We.P34.B-32
QUANTITATIVE ANALYSIS OF RELIABILITY AND ROBUSTNESS OF DEEP LEARNING–BASED BREAST TUMOR SEGMENTATION IN ULTRASOUND IMAGING
Darshan Dathiya, Institute of Chemical Technology; Khashayar Namdar, University of Toronto; Ajit Kumar, Institute of Chemical Technology
Session:
We.P34: Image registration and segmentation Poster
Track:
Biomedical Imaging and Image Processing
Location:
Hall E; Bay B, Board #32
Presentation Time:
Wednesday, 29 July, 16:30 - 18:30
Presentation
Discussion
Resources
No resources available.
Session We.P34
We.P34.B-32: QUANTITATIVE ANALYSIS OF RELIABILITY AND ROBUSTNESS OF DEEP LEARNING–BASED BREAST TUMOR SEGMENTATION IN ULTRASOUND IMAGING
Darshan Dathiya, Institute of Chemical Technology; Khashayar Namdar, University of Toronto; Ajit Kumar, Institute of Chemical Technology
We.P34.B-33: IMPACT OF COUNTERFACTUAL-BASED DATA AUGMENTATION ON DERMOSCOPIC IMAGE CLASSIFICATION
Sho Hattori, Jinichiro Ogawa, Takashi Nagoka, Graduate School of Biology-Oriented Science and Technology, Kindai University
We.P34.B-34: Impact of Small Lesion Enlargement on Lesion Segmentation Accuracy
Jinichiro Ogawa, Sho Hattori, Takashi Nagaoka, Graduate School of Biology-Oriented Science and Technology, Kindai University
We.P34.B-35: AISSIA: A Domain-Generalizable Software Framework for Automated Multi-Label Segmentation of the Circle of Willis on CTA
Omar Aljubairi, Davy Vanderweyen, Kevin Whittingstall, Pascal Tétreault, Université de Sherbrooke
We.P34.B-36: FAIM-ECHO: HYBRID DEEP LEARNING AND PHYSIOLOGIC GRAPH-SEARCH FUSION FOR ROBUST LV SEGMENTATION IN ECHOCARDIOGRAPHY
Ruhi Sharmin, Purdue University; Sayeed Shafayet Chowdhury, Indiana University Indianapolis; Brett Meyers, Pavlos Vlachos, Purdue University
Resources
No resources available.