ABSTRACT
Objective: To explore the value of radiomics based on CT in differential diagnosis of benign and malignant polypoid lesions of the gallbladder (PLG). Methods: Totally 145 patients with PLG ≥1 cm who underwent abdominal enhanced CT examination and confirmed by pathology were collected. Among them, benign PLG was found in 82 cases, while malignant ones were detected in 63 cases. The patients were randomly divided into training set and test set. 3D ROIs of portal vein phase CT images were manually segmented using ITK-SNAP software. AK software was introduced to extract high-dimensional radiomics features. Then Lasso regression was used to reduce the dimension of the features. Logistic regression model was established and tested with R language software. Finally, the diagnostic performance of the model was evaluated with ROC. Results: Seven features related to benign and malignant identification of gallbladder polyps were obtained. The optimal threshold based on training set was 0.370. After the model was established, the threshold was used for test set with accuracy was 0.886, the specificity and sensitivity was 0.880 and 0.895, respectively, and AUC was 0.924. Conclusion: CT radiomics can effectively identify benign and malignant PLG with the maximum diameter ≥1 cm.
ABSTRACT
PURPOSE: Since the laparoscopic cholecystectomy became an usual procedure, operative indications of the gallbladder polyps have had the tendency to enlarge. There are no precise management plan about the gallbladder polyps which is not included in the accepted operative indications. Therefore a management plan may be required for the patients who has gallbladder polyps which is not accepted operative indications. METHODS: We retrospectively analysed 106 patients with gallbladder polyps who were diagnosed preoperatively by ultrasound and CT from January 1991 to January 2005. Our operation indications are polyp above 10 mm, symptomatic polyp, sessile polyp, coincidence of stone, focal thickening of gallbladder wall, diffuse wall thickening and detection during other operations. The gallbladder polyps which were suspected to the gallbladder cancer strongly on radiologic studies and polyps above 20 mm size were excluded in this studies. RESULTS: Among the 106 patients, 87 patients underwent operation, and polypoid lesions disappeared during the follow-up period in 3 patients, and 16 patients are on regular follow up. Fifty-six cases received operation with accepted operative indications, and the thirty-one cases underwent operation by the patient's demand. Two groups showed significant difference in true polyp on pathological diagnosis (P < 0.001). There was 16.07% true polyp in opertive indication based 56 patients and no true polyp in patient's demanded 31 cases. The pathologic diagnoses were cholesterol polyp in 27 patients (87.15%), no polyp in 2 patients, adenomatous hyperplasia in 2 patients. The correlation of the polyp size and pathologic diagnosis was an inverse relation to the polyp size and incidence of pseudopolyp (P=0.014). CONCLUSION: We propose that the 6-month-interval follow-up observation is fully safe for polyps sized below 10 mm and not included in accepted operative indications.