Frontiers in radiology最新文献

Relative cerebral blood volume (rCBV) derived from dynamic susceptibility contrast (DSC) perfusion MR imaging (pMRI) has been shown to be a robust marker of neuroradiological tumor burden. Recent consensus recommendations in pMRI acquisition strategies have provided a pathway for pMRI inclusion in diverse patient care centers, regardless of size or experience. However, even with proper implementation and execution of the DSC-MRI protocol, issues will arise that many centers may not easily recognize or be aware of. Furthermore, missed pMRI issues are not always apparent in the resulting rCBV images, potentiating inaccurate or missed radiological diagnoses. Therefore, we gathered from our database of DSC-MRI datasets, true-to-life examples showcasing the breakdowns in acquisition, postprocessing, and interpretation, along with appropriate mitigation strategies when possible. The pMRI issues addressed include those related to image acquisition and postprocessing with a focus on contrast agent administration, timing, and rate, signal-to-noise quality, and susceptibility artifact. The goal of this work is to provide guidance to minimize and recognize pMRI issues to ensure that only quality data is interpreted.

Introduction: Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Manually identifying these foci (most commonly labeled green) is tedious, and an automated detection system could streamline the process. This study aims to evaluate the impact of a deep-learning (DL) algorithm developed for detecting green pixelations on DECT on reader time, accuracy, and confidence.

Methods: We collected a sample of positive and negative DECTs, reviewed twice-once with and once without the DL tool-with a 2-week washout period. An attending musculoskeletal radiologist and a fellow separately reviewed the cases, simulating clinical workflow. Metrics such as time taken, confidence in diagnosis, and the tool's helpfulness were recorded and statistically analyzed.

Results: We included thirty DECTs from different patients. The DL tool significantly reduced the reading time for the trainee radiologist (p = 0.02), but not for the attending radiologist (p = 0.15). Diagnostic confidence remained unchanged for both (p = 0.45). However, the DL model identified tiny MSU deposits that led to a change in diagnosis in two cases for the in-training radiologist and one case for the attending radiologist. In 3/3 of these cases, the diagnosis was correct when using DL.

Conclusions: The implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.

Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images. Most existing methods focus solely on the image data, disregarding the other patient information accessible to radiologists. In this paper, we present a novel multi-modal deep neural network framework for generating chest x-rays reports by integrating structured patient data, such as vital signs and symptoms, alongside unstructured clinical notes. We introduce a conditioned cross-multi-head attention module to fuse these heterogeneous data modalities, bridging the semantic gap between visual and textual data. Experiments demonstrate substantial improvements from using additional modalities compared to relying on images alone. Notably, our model achieves the highest reported performance on the ROUGE-L metric compared to relevant state-of-the-art models in the literature. Furthermore, we employed both human evaluation and clinical semantic similarity measurement alongside word-overlap metrics to improve the depth of quantitative analysis. A human evaluation, conducted by a board-certified radiologist, confirms the model's accuracy in identifying high-level findings, however, it also highlights that more improvement is needed to capture nuanced details and clinical context.

Rationale and objectives: Cerebral microdialysis is a technique that enables monitoring of the neurochemistry of patients with significant acquired brain injury, such as traumatic brain injury (TBI) and subarachnoid haemorrhage (SAH). Cerebral microdialysis can also be used to characterise the neuro-pharmacokinetics of small-molecule study substrates using retrodialysis/retromicrodialysis. However, challenges remain: (i) lack of a simple, stable, and inexpensive brain tissue model for the study of drug neuropharmacology; and (ii) it is unclear how far small study-molecules administered via retrodialysis diffuse within the human brain.

Materials and methods: Here, we studied the radial diffusion distance of small-molecule gadolinium-DTPA from microdialysis catheters in a newly developed, simple, stable, inexpensive brain tissue model as a precursor for in-vivo studies. Brain tissue models consisting of 0.65% weight/volume agarose gel in two kinds of buffers were created. The distribution of a paramagnetic contrast agent gadolinium-DTPA (Gd-DTPA) perfusion from microdialysis catheters using magnetic resonance imaging (MRI) was characterized as a surrogate for other small-molecule study substrates.

Results: We found the mean radial diffusion distance of Gd-DTPA to be 18.5 mm after 24 h (p < 0.0001).

Conclusion: Our brain tissue model provides avenues for further tests and research into infusion studies using cerebral microdialysis, and consequently effective focal drug delivery for patients with TBI and other brain disorders.

Artificial Intelligence (AI) methods, particularly Deep Neural Networks (DNNs), have shown great promise in a range of medical imaging tasks. However, the susceptibility of DNNs to producing erroneous outputs under the presence of input noise and variations is of great concern and one of the largest challenges to their adoption in medical settings. Towards addressing this challenge, we explore the robustness of DNNs trained for chest radiograph classification under a range of perturbations reflective of clinical settings. We propose RoMIA, a framework for the creation of Robust Medical Imaging AI models. RoMIA adds three key steps to the model training and deployment flow: (i) Noise-added training, wherein a part of the training data is synthetically transformed to represent common noise sources, (ii) Fine-tuning with input mixing, in which the model is refined with inputs formed by mixing data from the original training set with a small number of images from a different source, and (iii) DCT-based denoising, which removes a fraction of high-frequency components of each image before applying the model to classify it. We applied RoMIA to create six different robust models for classifying chest radiographs using the CheXpert dataset. We evaluated the models on the CheXphoto dataset, which consists of naturally and synthetically perturbed images intended to evaluate robustness. Models produced by RoMIA show 3%-5% improvement in robust accuracy, which corresponds to an average reduction of 22.6% in misclassifications. These results suggest that RoMIA can be a useful step towards enabling the adoption of AI models in medical imaging applications.