The diagnosis and outcome of Krukenberg tumors

Accurate diagnostic tools are crucial to distinguish patients with Krukenberg tumors from those with ovarian cancers before decision on initial management. To address this unmet need, we aimed to evaluate the diagnostic utility of clinical, biochemical, and radiographic factors in this patient population.

Patients with Krukenberg tumors or primary ovarian cancers were retrospectively identified from institutional cancer registry. Kaplan-Meier method and Cox proportional hazards models were used for survival analysis. Logistic regression evaluated clinical, biochemical, and radiographic factors; residual deep neural network model evaluated features in computed tomography images as predictors to distinguish Krukenberg tumors from ovarian cancers. Model performance was summarized as accuracy and area under the receiver operating characteristic curve (AUC).

This study included 214 patients with Krukenberg tumors with median age of 52 years. Among 104 (48.6%) patients with colorectal cancer, those who received palliative surgery had significantly higher median overall survival (48.1 versus 30.6 months, P=0.015) and progression-free survival (22.2 versus 6.7 months, P<0.001) than those with medical management only. The accuracy of radiology reports to make either diagnosis of Krukenberg tumors or primary ovarian cancers was 60.7%. In contrast, multivariable logistic regression model with age [odds ratio (OR) 2.98, P<0.001], carbohydrate antigen 125 (OR 1.57, P=0.004), and carcinoembryonic antigen (OR 0.03, P=0.031) had 87.5% [95% confidence interval (CI): 75.0-100.0%] accuracy with AUC 0.96 (95% CI: 0.87-1.00). The neural network model had 62.8% (95% CI: 51.8-74.5%) accuracy with AUC of 0.61 (95% CI: 0.53-0.72).

We developed a diagnostic model with clinical and biochemical features to distinguish Krukenberg tumors from primary ovarian cancers with promising accuracy.