Artificial intelligence development in pediatric body magnetic resonance imaging: best ideas to adapt from adults

T2 mapping magnetic resonance imaging of cartilage in hemophilia

Background

In hemophilia, recurrent hemarthrosis may lead to irreversible arthropathy. T2 mapping MRI may reflect cartilage changes at an earlier reversible stage of arthropathy as opposed to structural MRI.

Objectives

To evaluate interval changes of T2 mapping compared with the International Prophylaxis Study Group (IPSG) structural MRI scores of ankle cartilage in boys with hemophilia receiving prophylaxis.

Methods

Eight boys with hemophilia A (median age, 13; range, 9-17 years), 7 age- and sex-matched healthy boys (controls, median age, 15; range, 7-16 years). A multiecho spin-echo T2-weighted MRI sequence at 3.0T was used to obtain T2 maps of cartilage of boys with hemophilia and controls. Structural joint status was evaluated using the IPSG MRI score.

Results

T2 relaxation times of ankle cartilage increased significantly over time in both persons with hemophilia and controls (P = .002 and P = .00009, respectively). Changes in T2 relaxation time strongly correlated with changes in IPSG cartilage scores (rs = 0.93 to rs = 0.78 [P = .0007 to P = .023]), but not with changes in age (P = .304 to P = .840). Responsiveness of T2 relaxation times were higher than that of IPSG cartilage scores, with standardized response means >1.4 for T2 mapping in all regions-of-interest compared with 0.84 for IPSG cartilage scores. Baseline T2 relaxation time strongly correlated with timepoint 2 IPSG cartilage score (rs = 0.93 to rs = 0.82 [P = .001 to P = .012]) and T2 relaxation time (rs = 0.98 to rs = 0.88 [P = .00003 to P = .004]) changes in most regions-of-interest.

Conclusion

T2 mapping shows sensitivity to biochemical changes in cartilage prior to detectable damage using conventional MRI, offering potential for early detection of bleed-related cartilage damage in boys with hemophilia.

European Society of Paediatric Radiology Artificial Intelligence taskforce: a new taskforce for the digital age

A new task force dedicated to artificial intelligence (AI) with respect to paediatric radiology was created in 2021 at the International Paediatric Radiology (IPR) meeting in Rome, Italy (a joint society meeting by the European Society of Pediatric Radiology [ESPR] and the Society for Pediatric Radiology [SPR]). The concept of a separate task force dedicated to AI was borne from an ESPR-led international survey of health care professionals' opinions, expectations and concerns regarding AI integration within children's imaging departments. In this survey, the majority (> 80%) of ESPR respondents supported the creation of a task force and helped define our key objectives. These include providing educational content about AI relevant for paediatric radiologists, brainstorming ideas for future projects and collaborating on AI-related studies with respect to collating data sets, de-identifying images and engaging in multi-case, multi-reader studies. This manuscript outlines the starting point of the ESPR AI task force and where we wish to go.

[Clinical Application and Limitations of Myeloma Response Assessment and Diagnosis System (MY-RADS)]

Multiple myeloma, which is a proliferative disease of plasma cells that originate from a single clone, is the second most common hematologic malignancy following non-Hodgkin lymphoma. In the past, its diagnosis was made based on clinical findings (so-called "CRAB") and a skeletal survey using radiographs. However, since the implementation of the International Myeloma Working Group's revised guideline regarding the radiologic diagnosis of multiple myeloma, whole-body (WB) MRI has emerged to play a central role in the early diagnosis of multiple myeloma. Diffusion-weighted imaging and fat quantification using Dixon methods enable treatment response assessment by MRI. In keeping with the trend, a multi-institutional and multidisciplinary consensus for standardized image acquisition and reporting known as the Myeloma Response Assessment and Diagnostic System (MY-RADS) has recently been proposed. This review aims to describe the clinical application of WB-MRI based on MY-RADS in multiple myeloma, discuss its limitations, and suggest future directions for improvement.

Diagnostic performance of artificial intelligence approved for adults for the interpretation of pediatric chest radiographs

Artificial intelligence (AI) applied to pediatric chest radiographs are yet scarce. This study evaluated whether AI-based software developed for adult chest radiographs can be used for pediatric chest radiographs. Pediatric patients (≤ 18 years old) who underwent chest radiographs from March to May 2021 were included retrospectively. An AI-based lesion detection software assessed the presence of nodules, consolidation, fibrosis, atelectasis, cardiomegaly, pleural effusion, pneumothorax, and pneumoperitoneum. Using the pediatric radiologist’s results as standard reference, we assessed the diagnostic performance of the software. For the total 2273 chest radiographs, the AI-based software showed a sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of 67.2%, 91.1%, 57.7%, 93.9%, and 87.5%, respectively. Age was a significant factor for incorrect results (odds radio 0.821, 95% confidence interval 0.791–0.851). When we excluded cardiomegaly and children 2 years old or younger, sensitivity, specificity, PPV, NPV and accuracy significantly increased (86.4%, 97.9%, 79.7%, 98.7% and 96.9%, respectively, all p < 0.001). In conclusion, AI-based software developed with adult chest radiographs showed diagnostic accuracies up to 96.9% for pediatric chest radiographs when we excluded cardiomegaly and children 2 years old or younger. AI-based lesion detection software needs to be validated in younger children.