1. Diagnostic Value of the Texture Analysis Parameters of Retroperitoneal Residual Masses on Computed Tomographic Scan after Chemotherapy in Non-Seminomatous Germ Cell Tumors.
- Author
-
Fournier, Clémence, Leguillette, Clémence, Leblanc, Eric, Le Deley, Marie-Cécile, Carnot, Aurélien, Pasquier, David, Escande, Alexandre, Taieb, Sophie, Ceugnart, Luc, and Lebellec, Loïc
- Subjects
RETROPERITONEUM ,GERMINOMA ,CONFIDENCE intervals ,CANCER chemotherapy ,OPERATIVE surgery ,UNNECESSARY surgery ,RETROSPECTIVE studies ,CONTRAST media ,FIBROSIS ,RISK assessment ,CANCER patients ,DESCRIPTIVE statistics ,COMPUTED tomography ,SENSITIVITY & specificity (Statistics) ,LOGISTIC regression analysis ,NECROSIS ,EVALUATION - Abstract
Simple Summary: Approximately 50% of residual masses requiring surgery after chemotherapy in non-seminomatous germ cell tumors consist of necrosis/fibrosis. We aimed to develop a score to predict the malignant character of these masses to avoid surgical overtreatment and the complications. In a retrospective study, we included 76 patients, with 149 residual masses. The score was constructed from the textures of the masses on a computed tomography scan with a free software. In conclusion, our score may help in the prediction of the malignant nature. However, these results are insufficient to simply select patients for surgery. After chemotherapy, patients with non-seminomatous germ cell tumors (NSGCTs) with residual masses >1 cm on computed tomography (CT) undergo surgery. However, in approximately 50% of cases, these masses only consist of necrosis/fibrosis. We aimed to develop a radiomics score to predict the malignant character of residual masses to avoid surgical overtreatment. Patients with NSGCTs who underwent surgery for residual masses between September 2007 and July 2020 were retrospectively identified from a unicenter database. Residual masses were delineated on post-chemotherapy contrast-enhanced CT scans. Tumor textures were obtained using the free software LifeX. We constructed a radiomics score using a penalized logistic regression model in a training dataset, and evaluated its performance on a test dataset. We included 76 patients, with 149 residual masses; 97 masses were malignant (65%). In the training dataset (n = 99 residual masses), the best model (ELASTIC-NET) led to a radiomics score based on eight texture features. In the test dataset, the area under the curve (AUC), sensibility, and specificity of this model were respectively estimated at 0.82 (95%CI, 0.69–0.95), 90.6% (75.0–98.0), and 61.1% (35.7–82.7). Our radiomics score may help in the prediction of the malignant nature of residual post-chemotherapy masses in NSGCTs before surgery, and thus limit overtreatment. However, these results are insufficient to simply select patients for surgery. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF