Editorial: Non-invasive imaging techniques in children: clinical applications and advances

Hualin Yan¹Lin Huang²Yan Luo^1*

• ¹West China Hospital, Sichuan University, Chengdu, China
• ²University of Electronic Science and Technology of China School of Electronic Science and Engineering, Chengdu, China

This topic focuses on the clinical applications and advances of non-invasive imaging techniques in children. However, it is challenging to achieve accurate diagnosis and disease evaluation in children using non-invasive imaging techniques. Many children are unable to remain still or hold their breath during MRI scans, often necessitating sedation or general anesthesia. Besides, children are more sensitive to ionizing radiation from X-rays and CT scans compared to adults. Therefore, adherence to the ALARA (As Low As Reasonably Achievable) principle is essential to minimize unnecessary radiation exposure [1]. Compared with MRI or CT, ultrasonography and optical imaging are more friendly to pediatric patients. 2. Photoacoustic and optical imaging: photoacoustic imaging is now a mature clinically applicable technology that can quantify tissue oxygen saturation (sO2) and hemoglobin levels noninvasively. Multispectral optoacoustic tomography (MSOT) has been applied in various clinical scenarios, such as assessment of Crohn's disease activity [4] or monitoring pediatric inflammatory bowel disease activity [5]. Functional near-infrared spectroscopy (fNIRS) has been widely employed in assessing pediatric neurological and psychiatric conditions, such as cerebral palsy, autism spectrum disorder, and attention deficit hyperactivity disorder [6];3. MRI and CT innovations for children: faster and motion-robust MRI imaging in pediatric patients not only reduces scan times and minimizes the need for sedation or general anesthesia, but also improves the image quality, such as T2-weighted turbo-spin-echo PROPELLER for brain imaging [7] and 4D FreeBreathing MRI technique for abdominal imaging [8]. Low-dose CT is needed for pediatrics to reduce the radiation doses. Photon-counting detector CT can reduce the radiation doses and improve imaging quality in pediatric head imaging compared with conventional CT [9]; 4. Artificial intelligence (AI) integrated imaging: the pediatric disorder and imaging are distinct from adults, and the AI model developed for adults has not been shown to work consistently in children [10]. Recently, several ultrasound-based deep learning models have been developed to improve the accuracy and efficiency of diagnosing pediatric diseases, such as ileocolic intussusception [11] and biliary atresia [12]. To ensure the robustness and external validity of AI model, multi-center and internationally diverse patients should be included in the database. For example, a federated learning platform based on international multi-center MRI images achieved accurate segmentation and high classification accuracy in pediatric brain tumors [13].In summary, accurate diagnosis in pediatric imaging remains challenging due to technical and patientrelated factors. However, rapid technological advancements, ranging from improved imaging modalities to AI-integrated analysis, are making pediatric imaging more child-friendly, accurate, and clinically valuable.