Automation of Wilms' tumor segmentation by artificial intelligence.

BACKGROUND: 3D reconstruction of Wilms' tumor provides several advantages but are not systematically performed because manual segmentation is extremely time-consuming. The objective of our study was to develop an artificial intelligence tool to automate the segmentation of tumors and kidneys in children. METHODS: A manual segmentation was carried out by two experts on 14 CT scans. Then, the segmentation of Wilms' tumor and neoplastic kidney was automatically performed using the CNN U-Net and the same CNN U-Net trained according to the OV2ASSION method. The time saving for the expert was estimated depending on the number of sections automatically segmented. RESULTS: When segmentations were performed manually by two experts, the inter-individual variability resulted in a Dice index of 0.95 for tumor and 0.87 for kidney. Fully automatic segmentation with the CNN U-Net yielded a poor Dice index of 0.69 for Wilms' tumor and 0.27 for kidney. With the OV2ASSION method, the Dice index varied depending on the number of manually segmented sections. For the segmentation of the Wilms' tumor and neoplastic kidney, it varied respectively from 0.97 to 0.94 for a gap of 1 (2 out of 3 sections performed manually) to 0.94 and 0.86 for a gap of 10 (1 section out of 6 performed manually). CONCLUSION: Fully automated segmentation remains a challenge in the field of medical image processing. Although it is possible to use already developed neural networks, such as U-Net, we found that the results obtained were not satisfactory for segmentation of neoplastic kidneys or Wilms' tumors in children. We developed an innovative CNN U-Net training method that makes it possible to segment the kidney and its tumor with the same precision as an expert while reducing their intervention time by 80%.

Automated segmentation and volume prediction in pediatric Wilms' tumor CT using nnu-net.

BACKGROUND: Radiologic volumetric evaluation of Wilms' tumor (WT) is an important indicator to guide treatment decisions. However, due to the heterogeneity of the tumors, radiologists have main-guard differences in diagnosis that can lead to misdiagnosis and poor treatment. The aim of this study was to explore whether CT-based outlining of WT foci can be automated using deep learning. METHODS: We included CT intravenous phase images of 105 patients with WT and double-blind outlining of lesions by two radiologists. Then, we trained an automatic segmentation model using nnUnet. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95) were used to assess the performance. Next, we optimized the automatic segmentation results based on the ratio of the three-dimensional diameter of the lesion to improve the performance of volumetric assessment. RESULTS: The DSC and HD95 was 0.83 ± 0.22 and 10.50 ± 8.98 mm. The absolute difference and percentage difference in tumor size was 72.27 ± 134.84 cm3 and 21.08% ± 30.46%. After optimization according to our method, it decreased to 40.22 ± 96.06 cm3 and 10.16% ± 9.70%. CONCLUSION: We introduce a novel method that enhances the accuracy of predicting WT volume by integrating AI automated outlining and 3D tumor diameters. This approach surpasses the accuracy of using AI outcomes alone and has the potential to enhance the clinical evaluation of pediatric patients with WT. By intertwining AI outcomes with clinical data, this method becomes more interpretive and offers promising applications beyond Wilms tumor, extending to other pediatric diseases.

Preoperative three-dimensional modelling and virtual reality planning aids nephron sparing surgery in a child with bilateral Wilms tumour.

Bilateral Wilms tumour (BWT) is a surgically challenging condition. Virtual reality (VR) reconstruction aids surgeons to foresee the anatomy ahead of Nephron Sparing Surgery (NSS). Three-dimensional (3D) visualisation improves the anatomical orientation of surgeons performing NSS. We herewith report a case of BWT where VR planning and 3D printing were used to aid NSS. Conventional imaging is often found to be inadequate while assessing the tumour-organ-vascular anatomy. Advances like VR and 3D printing help surgeons plan better for complex surgeries like bilateral NSS. Next-generation extended reality tools will likely aid robotic-assisted precision NSS and improve patient outcomes.

Correlation of CT Scan Response to Necrosis and Volume Changes With Histopathology in Children With Wilms' Tumor.

BACKGROUND: Wilms' tumor is the most common renal tumor in children. OBJECTIVE: To correlate the percentage of necrosis and tumor volume change found in preoperative Contrast Enhance Computed Tomography (CECT) scan of the abdomen with post-operative histopathological findings of Wilms Tumor (WT). METHODS: In this prospective study from January 2020 to December 2022, out of 33 patients, 15 patients with unilateral localized WT (stage I, II, and III) treated according to SIOP UMBRELLA protocol 2016 were included. Bilateral, syndromic, and stage IV WT were excluded. The radiological response was measured in preoperative CECT by estimating the percentage of necrosis found in static images and compared with post-operative histopathological findings. Tumor volume changes were measured by comparing CECT at diagnosis and following chemotherapy. Tumor volume change was also compared with histology. RESULTS: There was a significant positive correlation between radiological response to necrosis with histology as per Pearson correlation. Significant positive correlation also found between volume changes on pre and post chemotherapy CECT with histology as per Spearman correlation. CONCLUSIONS: The changes in tumors during preoperative radiological evaluation and histologically confirmed necrosis are strongly related.

Radiomics in differential diagnosis of Wilms tumor and neuroblastoma with adrenal location in children.

OBJECTIVES: Machine learning methods can be applied successfully to various medical imaging tasks. Our aim with this study was to build a robust classifier using radiomics and clinical data for preoperative diagnosis of Wilms tumor (WT) or neuroblastoma (NB) in pediatric abdominal CT. MATERIAL AND METHODS: This is a single-center retrospective study approved by the Institutional Ethical Board. CT scans of consecutive patients diagnosed with WT or NB admitted to our hospital from January 2005 to December 2021 were evaluated. Three distinct datasets based on clinical centers and CT machines were curated. Robust, non-redundant, high variance, and relevant radiomics features were selected using data science methods. Clinically relevant variables were integrated into the final model. Dice score for similarity of tumor ROI, Cohen's kappa for interobserver agreement among observers, and AUC for model selection were used. RESULTS: A total of 147 patients, including 90 WT (mean age 34.78 SD: 22.06 months; 43 male) and 57 NB (mean age 23.77 SD:22.56 months; 31 male), were analyzed. After binarization at 24 months cut-off, there was no statistically significant difference between the two groups for age (p = .07) and gender (p = .54). CT clinic radiomics combined model achieved an F1 score of 0.94, 0.93 accuracy, and an AUC 0.96. CONCLUSION: In conclusion, the CT-based clinic-radiologic-radiomics combined model could noninvasively predict WT or NB preoperatively. Notably, that model correctly predicted two patients, which none of the radiologists could correctly predict. This model may serve as a noninvasive preoperative predictor of NB/WT differentiation in CT, which should be further validated in large prospective models. CLINICAL RELEVANCE STATEMENT: CT-based clinic-radiologic-radiomics combined model could noninvasively predict Wilms tumor or neuroblastoma preoperatively. KEY POINTS: • CT radiomics features can predict Wilms tumor or neuroblastoma from abdominal CT preoperatively. • Integrating clinic variables may further improve the performance of the model. • The performance of the combined model is equal to or greater than human readers, depending on the lesion size.

Congenital Mesoblastic Nephroma Mimic Wilms Tumor on 18 F-FDG PET/CT and PET/MR.

ABSTRACT: Congenital mesoblastic nephroma is an extremely rare, low-grade malignant renal tumor in children. A 10-month-old boy and a 4-month-old girl were admitted to our hospital with a huge abdominal mass. For staging of the mass, 18 F-FDG PET/CT and PET/MR were performed showing a huge heterogeneous abdominal mass accompanied by extensive heterogeneous aggregation. Both of them were highly suspected to be Wilms tumor, the most common renal malignant tumor in children. However, histopathological examination after surgery confirmed congenital mesodermal nephroma.

[Renal tumors in children and adolescents]. / Nierentumoren bei Kindern und Jugendlichen.

CLINICAL/METHODOLOGICAL ISSUE: Diagnosis and therapy of renal tumors in children and adolescents are standardized by study protocols from major international societies. Imaging plays a central role, and in Europe patients between the ages of 6 months and 14 years with renal tumors are referred to neoadjuvant chemotherapy without histological confirmation according to the study protocol due to the frequency of Wilms tumor. STANDARD RADIOLOGIC METHODS: Ultrasound is used worldwide as the primary investigative procedure for suspected renal tumors. In Europe, magnetic resonance imaging (MRI) has become established for more advanced diagnosis. In addition to differential diagnosis, staging is crucial for therapy. According to current protocol, this includes computed tomography (CT) of the thorax for the evaluation of pulmonary metastases. METHODOLOGICAL INNOVATIONS: Diffusion-weighted MRI provides promising results for the differentiation of nephroblastoma subtypes in addition to improved detectability of tumor foci. However, sufficient evidence is lacking. PERFORMANCE: Differentiation of Wilms tumor from the highly malignant non-Wilm tumors, such as malignant rhabdoid tumor and clear cell sarcoma of the kidney, remains inconclusive based on imaging alone. Differential diagnosis is, therefore, based on morphologic and epidemiologic criteria. ASSESSMENT: The high degree of standardization in the diagnosis and treatment of renal tumors in children and adolescents has led to a significant improvement in prognosis. Overall survival of patients with Wilms tumor is currently over 90%.

Clinical value of ultrasound in adult Wilms' tumor patient with uremia: A case report and literature review.

RATIONALE: Wilms' tumor (WT) is the most common pediatric kidney malignancy and is rarely found in adults. Nonspecific clinical symptoms and imaging features often lead to delayed diagnosis or misdiagnosis of adult WT, resulting in poor clinical outcomes. Ultrasound (US), as an efficient and noninvasive examination method, has been widely used in clinical diagnosis and treatment. Therefore, various US evidence is meaningful to improve understanding of adult WT characteristics in ultrasound. PATIENT CONCERNS: A 45-year-old female patient with uremia (regular hemodialysis for 13 years) with painless gross hematuria was diagnosed with a right kidney tumor penetrating to the lung. Preoperatively, B-mode ultrasonography showed an ill-defined hyperechoic mass in the right kidney, which revealed an unclear border, uneven internal echoes, and calcification. Besides, the internal blood flow signal of the tumor was detected. Contrast-enhanced ultrasound (CEUS) showed an uneven hyper-enhancement in the tumor ("fast in and slow out"). Contrast-enhanced computed tomography of the kidney indicated a similar result as the CEUS. Moreover, the chest CT identified multiple pulmonary metastatic nodules. DIAGNOSES: An ultrasound-guided percutaneous core needle biopsy of the tumor proceeded to make a definite diagnosis of adult WT (epithelial type). INTERVENTIONS: The patient was treated with tislelizumab. OUTCOMES: No progress was found to date. LESSONS: We report the first case in which CEUS was performed in an adult WT patient with uremia and multiple pulmonary metastases. The features obtained by the US can help in the diagnosis of adult WT and direct further diagnostic procedures.

Update on the Role of Imaging in Staging of Common Pediatric Abdominal Tumors.

Neuroblastoma, Wilms tumor, and hepatoblastoma are the most common pediatric abdominal malignancies. Management of these diseases is a multidisciplinary process that continues to evolve based on the results of international collaborative trials and advances in understanding of tumor biology. Each of these tumors has unique characteristics and behavior which are reflected in their respective staging systems. It is important for clinicians involved in the care of children with abdominal malignancies to be familiar with current staging guidelines and imaging recommendations. This article reviews the current role of imaging in the management of these common pediatric abdominal malignancies, with emphasis on initial staging.

CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center.

BACKGROUND: Deep learning (DL) is more and more widely used in children's medical treatment. In this study, we have developed a computed tomography (CT)-based DL model for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors. METHODS: This study collected and analyzed the preoperative clinical data and CT images of pediatric renal tumor patients diagnosed by our center from 2008 to 2020, and established a DL model to identify nWTs noninvasively. RESULTS: A total of 364 children who had been confirmed by histopathology with renal tumors from our center were enrolled, including 269 Wilms tumors (WTs) and 95 nWTs. For DL model development, all cases were randomly allocated to training set (218 cases), validation set (73 cases), and test set (73 cases). In the test set, the DL model achieved area under the curve of 0.831 (95% CI: 0.712-0.951) in discriminating WTs from nWTs, with the accuracy, sensitivity, and specificity of 0.781, 0.563, and 0.842, respectively. The sensitivity of our model was higher than a radiologist with 15 years of experience. CONCLUSIONS: We presented a DL model for identifying undiagnosed nWTs from pediatric renal tumors, with the potential to improve the image-based diagnosis. IMPACT: Deep learning model was used for the first time to identify pediatric renal tumors in this study. Deep learning model can identify non-Wilms tumors from pediatric renal tumors. Deep learning model based on computed tomography images can improve tumor diagnosis rate.

Diagnostic dilemma in left flank mass in an infant: A rare case of intrarenal neuroblastoma.

Neuroblastoma (NBL) and nephroblastoma present with abdominal mass and various imaging features help in differentiating the two; however, localisation is difficult in large masses and at times imaging features can be confusing. Here, we describe the case of large left-sided NBL arising from the adrenal and involving the left kidney with moderate hydronephrosis.

Botryoid Wilms Tumor with Left-Sided Inferior Vena Cava: A Case Report.

Wilms tumor (WT) is the second most common solid tumor in pediatric population. Botryoid WT is an uncommon growth pattern of WT, which is characterized by tumor extension into collecting system. A case of a 27-month-old boy with botryoid WT and left-sided inferior vena cava is reported in this article to emphasize the importance of preoperative imaging in preoperative planning.

Direct correlation of MRI with histopathology in pediatric renal tumors through the use of a patient-specific 3-D-printed cutting guide: a feasibility study.

BACKGROUND: Pediatric renal tumors are often heterogeneous lesions with variable regions of distinct histopathology. Direct comparison between in vivo imaging and ex vivo histopathology might be useful for identification of discriminating imaging features. OBJECTIVE: This feasibility study explored the use of a patient-specific three-dimensional (3D)-printed cutting guide to ensure correct alignment (orientation and slice thickness) between magnetic resonance imaging (MRI) and histopathology. MATERIALS AND METHODS: Before total nephrectomy, a patient-specific cutting guide based on each patient's preoperative renal MRI was generated and 3-D printed, to enable consistent transverse orientation of the histological specimen slices with MRI slices. This was expected to result in macroscopic slices of 5 mm each. The feasibility of the technique was determined qualitatively, through questionnaires administered to involved experts, and quantitatively, based on structured measurements including overlap calculation using the dice similarity coefficient. RESULTS: The cutting guide was used in eight Wilms tumor patients receiving a total nephrectomy, after preoperative chemotherapy. The median age at diagnosis was 50 months (range: 4-100 months). The positioning and slicing of the specimens were rated overall as easy and the median macroscopic slice thickness of each specimen ranged from 5 to 6 mm. Tumor consistency strongly influenced the practical application of the cutting guide. Digital correlation of a total of 32 slices resulted in a median dice similarity coefficient of 0.912 (range: 0.530-0.960). CONCLUSION: We report the feasibility of a patient-specific 3-D-printed MRI-based cutting guide for pediatric renal tumors, allowing improvement of the correlation of MRI and histopathology in future studies.

Imaging of pediatric renal tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper focused on Wilms tumor and nephrogenic rests.

Malignant renal tumors account for approximately 6% of pediatric malignancies, with Wilms tumor (WT) representing approximately 90% of pediatric renal tumors. This paper provides consensus-based imaging guidelines for the initial evaluation of a child with suspected WT and follow-up during and after therapy co-developed by the Children's Oncology Group (COG) Diagnostic Imaging and Society for Pediatric Radiology (SPR) oncology committees. The guidelines for Wilms Tumor Imaging in the Society of International Pediatric Oncology (SIOP) are briefly discussed to highlight some of the differences in imaging approach.

Multi-modality imaging and therapeutics used in a case of canine spinal nephroblastoma.

A 4-year-old castrated male golden retriever dog was brought to a veterinary teaching hospital for evaluation of acute progressive paraparesis. Neurological examination indicated a spinal cord lesion between the third thoracic vertebra and third lumbar vertebrae. Magnetic resonance imaging (MRI) revealed an intradural, extra medullary, and/or intramedullary mass centered over the eleventh and twelfth thoracic disc space. The dog underwent cytoreductive surgery and histopathologic analysis diagnosed a nephroblastoma. Following this, the dog underwent multimodal therapy, including multiple surgeries, 2 courses of radiation, and combination chemotherapy. The dog had serial restaging using MRI, computed tomography (CT), and fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography throughout the course of therapy. The dog survived 350 d from date of first presentation until humane euthanasia was elected due to worsening of neurologic status. During postmortem examination, extensive infiltration of the spinal cord by nephroblastoma cells was discovered as well as pulmonary metastatic disease. Key clinical message: Based on the literature search, this is the first case in which surgery, radiation therapy, and chemotherapy were all used for the treatment of canine spinal nephroblastoma. This case report details the aggressive nature of a case of canine spinal nephroblastoma despite multi-modal therapy.

Méthode d'imagerie et de thérapies multimodales utilisées dans un cas de néphroblastome spinal canin. Un chien golden retriever mâle castré âgé de 4 ans a été présenté dans un hôpital d'enseignement vétérinaire pour l'évaluation d'une paraparésie progressive aiguë. L'examen neurologique a révélé une lésion de la moelle épinière entre la troisième vertèbre thoracique et la troisième vertèbre lombaire. L'imagerie par résonance magnétique (MRI) a révélé une masse intradurale, extra-médullaire et/ou intramédullaire centrée sur les onzième et douzième espace de disque thoracique. Le chien a subi une chirurgie de cytoréduction et une analyse histopathologique a diagnostiqué un néphroblastome. Par la suite, le chien a subi une thérapie multimodale, comprenant plusieurs interventions chirurgicales, deux cycles de radiothérapie et une chimiothérapie combinée. Le chien a subi une reclassification en série par MRI, tomodensitométrie (CT) et tomographie par émission de positrons au fluor-18 fluorodésoxyglucose/tomodensitométrie tout au long du traitement. Le chien a survécu 350 jours à partir de la date de la première présentation jusqu'à ce que l'euthanasie soit choisie en raison de l'aggravation de l'état neurologique. Au cours de l'examen post-mortem, une infiltration étendue de la moelle épinière par des cellules de néphroblastome a été découverte ainsi qu'une maladie métastatique pulmonaire.Message clinique clé :D'après la recherche documentaire, il s'agit du premier cas dans lequel la chirurgie, la radiothérapie et la chimiothérapie ont toutes été utilisées pour le traitement du néphroblastome spinal canin. Ce rapport de cas détaille la nature agressive d'un cas de néphroblastome spinal canin malgré une thérapie multimodale.(Traduit par Dr Serge Messier).

The clinical impact of observer variability in lung nodule classification in children with Wilms tumour.

OBJECTIVES: To investigate the extent to which observer variability of computed tomography (CT) lung nodule assessment may affect clinical treatment stratification in Wilms tumour (WT) patients, according to the recent Société Internationale d'Oncologie Pédiatrique Renal Tumour Study Group (SIOP-RTSG) UMBRELLA protocol. METHODS: I: CT thoraces of children with WT submitted for central review were used to estimate size distribution of lung metastases. II: Scans were selected for blinded review by five radiologists to determine intra- and inter-observer variability. They assessed identical scans on two occasions 6 months apart. III: Monte Carlo simulation (MCMC) was used to predict the clinical impact of observer variation when applying the UMBRELLA protocol size criteria. RESULTS: Lung nodules were found in 84 out of 360 (23%) children with WT. For 21 identified lung nodules, inter-observer limits of agreement (LOA) for the five readers were ±2.4 and ±1.4 mm (AP diameter), ±1.9 and ±1.8 mm (TS diameter) and ±2.0 and ±2.4 mm (LS diameter) at assessments 1 and 2. Intra-observer LOA across the three dimensions were ±1.5, ±2.2, ±3.5, ±3.1 and ±2.6 mm (readers 1-5). MCMC demonstrated that 17% of the patients with a 'true' nodule size of ≥3 mm will be scored as <3 mm, and 21% of the patients with a 'true' nodule size of <3 mm will be scored as being ≥3 mm. CONCLUSION: A significant intra-inter observer variation was found when measuring lung nodules on CT for patients with WT. This may have significant implications on treatment stratification, and thereby outcome, when applying a threshold of ≥3 mm for a lung nodule to dictate metastatic status.

Beyond Wilms tumor: imaging findings and outcomes of rare renal tumors in children.

BACKGROUND: Compared to Wilms, non-Wilms renal tumors in children are less well understood due to their rare occurrence which limits precise definition of the typical imaging patterns. OBJECTIVE: This study aims to identify distinctive imaging findings, demographic characteristics and prognosis of pediatric non-Wilms renal tumors. MATERIALS AND METHODS: From January 2007 to December 2018, 207 patients with a diagnosis of primary kidney neoplasia were yielded from our radiology archive, 171 of whom were diagnosed with Wilms tumor, 4 with angiomyolipoma and one with nephrogenic rest. The remaining 31 patients with a diagnosis of primary kidney neoplasia were enrolled in this retrospective study. Imaging data, age, gender, prognosis and findings regarding follow-up were noted. RESULTS: Eight patients had renal cell carcinoma, seven had clear cell sarcoma, six had mesoblastic nephroma, four had rhabdoid tumor, three had desmoplastic small round cell tumor, two had cystic nephroma and one had metanephric stromal tumor. The age of diagnosis was > 8 years for renal cell carcinoma and desmoplastic small round cell tumor, < 5 years for rhabdoid tumor and < 7 months for mesoblastic nephroma. There was no gender preference for any tumor type. The prognosis for rhabdoid tumor was extremely poor in that all the patients followed up in our institute were deceased, whereas no recurrence was found in other tumors. Translocation type renal cell carcinoma had lower T2-weighted signal intensity, mesoblastic nephroma was a predominantly cystic mass, clear cell sarcoma was generally larger at presentation and extensive amorphous calcifications were seen in desmoplastic small round cell tumor. CONCLUSION: For the differential diagnosis of pediatric non-Wilms renal tumors, age is the most important factor, followed by propensity to metastasize/aggressive behavior of the mass. Knowledge of specific imaging findings of these tumors may help to narrow the differential diagnosis.