• 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.

• Korean Journal of Environmental Agriculture
• /
• v.34 no.4
• /
• pp.274-281
• /
• 2015

BACKGROUND: A lasting release of low levels of persistence chemicals including pesticides and pharmaceuticals into river has a bad influence on aquatic ecosystems and humans. The present study monitored pesticide residues in the Yeongsan and Seomjin river basins and their tributaries as a fundamental study for water quality standard of pesticides.METHODS AND RESULTS: Nine pesticides(aldicarb, carbaryl, carbofuran, chlorpyrifos, 2,4-D, MCPA, methomyl, metolachlor, and molinate) were determined from water samples using SPE-Oasis HLB(pH 2) and LC/MS/MS. Validation of the method was conducted through matrix-matched internal calibration curve, method detection limit(MDL), limit of quantification(LOQ), accuracy, precision, and recovery. MDLs of all pesticides satisfied the GV/10 values. Linearity(r²) was 0.9965- 0.9999, and a percentage of accuracy, precision, and recovery was 89.4-113.6%, 3.1-14.0%, and 90.8-106.2%, respectively. All pesticides exclusive of aldicarb were determined in the river samples, and there was a connection between the positive monitoring results and agricultural use of the pesticides.CONCLUSION: Monitoring outcomes of the present study implied that pesticides were a possible non-point pollutant source in the Yeongsan and Seomjin river basins and tributaries. Therefore, it is required to produce and accumulate more monitoring results on pesticides in river waters to set water quality standards, finally to preserve aquatic ecosystems.