RESUMEN
Objective To assess the effect of ultrasonic thyroid artificial intelligence(AI)-assisted diagnostic system(AI-assisted diagnostic system)for diagnosing medullary thyroid carcinoma(MTC)compared with different physicians and taken papillary thyroid carcinoma(PTC)as the controls.Methods Totally 63 MTC,70 PTC and 62 benign thyroid nodules confirmed by pathology were enrolled.AI-assisted diagnostic system was utilized to analyze thyroid nodules and identify the likelihood of malignancy,and the probability value threshold was set at ≥0.40.All thyroid nodules were retrospectively reviewed and categorized by 3 physicians(1 senior physician,1 attending physician and 1 junior physician)according to Chinese thyroid imaging reporting and data system(C-TIRADS).The efficacy of AI-assisted diagnostic system and physicians for diagnosing MTC and PTC were evaluated.Results AI-assisted diagnostic system showed lower sensitivity,specificity,positive predictive value,negative predictive value,accuracy,and area under the curve(AUC)for diagnosing MTC and PTC compared with physicians.Significant differences of AUC were found between senior physician and AI-assisted diagnostic system,as well as between attending physician and AI-assisted diagnostic system for diagnosing MTC and PTC(all P＜0.01),while no significant difference of AUC was between junior physicians and AI-assisted diagnostic system(both P＞0.05).The sensitivity,specificity,positive predictive value,negative predictive value,accuracy and AUC for AI-assisted diagnostic system for diagnosing MTC were all lower than those for diagnosing PTC,but the AUC was not significantly different(P＞0.05).Conclusion Ultrasonic thyroid AI-assisted diagnostic system had relatively high value for diagnosing MTC.
RESUMEN
Objective To explore the value of 2017 thyroid imaging reporting and data system (TI-RADS) suggested by American College of Radiology in diagnosis of benign and malignant thyroid nodules. Methods According to 2017 TI-RADS, the sonographic features of 1 109 pathologically diagnosed thyroid nodules in 1 039 patients were retrospectively analyzed. Taken coarse needle biopsy or surgical pathology as the gold standards, the diagnostic efficacy of 2017 TI-RADS for different types of nodules was analyzed. Results Of 1 109 nodules, 551 were benign and 558 were malignant. The composition, echogenicity, aspect ratio, boundary and calcification were statistically different between benign and malignant nodules (all P<0.05). The probability of malignancy in nodules with a classification of TI-RADS 2, 3, 4 and 5 was 0, 5.45% (3/55), 22.29% (39/175) and 58.84% (516/877), respectively, which had statistical difference (P<0.001). When TI-RADS classification were larger than 4, the diagnostic sensitivity, specificity, accuracy, positive predictive value and negative predictive value was 99.46% (555/558), 9.80% (54/551), 54.91% (609/1 109), 52.76% (555/1 052) and 94.74% (54/57), respectively. Conclusion 2017 TI-RADS classification is based on the morphology and maximum diameter management of thyroid nodules, demonstrating clinical application value in evaluating malignant nodules, but the specificity is low, therefore needing further improvement.
RESUMEN
Objective To investigate the pattern of nodal recurrence after curative resection in adenocarcinoma of the gastroesophageal junction ( AGE ) , and to provide a basis for delineation of the radiation range in the high-risk lymphatic drainage area.Methods A retrospective analysis was performed in 78 patients with locally advanced AGE who were newly treated in our hospital from January 2009 to December 2013 and had complete clinical data.All patients received curative resection and were pathologically diagnosed with stage T3/T4 or N (+) AGE.Those patients were also diagnosed with SiewertⅡor Ⅲ AGE by endoscopy, upper gastroenterography, macroscopic examination during operation, and pathological specimens.None of the patients received preoperative or postoperative radiotherapy.All patients were diagnosed by imaging with postoperative nodal recurrence.The computed tomography images of those patients were accessible and had all the recurrence sites clearly and fully displayed.Results The median time to recurrence was 10 months ( 1-48 months) , and 90%of the recurrence occurred within 2 years after surgery.The lymph nodes with the highest risk of recurrence were No.16b1( 39%) , No.16a2( 37%) , No.9 (30%), and No.11p (26%), respectively.There was no significant difference in the recurrence rate within each lymphatic drainage area between patients with SiewertⅡandⅢAGE ( P=0.090-1.000) .The lymph nodes with the most frequent recurrence were No.16b1, No.16a2, No.9, No.16b2, No.11p, and No.7 in patients with stage N3 AGE and No.11p, No.16b1, No.16a2, No.9, No.8, and No.7 in patients with stage non-N3 AGE.Patients with stage N3 AGE had a significantly higher recurrence rate in the para-aortic regions (No.16a2-b2) than those with stage non-N3 AGE (67%vs.33%, P=0.004, OR=4.00, 95% CI=1.54-10.37) .Conclusions The lymph nodes with the highest risk of recurrence are located in the celiac artery, proximal splenic artery, and retroperitoneal areas ( No.16a2 and No.16b1) in patients with SiewertⅡorⅢlocally advanced AEG.Moreover, patients with stage N3 AGE have a higher risk of retroperitoneal recurrence.The above areas should be involved in target volume delineation for postoperative radiotherapy.