iRadiology最新文献

A 35-year-old woman with a history of regular menstruation presented with a positive urine pregnancy test and elevated blood human chorionic gonadotropin concentrations. Color Doppler ultrasound showed multiple slightly hyperechoic areas within the uterine cavity. She was admitted to the hospital with a preliminary outpatient diagnosis of “suspected molar pregnancy, pending further evaluation.” After electrocution and curettage, no villous tissue was identified, and postoperative human chorionic gonadotropin concentrations failed to decline. Pelvic MRI showed a round, thick-walled cystic mass in the anterior sacral region (Figure 1). Color Doppler ultrasound showed that the cystic mass contained a yolk sac, fetal bud, and fetal cardiac activity (Figure 2). Surgical pathology subsequently confirmed the presence of villous tissue, consistent with a diagnosis of ectopic pregnancy.

Qingying Song: writing – original draft preparation (lead), writing – review and editing (lead). Dan Li: writing – original draft preparation (supporting), writing – review and editing (supporting).

The study was reviewed and approved by the Ethics Committee of Linyi Maternal and Child Health Hospital (QTL-YXLL-2023080).

Informed consent was waived because the patient’s information has been anonymized, which was approved by the ethics committee.

The authors declare no conflicts of interest.

A pregnant woman underwent fetal brain magnetic resonance imaging (MRI) following ultrasound detection of a posterior fossa cyst at 29 weeks' gestation. She presented with no relevant medical history and underwent a routine obstetric examination during pregnancy. The fetal head position, fetal cranial development, and limb development remained normal until 29 weeks. A fetal MRI examination showed a posterior fossa cyst, and another nodular gray matter signal was observed adjacent to the right lateral ventricle. Follow-up MRI at 31 weeks + 3 days showed no major changes (Figure 1). The patient successfully delivered a male neonate at 40 weeks' gestation. A brain MRI was performed at 7 months of age and confirmed the diagnosis of fetal gray matter heterotopia (GMH) (periventricular type) (Figure 2). He showed no neurological abnormalities such as epilepsy. Moreover, his skin manifestations were normal, and his growth and development were consistent with his monthly age.

Fetal GMH is a relatively uncommon congenital disorder that arises from impaired neuronal migration. The three main types of GMH are periventricular nodular heterotopia, subcortical heterotopia, and subcortical band heterotopia. The most common type is periventricular nodular heterotopia, as found in the present case. GMH can sometimes be accompanied by other abnormalities, such as ventriculomegaly, agenesis of the corpus callosum, and congenital heart disease. Fetal MRI is increasingly being used to diagnose fetal GMH because of its high soft tissue resolution. However, there have been few reports of pathological or postnatally confirmed fetal GMH.

Jiaojiao Liu: writing – original draft (lead). Lianxiang Xiao: conceptualization (lead), supervision (lead).

This study was approved by Shandong Provincial Maternal and Child Research Ethics Approval (Approval No.: 2024-13).

The case was retrospectively analysed, the fetal and postnatal imaging data used were from previous medical records, and the images were anonymised, which does not pose a risk of compromising the patient's privacy. Therefore, informed consent was exempted.

This article belongs to a special issue (SI)—fetal imaging, maternal and children imaging. As the SI's guest editor, Professor Lianxiang Xiao is excluded from all the editorial decisions related to the publication of this article. The remaining author declares no conflicts of interest.

A revolution in medical diagnosis and treatment is being driven by the use of artificial intelligence (AI) in medical imaging. The diagnostic efficacy and accuracy of medical imaging are greatly enhanced by AI technologies, especially deep learning, that performs image recognition, feature extraction, and pattern analysis. Furthermore, AI has demonstrated significant promise in assessing the effects of treatments and forecasting the course of diseases. It also provides doctors with more advanced tools for managing the conditions of their patients. AI is poised to play a more significant role in medical imaging, especially in real-time image processing and multimodal fusion. By integrating multiple forms of image data, multimodal fusion technology provides more comprehensive disease information, whereas real-time image analysis can assist surgeons in making more precise decisions. By tailoring treatment regimens to each patient's unique needs, AI enhances both the effectiveness of treatment and the patient experience. Overall, AI in medical imaging promises a bright future, significantly enhancing diagnostic precision and therapeutic efficacy, and ultimately delivering higher-quality medical care to patients.

Radiomics and machine learning (ML) are increasingly utilized to predict treatment response by uncovering latent information in medical images. This study systematically reviews radiomics studies on brain metastasis treated with stereotactic radiosurgery (SRS) and quantifies their radiomic quality score (RQS). A systematic search on Scopus, Web of Science, and PubMed was conducted to identify original studies on radiomics for predicting treatment response, adhering to predefined patient, intervention, comparator, and outcome (PICO) criteria. No restrictions were placed on language or publication date. Two independent reviewers assessed eligible studies, and the RQS was calculated based on Lambin’s guidelines. The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) 2020 guidelines were followed. Seventeen studies involving 2744 patients met the inclusion criteria out of 200 identified. All studies were retrospective and utilizing various MRI scanners models with different field strength. The average RQS across studies was low (39.2%), with a maximum score of 19 points (52.7%). Radiomic-based models demonstrated superior predictive accuracy compared to clinical or visual assessment, with AUC values ranging from 0.74 to 0.92. Integration of clinical features such as Karnofsky performance status, dose, and isodose line further improved model performance. Deep learning models achieved the highest predictive accuracy, with AUC of 0.92. Radiomics demonstrate significant potential in predicting treatment outcomes with high accuracy, offering opportunities to advance personalized management for BM. To facilitate clinical adoption, future studies must prioritize adherence to standardized guidelines and robust model validation to ensure reproducibility.

Artificial intelligence (AI) technology is expanding at a rapid pace, offering means of improving the precision of judgments made by medical professionals. AI-driven machine learning (ML) facilitates rapid and effective data processing for diagnosis and treatment of different diseases including stroke. This technology has vastly improved the patient classification based on their predicted stroke outcome. It helps in quicker decision-making, improves diagnosis precision, and enhances patient care. ML techniques have occasionally been applied extensively to address complex issues related to stroke such as the prediction of stroke prevalence at an early stage. The ability of deep learning (DL) algorithms, a crucial element of AI, is becoming popular in stroke imaging analysis because it automatically extracts features without requiring domain expertise. In the preclinical setup for stroke studies, ML/DL models are commendably used for the detection of vascular thrombi, stroke core, and penumbra size, to identify artery occlusion, compute perfusion maps, detect intracranial hemorrhage (ICH), prediction of infarct, assessing the severity of hemorrhagic transformation, and forecasting patient outcomes. The robust automatic data processing, excellent generalization, self-learning, and precise decision-making abilities of such models have contributed immensely to the advancement of stroke therapy. In the preclinical setup, the time-investing behavioral studies of the animals are also effectively analyzed by AI based algorithms. Understanding the algorithms and models based on AI is yet to be simplified for its application in stroke therapy in present clinical settings, thus, in the present review attempts have been made to present it in a simplified manner to facilitate translation.