RESUMO
BACKGROUND/AIMS: This study aims to compare polyp detection performance of "Deep-GI," a newly developed artificial intelligence (AI) model, to a previously validated AI model computer-aided polyp detection (CADe) using various false positive (FP) thresholds and determining the best threshold for each model. METHODS: Colonoscopy videos were collected prospectively and reviewed by three expert endoscopists (gold standard), trainees, CADe (CAD EYE; Fujifilm Corp.), and Deep-GI. Polyp detection sensitivity (PDS), polyp miss rates (PMR), and false-positive alarm rates (FPR) were compared among the three groups using different FP thresholds for the duration of bounding boxes appearing on the screen. RESULTS: In total, 170 colonoscopy videos were used in this study. Deep-GI showed the highest PDS (99.4% vs. 85.4% vs. 66.7%, p<0.01) and the lowest PMR (0.6% vs. 14.6% vs. 33.3%, p<0.01) when compared to CADe and trainees, respectively. Compared to CADe, Deep-GI demonstrated lower FPR at FP thresholds of ≥0.5 (12.1 vs. 22.4) and ≥1 second (4.4 vs. 6.8) (both p<0.05). However, when the threshold was raised to ≥1.5 seconds, the FPR became comparable (2 vs. 2.4, p=0.3), while the PMR increased from 2% to 10%. CONCLUSION: Compared to CADe, Deep-GI demonstrated a higher PDS with significantly lower FPR at ≥0.5- and ≥1-second thresholds. At the ≥1.5-second threshold, both systems showed comparable FPR with increased PMR.
RESUMO
Background: No study has compared EUS-guided radiofrequency ablation (EUS-RFA) plus systemic chemotherapy (CMT) with CMT alone for unresectable pancreatic ductal adenocarcinoma. Methods: This study compared the results of treatment in patients receiving EUS-RFA plus concomitant CMT (group A; n = 14) with those receiving CMT (group B; n = 14) as a pilot study. Results: From July 2017 to August 2018, 4 and 2 patients from groups A and B, respectively, withdrew from the study because of progression of the disease. In total, 10 and 12 patients from groups A and B, respectively, completed the study. All 30 EUS-RFA procedures were successful. Mean maximal tumor diameter before treatment of group A (n = 10) versus B (n = 12) was 62.2 ± 21.0 versus 50.5 ± 22.0 mm, respectively (P = not significant). After treatment, no statistically significant difference in mean maximal tumor diameter was found between both groups. However, in group B, mean maximal tumor diameter was significantly increased from 50.5 ± 22.0 to 56.3 ± 18.7 mm, respectively (P = 0.017). Tumor necrosis occurred in group A versus B at 10 of 10 (100%) versus 6 of 12 (50%) patients, respectively (P = 0.014). After treatment, group A patients could reduce the mean narcotic pain drug dosage at 26.5 mg of morphine equivalent per day (from 63.6 to 37.1 mg, P = 0.022), whereas group B patients could not reduce the dosage of pain-controlled medication. No statistically significant difference in 6-month mortality rate was found. In group A, 1 procedure-related nonsevere adverse event (n = 1 of 30 [3.3%]) occurred in 1 patient (n = 1 of 14 [7.1%]). Conclusions: In this study, the mean tumor diameter of group B was significantly increased after the treatment. Group A had a significantly higher rate of necrosis of tumor and required less narcotic.