High-Quality Medical Image Generation from Free-hand Sketch

Generating medical images from human-drawn free-hand sketches holds promise for various important medical imaging applications. Due to the extreme difficulty in collecting free-hand sketch data in the medical domain, most deep learning-based methods have been proposed to generate medical images from...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cap, Quan Huu, Fukuda, Atsushi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Cap, Quan Huu
Fukuda, Atsushi
description Generating medical images from human-drawn free-hand sketches holds promise for various important medical imaging applications. Due to the extreme difficulty in collecting free-hand sketch data in the medical domain, most deep learning-based methods have been proposed to generate medical images from the synthesized sketches (e.g., edge maps or contours of segmentation masks from real images). However, these models often fail to generalize on the free-hand sketches, leading to unsatisfactory results. In this paper, we propose a practical free-hand sketch-to-image generation model called Sketch2MedI that learns to represent sketches in StyleGAN's latent space and generate medical images from it. Thanks to the ability to encode sketches into this meaningful representation space, Sketch2MedI only requires synthesized sketches for training, enabling a cost-effective learning process. Our Sketch2MedI demonstrates a robust generalization to free-hand sketches, resulting in high-quality and realistic medical image generations. Comparative evaluations of Sketch2MedI against the pix2pix, CycleGAN, UNIT, and U-GAT-IT models show superior performance in generating pharyngeal images, both quantitative and qualitative across various metrics.
doi_str_mv 10.48550/arxiv.2402.00353
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2402_00353</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2402_00353</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-15ad20a73c084519d94728cb99a160636ca8566440a400d7393b8d301c5903063</originalsourceid><addsrcrecordid>eNotj81OAjEURrtxYdAHcGVfoMPt3LbThhUh8pNAjJH95NIWpmFmMHU08vYCujqbLyffYexJQqGs1jCm_JO-i1JBWQCgxns2WaZDI96-qE3DmW9iSJ5avuroEPki9jHTkE493-dTx-c5RtFQH_j7MQ6-eWB3e2o_4-M_R2w7f9nOlmL9uljNpmtBpkIhNYUSqEIPVmnpglNVaf3OOZIGDBpPVhujFJACCBU63NmAIL12gJfBiD3_aW_v64-cOsrn-lpR3yrwF4T4Pz8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>High-Quality Medical Image Generation from Free-hand Sketch</title><source>arXiv.org</source><creator>Cap, Quan Huu ; Fukuda, Atsushi</creator><creatorcontrib>Cap, Quan Huu ; Fukuda, Atsushi</creatorcontrib><description>Generating medical images from human-drawn free-hand sketches holds promise for various important medical imaging applications. Due to the extreme difficulty in collecting free-hand sketch data in the medical domain, most deep learning-based methods have been proposed to generate medical images from the synthesized sketches (e.g., edge maps or contours of segmentation masks from real images). However, these models often fail to generalize on the free-hand sketches, leading to unsatisfactory results. In this paper, we propose a practical free-hand sketch-to-image generation model called Sketch2MedI that learns to represent sketches in StyleGAN's latent space and generate medical images from it. Thanks to the ability to encode sketches into this meaningful representation space, Sketch2MedI only requires synthesized sketches for training, enabling a cost-effective learning process. Our Sketch2MedI demonstrates a robust generalization to free-hand sketches, resulting in high-quality and realistic medical image generations. Comparative evaluations of Sketch2MedI against the pix2pix, CycleGAN, UNIT, and U-GAT-IT models show superior performance in generating pharyngeal images, both quantitative and qualitative across various metrics.</description><identifier>DOI: 10.48550/arxiv.2402.00353</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2402.00353$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2402.00353$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Cap, Quan Huu</creatorcontrib><creatorcontrib>Fukuda, Atsushi</creatorcontrib><title>High-Quality Medical Image Generation from Free-hand Sketch</title><description>Generating medical images from human-drawn free-hand sketches holds promise for various important medical imaging applications. Due to the extreme difficulty in collecting free-hand sketch data in the medical domain, most deep learning-based methods have been proposed to generate medical images from the synthesized sketches (e.g., edge maps or contours of segmentation masks from real images). However, these models often fail to generalize on the free-hand sketches, leading to unsatisfactory results. In this paper, we propose a practical free-hand sketch-to-image generation model called Sketch2MedI that learns to represent sketches in StyleGAN's latent space and generate medical images from it. Thanks to the ability to encode sketches into this meaningful representation space, Sketch2MedI only requires synthesized sketches for training, enabling a cost-effective learning process. Our Sketch2MedI demonstrates a robust generalization to free-hand sketches, resulting in high-quality and realistic medical image generations. Comparative evaluations of Sketch2MedI against the pix2pix, CycleGAN, UNIT, and U-GAT-IT models show superior performance in generating pharyngeal images, both quantitative and qualitative across various metrics.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81OAjEURrtxYdAHcGVfoMPt3LbThhUh8pNAjJH95NIWpmFmMHU08vYCujqbLyffYexJQqGs1jCm_JO-i1JBWQCgxns2WaZDI96-qE3DmW9iSJ5avuroEPki9jHTkE493-dTx-c5RtFQH_j7MQ6-eWB3e2o_4-M_R2w7f9nOlmL9uljNpmtBpkIhNYUSqEIPVmnpglNVaf3OOZIGDBpPVhujFJACCBU63NmAIL12gJfBiD3_aW_v64-cOsrn-lpR3yrwF4T4Pz8</recordid><startdate>20240201</startdate><enddate>20240201</enddate><creator>Cap, Quan Huu</creator><creator>Fukuda, Atsushi</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240201</creationdate><title>High-Quality Medical Image Generation from Free-hand Sketch</title><author>Cap, Quan Huu ; Fukuda, Atsushi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-15ad20a73c084519d94728cb99a160636ca8566440a400d7393b8d301c5903063</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Cap, Quan Huu</creatorcontrib><creatorcontrib>Fukuda, Atsushi</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cap, Quan Huu</au><au>Fukuda, Atsushi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>High-Quality Medical Image Generation from Free-hand Sketch</atitle><date>2024-02-01</date><risdate>2024</risdate><abstract>Generating medical images from human-drawn free-hand sketches holds promise for various important medical imaging applications. Due to the extreme difficulty in collecting free-hand sketch data in the medical domain, most deep learning-based methods have been proposed to generate medical images from the synthesized sketches (e.g., edge maps or contours of segmentation masks from real images). However, these models often fail to generalize on the free-hand sketches, leading to unsatisfactory results. In this paper, we propose a practical free-hand sketch-to-image generation model called Sketch2MedI that learns to represent sketches in StyleGAN's latent space and generate medical images from it. Thanks to the ability to encode sketches into this meaningful representation space, Sketch2MedI only requires synthesized sketches for training, enabling a cost-effective learning process. Our Sketch2MedI demonstrates a robust generalization to free-hand sketches, resulting in high-quality and realistic medical image generations. Comparative evaluations of Sketch2MedI against the pix2pix, CycleGAN, UNIT, and U-GAT-IT models show superior performance in generating pharyngeal images, both quantitative and qualitative across various metrics.</abstract><doi>10.48550/arxiv.2402.00353</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2402.00353
ispartof
issn
language eng
recordid cdi_arxiv_primary_2402_00353
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title High-Quality Medical Image Generation from Free-hand Sketch
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T10%3A10%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=High-Quality%20Medical%20Image%20Generation%20from%20Free-hand%20Sketch&rft.au=Cap,%20Quan%20Huu&rft.date=2024-02-01&rft_id=info:doi/10.48550/arxiv.2402.00353&rft_dat=%3Carxiv_GOX%3E2402_00353%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true