Computer Aided Diagnostic Tool on Computed Tomography Images for Diagnosis of Retroperitoneal Tumor in Children

Sichuan University

Status: Unknown

Conditions: Germ Cell Tumor; Sarcoma; Teratoma; Neuroblastoma; Lymphoma; Wilms' Tumor

Treatments: Diagnostic Test: Radiomic Algorithm

Study type: Observational

Funder types: Other

Identifiers

NCT05179850

HX-2021477

Details and patient eligibility

About

The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for retroperitoneal tumor using machine learning and deep learning techniques on computed tomography images in children.

Full description

The retroperitoneal space extends from the lumbar region to the pelvic region and houses vital structures such as the kidney, the ureter, the adrenal glands, the pancreas, the aorta and its branches, the inferior vena cava and its tributaries, lymph nodes, and loose connective tissue meshwork along with fat. This space thus allows the silent growth of primary and metastatic tumors, such that clinical features appear often too late. The therapeutic regimen differs on various types of retroperitoneal tumor in children. It is damaging for pediatric patients to acquire histological specimens through invasive procedures. Hence, an urgent evaluation is absolutely necessary for preoperative diagnosis in such cases via noninvasive approaches. This study is a retrospective-prospective design by West China Hospital, Sichuan University, including clinical data and radiological images. A retrospective database was enrolled for patients with definite histological diagnosis and available computed tomography images from June 2010 and December 2020. The investigators have constructed deep learning and machine learning radiomics diagnostic models on this retrospective cohort and validated it internally. A prospective cohort would recruit infantile patients diagnosed as retroperitoneal tumor since January 2021. The proposed deep learning model would also be validated in this prospective cohort externally. The aim of this study was to evaluate the diagnostic efficacy of computer aided diagnostic tool for retroperitoneal tumor using machine learning and deep learning techniques on computed tomography images in children.

Enrollment: 400 estimated patients

Sex: All

Ages: Under 18 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Age up to 18 years old
• Receiving no treatment before diagnosis
• With written informed consent

Exclusion criteria

• Clinical data missing
• Unavailable computed tomography images
• Without written informed consent

Trial design

400 participants in 2 patient groups

Retrospective cohort

Description:

The internal cohort was retrospectively enrolled in West China Hospital, Sichuan University from June 2010 and December 2020. It is a training and internal validation cohort.

Treatment:

Diagnostic Test: Radiomic Algorithm

Prospective cohort

Description:

The same inclusion/exclusion criteria were applied for the same center prospectively. It is a external validation cohort.

Treatment:

Diagnostic Test: Radiomic Algorithm