{"id":490910,"date":"2018-06-12T23:21:32","date_gmt":"2018-06-13T06:21:32","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=490910"},"modified":"2018-10-16T22:19:38","modified_gmt":"2018-10-17T05:19:38","slug":"gland-instance-segmentation-using-deep-multichannel-neural-networks","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/gland-instance-segmentation-using-deep-multichannel-neural-networks\/","title":{"rendered":"Gland instance segmentation using deep multichannel neural networks"},"content":{"rendered":"<p><strong>Objective:<\/strong> A new image instance segmentation\u00a0method is proposed to segment individual glands\u00a0(instances) in colon histology images. This process is\u00a0challenging since the glands not only need to be segmented\u00a0from a complex background, they must also be individually\u00a0identified. Methods:We leverage the idea of image-to-image\u00a0prediction in recent deep learning by designing an algorithm\u00a0that automatically exploits and fuses complex multichannel\u00a0information\u2014regional, location, and boundary cues\u2014in\u00a0gland histology images. Our proposed algorithm, a deep\u00a0multichannel framework, alleviates heavy feature design\u00a0due to the use of convolutional neural networks and is able\u00a0to meet multifarious requirements by altering channels.<\/p>\n<p><strong>Results:\u00a0<\/strong>Compared with methods reported in the 2015 MICCAI\u00a0Gland Segmentation Challenge and other currently prevalent\u00a0instance segmentation methods, we observe state-of-the-art results based on the evaluation metrics.<\/p>\n<p><strong>Conclusion:<\/strong>\u00a0The proposed deep multichannel algorithm is an effective\u00a0method for gland instance segmentation. Significance: The\u00a0generalization ability of our model not only enable the algorithm\u00a0to solve gland instance segmentation problems, but\u00a0the channel is also alternative that can be replaced for a\u00a0specific task.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Objective: A new image instance segmentation\u00a0method is proposed to segment individual glands\u00a0(instances) in colon histology images. This process is\u00a0challenging since the glands not only need to be segmented\u00a0from a complex background, they must also be individually\u00a0identified. Methods:We leverage the idea of image-to-image\u00a0prediction in recent deep learning by designing an algorithm\u00a0that automatically exploits and fuses complex [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"IEEE Transactions on Biomedical Engineering","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"IEEE Transactions on Biomedical Engineering","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"IEEE Transactions on Biomedical Engineering","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2017-12-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13553],"msr-publication-type":[193715],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-490910","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-medical-health-genomics","msr-locale-en_us"],"msr_publishername":"","msr_edition":"IEEE Transactions on Biomedical Engineering","msr_affiliation":"","msr_published_date":"2017-12-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"IEEE Transactions on Biomedical Engineering","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"490952","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"[2017][SCI][TBME]Gland Instance Segmentation Using Deep Multichannel Neural Networks","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2018\/06\/2017SCITBMEGland-Instance-Segmentation-Using-Deep-Multichannel-Neural-Networks.pdf","id":490952,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Yan Xu","user_id":0,"rest_url":false},{"type":"text","value":"Yang Li","user_id":0,"rest_url":false},{"type":"text","value":"Yipei Wang","user_id":0,"rest_url":false},{"type":"text","value":"Mingyuan Liu","user_id":0,"rest_url":false},{"type":"text","value":"Yubo Fan","user_id":0,"rest_url":false},{"type":"text","value":"Maode Lai","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Eric Chang","user_id":31709,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Eric Chang"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[780706],"msr_project":[170702],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":{"projects":[{"ID":170702,"post_title":"eHuatuo: Teaching Computer to Read Medical Records","post_name":"ehuatuo-teaching-computer-to-read-medical-records","post_type":"msr-project","post_date":"2011-04-10 20:16:13","post_modified":"2019-05-16 04:27:03","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/ehuatuo-teaching-computer-to-read-medical-records\/","post_excerpt":"eHuatuo is an eHealthcare project about Teaching Computer to Read Medical Records developed by Microsoft Research Asia. The goal of the project is to utilize the power of computers to help doctors process the increasing amount of data available in healthcare, ranging from text data, medical imaging data, to genomic data. We aim to link these disparate types of data together for new insights and discoveries. Resources eHuatuo: Teaching Computers to Read Medical Records Dictionary&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170702"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/490910","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/490910\/revisions"}],"predecessor-version":[{"id":490979,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/490910\/revisions\/490979"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=490910"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=490910"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=490910"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=490910"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=490910"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=490910"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=490910"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=490910"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=490910"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=490910"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=490910"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=490910"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=490910"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}