Evaluation of the utility of 99m Tc-MDP bone scintigraphy versus MIBG scintigraphy and cross-sectional imaging for staging patients with neuroblastoma

Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [ 99M Tc] Tc-MDP scintigraphy images

PURPOSE

Neural network has widely been applied for medical classifications and disease diagnosis. This study employs deep learning to best discriminate Juvenile Idiopathic Arthritis (JIA), a pediatric chronic joint inflammatory disease, from healthy joints by exploring blood pool images of 2phase [ 99m Tc] Tc-MDP bone scintigraphy.

METHODS

Self-deigned multi-input Convolutional Neural Network (CNN) in addition to three available pre-trained models including VGG16, ResNet50 and Xception are applied on 1304 blood pool images of 326 healthy and known JIA children and adolescents (aged 1-16).

RESULTS

The self-designed model ROC analysis shows diagnostic efficiency with Area Under the Curve (AUC) 0.82 and 0.86 for knee and ankle joints, respectively. Among the three pertained models, VGG16 ROC analysis reveals AUC 0.76 and 0.81 for knee and ankle images, respectively.

CONCLUSION

The self-designed model shows best performance on blood pool scintigraph diagnosis of patients with JIA. VGG16 was the most efficient model rather to other pre-trained networks. This study can pave the way of artificial intelligence (AI) application in nuclear medicine for the diagnosis of pediatric inflammatory disease.

A nomogram for the preoperative estimation of neuroblastoma risk despite inadequate biopsy information

BACKGROUND AND PURPOSE

If the preoperative pathological information is inadequate, a risk classification may not be able to be determined for some patients with neuroblastoma. Our objectives were to include imaging factors, serum biomarkers, and demographic factors in a nomogram to distinguish high-risk patients before surgical resection based on the COG classification.

METHOD

A total of 106 patients were included in the study. Of these, patients with clinicopathologically confirmed neuroblastoma at Tianjin Children's Hospital from January 2013 to November 2021 formed the training cohort (n = 82) for nomogram development, and those patients from January 2010 to December 2013 formed the validation cohort (n = 24) to confirm the model's performance.

RESULT

On multivariate analysis of the primary cohort, independent factors for high risk were the presence of distant metastasis (p = 0.004), lactate dehydrogenase (LDH) (p = 0.009), and tumor volume (p = 0.033), which were all selected into the nomogram. The calibration curve for probability showed good agreement between prediction by nomogram and actual observation. The C-index of the nomogram was 0.95 95% [0.916-0.99]. Application of the nomogram in the validation cohort still gave good discrimination and good calibration.

CONCLUSION

Three independent factors including the presence of distant metastasis, lactate dehydrogenase (LDH), and tumor volume are associated with high-risk neuroblastoma and selected into the nomogram. The novel nomogram has the flexibility to apply a clinically suitable cutoff to identify high-risk neuroblastoma patients despite inadequate preoperative pathological information. The nomogram can allow these patients to be offered suitable induction chemotherapy regimens and surgical plans.

LEVELS OF EVIDENCE

Level III.

A review of pediatric neuroendocrine tumors, their detection, and treatment by radioisotopes

Neuroendocrine tumors (NETs) are rare in childhood. Neuroblastoma is the most common pediatric extracranial solid tumor, occurring >90% in children younger than 5 years of age. Pheochromocytoma and paraganglioma are rare NETs, causing hypertension in 0.5-2% of hypertensive children. Gastroenteropancreatic NETs can occur in children and are classified into carcinoids and pancreatic tumors. Nuclear medicine procedures have an essential role both in the diagnosis and treatment of NETs. Metaiodobenzylguanidine (MIBG) labeled with radioiodine has a well-established role in diagnosis as well as therapeutic management of the neuroblastoma group of diseases. During recent decades, establishing the abundant expression of somatostatin receptors by NETs first led to scintigraphy with somatostatin analogs (i.e. Tc/In-octreotide) and, later, with the emergence of positron-emitting labeled agents (i.e. Ga-DOTATATE/DOTATOC/DOTANOC) PET scans with significantly higher detection efficiency became available. Therapy with somatostatin analogs labeled with beta emitters such as Lu-177 and Y-90, known as peptide receptor radionuclide therapy, is a promising new option in the management of patients with inoperable or metastasized NETs. In this article, pediatric NETs are briefly reviewed and the role of radioactive agents in the detection and treatment of these tumors is discussed.

Functional and anatomical imaging in pediatric oncology: which is best for which tumors

Functional imaging techniques are playing an increasingly important role in the management of pediatric cancer. Technological advances have pushed the development of hybrid imaging techniques, including positron emission tomography (PET)/CT, PET/MR and single-photon emission computed tomography (SPECT)/CT. Together with an increasing need to identify surrogate biomarkers for response to novel therapies, the use of functional imaging techniques, which had been reserved primarily for lymphoma patients, is now being recognized as standard of care for the management of many other pediatric solid tumors. The purpose of this review is to summarize recent data describing the use of functional and metabolic imaging strategies for the staging and response assessment of common pediatric solid tumors, and to offer some guidance as to which techniques are most appropriate for which tumor types.

Staging and following common pediatric malignancies: MRI versus CT versus functional imaging

Most pediatric malignancies require some form of cross-sectional imaging, either for staging or response assessment. The majority of these are solid tumors and this review addresses the role of MRI, as well as other cross-sectional and functional imaging techniques, for evaluating the most common pediatric solid tumors. The primary emphasis is on neuroblastoma, hepatoblastoma and Wilms tumor, three of the most common non-central-nervous-system (CNS) pediatric solid tumors encountered in young children. The initial focus will be a review of the imaging techniques and approaches used for diagnosis, staging and early post-treatment response assessment, followed by a discussion of the role surveillance imaging plays in pediatric oncology and a brief review of other emerging imaging techniques. The lessons learned here can be applied to most other pediatric tumors, including rhabdomyosarcoma, Ewing sarcoma and osteosarcoma, as well as germ cell tumors, neurofibromatosis and other rare tumors. Although lymphoma, in particular Hodgkin lymphoma, represents one of the more common pediatric malignancies, this is not discussed in detail here. Rather, many of the lessons that we have learned from lymphoma, specifically with regard to how we integrate both anatomical imaging and functional imaging techniques, is applied to the discussion of the other pediatric solid tumors.

Neuroblastoma: clinical and biological approach to risk stratification and treatment

Neuroblastoma is the most common extra-cranial solid tumor of childhood and the most common in the first year of life. It is a unique malignancy in that infants often present with either localized or metastatic disease that can spontaneously regress without intervention while older children can succumb to the disease after months to years of arduous therapy. Given this wide range of outcomes, the International Neuroblastoma Risk Group was created to stratify patients based on presenting characteristics and tumor biology in order to guide intensity of treatment strategies. The goal has been to decrease therapy for low-risk patients to avoid long-term complications while augmenting and targeting therapies for high-risk patients to improve overall survival. The international risk stratification depends on age, stage, histology, MYCN gene amplification status, tumor cell ploidy and segmental chromosomal abnormalities. Treatment for asymptomatic low-risk patients with an estimated survival of > 98% is often observation or surgical resection alone, whereas intermediate-risk patients with an estimated survival of > 90% require moderate doses of response-adjusted chemotherapy along with resection. High-risk patients undergo multiple cycles of combination chemotherapy before surgery, followed by consolidation with myeloablative autologous hematopoietic stem cell transplantation and local radiation and finally immunotherapy with differentiation therapy as maintenance phase. With this approach, outcome for patients with neuroblastoma has improved, as the field continues to expand efforts in more targeted therapies for high-risk patients.

Ionizing radiation from computed tomography versus anesthesia for magnetic resonance imaging in infants and children: patient safety considerations

In the context of health care, risk assessment is the identification, evaluation and estimation of risk related to a particular clinical situation or intervention compared to accepted medical practice standards. The goal of risk assessment is to determine an acceptable level of risk for a given clinical treatment or intervention in association with the provided clinical circumstances for a patient or group of patients. In spite of the inherent challenges related to risk assessment in pediatric cross-sectional imaging, the potential risks of ionizing radiation and sedation/anesthesia in the pediatric population are thought to be quite small. Nevertheless both issues continue to be topics of discussion concerning risk and generate significant anxiety and concern for patients, parents and practicing pediatricians. Recent advances in CT technology allow for more rapid imaging with substantially lower radiation exposures, obviating the need for anesthesia for many indications and potentially mitigating concerns related to radiation exposure. In this review, we compare and contrast the potential risks of CT without anesthesia against the potential risks of MRI with anesthesia, and discuss the implications of this analysis on exam selection, providing specific examples related to neuroblastoma surveillance imaging.