2026-09-21T02:47:48Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/120132 2023-09-04 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Kindratenko, Volodymyr 2023-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms The student, Hangzheng Lin, accepted the attached license on 2023-04-27 at 23:51. The student, Hangzheng Lin, submitted this Thesis for approval on 2023-04-28 at 00:03. This Thesis was approved for publication on 2023-05-01 at 16:28. DSpace SAF Submission Ingestion Package generated from Vireo submission #19228 on 2023-09-01 at 16:55:50 Intranet: infrared-based transformers for 2D medical image segmentation Lin, Hangzheng 2023-05-01 Machine Learning Biomedical Infrared Imaging Segmentation Transformer Deep Learning Infrared (IR) spectroscopic imaging is widely employed in medical imaging applications due to its ability to capture both chemical and spatial information of biological tissues. In recent years, convolutional neural networks (CNNs), including the well-known U-Net model, have demonstrated impressive performance in biomedical image segmentation. However, the inherent locality of convolution limits the effectiveness of these models for encoding IR data, resulting in suboptimal performance in for some applications. In this work we propose an infrared-based transformer network named INTRANET for IR image segmentation. This novel model leverages the strength of the transformer encoders to segment infrared colon images effectively. Incorporating the skip-connection and transformer encoders, INTRANET overcomes the issue of pure convolution models, such as the difficulty of capturing long-range dependencies. We train several encoder-decoder models on a colon dataset of IR images to evaluate the existing convolution models and our proposed method. Our model achieves an AUC score of 0.9872, using 17 spectral bands for the segmentation task. Experimental results demonstrate that INTRANET significantly improves over the pure convolution models, especially when the input IR band number is limited. Text eng https://hdl.handle.net/2142/120132 Copyright 2023 Hangzheng Lin M.S. Thesis Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng