumors near the growth plates of bones. This condition can greatly affect an individual's quality of life, resulting in restricted mobility, skeletal abnormalities, ongoing pain, inhibited growth, and the risk of the exostoses becoming malignant.

Artificial Intelligence (AI): Brain Tumor Detection

The detection and diagnosis of brain tumors, a critical medical challenge, have greatly benefited from the application of Artificial Intelligence (AI). This review paper explores the advancements, methods, and technologies of AI in the detection and classification of brain tumors from medical imaging modalities. It also highlights the importance of machine learning (ML) and deep learning (DL) algorithms, particularly Convolutional Neural Networks (CNNs), in improving diagnostic accuracy, early detection, and prognosis prediction. Moreover, the paper addresses challenges and future directions in integrating AI with clinical practices for brain tumor management.

Artificial Intelligence (AI) for Brain Tumor Detection: Automating MRI Image Analysis for Enhanced Accuracy

Accurately diagnosing and planning for the treatment of brain tumors is crucial in clinical practice. Brain tumor detection and diagnosis rely heavily on artificial intelligence (AI) systems that mainly employ medical imaging modalities like MRI. This study employs cutting-edge DL and image processing techniques to intelligently forecast the brain tumor using AI. The complicated and varied nature of brain tumors frequently presents challenges to deep learning models, despite their promising performance in this task. In order to overcome this obstacle, we present the InceptionV3 architecture, which is based on CNNs and uses 5-fold cross-validation to classify brain tumors from MRI images. A training, validation, and testing of a model were conducted using a publically accessible MRI dataset that included 7023 greyscale brain MRI pictures. These images were classified into four types of tumors: gliomas, meningiomas, no tumors, and pituitary. To enhance diversity of a training dataset, the photos were preprocessed by scaling, greyscale conversion, and labeling. Afterward, data augmentation techniques were applied. A model's performance was assessed using 5-fold cross-validation, yielding an F1-score of 99.98%, an average accuracy of 97.12%, precision of 97.97%, and recall of 96.59%. Other Artificial Intelligent models that were compared included InceptionV3, VGG19, CNN, and DenseNet and the results indicated that the InceptionV3 gave better results overall. These results demonstrate that deep learning can accurately and efficiently detect brain tumors utilizing MRI pictures.

Intelligent imaging technology applications in multidisciplinary hospitals.

With the rapid development of artificial intelligence technology, its applications in medical imaging have become increasingly extensive. This review aimed to analyze the current development status and future direction of intelligent imaging technology by investigating its application in various medical departments. To achieve this, we conducted a comprehensive search of various data sources up to 2024, including PubMed, Web of Science, and Google Scholar, based on the principle of comprehensive search. A total of 332 articles were screened, and after applying the inclusion and exclusion criteria, 56 articles were selected for this study. According to the findings, intelligent imaging technology exhibits robust image recognition capabilities, making it applicable across diverse medical imaging modalities within hospital departments. This technology offers an efficient solution for the analysis of various medical images by extracting and accurately identifying complex features. Consequently, it significantly aids in the detection and diagnosis of clinical diseases. Its high accuracy, sensitivity, and specificity render it an indispensable tool in clinical diagnostics and related tasks, thereby enhancing the overall quality of healthcare services. The application of intelligent imaging technology in healthcare significantly enhances the efficiency of clinical diagnostics, resulting in more accurate and timely patient assessments. This advanced technology offers a faster and more precise diagnostic approach, ultimately improving patient care and outcomes. This review analyzed the socioeconomic changes brought about by intelligent imaging technology to provide a more comprehensive evaluation. Also, we systematically analyzed the current shortcomings of intelligent imaging technology and its future development directions, to enable future research.

Improved Generalizability in Medical Computer Vision: Hyperbolic Deep Learning in Multi-Modality Neuroimaging.

Deep learning has shown significant value in automating radiological diagnostics but can be limited by a lack of generalizability to external datasets. Leveraging the geometric principles of non-Euclidean space, certain geometric deep learning approaches may offer an alternative means of improving model generalizability. This study investigates the potential advantages of hyperbolic convolutional neural networks (HCNNs) over traditional convolutional neural networks (CNNs) in neuroimaging tasks. We conducted a comparative analysis of HCNNs and CNNs across various medical imaging modalities and diseases, with a focus on a compiled multi-modality neuroimaging dataset. The models were assessed for their performance parity, robustness to adversarial attacks, semantic organization of embedding spaces, and generalizability. Zero-shot evaluations were also performed with ischemic stroke non-contrast CT images. HCNNs matched CNNs' performance in less complex settings and demonstrated superior semantic organization and robustness to adversarial attacks. While HCNNs equaled CNNs in out-of-sample datasets identifying Alzheimer's disease, in zero-shot evaluations, HCNNs outperformed CNNs and radiologists. HCNNs deliver enhanced robustness and organization in neuroimaging data. This likely underlies why, while HCNNs perform similarly to CNNs with respect to in-sample tasks, they confer improved generalizability. Nevertheless, HCNNs encounter efficiency and performance challenges with larger, complex datasets. These limitations underline the need for further optimization of HCNN architectures. HCNNs present promising improvements in generalizability and resilience for medical imaging applications, particularly in neuroimaging. Despite facing challenges with larger datasets, HCNNs enhance performance under adversarial conditions and offer better semantic organization, suggesting valuable potential in generalizable deep learning models in medical imaging and neuroimaging diagnostics.

Design, construction and validation of a magnetic particle imaging (MPI) system for human brain imaging.

Magnetic Particle Imaging (MPI) was introduced in 2005 as a promising, tracer-based medical imaging modality with the potential for high sensitivity and spatial resolution. Since then, numerous preclinical devices have been built but only a few human-scale devices, none of which targeted functional neuroimaging. In this work, we probe the challenges of scaling the technology to meet the needs of human functional neuroimaging with sufficient sensitivity for detecting the hemodynamic changes following brain activation with a spatio-temporal resolution comparable to current functional Magnetic Resonance Imaging (fMRI) approaches.

Approach: We built a human brain-scale MPI system using a mechanically-rotated, permanent-magnet-based field-free-line (1.1 T/m) with a water-cooled, 26 kHz drive coil producing a field of up to 7 mT, and receive coil that can fit over a human head. Images are acquired continuously at a temporal resolution of 5 sec/image, controlled by in-house LabView-based acquisition software with online reconstruction. We used a dilution series to quantify the detection limit, a series of parallel-line phantoms to assess the spatial resolution, and a large 'G' shaped phantom to demonstrate the human-scale field-of-view.

Main results: The imager has a sensitivity of about 1 μg Fe over an imaging field of view of 181 mm (132 pixels) diameter in a 5 sec image. Depending on the image reconstruction used, the spatial resolution defined by 50% contrast between adjacent lines was 5-7 mm. 

Significance: This proof-of-concept system demonstrates a pathway for human MPI functional neuroimaging with the potential for an order of magnitude increase of sensitivity compared to the other human hemodynamic imaging methods. It demonstrates the successful transition of the field-free-line based MPI architecture from the rodent to human scale and identifies areas which could benefit from further work.

Medical Image Segmentation Review: The Success of U-Net.

Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model has received tremendous attention from academic and industrial researchers who have extended it to address the scale and complexity created by medical tasks. These extensions are commonly related to enhancing the U-Net's backbone, bottleneck, or skip connections, or including representation learning, or combining it with a Transformer architecture, or even addressing probabilistic prediction of the segmentation map. Having a compendium of different previously proposed U-Net variants makes it easier for machine learning researchers to identify relevant research questions and understand the challenges of the biological tasks that challenge the model. In this work, we discuss the practical aspects of the U-Net model and organize each variant model into a taxonomy. Moreover, to measure the performance of these strategies in a clinical application, we propose fair evaluations of some unique and famous designs on well-known datasets. Furthermore, we provide a comprehensive implementation library with trained models. In addition, for ease of future studies, we created an online list of U-Net papers with their possible official implementation.

A multi-task framework for breast cancer segmentation and classification in ultrasound imaging

Background:Ultrasound (US) is a medical imaging modality that plays a crucial role in the early detection of breast cancer. The emergence of numerous deep learning systems has offered promising avenues for the segmentation and classification of breast cancer tumors in US images. However, challenges such as the absence of data standardization, the exclusion of non-tumor images during training, and the narrow view of single-task methodologies have hindered the practical applicability of these systems, often resulting in biased outcomes. This study aims to explore the potential of multi-task systems in enhancing the detection of breast cancer lesions. Methods:To address these limitations, our research introduces an end-to-end multi-task framework designed to leverage the inherent correlations between breast cancer lesion classification and segmentation tasks. Additionally, a comprehensive analysis of a widely utilized public breast cancer ultrasound dataset named BUSI was carried out, identifying its irregularities and devising an algorithm tailored for detecting duplicated images in it. Results:Experiments are conducted utilizing the curated dataset to minimize potential biases in outcomes. Our multi-task framework exhibits superior performance in breast cancer respecting single-task approaches, achieving improvements close to 15% in segmentation and classification. Moreover, a comparative analysis against the state-of-the-art reveals statistically significant enhancements across both tasks. Conclusion:The experimental findings underscore the efficacy of multi-task techniques, showcasing better generalization capabilities when considering all image types: benign, malignant, and non-tumor images. Consequently, our methodology represents an advance towards more general architectures with real clinical applications in the breast cancer field.

Machine learning applications in placenta accreta spectrum disorders.

This review examines the emerging applications of machine learning (ML) and radiomics in the diagnosis and prediction of placenta accreta spectrum (PAS) disorders, addressing a significant challenge in obstetric care. It highlights recent advancements in ML algorithms and radiomic techniques that utilize medical imaging modalities like magnetic resonance imaging (MRI) and ultrasound for effective classification and risk stratification of PAS. The review discusses the efficacy of various deep learning models, such as nnU-Net and DenseNet-PAS, which have demonstrated superior performance over traditional diagnostic methods through high AUC scores. Furthermore, it underscores the importance of integrating quantitative imaging features with clinical data to enhance diagnostic accuracy and optimize surgical planning. The potential of ML to predict surgical morbidity by analyzing demographic and obstetric factors is also explored. Emphasizing the need for standardized methodologies to ensure consistent feature extraction and model performance, this review advocates for the integration of radiomics and ML into clinical workflows, aiming to improve patient outcomes and foster a multidisciplinary approach in high-risk pregnancies. Future research should focus on larger datasets and validation of biomarkers to refine predictive models in obstetric care.

Resolution Enhancement Strategies in Photoacoustic Microscopy: A Comprehensive Review.

Photoacoustic imaging has emerged as a promising modality for medical imaging since its introduction. Photoacoustic microscopy (PAM), which is based on the photoacoustic effect, combines the advantages of both optical and acoustic imaging modalities. PAM facilitates high-sensitivity, high-resolution, non-contact, and non-invasive imaging by employing optical absorption as its primary contrast mechanism. The ability of PAM to specifically image parameters such as blood oxygenation and melanin content makes it a valuable addition to the suite of modern biomedical imaging techniques. This review aims to provide a comprehensive overview of the diverse technical approaches and methods employed by researchers to enhance the resolution of photoacoustic microscopy. Firstly, the fundamental principles of the photoacoustic effect and photoacoustic imaging will be presented. Subsequently, resolution enhancement methods for both acoustic-resolution photoacoustic microscopy (AR-PAM) and optical-resolution photoacoustic microscopy (OR-PAM) will be discussed independently. Finally, the aforementioned resolution enhancement methods for photoacoustic microscopy will be critically evaluated, and the current challenges and future prospects of this technology will be summarized.

Self-supervised learning for small-scale medical imaging dataset

In recent years, advancements in deep learning have dramatically improved performance in medical image analysis, yet these models typically rely on large-scale labeled datasets, which are often unattainable in medical settings due to privacy concerns, limited data availability, and high annotation costs. This study explores the application of self-supervised learning (SSL) techniques to overcome these limitations and effectively utilize small-scale medical imaging datasets. By leveraging SSL, we enable models to learn useful feature representations without requiring extensive labeled data. We investigate various self-supervised approaches, including contrastive learning and masked image modeling, and evaluate their effectiveness on a limited dataset of medical images. Our experiments demonstrate that SSL-based models can achieve competitive performance, even when trained on a fraction of the labeled data typically required for supervised methods. Additionally, we explore the impact of SSL on model robustness and generalization across diverse medical imaging modalities. The findings suggest that self-supervised techniques could reduce dependency on annotated data, paving the way for broader, more scalable applications in medical imaging. This research contributes to the development of efficient, scalable diagnostic tools that can be deployed in data-constrained environments, potentially improving diagnostic accuracy and accessibility in smaller healthcare facilities.

BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification.

Data augmentation is a crucial regularization technique for deep neural networks, particularly in medical imaging tasks with limited data. Deep learning models are highly effective at linearizing features, enabling the alteration of feature semantics through the shifting of latent space representations-an approach known as semantic data augmentation (SDA). The paradigm of SDA involves shifting features in a specified direction. Current SDA methods typically sample the amount of shifting from a Gaussian distribution or the sample variance. However, excessive shifting can lead to changes in data labels, which may negatively impact model performance. To address this issue, we propose a computationally efficient method called Bayesian Random Semantic Data Augmentation (BSDA). BSDA can be seamlessly integrated as a plug-and-play component into any neural network. Our experiments demonstrate that BSDA outperforms competitive methods and is suitable for both 2D and 3D medical image datasets, as well as most medical imaging modalities. Additionally, BSDA is compatible with mainstream neural network models and enhances baseline performance. The code is available online.

Generative modeling of the Circle of Willis using 3D-StyleGAN

The circle of Willis (CoW) is a network of cerebral arteries with significant inter-individual anatomical variations. Deep learning has been used to characterize and quantify the status of the CoW in various applications for the diagnosis and treatment of cerebrovascular disease. In medical imaging, the performance of deep learning models is limited by the diversity and size of training datasets. To address medical data scarcity, generative AI models have been applied to generate synthetic vessel neuroimaging data. However, the proposed methods produce synthetic data with limited anatomical fidelity or downstream utility in tasks concerning vessel characteristics.We adapted the StyleGANv2 architecture to 3D to synthesize Time-of-Flight Magnetic Resonance Angiography (TOF MRA) volumes of the CoW. For generative modeling, we used 1782 individual TOF MRA scans from 6 open source datasets. To train the adapted 3D StyleGAN model with limited data we employed differentiable data augmentations, used mixed precision and a cropped region of interest of size 32 × 128 × 128 to tackle computational constraints. The performance was evaluated quantitatively using the Fréchet Inception Distance (FID), MedicalNet distance (MD) and Area Under the Curve of the Precision and Recall Curve for Distributions (AUC-PRD). Qualitative analysis was performed via a visual Turing test. We demonstrated the utility of generated data in a downstream task of multiclass semantic segmentation of CoW arteries. Vessel segmentation performance was assessed quantitatively using the Dice coefficient and the Hausdorff distance.The best-performing 3D StyleGANv2 architecture generated high-quality and diverse synthetic TOF MRA volumes (FID: 12.17, MD: 0.00078, AUC-PRD: 0.9610). Multiclass vessel segmentation models trained on synthetic data alone achieved comparable performance to models trained using real data in most arteries. The addition of synthetic data to a baseline training set improved segmentation performance in underrepresented artery segments, similar to the addition of real data.In conclusion, generative modeling of the Circle of Willis via synthesis of 3D TOF MRA data paves the way for generalizable deep learning applications in cerebrovascular disease. In the future, the extensions of the provided methodology to other medical imaging problems or modalities with the inclusion of pathological datasets has the potential to advance the development of more robust AI models for clinical applications.

Optimizing quantitative photoacoustic imaging systems: the Bayesian Cramér–Rao bound approach

Quantitative photoacoustic computed tomography (qPACT) is an emerging medical imaging modality that carries the promise of high-contrast, fine-resolution imaging of clinically relevant quantities like hemoglobin concentration and blood-oxygen saturation. However, qPACT image reconstruction is governed by a multiphysics, partial differential equation (PDE) based inverse problem that is highly non-linear and severely ill-posed. Compounding the difficulty of the problem is the lack of established design standards for qPACT imaging systems, as there is currently a proliferation of qPACT system designs for various applications and it is unknown which ones are optimal or how to best modify the systems under various design constraints. This work introduces a novel computational approach for the optimal experimental design of qPACT imaging systems based on the Bayesian Cramér-Rao bound (CRB). Our approach incorporates several techniques to address challenges associated with forming the bound in the infinite-dimensional function space setting of qPACT, including priors with trace-class covariance operators and the use of the variational adjoint method to compute derivatives of the log-likelihood function needed in the bound computation. The resulting Bayesian CRB based design metric is computationally efficient and independent of the choice of estimator used to solve the inverse problem. The efficacy of the bound in guiding experimental design was demonstrated in a numerical study of qPACT design schemes under a stylized two-dimensional imaging geometry. To the best of our knowledge, this is the first work to propose Bayesian CRB based design for systems governed by PDEs.

X-Ray Interaction Mechanisms in Medical Imaging: A Critical Exploration

X-ray interactions with matter are fundamental to the success of medical imaging, influencing image quality, diagnostic accuracy, and patient safety. This study critically explores the primary interaction mechanisms—photoelectric absorption, Compton scattering, and coherent scattering—and their implications in various medical imaging modalities. By analyzing their effects on image resolution, contrast, and radiation dose, the study highlights the strengths and limitations of each interaction mechanism. The findings underscore the role of photoelectric absorption in high-contrast imaging, the challenges posed by Compton scattering in reducing noise, and the minimal clinical significance of coherent scattering. Emphasis is placed on optimizing imaging parameters and adopting advanced technologies such as dual-energy CT and AI-enhanced imaging to balance diagnostic efficacy with radiation safety. This exploration provides valuable insights into the interplay of X-ray physics and medical imaging, paving the way for enhanced diagnostic practices and future innovations.