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.

Imaging features and differences among the three primary malignant non-Wilms tumors in children.

BACKGROUND: The pathology, treatment and prognosis of malignant non-Wilms tumors (NWTs) are different, so it is necessary to differentiate these types of tumors. The purpose of this study was to review the clinical and imaging features of malignant NWTs and features of tumor metastasis. METHODS: We retrospectively analyzed the CT images of 65 pediatric patients with NWTs from March 2008 to July 2020, mainly including clear cell sarcoma of the kidney (CCSK), malignant rhabdomyoma tumor of the kidney (MRTK) and renal cell carcinoma (RCC). Available pretreatment contrast-enhanced abdominal CT examinations were reviewed. The clinical features of the patients, imaging findings of the primary mass, and locoregional metastasis patterns were evaluated in correlation with pathological and surgical findings. RESULTS: The study included CCSK (22 cases), MRTK (27 cases) and RCC (16 cases). There were no significant differences observed among the sex ratios of CCSK, MRTK and RCC (all P > 0.05). Among the three tumors, the onset age of MRTK patients was the smallest, while that of RCC patients was the largest (all P < 0.05). The tumor diameter of CCSK was larger than that of MRTK and RCC (all P < 0.001). For hemorrhage and necrosis, the proportion of MRTK patients was larger than that of the other two tumors (P = 0.017). For calcification in tumors, the proportion of calcification in RCC was highest (P = 0.009). Only MRTK showed subcapsular fluid (P < 0.001). In the arterial phase, the proportion of slight enhancement in RCC was lower than that in the other two tumors (P = 0.007), and the proportion of marked enhancement was the highest (P = 0.002). In the venous phase, the proportion of slight enhancement in RCC was lower than that in the other two tumors (P < 0.001). Only CCSK had bone metastasis. There was no liver and lung metastasis in RCC. CONCLUSIONS: NWTs have their own imaging and clinical manifestations. CCSK can cause vertebral metastasis, MRTK can cause subcapsular effusion, and RCC tumor density is usually high and calcification. These diagnostic points can play a role in clinical diagnosis.

Preparation of autoxidative water-reducible alkyd resins from waste polyethylene terephthalate.

In this paper, the waste polyethylene terephthalate (PET) was glycolysed by trimethylolpropane with zinc acetate as catalyst. The effects of different content glycolysis product of waste PET on the appearance, viscosity, particle size and molecular weight of autoxidative water-reducible alkyd resins and the corresponding film adhesion, flexibility, impact resistance, gloss, hardness and chemical resistance were studied. Meanwhile, experimental results were compared with commercial water-reducible alkyd and water-reducible alkyd without the glycolysis product of waste PET. The results show that the maximum concentration of PET in autoxidative water-reducible alkyd resins can reach 8.5 wt%, and the molecular weight, particle size and viscosity of water-reducible alkyd resin do not change much with the increase of PET concentration. The introduction of PET resulted in the viscosity of water-reducible alkyd resins being greater than that of water-reducible alkyd resin without PET; this is mainly because PET contains harder terephthalic acid monomer units. However, the particle size of water-reducible alkyd resins with waste PET is significantly lower than that of the water-reducible alkyd resin without PET; this is due to PET-free water-reducible alkyd resin containing more pentaerythritol with greater steric hindrance. In addition, the hardness of the water-reducible alkyd resin paint film (PET content is 8.5%) reaches 1H, which is higher than the hardness (HB) of the water-reducible alkyd resin paint film without PET and the commercial alkyd resin paint film, while the physical properties and chemical resistance of the former are comparable to those of the latter two kinds of paint films. Therefore, the use of waste PET in water-borne coatings systems not only reduces the cost of coatings, but also opens up a new market for recycled PET, which may contribute a promising method for management of waste PET.