No abstract

Accurate detection of pneumothorax on chest radiographs, the most common complication of percutaneous transthoracic needle biopsies (PTNBs), is not always easy in practice. A computer-aided detection (CAD) system may help detect pneumothorax.Purpose: To investigate whether a deep learning-based CAD system can improve detection performance for pneumothorax on chest radiographs after PTNB in clinical practice. Materials and Methods:A CAD system for post-PTNB pneumothorax detection on chest radiographs was implemented in an institution in February 2020. This retrospective cohort study consecutively included chest radiographs interpreted with CAD assistance (CAD-applied group; February 2020 to November 2020) and those interpreted before implementation (non-CAD group; January 2018 to January 2020). The reference standard was defined by consensus reading by two radiologists. The diagnostic accuracy for pneumothorax was compared between the two groups using generalized estimating equations. Matching was performed according to whether the radiograph reader and PTNB operator were the same using the greedy method.Results: A total of 676 radiographs from 655 patients (mean age: 67 years 6 11; 390 men) in the CAD-applied group and 676 radiographs from 664 patients (mean age: 66 years 6 12; 400 men) in the non-CAD group were included. The incidence of pneumothorax was 18.2% (123 of 676 radiographs) in the CAD-applied group and 22.5% (152 of 676 radiographs) in the non-CAD group (P = .05). The CAD-applied group showed higher sensitivity (85.4% vs 67.1%), negative predictive value (96.8% vs 91.3%), and accuracy (96.8% vs 92.3%) than the non-CAD group (all P , .001). The sensitivity for a small amount of pneumothorax improved in the CAD-applied group (pneumothorax of ,10%: 74.5% vs 51.4%, P = .009; pneumothorax of 10%-15%: 92.7% vs 70.2%, P = .008). Among patients with pneumothorax, 34 of 655 (5.0%) in the non-CAD group and 16 of 664 (2.4%) in the CAD-applied group (P = .009) required subsequent drainage catheter insertion. Conclusion:A deep learning-based computer-aided detection system improved the detection performance for pneumothorax on chest radiographs after lung biopsy.

No abstract

Purpose: This study aimed to assess the technical performance of ElastQ Imaging compared with ElastPQ and to investigate the correlation between liver stiffness (LS) values obtained using these two techniques. Methods: This retrospective study included 249 patients who underwent LS measurements using both ElastPQ and ElastQ Imaging equipped on the same machine. The applicability, repeatability (coefficient of variation [CV]), acquisition time, and LS values were compared using the chisquare or Wilcoxon signed-rank tests. In the development group, the correlation between the LS values obtained by the two techniques was assessed with Spearman correlation coefficients and linear regression analysis. In the validation group, the agreement between the estimated and real LS values was evaluated using a Bland-Altman plot. Results: ElastQ Imaging had higher applicability (94.0% vs. 78.3%, P<0.001) and higher repeatability, with a lower median CV (0.127 vs. 0.164, P<0.001) than did ElastPQ. The median acquisition time of ElastQ Imaging was significantly shorter than that of ElastPQ (45.5 seconds vs. 96.5 seconds, P<0.001). The median LS value obtained using ElastQ Imaging was significantly higher than that obtained using ElastPQ (5.60 kPa vs. 5.23 kPa, P<0.001). The LS values between the two techniques exhibited a strong positive correlation (r=0.851, P<0.001) in the development group. The mean difference and 95% limits of agreement were 0.0 kPa (-3.9 to 3.9 kPa) in the validation group. Conclusion: ElastQ Imaging may be more reliable and faster than ElastPQ, with strongly correlated LS measurements.

ObjectiveTo evaluate the effectiveness of computed tomography (CT) Hounsfield unit histogram analysis (HUHA) in postoperative pancreatic fistula (PF) prediction.Materials and MethodsFifty-four patients (33 males and 21 females; mean age, 65.6 years; age range, 37–89 years) who had undergone preoperative CT and pancreaticoduodenectomy were included in this retrospective study. Two radiologists measured mean CT Hounsfield unit (CTHU) values by drawing regions of interest (ROIs) at the level of the pancreaticojejunostomy site on preoperative pre-contrast images. The HUHA values were arbitrarily divided into three categories, comprising HUHA-A ≤ 0 HU, 0 HU < HUHA-B < 30 HU, and HUHA-C ≥ 30 HU. Each HUHA value within the ROI was calculated as a percentage of the entire area using commercial 3-dimensional analysis software. Pancreas texture was evaluated as soft or hard by manual palpation.ResultsFifteen patients (27.8%) had clinically relevant PFs. The PF group had significantly higher HUHA-A (p < 0.01) and significantly lower mean CTHU (p < 0.01) values than those of the non-PF group. The HUHA-A value had a moderately strong correlation with PF occurrence (r = 0.60, p < 0.01), whereas the mean CTHU had a weak negative correlation with PF occurrence (r = −0.27, p < 0.01). The HUHA-A and mean CTHU areas under the curve (AUCs) for predicting PF occurrence were 0.86 and 0.65, respectively, with significant difference (p < 0.01). The HUHA-A and mean CTHU AUCs for predicting pancreatic softness were 0.86 and 0.64, respectively, with significant difference (p < 0.01).ConclusionThe HUHA-A values on preoperative pre-contrast CT images demonstrate a strong correlation with PF occurrence.