Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
2.
Jpn J Radiol ; 40(11): 1156-1165, 2022 Nov.
Article in English | MEDLINE | ID: mdl-35727458

ABSTRACT

PURPOSE: To develop a support vector machine (SVM) classifier using CT texture-based analysis in differentiating focal-type autoimmune pancreatitis (AIP) and pancreatic duct carcinoma (PD), and to assess the radiologists' diagnostic performance with or without SVM. MATERIALS AND METHODS: This retrospective study included 50 patients (20 patients with focal-type AIP and 30 patients with PD) who underwent dynamic contrast-enhanced CT. Sixty-two CT texture-based features were extracted from 2D images of the arterial and portal phase CTs. We conducted data compression and feature selections using principal component analysis (PCA) and produced the SVM classifier. Four readers participated in this observer performance study and the statistical significance of differences with and without the SVM was assessed by receiver operating characteristic (ROC) analysis. RESULTS: The SVM performance indicated a high performance in differentiating focal-type AIP and PD (AUC = 0.920). The AUC for all 4 readers increased significantly from 0.827 to 0.911 when using the SVM outputs (p = 0.010). The AUC for inexperienced readers increased significantly from 0.781 to 0.905 when using the SVM outputs (p = 0.310). The AUC for experienced readers increased from 0.875 to 0.912 when using the SVM outputs, however, there was no significant difference (p = 0.018). CONCLUSION: The use of SVM classifier using CT texture-based features improved the diagnostic performance for differentiating focal-type AIP and PD on CT.


Subject(s)
Autoimmune Pancreatitis , Carcinoma, Pancreatic Ductal , Pancreatic Neoplasms , Humans , Autoimmune Pancreatitis/diagnostic imaging , Retrospective Studies , Diagnosis, Differential , Carcinoma, Pancreatic Ductal/diagnostic imaging , Pancreatic Neoplasms/diagnostic imaging , Tomography, X-Ray Computed/methods , Machine Learning , Pancreatic Ducts , Radiologists , Pancreatic Neoplasms
3.
Surg Case Rep ; 6(1): 193, 2020 Aug 03.
Article in English | MEDLINE | ID: mdl-32748059

ABSTRACT

INTRODUCTION: Multiple gallbladders represent a rare congenital disorder, and coexistence with carcinoma is extremely rare, leading to a high possibility of misdiagnosis and surgical complications. In this study, a case was reported and the literature was reviewed. CASE PRESENTATION: An 80-year-old woman was diagnosed with acute cholecystitis via ultrasonography and was successfully treated with antibiotics. After the patient's biliary colic relapsed, she was referred to our hospital. Multiple imaging modalities revealed duplication of her gallbladder (H-type) and suggested coexistence with carcinoma. According to preoperative evaluations, we assumed the patient had stage IIIA disease, and cholecystectomy, cholangiography using a near-infrared ray vision system, and sectionectomy of segments 4a and 5 were performed. Contrary to the high standardized uptake values obtained by 18F-fluoro-2-deoxy-D-glucose positron emission tomography, gallbladder carcinoma was pathologically diagnosed as stage 0 mucosal cancer. Seven days after the operation, portal thrombosis of the posterior branch was revealed, and conservative therapy was indicated; satisfactory results were achieved. The patient was discharged 65 days after surgery. No recurrence was observed for 1 year after surgery. CONCLUSIONS: An extremely rare case of malignancy in a duplicated gallbladder was reported, and the literature was reviewed. Accurate estimations are feasible for diagnoses of multiple gallbladders, where correct evaluations are vital, especially in malignant cases. Because of the possibility of malignancy, resected accessory gallbladders should be scrutinized pathologically.

SELECTION OF CITATIONS
SEARCH DETAIL
...