International Journal of Biomedical Imaging最新文献

Angiography by means of micro-computed tomography (m-CT) is extensively used for the diagnosis of vasculature disorders. To establish a connection between m-CT images and genuine histopathology findings, we developed two novel titanium dioxide nanoparticle (TiO₂-NP)-based perfusion contrast agents: TiNpCA-1 and TiNpCA-2. Three-dimensionally reconstructed m-CT images in mice perfused with these contrast agents showed high resolution and accuracy in various organs without deformation or dilation of vessels. Vessels < 20  μm in diameter were clearly visualized by m-CT, and capillaries of 4 μm in diameter were visualized by nano-CT. After perfusion, the contrast agents were kept in the vessels by the formation of an aggregate with ethanol. Histological samples were prepared from CT-scanned specimens. No perfusion-induced damage or abnormal structures were observed. The signals of the contrast agents were detected clearly, and the tissue histology was of adequate quality for pathological diagnosis. Agglomerates of TiO₂-NPs were present in both agents; their approximate sizes were 1.0 and 6.0 μm in TiNpCA-1 and 1.5 μm in TiNpCA-2. We considered that these agglomerates were trapped within capillaries at the beginning of perfusion. And at the end of perfusion, vessels of larger size were filled with agglomerates. These findings suggest a direct correlation between the signal intensity in m-CT imaging and the volume of contrast agent entering the vessels, indicating a quantitative aspect to the system. The low K-edge value of titanium (4.6 KeV) ensures that the signal intensity of the contrast agent remains unaffected at low energies (40 KeV). Lower energy levels improve the contrast-to-noise ratio. Consequently, using titanium dioxide as a contrast agent allows us to achieve a higher contrast-to-noise ratio while maintaining a favorable signal-to-noise ratio. Our results strongly support the notion that TiO₂-NPs as a contrast agents hold promise not only for investigating circulatory disorders in experimental pathology but also for uncovering new insights in anatomical physiology.

Background: The quality of CT images obtained from hepatocellular carcinoma (HCC) patients is complex, affecting diagnostic accuracy, precision, and radiation dose assessment due to increased exposure risks. Objectives: The study evaluated image quality qualitatively and quantitatively by comparing quality levels with an effective radiation dose to ensure acceptable quality accuracy. Materials and Methods: This study retrospectively reviewed 100 known HCC patients (Li-RADS-5) who underwent multidetector computed tomography (MDCT) multiphasic scans for follow-up of their health condition between January and October 2023. The evaluation involved quantitative and qualitative analyses of parameters such as SD, SNR, and CNR, as well as a qualitative assessment by two radiology consultants. The outcomes were compared, and the effective dose was calculated and compared with both quantitative and qualitative assessments of image quality. Results: ROC curve analysis revealed significant differences in CT image quality, with high to moderate specificity and sensitivity across all the quantitative parameters. However, multivariate examination revealed decreasing importance levels, except for CNR (B, 0.203; p = 0.001) and SD BG (B, 0.330; p = 0.002), which increased in B. The CNR and SD BG remained independent variables for CT image quality prediction, but no statistically significant relationship was found between the effective dose and image quality, either quantitatively or qualitatively. Conclusion: This study underscores the vital role of both quantitative and qualitative assessments of CT images in evaluating their quality for patients with HCC and highlights the predictive importance of CNR, SNR, and SD. These findings emphasize the value of these devices in assessing and predicting outcomes to minimize the effective dose.

Recent advancements in large language models (LLMs), particularly GPT-3.5 and GPT-4, have sparked significant interest in their application within the medical field. This research offers a detailed comparative analysis of the abilities of GPT-3.5 and GPT-4 in the context of annotating radiology reports and generating impressions from chest computed tomography (CT) scans. The primary objective is to use these models to assist healthcare professionals in handling routine documentation tasks. Employing methods such as in-context learning (ICL) and retrieval-augmented generation (RAG), the study focused on generating impression sections from radiological findings. Comprehensive evaluation was applied using a variety of metrics, including recall-oriented understudy for gisting evaluation (ROUGE) for n-gram analysis, Instructor Similarity for contextual similarity, and BERTScore for semantic similarity, to assess the performance of these models. The study shows distinct performance differences between GPT-3.5 and GPT-4 across both zero-shot and few-shot learning scenarios. It was observed that certain prompts significantly influenced the performance outcomes, with specific prompts leading to more accurate impressions. The RAG method achieved a superior BERTScore of 0.92, showcasing its ability to generate semantically rich and contextually accurate impressions. In contrast, GPT-3.5 and GPT-4 excel in preserving language tone, with Instructor Similarity scores of approximately 0.92 across scenarios, underscoring the importance of prompt design in effective summarization tasks. The findings of this research emphasize the critical role of prompt design in optimizing model efficacy and point to the significant potential for further exploration in prompt engineering. Moreover, the study advocates for the standardized integration of such advanced LLMs in healthcare practices, highlighting their potential to enhance the efficiency and accuracy of medical documentation.

Generative models, especially diffusion models, have gained traction in image generation for their high-quality image synthesis, surpassing generative adversarial networks (GANs). They have shown to excel in anomaly detection by modeling healthy reference data for scoring anomalies. However, one major disadvantage of these models is its sampling speed, which so far has made it unsuitable for use in time-sensitive scenarios. The time taken to generate a single image using the iterative sampling procedure introduced in denoising diffusion probabilistic model (DDPM) is quite significant. To address this, we propose a novel single-step sampling procedure that hugely improves the sampling speed while generating images of comparable quality. While DDPMs usually denoise images containing pure noise to generate an original image, we utilize a partial diffusion approach to preserve the image structure. In anomaly detection, we want the reconstructed image to have a structure similar to the original anomalous image, so that we can compare the pixel-level difference between them in order to segment the anomaly. The original DDPM algorithm suggests an iterative sampling procedure where the model slowly reduces the noise, until we have a noise-free image. Our single-step sampling approach attempts to remove all the noise in the image within a single step, while still being able to repair the anomaly and achieve comparable results. The output is a binary image showing the predicted anomalous regions, which is then compared to the ground truth to evaluate its segmentation performance. We find that, while it does achieve slightly better anomaly masks, the main improvement is in sampling speed, where our approach was found to perform significantly faster as compared to the iterative procedure. Our work is mainly focused on anomaly detection in brain MR volumes, and therefore, this approach could be used by radiologists in a clinical setting to find anomalies in large quantities of brain MRI.

Fast, accurate, and affordable bacterial identification methods are paramount for the timely treatment of infections, especially in resource-limited settings (RLS). However, today, only 1.3% of the sub-Saharan African diagnostic laboratories are performing clinical bacteriology. To improve this, diagnostic tools for RLS should prioritize simplicity, affordability, and ease of maintenance, as opposed to the costly equipment utilized for bacterial identification in high-income countries, such as matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). In this work, we present a new high-throughput approach based on a simple wide-field (864 mm²) lensless imaging system allowing for the acquisition of a large portion of a Petri dish coupled with a supervised deep learning algorithm for identification at the bacterial colony scale. This wide-field imaging system is particularly well suited to RLS since it includes neither moving mechanical parts nor optics. We validated this approach through the acquisition and the subsequent analysis of a dataset comprising 252 clinical isolates from five species, encompassing some of the most prevalent pathogens. The resulting optical morphotypes exhibited intra- and interspecies variability, a scenario considerably more akin to real-world clinical practice than the one achievable by solely concentrating on reference strains. Despite this variability, high identification performance was achieved with a correct species identification rate of 91.7%. These results open up some new prospects for identification in RLS. We released both the acquired dataset and the trained identification algorithm in publicly available repositories.

Introduction: Pulmonary transit time (PTT) is the time it takes blood to pass from the right ventricle to the left ventricle via the pulmonary circulation, making it a potentially useful marker for heart failure. We assessed the association of PTT with diastolic dysfunction (DD) and mitral valve regurgitation (MVR). Methods: We evaluated routine stress perfusion cardiovascular magnetic resonance (CMR) scans in 83 patients including assessment of PTT with simultaneously available echocardiographic assessment. Relevant DD and MVR were defined as exceeding Grade I (impaired relaxation and mild regurgitation). PTT was determined from CMR rest perfusion scans. Normalized PTT (nPTT), adjusted for heart rate, was calculated using Bazett's formula. Results: Higher PTT and nPTT values were associated with higher grade DD and MVR. The diagnostic accuracy for the prediction of DD as quantified by the area under the ROC curve (AUC) was 0.73 (CI 0.61-0.85; p = 0.001) for PTT and 0.81 (CI 0.71-0.89; p < 0.001) for nPTT. For MVR, the diagnostic performance amounted to an AUC of 0.80 (CI 0.68-0.92; p < 0.001) for PTT and 0.78 (CI 0.65-0.90; p < 0.001) for nPTT. PTT values < 8 s rule out the presence of DD and MVR with a probability of 70% (negative predictive value 78%). Conclusion: CMR-derived PTT is a readily obtainable hemodynamic parameter. It is elevated in patients with DD and moderate to severe MVR. Low PTT values make the presence of DD and MVR-as assessed by echocardiography-unlikely.

Background: Three-dimensional gradient-echo (3D-GRE) sequences provide isotropic or nearly isotropic 3D images, leading to better visualization of smaller structures, compared to two-dimensional (2D) sequences. The aim of this study was to prospectively compare 2D and 3D-GRE sequences in terms of key imaging metrics, including signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), glenohumeral joint space, image quality, artifacts, and acquisition time in shoulder joint images, using 1.5-T MRI scanner. Methods: Thirty-five normal volunteers with no history of shoulder disorders prospectively underwent a shoulder MRI examination with conventional 2D sequences, including T ₁- and T ₂-weighted fast spin echo (T₁/T₂w FSE) as well as proton density-weighted FSE with fat saturation (PD-FS) followed by 3D-GRE sequences including VIBE, TRUEFISP, DESS, and MEDIC techniques. Two independent reviewers assessed all images of the shoulder joints. Pearson correlation coefficient and intra-RR were used for reliability test. Results: Among 3D-GRE sequences, TRUEFISP showed significantly the best CNR between cartilage-bone (31.37 ± 2.57, p < 0.05) and cartilage-muscle (13.51 ± 1.14, p < 0.05). TRUEFISP also showed the highest SNR for cartilage (41.65 ± 2.19, p < 0.01) and muscle (26.71 ± 0.79, p < 0.05). Furthermore, 3D-GRE sequences showed significantly higher image quality, compared to 2D sequences (p < 0.001). Moreover, the acquisition time of the 3D-GRE sequences was considerably shorter than the total acquisition time of PD-FS sequences in three orientations (p < 0.01). Conclusions: 3D-GRE sequences provide superior image quality and efficiency for evaluating articular joints, particularly in shoulder imaging. The TRUEFISP technique offers the best contrast and signal quality, making it a valuable tool in clinical practice.

Background: The blood-brain barrier (BBB) is part of the neurovascular unit (NVU) which plays a key role in maintaining homeostasis. However, its 3D structure is hardly known. The present study is aimed at imaging the BBB using tissue clearing and 3D imaging techniques in both human brain tissue and rat brain tissue. Methods: Both human and rat brain tissue were cleared using the CUBIC technique and imaged with either a confocal or two-photon microscope. Image stacks were reconstructed using Imaris. Results: Double staining with various antibodies targeting endothelial cells, basal membrane, pericytes of blood vessels, microglial cells, and the spatial relationship between astrocytes and blood vessels showed that endothelial cells do not evenly express CD31 and Glut1 transporter in the human brain. Astrocytes covered only a small portion of the vessels as shown by the overlap between GFAP-positive astrocytes and Collagen IV/CD31-positive endothelial cells as well as between GFAP-positive astrocytes and CD146-positive pericytes, leaving a big gap between their end feet. A similar structure was observed in the rat brain. Conclusions: The present study demonstrated the 3D structure of both the human and rat BBB, which is discrepant from the 2D one. Tissue clearing and 3D imaging are promising techniques to answer more questions about the real structure of biological specimens.

Accurate segmentation of breast masses in mammogram images is essential for early cancer diagnosis and treatment planning. Several deep learning (DL) models have been proposed for whole mammogram segmentation and mass patch/crop segmentation. However, current DL models for breast mammogram mass segmentation face several limitations, including false positives (FPs), false negatives (FNs), and challenges with the end-to-end approach. This paper presents a novel two-stage end-to-end cascaded breast mass segmentation framework that incorporates a saliency map of potential mass regions to guide the DL models for breast mass segmentation. The first-stage segmentation model of the cascade framework is used to generate a saliency map to establish a coarse region of interest (ROI), effectively narrowing the focus to probable mass regions. The proposed presegmenter attention (PSA) blocks are introduced in the second-stage segmentation model to enable dynamic adaptation to the most informative regions within the mammogram images based on the generated saliency map. Comparative analysis of the Attention U-net model with and without the cascade framework is provided in terms of dice scores, precision, recall, FP rates (FPRs), and FN outcomes. Experimental results consistently demonstrate enhanced breast mass segmentation performance by the proposed cascade framework across all three datasets: INbreast, CSAW-S, and DMID. The cascade framework shows superior segmentation performance by improving the dice score by about 6% for the INbreast dataset, 3% for the CSAW-S dataset, and 2% for the DMID dataset. Similarly, the FN outcomes were reduced by 10% for the INbreast dataset, 19% for the CSAW-S dataset, and 4% for the DMID dataset. Moreover, the proposed cascade framework's performance is validated with varying state-of-the-art segmentation models such as DeepLabV3+ and Swin transformer U-net. The presegmenter cascade framework has the potential to improve segmentation performance and mitigate FNs when integrated with any medical image segmentation framework, irrespective of the choice of the model.

Chronic rhinosinusitis (CRS) is a global disease characterized by poor treatment outcomes and high recurrence rates, significantly affecting patients' quality of life. Due to its complex pathophysiology and diverse clinical presentations, CRS is categorized into various subtypes to facilitate more precise diagnosis, treatment, and prognosis prediction. Among these, CRS with nasal polyps (CRSwNP) is further divided into eosinophilic CRSwNP (eCRSwNP) and noneosinophilic CRSwNP (non-eCRSwNP). However, there is a lack of precise predictive diagnostic and treatment methods, making research into accurate diagnostic techniques for CRSwNP endotypes crucial for achieving precision medicine in CRSwNP. This paper proposes a method using multiangle sinus computed tomography (CT) images combined with artificial intelligence (AI) to predict CRSwNP endotypes, distinguishing between patients with eCRSwNP and non-eCRSwNP. The considered dataset comprises 22,265 CT images from 192 CRSwNP patients, including 13,203 images from non-eCRSwNP patients and 9,062 images from eCRSwNP patients. Test results from the network model demonstrate that multiangle images provide more useful information for the network, achieving an accuracy of 98.43%, precision of 98.1%, recall of 98.1%, specificity of 98.7%, and an AUC value of 0.984. Compared to the limited learning capacity of single-channel neural networks, our proposed multichannel feature adaptive fusion model captures multiscale spatial features, enhancing the model's focus on crucial sinus information within the CT images to maximize detection accuracy. This deep learning-based diagnostic model for CRSwNP endotypes offers excellent classification performance, providing a noninvasive method for accurately predicting CRSwNP endotypes before treatment and paving the way for precision medicine in the new era of CRSwNP.