Radiologists have difficulty distinguishing benign from malignant bone lesions because these lesions may have similar imaging appearances. The purpose of this study was to develop a deep learning algorithm that can differentiate benign and malignant bone lesions using routine magnetic resonance imaging (MRI) and patient demographics. 1,060 histologically confirmed bone lesions with T1- and T2-weighted pre-operative MRI were retrospectively identified and included, with lesions from 4 institutions used for model development and internal validation, and data from a fifth institution used for external validation. Image-based models were generated using the EfficientNet-B0 architecture and a logistic regression model was trained using patient age, sex, and lesion location. A voting ensemble was created as the final model. The performance of the model was compared to classification performance by radiology experts. The cohort had a mean age of 30±23 years and was 58.3% male, with 582 benign lesions and 478 malignant. Compared to a contrived expert committee result, the ensemble deep learning model achieved (ensemble vs. experts): similar accuracy (0·76 vs. 0·73, p=0·7), sensitivity (0·79 vs. 0·81, p=1·0) and specificity (0·75 vs. 0·66, p=0·48), with a ROC AUC of 0·82. On external testing, the model achieved ROC AUC of 0·79. Deep learning can be used to distinguish benign and malignant bone lesions on par with experts. These findings could aid in the development of computer-aided diagnostic tools to reduce unnecessary referrals to specialized centers from community clinics and limit unnecessary biopsies. This work was funded by a Radiological Society of North America Research Medical Student Grant (#RMS2013) and supported by the Amazon Web Services Diagnostic Development Initiative.

Wilms tumors are commonly associated with predisposition syndromes, many but not all of which include overgrowth. Several of these syndromes also include a risk of other embryonal malignancies—particularly hepatoblastoma. Guidelines for surveillance in this population were published in 2017, and recently, members of the American Association for Cancer Research Pediatric Cancer Working Group met to update those guidelines with a review of more recently published evidence and risk estimates. This perspective serves to update pediatric oncologists, geneticists, radiologists, counselors, and other health care professionals on revised diagnostic criteria; review previously published surveillance guidelines; and harmonize updated surveillance recommendations in the North American and Australian contexts for patients with overgrowth syndromes and other syndromes associated with Wilms tumor predisposition.

Replication repair deficiency (RRD) is a pan-cancer mechanism characterized by abnormalities in the DNA mismatch repair (MMR) system due to pathogenic variants in the PMS2, MSH6, MSH2, or MLH1 genes, and/or in the polymerase-proofreading genes POLE and POLD1. RRD predisposition syndromes (constitutional MMR deficiency, Lynch, and polymerase proofreading–associated polyposis) share overlapping phenotypic and biological characteristics. Moreover, cancers stemming from germline defects of one mechanism can acquire somatic defects in another, leading to complete RRD. Here we describe the recent advances in the diagnostics, surveillance, and clinical management for children with RRD syndromes. For patients with constitutional MMR deficiency, new data combining clinical insights and cancer genomics have revealed genotype–phenotype associations and helped in the development of novel functional assays, diagnostic guidelines, and surveillance recommendations. Recognition of non-gastrointestinal/genitourinary malignancies, particularly aggressive brain tumors, in select children with Lynch and polymerase proofreading–associated polyposis syndromes harboring an RRD biology have led to new management considerations. Additionally, universal hypermutation and microsatellite instability have allowed immunotherapy to be a paradigm shift in the treatment of RRD cancers independent of their germline etiology. These advances have also stimulated a need for expert recommendations about genetic counseling for these patients and their families. Future collaborative work will focus on newer technologies such as quantitative measurement of circulating tumor DNA and functional genomics to tailor surveillance and clinical care, improving immune surveillance; develop prevention strategies; and deliver these novel discoveries to resource-limited settings to maximize benefits for patients globally.

Whole-body MRI (WBMRI) is an integral part of screening infants, children, and adolescents for presymptomatic neoplasms in certain cancer predisposition syndromes, which include Li–Fraumeni and constitutional mismatch repair deficiency syndromes, among others. The list of syndromes in which WBMRI adds value, as part of a comprehensive surveillance protocol, continues to evolve in response to new evidence, growing experience, and more widespread adoption. In July 2023, the AACR reconvened an international, multidisciplinary panel to revise and update recommendations stemming from the 2016 AACR Special Workshop on Childhood Cancer Predisposition. That initial meeting resulted in a series of publications in Clinical Cancer Research in 2017, including “Pediatric Cancer Predisposition Imaging: Focus on Whole-Body MRI.” This 2024 review of WBMRI in cancer predisposition syndrome updates the 2017 WBMRI publication, the revised recommendations derived from the 2023 AACR Childhood Cancer Predisposition Workshop based on available data, societal guidelines, and expert opinion. Different aspects of acquiring and interpreting WBMRI, including diagnostic accuracy, are discussed. The application of WBMRI in resource-poor environments, as well as integration of whole-body imaging techniques with emerging technologies, such as cell-free DNA (“liquid biopsies”) and artificial intelligence/machine learning, is also considered.

Gastrointestinal (GI) polyposis and cancer in pediatric patients is frequently due to an underlying hereditary cancer risk syndrome requiring ongoing cancer screening. Identification of at-risk patients through family history, clinical features of a syndrome, or symptom onset ensures appropriate cancer risk assessment and management in childhood and beyond. In this 2024 perspective, we outline updates to the hereditary GI cancer screening guidelines first published by the American Association of Cancer Research Pediatric Cancer Predisposition Workshop in 2017. These guidelines consider existing recommendations by pediatric and adult gastroenterology consortia to ensure alignment with gastroenterology practices in managing polyposis conditions. We specifically address the recommendations for pediatric screening in familial adenomatous polyposis, Peutz-Jeghers syndrome, and juvenile polyposis syndrome. Further, we emphasize the importance of multidisciplinary care and partnership with gastroenterology, as it is crucial in management of children and families with these conditions.