Tumor segmentation is one of the key steps in imaging processing. The goals of this study were to assess the inter-observer variability in manual segmentation of neuroblastic tumors and to analyze whether the state-of-the-art deep learning architecture nnU-Net can provide a robust solution to detect and segment tumors on MR images. A retrospective multicenter study of 132 patients with neuroblastic tumors was performed. Dice Similarity Coefficient (DSC) and Area Under the Receiver Operating Characteristic Curve (AUC ROC) were used to compare segmentation sets. Two more metrics were elaborated to understand the direction of the errors: the modified version of False Positive (FPRm) and False Negative (FNR) rates. Two radiologists manually segmented 46 tumors and a comparative study was performed. nnU-Net was trained-tuned with 106 cases divided into five balanced folds to perform cross-validation. The five resulting models were used as an ensemble solution to measure training (n = 106) and validation (n = 26) performance, independently. The time needed by the model to automatically segment 20 cases was compared to the time required for manual segmentation. The median DSC for manual segmentation sets was 0.969 (±0.032 IQR). The median DSC for the automatic tool was 0.965 (±0.018 IQR). The automatic segmentation model achieved a better performance regarding the FPRm. MR images segmentation variability is similar between radiologists and nnU-Net. Time leverage when using the automatic model with posterior visual validation and manual adjustment corresponds to 92.8%.

Testicular tumours are rare in children. Painless scrotal mass is the most frequent clinical presentation. Tumoural markers (alpha-fetoprotein, beta-human gonadotropin chorionic) and hormone levels (testosterone) contribute to the diagnosis and management of a testicular mass in boys. Ultrasonography is the best imaging modality to study testicular tumours. A benign tumour is suggested when ultrasonography shows a mainly cystic component, well-defined borders, echogenic rim or normal to increased echogenicity lesion when compared to the healthy testicular parenchyma. Malignant tumour is suspected when ultrasonography shows inhomogeneous, hypoechoic, not well-circumscribed or diffuse infiltration lesion. However, these ultrasonographic findings may overlap. Colour Doppler, power Doppler, elastography and contrast-enhanced ultrasonography are useful complementary methods to characterise the focal testicular lesions. Chest computerised tomography and abdominopelvic magnetic resonance are necessary to establish the extension in case of malignant proved tumours.Benign tumours are more frequent in prepuberal boys and malignant tumours in pubertal boys. Mature teratoma prepubertal-type is the most common histologic type. Testicular sparing surgery is the choice in benign tumours. Radical inguinal orchiectomy is indicated in malignant tumours. Prognostic is excellent.The purpose of our study is to show an approach to the diagnosis and management of the most frequent testicular tumours in children according to clinical manifestations, imaging findings and tumour markers levels based on histologically confirmed tumours in our hospital.

Objectives. To externally validate and assess the accuracy of a previously trained fully automatic nnU-Net CNN algorithm to identify and segment primary neuroblastoma tumors in MR images in a large children cohort. Methods. An international multicenter, multivendor imaging repository of patients with neuroblastic tumors was used to validate the performance of a trained Machine Learning (ML) tool to identify and delineate primary neuroblastoma tumors. The dataset was heterogeneous and completely independent from the one used to train and tune the model, consisting of 300 children with neuroblastic tumors having 535 MR T2-weighted sequences (486 sequences at diagnosis and 49 after finalization of the first phase of chemotherapy). The automatic segmentation algorithm was based on a nnU-Net architecture developed within the PRIMAGE project. For comparison, the segmentation masks were manually edited by an expert radiologist, and the time for the manual editing was recorded. Different overlaps and spatial metrics were calculated to compare both masks. Results. The median Dice Similarity Coefficient (DSC) was high 0.997; 0.944–1.000 (median; Q1–Q3). In 18 MR sequences (6%), the net was not able neither to identify nor segment the tumor. No differences were found regarding the MR magnetic field, type of T2 sequence, or tumor location. No significant differences in the performance of the net were found in patients with an MR performed after chemotherapy. The time for visual inspection of the generated masks was 7.9 ± 7.5 (mean ± Standard Deviation (SD)) seconds. Those cases where manual editing was needed (136 masks) required 124 ± 120 s. Conclusions. The automatic CNN was able to locate and segment the primary tumor on the T2-weighted images in 94% of cases. There was an extremely high agreement between the automatic tool and the manually edited masks. This is the first study to validate an automatic segmentation model for neuroblastic tumor identification and segmentation with body MR images. The semi-automatic approach with minor manual editing of the deep learning segmentation increases the radiologist’s confidence in the solution with a minor workload for the radiologist.