iRadiology最新文献

We conducted a comprehensive literature search in PubMed to illustrate the current landscape of transformer-based tools from the perspective of transformer's two integral components: encoder exemplified by BERT and decoder characterized by GPT. Also, we discussed adoption barriers and potential solutions in terms of computational burdens, interpretability concerns, ethical issues, hallucination problems, malpractice, and legal liabilities. We hope that this commentary will serve as a foundational introduction for radiologists seeking to explore the evolving technical landscape of chest X-ray report analysis in the transformer era.

Transcranial focused ultrasound (tFUS) is an emerging modality with strong potential for non-invasively treating brain disorders. However, the inhomogeneity and complex structure of the skull induce substantial phase aberrations and pressure attenuation; these can distort and shift the acoustic focus, thus hindering the efficiency of tFUS therapy. To achieve effective treatments, phased array transducers combined with aberration correction algorithms are commonly implemented. The present report aims to provide a comprehensive review of the current methods used for tFUS phase aberration correction. We first searched the PubMed and Web of Science databases for studies on phase aberration correction algorithms, identifying 54 articles for review. Relevant information, including the principles of algorithms and refocusing performances, were then extracted from the selected articles. The phase correction algorithms involved two main steps: acoustic field estimation and transmitted pulse adjustment. Our review identified key benchmarks for evaluating the effectiveness of these algorithms, each of which was used in at least three studies. These benchmarks included pressure and intensity, positioning error, focal region size, peak sidelobe ratio, and computational efficiency. Algorithm performances varied under different benchmarks, thus highlighting the importance of application-specific algorithm selection for achieving optimal tFUS therapy outcomes. The present review provides a thorough overview and comparison of various phase correction algorithms, and may offer valuable guidance to tFUS researchers when selecting appropriate phase correction algorithms for specific applications.

With the rapid development of science and technology, the application of artificial intelligence (AI) in various fields is constantly expanding, especially in the field of medical imaging [1]. AI technology is suitable to be applied to standardized digital medical image big data based on digital imaging and communications in medicine protocol and picture archiving and communication system. With the integration of AI technology, this field is undergoing profound transformation, not only improving the accuracy and efficiency of diagnosis, but also significantly reducing the workload of doctors [2]. At present, AI is widely used in medical imaging, including risk modeling and stratification, personalized screening, diagnosis (including classification of molecular pathologic subtypes), treatment response prediction, prognosis prediction, image segmentation, and image quality control. AI can help doctors identify and analyze lesions in various medical images, especially in diseases such as lung, breast, and prostate cancer. The research mainly focuses on the identification of benign and malignant, the measurement of risk factors, prognosis judgment and treatment guidance, and it is increasingly being used in the field of psychoradiology [3]. In addition, AI is also focused on reducing image acquisition time and improving data quality. Through deep learning algorithms, AI can optimize imaging parameters, improve imaging quality, and reduce noise and artifacts.

This special issue of AI includes seven latest studies, which covers artificial intelligence of disease diagnosis and prediction, imaging technology model construction, image segmentation and quality control. Wang et al. [4] used systematic review to summarize the technical methods, clinical applications and existing problems of artificial intelligence in cerebrovascular diseases, they found that the availability of algorithms, reliability of validation, and consistency of evaluation metrics may facilitate better clinical applicability and acceptance. Zhu et al. [5] proposed a diffusion magnetic diffusion magnetic (dMRI) index reconstruction model based on deep learning methods-qIRR-Net and a training framework based on data enhancement and consistency loss, The reconstruction of dMRI index is realized without the influence of signal inhomogeneity, and the model validity is verified on simulated inhomogeneity data and real ultra-high field data, thus promoting the application of ultra-high field dMRI technology in medicine and clinic. Artificial intelligence-assisted compressed sensing is a deep learning technology based on convolutional neural networks which can reconstruct images with ultra-high resolution and reduce noise. On the premise of ensuring the quality of the image, the collection time of the sequence is greatly shortened. In this special issue, The application of assisted compressed sensing technology in 5T MRI

A 53 year-old woman presented with a 4 year history of recurrent dizziness episodes. Each episode lasted approximately 1 week and was not accompanied by nausea, or vomiting. Comprehensive vestibular assessments, including vestibular function tests, Dix–Hallpike maneuver, and the roll test, were all negative. The patient reported no atherosclerotic risk factors, such as hypertension, hyperlipidemia or diabetes mellitus, and her family history was unremarkable. General physical and neurological examinations were unremarkable. Central causes of dizziness were considered. A computed tomography angiography of the head revealed a plexiform configuration in the M1 segment of the right middle cerebral artery (MCA), with no other significant abnormalities (Figure 1a). Moyamoya disease was considered a possible diagnosis. Subsequent digital subtraction angiography demonstrated the absence of a normal right M1 segment, with a twig-like vascular network connecting to the distal MCA (Figure 1b,c). Additionally, the right carotid canal was found to be smaller than the left, suggesting potential congenital variants consistent with rete MCA (Figure 1d). The patient was treated with betahistine 6 mg three times daily, resulting in alleviation of her dizziness.

Rete MCA, also known as twig-like MCA, is a rare vascular anomaly characterized by the presence of a twig-like arterial network in the M1 segment of the MCA. This variant may present with either hemorrhagic or ischemic strokes, or, as in this case, with no clinical symptoms. The primary differential diagnoses for rete MCA include moyamoya disease/syndrome and atherosclerotic occlusion. In contrast to these conditions, rete MCA is typically unilateral, occurs exclusively in the M1 segment with a distinctive twig-like appearance, and does not involve atherosclerotic risk factors. Notably, it preserves the caliber and flow of the distal MCA. In surgical settings, rete MCA often presents as a white cord-like structure. Accurate diagnosis is essential, particularly for asymptomatic patients, to avoid unnecessary concerns about occlusion. For symptomatic individuals, surgical intervention may be considered.

Yongming Wang: writing–original draft (lead). Xi Chen: writing–original draft (equal). Junsheng Liu: writing–review and editing (equal).

This study was approved by the Ethics Committee of The People's Hospital of Pingchang in 2024 (Approval Number: 20240731-121).

The patient provided informed consent for the publication of the case.

The authors declare no conflicts of interest.

Metastatic renal cell carcinoma (RCC) lesions in the foot are a rare entity and uncommon finding in a series of foot radiographs ordered to investigate foot pain. We report the case of a 72 year old male who experienced left foot pain for a year, before developing intermittent haematuria and right flank pain, and subsequently being found to have right RCC with an osseous metastatic lesion in the left medial cuneiform.