3D reconstruction of Wilms' tumor and kidneys in children: Variability, usefulness and constraints

Direct correlation of MR-DWI and histopathology of Wilms' tumours through a patient-specific 3D-printed cutting guide

OBJECTIVES

The International Society of Paediatric Oncology-Renal Tumour Study Group (SIOP-RTSG) discourages invasive procedures to determine the histology of paediatric renal neoplasms at diagnosis. Therefore, the histological subtype of Wilms' tumours (WT) is unknown at the start of neoadjuvant chemotherapy. MR-DWI shows potential value as a non-invasive biomarker through apparent diffusion coefficients (ADCs). This study aimed to describe MR characteristics and ADC values of paediatric renal tumours to differentiate subtypes.

MATERIALS AND METHODS

Children with a renal tumour undergoing surgery within the SIOP-RTSG 2016-UMBRELLA protocol were prospectively included between May 2021 and 2023. In the case of a total nephrectomy, a patient-specific cutting guide based on the neoadjuvant MR was 3D-printed, allowing a correlation between imaging and histopathology. Whole-tumour volumes and ADC values were statistically compared with the Mann-Whitney U-test. Direct correlation on the microscopic slide level was analysed through mixed model analysis.

RESULTS

Fifty-nine lesions of 54 patients (58% male, median age 3.0 years (range 0-17.7 years)) were included. Forty-four lesions involved a WT. Stromal type WT showed the lowest median decrease in volume after neoadjuvant chemotherapy (48.1 cm3, range 561.5-(+)332.7 cm3, p = 0.035). On a microscopic slide level (n = 240 slides) after direct correlation through the cutting guide, stromal areas showed a significantly higher median ADC value compared to epithelial and blastemal foci (p < 0.001). With a cut-off value of 1.195 * 10-3 mm2/s, sensitivity, and specificity were 95.2% (95% confidence interval 87.6-98.4%) and 90.5% (95% confidence interval 68.2-98.3%), respectively.

CONCLUSION

Correlation between histopathology and MR-DWI through a patient-specific 3D-printed cutting guide resulted in significant discrimination of stromal type WT from epithelial and blastemal subtypes.

CLINICAL RELEVANCE STATEMENT

Stromal Wilms' tumours could be discriminated from epithelial- and blastemal lesions based on high apparent diffusion coefficient values and limited decrease in volume after neoadjuvant chemotherapy. This may aid in future decision-making, especially concerning discrimination between low- and high-risk neoplasms.

KEY POINTS

MR-DWI shows potential value as a non-invasive biomarker in paediatric renal tumours. The patient-specific cutting guide leads to a correlation between apparent diffusion coefficient values and Wilms' tumour subtype. Stromal areas could be discriminated from epithelial and blastemal foci in Wilms' tumours based on apparent diffusion coefficient values.

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%.

Insights into Personalized Care Strategies for Wilms Tumor: A Narrative Literature Review

Wilms tumor (WT), or nephroblastoma, is the predominant renal malignancy in the pediatric population. This narrative review explores the evolution of personalized care strategies for WT, synthesizing critical developments in molecular diagnostics and treatment approaches to enhance patient-specific outcomes. We surveyed recent literature from the last five years, focusing on high-impact research across major databases such as PubMed, Scopus, and Web of Science. Diagnostic advancements, including liquid biopsies and diffusion-weighted MRI, have improved early detection precision. The prognostic significance of genetic markers, particularly WT1 mutations and miRNA profiles, is discussed. Novel predictive tools integrating genetic and clinical data to anticipate disease trajectory and therapy response are explored. Progressive treatment strategies, particularly immunotherapy and targeted agents such as HIF-2α inhibitors and GD2-targeted immunotherapy, are highlighted for their role in personalized treatment protocols, especially for refractory or recurrent WT. This review underscores the necessity for personalized management supported by genetic insights, with improved survival rates for localized disease exceeding 90%. However, knowledge gaps persist in therapies for high-risk patients and strategies to reduce long-term treatment-related morbidity. In conclusion, this narrative review highlights the need for ongoing research, particularly on the long-term outcomes of emerging therapies and integrating multi-omic data to inform clinical decision-making, paving the way for more individualized treatment pathways.

Current surgical approaches to pediatric renal tumors

Pediatric renal tumors are among the most common pediatric solid malignancies. Surgical resection is a key component in the multidisciplinary therapy for children with kidney tumors. Therefore, it is imperative that surgeons caring for children with renal tumors fully understand the current standards of care in order to provide appropriate surgical expertise within this multimodal framework. Fortunately, the last 60 years of international, multidisciplinary pediatric cancer cooperative group studies have enabled high rates of cure for these patients. This review will highlight the international surgical approaches to pediatric patients with kidney cancer to help surgeons understand the key differences and similarities between the European (International Society of Pediatric Oncology) and North American (Children's Oncology Group) recommendations.

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.

Using three-dimensional model-based tumour volume change to predict the symptom improvement in patients with renal cell cancer

In our recent study, we explored the efficacy of three-dimensional (3D) measurement of tumor volume in predicting the improvement of quality of life (QoL) in patients suffering from renal cell cancer (RCC), who were treated with axitinib and anti-PD-L1 antibodies. This study encompassed 18 RCC patients, including 10 men and 8 women, with an average age of 56.83 ± 9.94 years. By utilizing 3D Slicer software, we analyzed pre- and post-treatment CT scans to assess changes in tumor volume. Patients' QoL was evaluated through the FKSI-DRS questionnaire. Our findings revealed that 3D models for all patients were successfully created, and there was a moderate agreement between treatment response classifications based on RECIST 1.1 criteria and volumetric analysis (kappa = 0.556, p = 0.001). Notably, nine patients reported a clinically meaningful improvement in QoL following the treatment. Interestingly, the change in tumor volume as indicated by the 3D model showed a higher area under the curve in predicting QoL improvement compared to the change in diameter measured by CT, although this difference was not statistically significant (z = 0.593, p = 0.553). Furthermore, a multivariable analysis identified the change in tumor volume based on the 3D model as an independent predictor of QoL improvement (odds ratio = 1.073, 95% CI 1.002-1.149, p = 0.045).In conclusion, our study suggests that the change in tumor volume measured by a 3D model may be a more effective predictor of symptom improvement in RCC patients than traditional CT-based diameter measurements. This offers a novel approach for assessing treatment response and patient well-being, presenting a significant advancement in the field of RCC treatment.

Nephrometry Scoring Systems for Nephron Sparing Surgery in Children

The surgical decision to attempt nephron-sparing surgery (NSS) in children with renal tumors can be difficult. In adults, nephrometric tools are used for decision-making. More than 90% of low-complexity tumors are eligible for NSS, and high-complexity tumors often require total nephrectomy. We retrospectively applied those nephrometric tools [Radius, Exophytic, Nearness to the sinus or collecting system, Anterior/posterior, Location relative to polar lines (RENAL), Preoperative Aspects and Dimensions Used for an Anatomical classification (PADUA), and Renal Tumor Invasion Index (RTII) scoring systems] to the preoperative imaging of children operated for renal tumors in our institution from 2015 to 2019 and correlated them with the type of surgery. The scores were assessed by 2 independent surgeons and 1 radiologist. Forty-four tumors were removed, including 16 NSS, 38 after neo-adjuvant chemotherapy, and 6 upfront surgeries, in 30 children. More than 50% of patients in the low and medium-risk population for RENAL, PADUA, and RTII scores, and ~15% in the high-complexity categories underwent NSS. Tumors removed through NSS were significantly less complex according to each score. Interobserver reliability was good for 3 scores. The application of the RENAL, PADUA, and RTII was able to accurately classify most of the pediatric tumors, according to their complexity. These scores could help increase the indications of NSS in renal tumor surgery.

Surgery in Bilateral Wilms Tumor-A Single-Center Experience

The treatment of bilateral Wilms tumors (BWT) involves curing the cancer, preserving long-term renal function, and maintaining a good quality of life. Established methods for achieving these goals include preoperative chemotherapy and nephron-sparing surgery (NSS). This study aimed to evaluate the experience of a single institution in treating patients with BWT. We analyzed cases of BWT treated at the Pediatric Oncology Institute-GRAACC-Federal University of São Paulo over a period of 35 years. Bleeding control was performed with manual compression of the renal parenchyma. Thirty-three patients were included in the study. Thirty cases were synchronous tumors. The mean age at diagnosis was 30.4 months (±22 m) and 66.7% were girls. The median follow-up period was 83 months. Neoadjuvant chemotherapy was the primary approach in most patients (87.9%), with a simultaneous upfront surgical approach performed in 84.8%. Most patients underwent bilateral NSS (70.4%). There were no early complications in this series, but 39.4% had clinical complications. The five-year survival rate was 76%. Therefore, it is clear that the surgical approach to BWT plays a crucial role in achieving good outcomes. However, it is difficult to standardize surgical techniques and technology may have the potential to enhance safety.

Survey of methods and principles in three-dimensional reconstruction from two-dimensional medical images

Three-dimensional (3D) reconstruction of human organs has gained attention in recent years due to advances in the Internet and graphics processing units. In the coming years, most patient care will shift toward this new paradigm. However, development of fast and accurate 3D models from medical images or a set of medical scans remains a daunting task due to the number of pre-processing steps involved, most of which are dependent on human expertise. In this review, a survey of pre-processing steps was conducted, and reconstruction techniques for several organs in medical diagnosis were studied. Various methods and principles related to 3D reconstruction were highlighted. The usefulness of 3D reconstruction of organs in medical diagnosis was also highlighted.

Radiologic versus Segmentation Measurements to Quantify Wilms Tumor Volume on MRI in Pediatric Patients

Wilms tumor is a common pediatric solid tumor. To evaluate tumor response to chemotherapy and decide whether nephron-sparing surgery is possible, tumor volume measurements based on magnetic resonance imaging (MRI) are important. Currently, radiological volume measurements are based on measuring tumor dimensions in three directions. Manual segmentation-based volume measurements might be more accurate, but this process is time-consuming and user-dependent. The aim of this study was to investigate whether manual segmentation-based volume measurements are more accurate and to explore whether these segmentations can be automated using deep learning. We included the MRI images of 45 Wilms tumor patients (age 0–18 years). First, we compared radiological tumor volumes with manual segmentation-based tumor volume measurements. Next, we created an automated segmentation method by training a nnU-Net in a five-fold cross-validation. Segmentation quality was validated by comparing the automated segmentation with the manually created ground truth segmentations, using Dice scores and the 95th percentile of the Hausdorff distances (HD95). On average, manual tumor segmentations result in larger tumor volumes. For automated segmentation, the median dice was 0.90. The median HD95 was 7.2 mm. We showed that radiological volume measurements underestimated tumor volume by about 10% when compared to manual segmentation-based volume measurements. Deep learning can potentially be used to replace manual segmentation to benefit from accurate volume measurements without time and observer constraints.

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.

Kidney Failure in Children with Wilms Tumor: A Study Based on Urine Analysis and Ultrasound

BACKGROUND

Renal insufficiency is one of the inevitable complications in patients with Wilms tumor (WT). The purpose of this study was to assess the renal function in children with WT at baseline and every 3 months to 2 years.

MATERIALS AND METHODS

In a descriptive-analytical study from 2018 to 2020, 48 children with WT were included in the study. Urine creatinine (U_Cr), serum calcium (S_Cr), blood pressure (BP), estimated glomerular filtration rate (eGFR), and urinary protein (U_Pro) were evaluated at baseline and every 3 months during the study. Spot U_Ca/U_Cr and spot U_Pro/U_Cr ratio were calculated. Kidney ultrasonography was used in all patients. Independent Sample t-test and Chi-square tests were utilized to compare age and sex, respectively.

RESULTS

The mean age of patients at follow-up was 7.3 years. There was no significant difference in mean U_Cr, S_Cr, eGFR, 24-h U_Pro, U_Ca/U_Cr ratio, and spot U_Pro/U_Cr ratio at baseline and end of study (P _baseline> 0.05, P _{end of study}> 0.05). Analysis of kidney size showed a statistical association with tumor stage (P < 0.05). Comparison of the kidney size in patients showed that there is a statistically significant difference (P < 0.0001) at baseline and end of the study.

CONCLUSION

This study showed that as WT progressed, the size of the kidneys increases without any renal insufficiency. Therefore, it seems that urinalysis of patients with WT along with sonography is necessary to determine renal insufficiency and the use of ultrasound alone to determine kidney insufficiency is not recommended.

Fluorescence-Guided Surgery and Novel Innovative Technologies for Improved Visualization in Pediatric Urology

Fluorescence-guided surgery (FGS), three-dimensional (3D) imaging technologies, and other innovative devices are rapidly revolutionizing the field of urology, providing surgeons with powerful tools for a more complete understanding of patient-specific anatomy. Today, several new intraoperative imaging technologies and cutting-edge devices are available in adult urology to assist surgeons in delivering personalized interventions. Their applications are also gradually growing in general pediatric surgery, where the detailed visualization of normal and pathological structures has the potential to significantly minimize perioperative complications and improve surgical outcomes. In the field of pediatric urology, FGS, 3D reconstructions and printing technologies, augmented reality (AR) devices, contrast-enhanced ultrasound (CEUS), and intraoperative magnetic resonance imaging (iMRI) have been increasingly adopted for a more realistic understanding of the normal and abnormal anatomy, providing a valuable insight to deliver customized treatments in real time. This narrative review aims to illustrate the main applications of these new technologies and imaging devices in the clinical setting of pediatric urology by selecting, with a strict methodology, the most promising articles published in the international scientific literature on this topic. The purpose is to favor early adoption and stimulate more research on this topic for the benefit of children.