• Korean Journal of Radiology
• /
• 제21권6호
• /
• pp.660-669
• /
• 2020

Objective: To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. Materials and Methods: To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. Results: The sensitivity and specificity of automated segmentation for each segment (1-16 segments) were high (85.5-100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. Conclusion: We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.93-93
• /
• 2017

To develop rice cultivars with increased biomass and grain yield, superior lodging resistance is an essential trait. The new breeding approach can be adopted for the improvement of stem lodging resistance by enhancing culm strength. The resistance to breaking type lodging is attributed to bending moment of basal culm (M), which is composed of the section modulus (SM) and bending stress (BS). The resistance to the bending type lodging is attributed to flexural rigidity (FR) of stem, which is composed of the secondary moment of inertia (SMI) and Young's modulus (YM). Starch and cell wall components such as cellulose, hemicellulose and lignin also play a significant role in physical strength of culm, and thus affect lodging. Leaf Star has a superior lodging resistance due to its thick and stiff culm because of its high M and FR compared with Koshihikari. Furthermore, Leaf Star contains high densities of hemicellulose, cellulose and low lignin density in culm compared with Koshihikari. In this study, we performed QTL analysis for these traits associated with culm strength, using 94 recombinant inbred lines (RILs, $F_8$), derived from a cross between Leaf Star and Koshihikari. The SM in the RILs showed a continuous distribution. QTLs for SM were detected on chrs.2, 3 and 10. Leaf Star alleles increased SM on chrs. 2 and 3, but Koshihikari allele increased on chr.10. These QTLs overlapped with those QTLs identified using backcrossed inbred line derived from a cross between Chugoku 117 and Koshihikari, the parents of Leaf Star. The FR in Leaf Star was higher than that in Koshihikari due to the larger SMI and YM. 3 QTLs for SMI were detected on chrs.2, 3 and 10. Leaf Star alleles increased SMI on chrs.2 and 3, and Koshihikari alleles increased on chr.10. One QTL on chr.3 and two QTLs on chr.5 for hollocelulose content were detected with Leaf Star alleles contribution. Moreover, two QTLs were detected for hemicellulose density on chrs.3 and 5. Leaf Star allele increased hemicellulose density on chr.5, and Koshihikari allele increased on chr.3. Furthermore, two QTLs for cellulose density were detected on chr.5, and one QTL on chr.2. For starch content, one QTL on chr.3 and two QTLs on chr.5 with Leaf Star alleles contribution were detected. TULK-6 carrying a chromosome segment of Leaf Star on chr.5 in the Koshihikari genetic background showed higher densities of starch and hemicellulose than those in Koshihikari. These results suggest that the detected QTLs for culm strength could be utilized for the improvement of lodging resistance in rice by marker-assisted selection.