Enabling Low-Dose In Vivo Benchtop X-ray Fluorescence Computed Tomography through Deep-Learning-Based Denoising.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing high-resolution molecular-level data. However, increased sensitivity with current benchtop X-ray sources comes at the cost of high radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for background noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized Swin-Conv-UNet (SCUNet) model for background noise reduction in X-ray fluorescence (XRF) images at low tracer concentrations. Our method's effectiveness is evaluated against higher-dose images, while various denoising techniques exist for X-ray and computed tomography (CT) techniques, only a few address XFCT. The DL model is trained and assessed using augmented data, focusing on background noise reduction. Image quality is measured using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), comparing outcomes with 100% X-ray-dose images. Results demonstrate that the proposed algorithm yields high-quality images from low-dose inputs, with maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms block-matching and 3D filtering (BM3D), block-matching and 4D filtering (BM4D), non-local means (NLM), denoising convolutional neural network (DnCNN), and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

Multi-class Tissue Segmentation of CT images using an Ensemble Deep Learning method.

Microwave ablation (MWA) therapy is a well-known technique for locally destroying lung tumors with the help of computed tomography (CT) images. However, tumor recurrence occurs because of insufficient ablation of the tumor. In order to perform an accurate treatment of lung cancer, there is a demand to determine the tumor area precisely. To address the problem at hand, which involves accurately segmenting organs and tumors in CT images obtained during MWA therapy, physicians could benefit from a semantic segmentation method. However, such a method typically requires a large number of images to achieve optimal results through deep learning techniques. To overcome this challenge, our team developed four different (multiple) U-Net based semantic segmentation models that work in conjunction with one another to produce a more precise segmented image, even when working with a relatively small dataset. By combining the highest weight value of segmentation from multiple methods into a single output, we can achieve a more reliable and accurate segmentation outcome. Our approach proved successful in segmenting four different tissue structures, including lungs, lung tumors, and ablated tissues in CT medical images. The Intersection over Union (IoU) is employed to quantitatively evaluate the proposed method. The method shows the highest average IoU, with 0.99 for the background, 0.98 for the lung, 0.77 for the ablated, and 0.54 for the tumor tissue. The results show that employing multiple DL methods is superior to that of individual base-learner models for all four different tissue structures, even in the presence of the relatively small dataset.Clinical relevance- An essential issue of tumor ablation therapy is to know when the entire tumor tissue has completely been destroyed. However, as it is difficult to distinguish between destroyed and living tumor, this is hardly reliable in clinical practice during MWA therapy, especially when working with a small dataset. Improved AI segmentation methods can help to improve performance to reduce recurrence.

Complex network based models of ECoG signals for detection of induced epileptic seizures in rats.

The automatic detection of seizures bears a considerable significance in epileptic diagnosis as it can efficiently lead to a considerable reduction of the workload of the medical staff. The present study aims at automatic detecting epileptic seizures in epileptic rats. To this end, seizures were induced in rats implementing the pentylenetetrazole model, with the electrocorticogram (ECoG) signals during, before and after the seizure periods being recorded. For this purpose, five algorithms for transforming time series into complex networks based on visibility graph (VG) algorithm were used. In this study, VG based methods were used for the first time to analyze ECoG signals in rats. Afterward, Standard measures in network science (graph properties) were made to examine the topological structure of these networks produced on the basis of ECoG signals. Then these measures were given to a classifier as input features so that the ECoG signals could be classified into seizure periods and seizure-free periods. Artificial Neural Network, considered a popular classifier, was used in this work. The experimental results showed that the method managed to detect epileptic seizure in rats with a high accuracy of 92.13%. Our proposed method was also applied to the recorded EEG signals from Bonn database to show the efficiency of the proposed method for human seizure detection.

Epileptic seizure detection using cross-bispectrum of electroencephalogram signal.

PURPOSE: The automatic detection of epileptic seizures in EEG data from extended recordings can make an important contribution to the diagnosis of epilepsy as it can efficiently reduce the workload of medical staff. METHODS: This paper describes how features based on cross-bispectrum can help with the detection of epileptic seizure activity in EEG data. Features were extracted from multi-channel intracranial EEG (iEEG) data from the Freiburg iEEG recordings of 21 patients with focal epilepsy. These features were used as a support vector machine classifier input to discriminate ictal from inter-ictal states. A post-processing method was applied to the classifier output in order to improve classification accuracy. RESULTS: A sensitivity of 95.8%, specificity of 96.7%, and accuracy of 96.8% were achieved. The false detection rate (FDR) was zero for 10 patients and very low for the rest. CONCLUSIONS: The results show that the proposed method distinguishes better between ictal and inter-ictal iEEG epochs than other seizure detection methods. The proposed method has a higher accuracy index than achievable with a number of previously described approaches. Also, the method is rapid and easy and may be helpful in online epileptic seizure detection and prediction systems.

Proximal detection of guide wire perforation using feature extraction from bispectral audio signal analysis combined with machine learning.

Artery perforation during a vascular catheterization procedure is a potentially life threatening event. It is of particular importance for the surgeons to be aware of hidden or non-obvious events. To minimize the impact it is crucial for the surgeon to detect such a perforation very early. We propose a novel approach to identify perforations based on the acquisition and analysis of audio signals on the outside proximal end of a guide wire. The signals were acquired using a stethoscope equipped with a microphone and attached to the proximal end of the guide wire via a 3D printed adapter. Bispectral analysis was employed to extract acoustic signatures in the signal and several features were extracted from the bispectrum of the signal. Finally, three machine learning algorithms - K-nearest Neighbor, Support Vector Machine (SVM), and Artificial Neural Network (ANN)- were used to classify a signal as a perforation or as an artifact. The bispectrum-based features resulted in valuable features allowing a perforation to be clearly identifiable from other occurring events. A perforation leaves a clear audio signal trace in the time-frequency domain. The recordings were classified as perforation, friction or guide wire bump using SVM with 97% (polykernel) and 98.62% (RBF) accuracy, k-nearest Neighbor an accuracy of 98.28% and ANN with accuracy of 98.73% was obtained. The presented approach shows that interactions starting at the tip of a guide wire can be picked up at its proximal end providing a valuable additional information that could be used during a guide wire procedure.

Higher Order Statistical Analysis for Thyroid Texture Classification and Segmentation in 2D ultrasound Images.

Ultrasound (US) imaging is one of the most cost-effective imaging modality that utilizes sound waves for generating medical images of anatomical structure. However, the presence of speckle noise and low contrast in the US images makes it difficult to use for proper classification of anatomical structures in clinical scenarios. Hence, it is important to devise a method that is robust and accurate even in the presence of speckle noise and is not affected by the low image contrast. In this work, a novel approach for thyroid texture characterization based on extracting features utilizing higher order spectral analysis (HOSA) was used. A Support Vector Machine (SVM) was applied on the extracted features to classify the thyroid texture. Since HOSA is a well suited technique for processing non-Gaussian data involving non-linear dynamics, good classification of thyroid texture can be obtained in US images as they also contain non-Gaussian Speckle noise and nonlinear characteristics. A final accuracy of 93.27%, sensitivity of 0.92 and specificity of 0.62 were obtained using the proposed approach.

Design of an Auscultation System for Phonoangiography and Monitoring of Carotid Artery Diseases.

Cerebrovascular diseases such as stenosis of the carotid artery are accountable for about 1 million death per year across Europe. Diagnostic tools like US, angiography or MRI require specific hardware and highly depend on the experience of the examining clinician. In contrast auscultation with a stethoscope can be used to screen for bruits - audible vascular sounds associated with turbulent blood flow. Dynamical changes in the flow due to pathological narrowing of the vessel can indicate the need for additional diagnostic investigations. A reliable auscultation setup is prerequisite to ensure high signal quality, adequate processing and the objective evaluation of a still subjectively assessed audible signal. We propose a computer assisted auscultation device for the characterisation of carotid bruits to facilitate the assessment of long-term changes in the vessel condition. Main goal of this work are design considerations regarding the mechanical interface of the proposed system to the skin. An experimental setup was used to compare the signal quality and morphology of different setups to a digital stethoscope. A combined system with two different interface configurations is proposed, current limitations of the system and potential improvements are discussed.