Explore the vast range of titles available.

This paper presents new findings concerning a hand-held stiffness probe for the medical diagnosis of abnormalities during palpation of soft-tissue. Palpation is recognized by the medical community as an essential and low-cost method to detect and diagnose disease in soft-tissue. However, differences are often subtle and clinicians need to train for many years before they can conduct a reliable diagnosis. The probe presented here fills this gap providing a means to easily obtain stiffness values of soft tissue during a palpation procedure. Our stiffness sensor is equipped with a multi degree of freedom (DoF) Aurora magnetic tracker, allowing us to track and record the 3D position of the probe whilst examining a tissue area, and generate a 3D stiffness map in real-time. The stiffness probe was integrated in a robotic arm and tested in an artificial environment representing a good model of soft tissue organs; the results show that the sensor can accurately measure and map the stiffness of a silicon phantom embedded with areas of varying stiffness.

Purpose Coming up with a quantitative diagnosis method for liver fibrosis using ultrasound would be highly significant. To permit tissue characterization using the characteristics of the echo signal such as power spectrum, texture parameters, local attenuation, and statistical characteristics, the relation between complicated scatterer structures and the echo signal must be understood. Methods In this study, we analyzed the property of the echo amplitude envelope using computer-simulated scatterer models. These models mimicked various liver conditions to evaluate our quantitative parametric imaging methods. Statistical echo characteristics changed with the density of the heterogeneous scatterer buried in a speckle. Results The new analysis method for a medium in which some tissues are embedded was proposed in consideration of analysis results from computer simulations. In the new method, it is possible to eliminate the influence of a cyst or veins and to detect the existence of fibers more clearly than in previous methods.

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful classification. In this study, we exploit HSI and DL for the automatic differentiation of glioblastoma (GB) and non-tumor tissue on hematoxylin and eosin (H&E) stained histological slides of human brain tissue. GB detection is a challenging application, showing high heterogeneity in the cellular morphology across different patients. We employed an HSI microscope, with a spectral range from 400 to 1000 nm, to collect 517 HS cubes from 13 GB patients using 20× magnification. Using a convolutional neural network (CNN), we were able to automatically detect GB within the pathological slides, achieving average sensitivity and specificity values of 88% and 77%, respectively, representing an improvement of 7% and 8% respectively, as compared to the results obtained using RGB (red, green, and blue) images. This study demonstrates that the combination of hyperspectral microscopic imaging and deep learning is a promising tool for future computational pathologies.

Early and automated detection of carotid plaques prevents strokes, which are the second leading cause of death worldwide according to the World Health Organization. Artificial intelligence (AI) offers automated solutions for plaque tissue characterization. Recently, solo deep learning (SDL) models have been used, but they do not take advantage of the tandem connectivity offered by AI's hybrid nature. Therefore, this study explores the use of hybrid deep learning (HDL) models in a multicenter framework, making this study the first of its kind. We hypothesize that HDL techniques perform better than SDL and transfer learning (TL) techniques. We propose two kinds of HDL frameworks: (i) the fusion of two SDLs (Inception with ResNet) or (ii) 10 other kinds of tandem models that fuse SDL with ML. The system Atheromatic™ 2.0HDL (AtheroPoint, CA, USA) was designed on an augmentation framework and three kinds of loss functions (cross-entropy, hinge, and mean-square-error) during training to determine the best optimization paradigm. These 11 combined HDL models were then benchmarked against one SDL model and five types of TL models; thus, this study considers a total of 17 AI models. Among the 17 AI models, the best performing HDL system was that comprising CNN and decision tree (DT), as its accuracy and area-under-the-curve were 99.78 ± 1.05% and 0.99 (p<0.0001), respectively. These values are 6.4% and 3.2% better than those recorded for the SDL and TL models, respectively. We validated the performance of the HDL models with diagnostics odds ratio (DOR) and Cohen and Kappa statistics; here, HDL outperformed DL and TL by 23% and 7%, respectively. The online system ran in <2 s. HDL is a fast, reliable, and effective tool for characterizing the carotid plaque for early stroke risk stratification. •Fusion of deep learning with ten kinds of machine learning classifiers.•Fusion of Inception and ResNet.•Three kinds of loss functions such as cross-entropy loss, hinge loss, or mean-squared-error loss, and hypothesis was validated.•These overall paradigms of hybrid deep learning were tried on multicenter study.•17 kinds of plaque tissue characterization for symptomatic vs. asymptomatic tissue classification models.

Towards the characterization of viscoelasticity of the soft tissue, which is an important biomarker, this study aims to investigate the effectiveness of the Harmonic Shear Wave Elastography (HSWE) framework by analyzing the frequency-dependent phase velocity maps, using a 3D Finite-Element-based simulation framework. Here, we developed and verified a 3D finite-element framework to accurately model the tissue displacement under a multi-frequency HSWE setting. The HSWE results were compared using both simulation and phantom experiments against those from the Pulsed Shear Wave Elastography (PSWE) method which is widely used in shear wave elastography problems. Particularly, we analyzed the group and frequency-dependent phase velocities, focusing on the frequency range of 300 to 800 Hz. Additionally, we conducted parametric studies to examine the effects of inclusion size, stiffness, and viscosity. The HSWE framework provided accurate measurements of group and phase velocities, comparable to those obtained using the PSWE method. The median differences between HSWE and PSWE results were 5.21 % and 9.14 % for group and phase velocities, respectively, in simulations, and 13.98 % and 22.32 % for group and phase velocities, respectively, in phantom experiments. Parametric studies showed that the HSWE framework is effective in accurately characterizing the location, size, stiffness and viscoelastic properties of tissue inclusions, with notable improvements over PSWE, particularly for smaller inclusions at lower frequencies. Future work will focus on optimizing the HSWE framework for clinical use and developing inverse models to estimate the underlying viscoelastic shear moduli of the tissue to enhance its diagnostic capabilities.

Purpose To develop and evaluate MyoMapNet, a rapid myocardial T 1 mapping approach that uses fully connected neural networks (FCNN) to estimate T 1 values from four T 1 -weighted images collected after a single inversion pulse in four heartbeats (Look-Locker, LL4). Method We implemented an FCNN for MyoMapNet to estimate T 1 values from a reduced number of T 1 -weighted images and corresponding inversion-recovery times. We studied MyoMapNet performance when trained using native, post-contrast T 1 , or a combination of both. We also explored the effects of number of T 1 -weighted images (four and five) for native T 1 . After rigorous training using in-vivo modified Look-Locker inversion recovery (MOLLI) T 1 mapping data of 607 patients, MyoMapNet performance was evaluated using MOLLI T 1 data from 61 patients by discarding the additional T 1 -weighted images. Subsequently, we implemented a prototype MyoMapNet and LL4 on a 3 T scanner. LL4 was used to collect T 1 mapping data in 27 subjects with inline T 1 map reconstruction by MyoMapNet. The resulting T 1 values were compared to MOLLI. Results MyoMapNet trained using a combination of native and post-contrast T 1 -weighted images had excellent native and post-contrast T 1 accuracy compared to MOLLI. The FCNN model using four T 1 -weighted images yields similar performance compared to five T 1 -weighted images, suggesting that four T 1 weighted images may be sufficient. The inline implementation of LL4 and MyoMapNet enables successful acquisition and reconstruction of T 1 maps on the scanner. Native and post-contrast myocardium T 1 by MOLLI and MyoMapNet was 1170 ± 55 ms vs. 1183 ± 57 ms (P = 0.03), and 645 ± 26 ms vs. 630 ± 30 ms (P = 0.60), and native and post-contrast blood T 1 was 1820 ± 29 ms vs. 1854 ± 34 ms (P = 0.14), and 508 ± 9 ms vs. 514 ± 15 ms (P = 0.02), respectively. Conclusion A FCNN, trained using MOLLI data, can estimate T 1 values from only four T 1 -weighted images. MyoMapNet enables myocardial T 1 mapping in four heartbeats with similar accuracy as MOLLI with inline map reconstruction.

Accurate and detailed tissue characterization is a central goal in medical diagnostics, often requiring the combination of multiple imaging modalities. This study presents a multimodal imaging system that integrates mid-infrared (MIR) scanning with fluorescence imaging to enhance the chemical specificity and spatial resolution in biological samples. A motorized mirror allows rapid switching between MIR and fluorescence modes, enabling efficient, co-registered data acquisition. The MIR modality captures label-free chemical maps based on molecular vibrations, while the fluorescence channel records endogenous autofluorescence for additional biochemical contrast. Applied to mouse brain tissue, the system enabled the clear differentiation of gray matter and white matter, supported by the clustering analysis of spectral features. The addition of autofluorescence imaging further improved anatomical segmentation and revealed fine structural details. In mouse skin, the approach allowed the precise mapping of the layered tissue architecture. These results demonstrate that combining MIR scanning and fluorescence imaging provides complementary, label-free insights into tissue morphology and chemistry. The findings support the utility of this approach as a powerful tool for biomedical research and diagnostic applications, offering a more comprehensive understanding of tissue composition without relying on staining or external markers.

Computer Tomography (CT) is currently being adapted for visualization of COVID-19 lung damage. Manual classification and characterization of COVID-19 may be biased depending on the expert’s opinion. Artificial Intelligence has recently penetrated COVID-19, especially deep learning paradigms. There are nine kinds of classification systems in this study, namely one deep learning-based CNN, five kinds of transfer learning (TL) systems namely VGG16, DenseNet121, DenseNet169, DenseNet201 and MobileNet, three kinds of machine-learning (ML) systems, namely artificial neural network (ANN), decision tree (DT), and random forest (RF) that have been designed for classification of COVID-19 segmented CT lung against Controls. Three kinds of characterization systems were developed namely (a) Block imaging for COVID-19 severity index (CSI); (b) Bispectrum analysis; and (c) Block Entropy. A cohort of Italian patients with 30 controls (990 slices) and 30 COVID-19 patients (705 slices) was used to test the performance of three types of classifiers. Using K10 protocol (90% training and 10% testing), the best accuracy and AUC was for DCNN and RF pairs were 99.41 ± 5.12%, 0.991 (p < 0.0001), and 99.41 ± 0.62%, 0.988 (p < 0.0001), respectively, followed by other ML and TL classifiers. We show that diagnostics odds ratio (DOR) was higher for DL compared to ML, and both, Bispecturm and Block Entropy shows higher values for COVID-19 patients. CSI shows an association with Ground Glass Opacities (0.9146, p < 0.0001). Our hypothesis holds true that deep learning shows superior performance compared to machine learning models. Block imaging is a powerful novel approach for pinpointing COVID-19 severity and is clinically validated.

Non-invasive quantification of the extracellular volume (ECV) is a method for the evaluation of focal and diffuse myocardial fibrosis, potentially obviating the need for invasive endomyocardial biopsy. While ECV quantification with cardiac magnetic resonance imaging (ECVMRI) is already an established method, ECV quantification with CT (ECVCT) is an attractive alternative to ECVMRI, similarly using the properties of extracellular contrast media for ECV calculation. In contrast to ECVMRI, ECVCT provides a more widely available, cheaper and faster tool for ECV quantification and allows for ECV calculation also in patients with contraindications for MRI. Many studies have already shown a high correlation between ECVCT and ECVMRI and accumulating evidence suggests a prognostic value of ECVCT quantification in various cardiovascular diseases. Adding a late enhancement scan (for dual energy acquisitions) or a non-enhanced and late enhancement scan (for single-energy acquisitions) to a conventional coronary CT angiography scan improves risk stratification, requiring only minor adaptations of the contrast media and data acquisition protocols and adding only little radiation dose to the entire scan.Critical relevance statementThis article summarizes the technical principles of myocardial extracellular volume (ECV) quantification with CT, reviews the literature comparing ECVCT with ECVMRI and histopathology, and reviews the prognostic value of myocardial ECV quantification for various cardiovascular disease.Key points• Non-invasive quantification of myocardial fibrosis can be performed with CT.• Myocardial ECV quantification with CT is an alternative in patients non-eligible for MRI.• Myocardial ECV quantification with CT strongly correlates with ECV quantification using MRI.• Myocardial ECV quantification provides incremental prognostic information for various pathologies affecting the heart (e.g., cardiac amyloidosis).

Heart failure with preserved ejection fraction (HFpEF) is a complex clinical syndrome responsible for high mortality and morbidity rates. It has an ever growing social and economic impact and a deeper knowledge of molecular and pathophysiological basis is essential for the ideal management of HFpEF patients. The association between HFpEF and traditional cardiovascular risk factors is known. However, myocardial alterations, as well as pathophysiological mechanisms involved are not completely defined. Under the definition of HFpEF there is a wide spectrum of different myocardial structural alterations. Myocardial hypertrophy and fibrosis, coronary microvascular dysfunction, oxidative stress and inflammation are only some of the main pathological detectable processes. Furthermore, there is a lack of effective pharmacological targets to improve HFpEF patients’ outcomes and risk factors control is the primary and unique approach to treat those patients. Myocardial tissue characterization, through invasive and non-invasive techniques, such as endomyocardial biopsy and cardiac magnetic resonance respectively, may represent the starting point to understand the genetic, molecular and pathophysiological mechanisms underlying this complex syndrome. The correlation between histopathological findings and imaging aspects may be the future challenge for the earlier and large-scale HFpEF diagnosis, in order to plan a specific and effective treatment able to modify the disease’s natural course.