Dong-Bum Kim

Mr. Dong-Bum Kim

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2025 in IEEE Access
Verified
Journal Article
Open access
DKDong-Bum Kim
Dong-Bum Kim
Jong-Ha LeeJong-Ha Lee
Jong-Ha Lee
Digital staining is an artificial intelligence-based technology that replaces the conventional staining process. This technology addresses the challenges associated with the traditional staining procedure, which is complex, time-consuming, and costly, as it relies heavily on manual labor. However, inconsistencies in staining color and quality, arising from variations in staining protocols caused by factors such as solution concentration, staining duration, patient-to-patient variability, and the type of scanner used, remain unresolved. To address this issue, a multi-domain digital staining method was employed. This study proposes a multi-hematoxylin and eosin (H&E) digital staining transformation method based on the phase image of fourier ptychographic microscopy (FPM) using a single model in bright-field microscopy (BM). The proposed model was trained by incorporating a mask and latent loss within the framework of the StarGAN algorithm. The model’s performance was quantitatively evaluated using a cell detection model trained on the MoNuSeg dataset. The results demonstrated improvements of 7.96% and 10.81% in Dice and Jaccard indices, respectively, compared to the CycleGAN model. These findings indicate that the proposed model achieves digital staining that closely replicates the conventional H&E staining method. Additionally, the visual assessment results revealed that the proposed method provides clearer differentiation between background and cytoplasmic boundaries. These results suggest that the proposed approach may effectively address quality degradation issues caused by the limitations of FPM data.

1 August 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
DKDong-Bum Kim
Dong-Bum Kim
JHJin-Chul Heo
Jin-Chul Heo
SASitara Afzal
Sitara Afzal
Jong-Ha LeeJong-Ha Lee
Jong-Ha Lee
Cracks indicate the deterioration of civil engineering structures, and early detection through regular inspection is crucial for structural safety. However, traditional manual inspection is time- and labor-intensive and depends heavily on the inspector’s expertise. Although deep learning-based crack detection has been actively studied, most prior studies focus on a single environment such as asphalt or concrete, and research integrating asphalt, concrete, and tunnel environments remains scarce. In this study, we propose a Dense U-Net++-based model trained on a unified dataset of drone-captured crack images across all three environments. The model combines dense connections with U-Net++’s nested skip pathways to mitigate the semantic gap in the encoder–decoder structure, enabling effective feature fusion and precise restoration of fine crack boundaries. Focal loss addresses the severe class imbalance between background and crack pixels, and area-based postprocessing suppresses spurious detections. The proposed method achieved a precision of 95.47%, a recall of 92.35%, an F1-score of 93.91%, and an IoU of 88.58%, outperforming both the baseline Dense U-Net++ and Mask R-CNN. Qualitative evaluation confirmed reliable detection across rough asphalt textures, striped concrete patterns, and low illumination in tunnels. These results indicate that the proposed framework achieves promising crack segmentation performance for automated structural inspection.

19 September 2026 in Biosensors
Verified
Journal Article
Open access
PDF file
DKDong-Bum Kim
Dong-Bum Kim
Jong-Ha LeeJong-Ha Lee
Jong-Ha Lee
Breast cancer is the most common cancer and the second leading cause of cancer-related death among women worldwide. For accurate diagnosis, pathologists use immunohistochemical (IHC) staining for biomarkers such as human epidermal growth factor receptor 2 (HER2) as an auxiliary test, in addition to hematoxylin and eosin (H&E) staining for evaluating tissue morphology. Traditional IHC staining is limited by high cost, time, and labor, with a shortage of pathologists to meet demand. In this work, we propose a digital HER2 IHC staining algorithm based on tumor masks. The proposed model builds on the Dual Contrastive Learning Generative Adversarial Network (DCLGAN), adding tumor mask loss, structural similarity index measure (SSIM) loss, and a modified identity loss that differentiates between active and inactive regions. Performance was quantitatively assessed by comparing HER2 scores using the Fréchet Inception Distance (FID) and a grade classification model. Compared to DCLGAN, the proposed model achieved a 27.2% decrease in FID and a 2.57% increase in soft accuracy. Visual evaluation further showed that it prevents yellow discoloration and suppresses nonspecific region staining seen in unsupervised learning. These results indicate that effective learning is achievable even with limited and unaligned data, thereby accelerating digital pathology workflows.