Boram Song

Boram Song

Auto-generated profile, based on publicly available information

Boram Song

Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Korea

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
9 February 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
TDTan N. N. Doan
Tan N. N. Doan
BSBoram Song
Boram Song
TVTrinh T. L. Vuong
Trinh T. L. Vuong
KKKyungeun Kim
Kyungeun Kim
JKJin T. Kwak
Jin T. Kwak
Automated nuclei segmentation and classification are the keys to analyze and understand the cellular characteristics and functionality, supporting computer-aided digital pathology in disease diagnosis. However, the task still remains challenging due to the intrinsic variations in size, intensity, and morphology of different types of nuclei. Herein, we propose a self-guided ordinal regression neural network for simultaneous nuclear segmentation and classification that can exploit the intrinsic characteristics of nuclei and focus on highly uncertain areas during training. The proposed network formulates nuclei segmentation as an ordinal regression learning by introducing a distance decreasing discretization strategy, which stratifies nuclei in a way that inner regions forming a regular shape of nuclei are separated from outer regions forming an irregular shape. It also adopts a self-guided training strategy to adaptively adjust the weights associated with nuclear pixels, depending on the difficulty of the pixels that is assessed by the network itself. To evaluate the performance of the proposed network, we employ large-scale multi-tissue datasets with 276349 exhaustively annotated nuclei. We show that the proposed network achieves the state-of-the-art performance in both nuclei segmentation and classification in comparison to several methods that are recently developed for segmentation and/or classification.

26 July 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
TVTrinh T. L. Vuong
Trinh T. L. Vuong
BSBoram Song
Boram Song
KKKyungeun Kim
Kyungeun Kim
YCYong M. Cho
Yong M. Cho
JKJin T. Kwak
Jin T. Kwak
Multi-scale approaches have been widely studied in pathology image analysis. These offer an ability to characterize tissues in an image at various scales, in which the tissues may appear differently. Many of such methods have focused on extracting multi-scale hand-crafted features and applied them to various tasks in pathology image analysis. Even, several deep learning methods explicitly adopt the multi-scale approaches. However, most of these methods simply merge the multi-scale features together or adopt the coarse-to-fine/fine-to-coarse strategy, which uses the features one at a time in a sequential manner. Utilizing the multi-scale features in a cooperative and discriminative fashion, the learning capabilities could be further improved. Herein, we propose a multi-scale approach that can identify and leverage the patterns of the multiple scales within a deep neural network and provide the superior capability of cancer classification. The patterns of the features across multiple scales are encoded as a binary pattern code and further converted to a decimal number, which can be easily embedded in the current framework of the deep neural networks. To evaluate the proposed method, multiple sets of pathology images are employed. Under the various experimental settings, the proposed method is systematically assessed and shows an improved classification performance in comparison to other competing methods.

25 August 2023 in Medical Image Analysis
Verified
Journal Article
Open access
SASyed Farhan Abbas
Syed Farhan Abbas
TVTrinh Thi Le Vuong
Trinh Thi Le Vuong
KKKyungeun Kim
Kyungeun Kim
BSBoram Song
Boram Song
JKJin Tae Kwak
Jin Tae Kwak
In pathology, cancer grading is crucial for patient management and treatment. Recent deep learning methods, based upon convolutional neural networks (CNNs), have shown great potential for automated and accurate cancer diagnosis. However, these do not explicitly utilize tissue/cellular composition, and thus difficult to incorporate the existing knowledge of cancer pathology. In this study, we propose a multi-cell type and multi-level graph aggregation network (MMGA-Net) for cancer grading. Given a pathology image, MMGA-Net constructs multiple cell graphs at multiple levels to represent intra- and inter-cell type relationships and to incorporate global and local cell-to-cell interactions. In addition, it extracts tissue contextual information using a CNN. Then, the tissue and cellular information are fused to predict a cancer grade. The experimental results on two types of cancer datasets demonstrate the effectiveness of MMGA-Net, outperforming other competing models. The results also suggest that the information fusion of multiple cell types and multiple levels via graphs is critical for improved pathology image analysis.

7 March 2024 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Open access
DBDoanh C. Bui
Doanh C. Bui
BSBoram Song
Boram Song
KKKyungeun Kim
Kyungeun Kim
JKJin Tae Kwak
Jin Tae Kwak
Multi-class cancer classification has been extensively studied in digital and computational pathology due to its importance in clinical decision-making. Numerous computational tools have been proposed for various types of cancer classification. Many of them are built based on convolutional neural networks. Recently, Transformer-style networks have shown to be effective for cancer classification. Herein, we present a hybrid design that leverages both convolutional neural networks and transformer architecture to obtain superior performance in cancer classification. We propose a dual-branch dual-task adaptive cross-weight feature fusion network, called DAX-Net, which exploits heterogeneous feature representations from the convolutional neural network and Transformer network, adaptively combines them to boost their representation power, and conducts cancer classification as categorical classification and ordinal classification. For an efficient and effective optimization of the proposed model, we introduce two loss functions that are tailored to the two classification tasks. To evaluate the proposed method, we employed colorectal and prostate cancer datasets, of which each contains both in-domain and out-of-domain test sets. For colorectal cancer, the proposed method obtained an accuracy of 88.4%, a quadratic kappa score of 0.945, and an F1 score of 0.831 for the in-domain test set, and 84.4%, 0.910, and 0.768 for the out-of-domain test set. For prostate cancer, it achieved an accuracy of 71.6%, a kappa score of 0.635, and an F1 score of 0.655 for the in-domain test set, 79.2% accuracy, 0.721 kappa score, and 0.686 F1 score for the first out-of-domain test set, and 58.1% accuracy, 0.564 kappa score, and 0.493 F1 score for the second out-of-domain test set. It is worth noting that the performance of the proposed method outperformed other competitors by significant margins, in particular, with respect to the out-of-domain test sets. The experimental results demonstrate that the proposed method is not only accurate but also robust to varying conditions of the test sets in comparison to several, related methods. These results suggest that the proposed method can facilitate automated cancer classification in various clinical settings.

15 January 2024 in Cancer Research and Treatment
Verified
Journal Article
Open access
PDF file
BSBoram Song
Boram Song
SLSeok Hyun Lee
Seok Hyun Lee
JPJeong Hwan Park
Jeong Hwan Park
KMKyung Chul Moon
Kyung Chul Moon
Purpose This study aimed to evaluate the molecular features of clear cell adenocarcinoma (CCA) of the urinary tract and investigate its pathogenic pathways and possible actionable targets.Materials and Methods We retrospectively collected the data of patients with CCA between January 1999 and December 2016; the data were independently reviewed by two pathologists. We selected five cases of urinary CCA, based on the clinicopathological features. We analyzed these five cases by whole exome sequencing (WES) and subsequent bioinformatics analyses to determine the mutational spectrum and possible pathogenic pathways.Results All patients were female with a median age of 62 years. All tumors were located in the urethra and showed aggressive behavior with disease progression. WES revealed several genetic alterations, including driver gene mutations (AMER1, ARID1A, CHD4, KMT2D, KRAS, PBRM1, and PIK3R1) and mutations in other important genes with tumor-suppressive and oncogenic roles (CSMD3, KEAP1, SMARCA4, and CACNA1D). We suggest putative pathogenic pathways (chromatin remodeling pathway, mitogen-activated protein kinase signaling pathway, phosphoinositide 3-kinase/AKT/mammalian target of rapamycin pathway, and Wnt/β-catenin pathway) as candidates for targeted therapies.Conclusion Our findings shed light on the molecular background of this extremely rare tumor with poor prognosis and can help improve treatment options.

3 July 2025 in Medical Image Analysis
Verified
Journal Article
Open access
JLJu Cheon Lee
Ju Cheon Lee
KBKeunho Byeon
Keunho Byeon
BSBoram Song
Boram Song
KKKyungeun Kim
Kyungeun Kim
JKJin Tae Kwak
Jin Tae Kwak
In computational pathology, cancer grading has been mainly studied as a categorical classification problem, which does not utilize the ordering nature of cancer grades such as the higher the grade is, the worse the cancer is. To incorporate the ordering relationship among cancer grades, we introduce a differential ordinal learning problem in which we define and learn the degree of difference in the categorical class labels between pairs of samples by using their differences in the feature space. To this end, we propose a transformer-based neural network that simultaneously conducts both categorical classification and differential ordinal classification for cancer grading. We also propose a tailored loss function for differential ordinal learning. Evaluating the proposed method on three different types of cancer datasets, we demonstrate that the adoption of differential ordinal learning can improve the accuracy and reliability of cancer grading, outperforming conventional cancer grading approaches. The proposed approach should be applicable to other diseases and problems as they involve ordinal relationship among class labels.