• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.505-516
• /
• 2022

Objective: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms. Materials and Methods: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated. Results: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001). Conclusion: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.

• Journal of Chest Surgery
• /
• v.19 no.1
• /
• pp.35-42
• /
• 1986

Prevention of thrombombolism after rosthetic cardiac valve replacement is essential for the patients. About 90% of patients are free of major and minor thromboembolic complications 5 year after replacement of cardiac valves with prosthetic devices when they are under control of anticoagulant therapy. Ticlopidine is a drug that alter platelet function to have an antithrombotic effect. It is an antiaggregating agent which inhibits primary platelet function to have an antithrombotic effect. It is an antiaggregating agent which inhibits primary platelet aggregation induced by ADP and increases the production of prostaglandin $D_{2}$. Aspirin in small doses inhibits platelet synthesis of prostaglandins by irreversibly blocking the enzyme cyclo-oxygenase. Platelet secretion and aggregation are impaired with Ticlopidine and Aspirin. the thromboembolic event sof 54 patient s who were treated with Ticlopidine and Aspirin after cardiac valve replacement were evaluated and compared with that of 79 patients who were treated with Wafarin and Aspirin after the same type of operation. The follow-up period ranged from 4 to 110 months (mean of 48 months). there were 11 major thromboembolic episodes including three deaths in the warfarin goup during mean follow-up period of 56 months. two cases of CVA and one hemoarthrosis were noted due to overdose of Warfarin. Inticlopidine group, there was only one fatal thromboembolic epdisode three month after mitral valve replacement during mean follow-up period of 18 months. Two episodes of hypermenorrhea resulting anemia ere noted in the ticlopidine group. We measured the parameters of platelet function in aggreagation curve of platelet with platelet aggregometer (chrono-log Aggregometer, Model No. 430) Aggregation test was performed with three final concentrations of epinephrine in 10 uM/L, ADP in 5uM/L. 28 patients with prosthetic cardiac valves and 35 healthy volunteers were subgrouped as follows to analyze the effect of antithrombotic drugs used. Group I ; 11 patients treated with 250-500 mg of ticlopidine and 0.5gm of Aspirin as a daily single dose after cardiac valve replacement (14 St. Jude Medical and 1 Carpentier-Edwards, 9 patients with atrial fibrillation among them) Group II ; 10 patients treated with 3-5 mg of Warfarin and 0.75 gm of Aspirin daily to prolong prothrombin time around 20 seconds for more than 6 months and single Aspirin dose was maintained afterward as a life-long regimes(3 St. Jude Medical, 1 Hall-Kaster and 7 Carpentier-Edwards valve, 9 patients in atrial fibrilation). Group III ; 7 patients who quit anticoagulant treatment (Warfarin + Aspirin) 6-12 months after the regime as group II (3 St. Jude Medical. 1 bjork-Shiley, 1 Hall-Kaster, 3 Carpentier-Edwards valve, 2 of them are with atrial fibrillation). Group IV ; 35 healthy vounteers (28 males and 7 females). The following results were obtained. 1. The mean maximal platelet aggregability in Group I induced by 10uM/L epinephrine was 15.6%, and 17.5 and 18.7% in BM in proportion to the induction by 5 and 10 uM/L ADP. 2. The mean maximal platelet aggregability in Group II induced by 10uM/L epinephrine was 16.5%, and 27.4 and 44.7% in BM in proportion to the induction by 5 and 10uM/L ADP. 3. The mean maximal platelet aggregability in group III induced by 10uM/L epinephrine was 65%, and 56.5 and 51.8% in BM in proportion to the induction by 5 and 10 uM/L ADP. 4. The mean maximal platelet aggregability in the normal subjects induced by 10 uM/L epinephrine was 64%, and 65 and 69% in Bm inproportion to the induction by 5 and 10 uM/L ADP. 5. Reversible change of platelet aggregation curve induced by 5 and 10uM/L was noted all of the patients in Group I. conclusion : Ticlopidine is an antiaggregating agent which inhibits primary platelet aggregation induced by ADP, and increases the production of prostaglandin $D_{2}$. Ticlopidine and Aspirin produced a significant inhibition of platelet in the presence of ADP and epinephrine in our study. Acccording to our brief experience, 250 mg of ticlopidine and low dose of Aspirin resulted synergistic superior effect to each drug alone in prevention of thromboembolism after prosthetic cardiac valve replacement.

• Clinical and Experimental Pediatrics
• /
• v.51 no.5
• /
• pp.518-522
• /
• 2008

Purpose : The purpose of this study was to investigate the prevalence of enuresis in association with voiding habits and socioeconomic status in elementary school children. Methods : A dynamic survey was done of 1,514 students from two elementary schools in Suwon, Korea in December 2006. Data regarding gender, age, height and weight, voiding habits, and monthly family incomes were gathered and analyzed to discover any correlation with the incidence of enuresis. The percentile value of height or weight was extrapolated from the standard population curve. Results : Among 1,514 children, 1,063 (70.2%) answered and returned the questionnaires. Overall, the prevalence of enuresis was 8.7% and there was no difference between the public (8.8%) and private school (8.7%). The family incomes of the students from the two schools differed greatly from each other, but there was no difference in the prevalence of enuresis between the two schools. Children with a habit of void-holding showed a higher prevalence of enuresis. No significant correlation was found between the prevalence of enuresis and the height and weight percentile of children. Experience with hospital visits was low among enuretic children (20.8%), suggesting that Korean parents tend to neglect treatment of enuresis for their children. The prevalence of enuresis decreased by 2.0% each year, as school children aged. Conclusion : The overall prevalence of enuresis among elementary school children in Suwon district was 8.7%. The 12.1% prevalence of enuresis at the seven years came down gradually, to be nil at the age of 13. Infrequent urination or void-holding was assumed to be one of the important factors causing enuresis in elementary school children.

• The Korean Journal of Nuclear Medicine
• /
• v.23 no.2
• /
• pp.175-181
• /
• 1989

Visual assessment of regional wall motion abnormality (RWMA) by gated blood pol scan (GBPS) serves as an useful parameter in the diagnosis, functional evaluation, and follow up in various clinical settings, but are still subject to some inherent limitations. On important problem may be the interobserver as well as intraobsever variation that may well be present due to the subjective nature of the interpretations. This study was carried out to determine the reliability and reproducibility of visual assessments made in GBPSs, and to observe the degree to which the results would be influenced by observer variation. Fifty two patients with coronary heart disease had resting GBPS and contrast ventriculography within 4 days appall. Contrast ventriculography-showed normal wall motion in 6 patients and the remaining 46 had RWMA in one or more segments. The anterior and left anterolateral views of all 52 GBPSs were analyzed by three independent observers, who selected from 5 scales, their level of confidence that there was RWMA in that segment. Reciever operating characteristic (ROC) curves for each analysis was plotted and the area under the curve $(\theta)$ was used as a parameter representing each observer's performance in his interpretations. The findings of contrast ventriculographies were used as the standard for RWMA. The apical and inferoapical segments showed the best correlation with contrast ventriculography ($\theta=0.90-0.94$, 0.81-0.94, respectively), and the inferior wall showed the poorest correlation $(\theta=0.70-0.74)$. The interpretations of the inferior, septal, apical, and posteroinferior, segments showed no difference between the observers, but there was significantly better performance in assessment by observer A compared to that by B or C for the anterolateral segments ($\theta=0.87$, 0.78, 0.76, respectively. p<0.01 for A vs B, p<0.05 for A vs C), as well as when all segments were considered altogether ($\theta=0.88$, 0.83, 0.82, respectively. both p<0.05). This was also true for the infero-apical segment between A and C ($\theta=0.09$, 0.81, p<0.05). The intraobserver variation, however, did not appear significant, with only the inferior segment for observer B showing any significant difference when observer A and B repeated the analysis 10 days latter. There was no difference in assessing dyskinesia, with all observers showing a high performance ($\theta=0.98$, 0.87, 0.97, respectively). The visual assessment of left ventricular ejection fraction by all three observers correlated well with the calculated value from a semiautomated method (Spearman's r = 0.91, 0.83, 0.83. p<0.01, p<0.05, p < 0.05). The assessment of LV and RV size also correlated well between the three observers (Kendall's w = 0.80, 0.51, p<0.01 for both left and right ventricles). The above findings suggest that RWMA visually assessed by GBPS correlates well with that done by contrast ventriculography. And although the observer's experience or skill may influence the results in certain segments, visual analysis of GBPS may serve as a reliable and reproducible means for evaluating ventricular function.