Choi YW, et al. J Korean Med Sci. 2014 Nov;29(11):1493-1500. http://dx.doi.org/10.3346/jkms.2014.29.11.1493

This paper proposes an algorithm that improves ship detection accuracy using preprocessing and post-processing. To achieve this, high-resolution electro-optical satellite images with a wide range of shape and texture information were considered. The developed algorithms display the problem of unreliable detection of ships owing to clouds, large waves, weather influences, and shadows from large terrains. False detections in land areas with image information similar to that of ships are observed frequently. Therefore, this study involves three algorithms: global feature enhancement pre-processing (GFEP), multiclass ship detector (MSD), and false detected ship exclusion by sea land segmentation image (FDSESI). First, GFEP enhances the image contrast of high-resolution electro-optical satellite images. Second, the MSD extracts many primary ship candidates. Third, falsely detected ships in the land region are excluded using the mask image that divides the sea and land. A series of experiments was performed using the proposed method on a database of 1984 images. The database includes five ship classes. Therefore, a method focused on improving the accuracy of various ships is proposed. The results show a mean average precision (mAP) improvement from 50.55% to 63.39% compared with other deep learning-based detection algorithms.

PurposeFebrile neutropenia (FN) can cause suboptimal treatment and treatment-related mortality (TRM) in diffuse large B-cell lymphoma (DLBCL) patients treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisolone (R-CHOP). Materials and methodsWe conducted a prospective cohort study to evaluate the effectiveness of pegfilgrastim prophylaxis in DLBCL patients receiving R-CHOP, and we compared them with the PROCESS cohort (n=485). ResultsSince January 2015, 986 patients with DLBCL were enrolled. Pegfilgrastim was administered at least once in 930 patients (94.3%), covering 90.3% of all cycles. FN developed in 137 patients (13.9%) in this cohort (23.7% in the PROCESS cohort, p<0.001), and 4.2% of all cycles (10.2% in the PROCESS cohort, p<0.001). Dose delay was less common (≥3 days: 18.1% vs. 23.7%, p=0.015; ≥5 days: 12.0% vs. 18.3%, p=0.023) in this cohort than in the PROCESS cohort. The incidence of TRM (3.2% vs. 5.6%, p=0.047) and infection-related death (1.8% vs. 4.5%, p=0.004) was lower in this cohort than in the PROCESS cohort. The 4-year overall survival (OS) and progression-free survival (PFS) rates of the two cohorts were not different (OS: 73.0% vs. 71.9%, p=0.545; PFS: 69.5% vs. 68.8%, p=0.616). However, in patients aged ≥75 years, the 4-year OS and PFS rates were higher in this cohort than in the PROCESS cohort (OS: 49.6% vs. 33.7%, p=0.032; PFS: 44.2% vs. 30.3% p=0.047). Conclusion Pegfilgrastim prophylaxis is effective in the prevention of FN and infection-related death in DLBCL patients receiving R-CHOP, and it also improves OS in patients aged ≥75 years.

Choi YW, et al. J Korean Med Sci. 2015 Oct;30(10):1416-1422. http://dx.doi.org/10.3346/jkms.2015.30.10.1416

In this paper, a method using a semantic segmentation method based on edge-region focal loss was proposed to estimate the heading angle of resin in a catheter-extrusion process. The approach leveraged an improved semantic segmentation facilitated by this new loss function and principal component analysis. Accurate heading angle estimation was critical and depended on the precision of segmentation, demanding robust and precise segmentation even in the presence of external disturbances. The edge-region focal loss enhanceed segmentation by heavily weighting areas with ambiguous boundaries, which was particularly important in scenarios with various semantic elements in the background and foreground or near object boundaries. Image data were collected using RGB cameras to validate the effectiveness of this method. The method’s accuracy was affirmed by the mean intersection over union (mIoU) and mean absolute error measurements, achieving mean absolute errors of the angle and mIoU at 0.5002 and 0.8657, respectively. These results demonstrate the method’s suitability for monitoring the extrusion process. Furthermore, compared to traditional loss functions, the edge-region focal loss shows superior performance in segmenting adjacent boundary regions between the background and objects and maintains robustness in noisy environments.