Volumetric Assessment of Unaffected Parenchyma and Wilms' Tumors: Analysis of response to Chemotherapy and Surgery using a Semi-Automated Segmentation Algorithm in Children with Renal Neoplasms.

To present our proof-of-concept with semi-automatic image recognition/segmentation technology for calculation of tumor/parenchyma volume.We reviewed WTs between 2000-2018, capturing CT scan images at baseline, post-neoadjuvant chemotherapy (NaC) and post-operatively. Images were uploaded into MATLAB-3-D volumetric image processing software. The program was trained by 2 clinicians who supervised the demarcation of tumor and parenchyma, followed by automatic recognition and delineation of tumor margins on serial imaging, and differentiation from uninvolved renal parenchyma. Volume was automatically calculated for both.During the study period 98patients were identified. Of these, based on image quality and availability, 32(38 affected moieties) were selected. Most patients(65%) were female, diagnosed at50+37 months of age. NaC was employed in64%. Surgical management included27 radical and 11partial nephrectomies. Automated volume assessment demonstrated objective response to NAC for unilateral and bilateral tumors(68+/-20% and 53+/-39% respectively), as well as preservation on uninvolved parenchyma with partial nephrectomy(70+/-46 cm3 at presentation to57+/-41 cm3 post-surgery).Volumetric analysis is feasible and allows objective assessment of tumor and parenchyma volume in response to chemotherapy and surgery. Our data shows changes after therapy that may be otherwise difficult to quantify. Utilizing such technology may improve surgical planning, quantification of response to treatment, as well as serve as a tool to predict renal reserve and long-term changes in renal function.