Philip Chikontwe Profile Photo

Philip Chikontwe

Research Fellow in Biomedical Informatics

Philip Chikontwe received his PhD from the Daegu Gyeongbuk Institute of Science and Technology (DGIST), South Korea, where he focused on designing machine learning algorithms that can reliably learn data representations from inexact or incomplete supervision with a primary focus on computational pathology. His research resulted in several contributions that improve automated disease detection and localization in histopathology images, equally extendable to other medical image modalities. Philip’s current research focus is investigating data efficient and integrative approaches for histopathology image analysis (multi-modal multi-omics), including rare central nervous system tumors detection.

Video domain adaptation for semantic segmentation using perceptual consistency matching.
Authors: Ullah I, An S, Kang M, Chikontwe P, Lee H, Choi J, Park SH.
Neural Netw
View full abstract on Pubmed
Enhanced Nuclei Segmentation and Classification via Category Descriptors in the SAM Model.
Authors: Luna M, Chikontwe P, Park SH.
Bioengineering (Basel)
View full abstract on Pubmed
Attention guided multi-scale cluster refinement with extended field of view for amodal nuclei segmentation.
Authors: Luna M, Chikontwe P, Nam S, Park SH.
Comput Biol Med
View full abstract on Pubmed
One-shot Federated Learning on Medical Data using Knowledge Distillation with Image Synthesis and Client Model Adaptation.
Authors: Kang M, Chikontwe P, Kim S, Jin KH, Adeli E, Pohl KM, Park SH.
Med Image Comput Comput Assist Interv
View full abstract on Pubmed
Content preserving image translation with texture co-occurrence and spatial self-similarity for texture debiasing and domain adaptation.
Authors: Kang M, Won D, Luna M, Chikontwe P, Hong KS, Ahn JH, Park SH.
Neural Netw
View full abstract on Pubmed
Dual Attention Relation Network With Fine-Tuning for Few-Shot EEG Motor Imagery Classification.
Authors: An S, Kim S, Chikontwe P, Park SH.
IEEE Trans Neural Netw Learn Syst
View full abstract on Pubmed
Weakly supervised segmentation on neural compressed histopathology with self-equivariant regularization.
Authors: Chikontwe P, Jung Sung H, Jeong J, Kim M, Go H, Jeong Nam S, Hyun Park S.
Med Image Anal
View full abstract on Pubmed
Dual attention multiple instance learning with unsupervised complementary loss for COVID-19 screening.
Authors: Chikontwe P, Luna M, Kang M, Hong KS, Ahn JH, Park SH.
Med Image Anal
View full abstract on Pubmed
Quantitative Assessment of Chest CT Patterns in COVID-19 and Bacterial Pneumonia Patients: a Deep Learning Perspective.
Authors: Kang M, Hong KS, Chikontwe P, Luna M, Jang JG, Park J, Shin KC, Park SH, Ahn JH.
J Korean Med Sci
View full abstract on Pubmed
Enhancement of Perivascular Spaces Using Densely Connected Deep Convolutional Neural Network.
Authors: Jung E, Chikontwe P, Zong X, Lin W, Shen D, Park SH.
IEEE Access
View full abstract on Pubmed