{"id":5461,"date":"2026-02-19T09:42:10","date_gmt":"2026-02-19T09:42:10","guid":{"rendered":"https:\/\/www.neugrid2.eu\/?page_id=5461"},"modified":"2026-06-08T12:04:43","modified_gmt":"2026-06-08T12:04:43","slug":"lst_ai","status":"publish","type":"page","link":"https:\/\/www.neugrid2.eu\/index.php\/lst_ai\/","title":{"rendered":"LST_AI"},"content":{"rendered":"\n<p class=\"pipelinetitle\">Welcome to the LST-AI segmentation service in neuGRID!<\/p>\n<p class=\"pipelinesubtitle\">How to run the segmentation on MRI scans:<\/p>\n<p class=\"pipelinedescription\">You have to upload:<\/p>\n<p class=\"pipelinedescription\" style=\"padding-left: 25px;\">i. Zip file containing DICOMS<\/p>\n<p class=\"pipelinedescription\">or<\/p>\n<p class=\"pipelinedescription\" style=\"padding-left: 25px;\">ii. nii.gz archive<\/p>\n<p class=\"pipelinedescription\">Then provide the following information:<\/p>\n<ul>\n<li><span class=\"pipelinedescription\">Age of the patient<\/span><\/li>\n<li><span class=\"pipelinedescription\">Sex of the patient (Male or Female)<\/span><\/li>\n<li><span class=\"pipelinedescription\">Flair type (2D or 3D)<\/span><\/li>\n<\/ul>\n<p class=\"pipelinedescription\">and click the submit button!<\/p>\n<hr \/><form action=\"https:\/\/www.neugrid2.eu\/functions\/lst_ai.php\" enctype=\"multipart\/form-data\" method=\"post\">\n<table style=\"border-style: none; width: 100%;\">\n<tbody>\n<tr>\n<td class=\"inputtablefirstcolumn\">\n<p class=\"inputformtext\">Select patient&#8217;s sex:<\/p>\n<\/td>\n<td class=\"inputtablesecondcolumn\"><select class=\"inputformtext\" name=\"sex\" required=\"\">\n<option value=\"\">Select&#8230;<\/option>\n<option value=\"M\">Male<\/option>\n<option value=\"F\">Female<\/option>\n<\/select><\/td>\n<\/tr>\n<tr>\n<tr>\n<td class=\"inputtablefirstcolumn\">\n<\/tr>\n<td class=\"inputtablefirstcolumn\">\n<p class=\"inputformtext\">Select patient&#8217;s age:<\/p>\n<\/td>\n<td class=\"inputtablesecondcolumn\"><select class=\"inputformtext\" name=\"age\" required=\"\">\n<option value=\"\">Select&#8230;<\/option>\n<option value=\"40\">40<\/option>\n<option value=\"41\">41<\/option>\n<option value=\"42\">42<\/option>\n<option value=\"43\">43<\/option>\n<option value=\"44\">44<\/option>\n<option value=\"45\">45<\/option>\n<option value=\"46\">46<\/option>\n<option value=\"47\">47<\/option>\n<option value=\"48\">48<\/option>\n<option value=\"49\">49<\/option>\n<option value=\"50\">50<\/option>\n<option value=\"51\">51<\/option>\n<option value=\"52\">52<\/option>\n<option value=\"53\">53<\/option>\n<option value=\"54\">54<\/option>\n<option value=\"55\">55<\/option>\n<option value=\"56\">56<\/option>\n<option value=\"57\">57<\/option>\n<option value=\"58\">58<\/option>\n<option value=\"59\">59<\/option>\n<option value=\"60\">60<\/option>\n<option value=\"61\">61<\/option>\n<option value=\"62\">62<\/option>\n<option value=\"63\">63<\/option>\n<option value=\"64\">64<\/option>\n<option value=\"65\">65<\/option>\n<option value=\"66\">66<\/option>\n<option value=\"67\">67<\/option>\n<option value=\"68\">68<\/option>\n<option value=\"69\">69<\/option>\n<option value=\"70\">70<\/option>\n<option value=\"71\">71<\/option>\n<option value=\"72\">72<\/option>\n<option value=\"73\">73<\/option>\n<option value=\"74\">74<\/option>\n<option value=\"75\">75<\/option>\n<option value=\"76\">76<\/option>\n<option value=\"77\">77<\/option>\n<option value=\"78\">78<\/option>\n<option value=\"79\">79<\/option>\n<option value=\"80\">80<\/option>\n<option value=\"81\">81<\/option>\n<option value=\"82\">82<\/option>\n<option value=\"83\">83<\/option>\n<option value=\"84\">84<\/option>\n<option value=\"85\">85<\/option>\n<option value=\"86\">86<\/option>\n<option value=\"87\">87<\/option>\n<option value=\"88\">88<\/option>\n<option value=\"89\">89<\/option>\n<option value=\"90\">90<\/option>\n<\/select><\/td>\n<\/tr>\n<tr>\n<td class=\"inputtablefirstcolumn\">\n<p class=\"inputformtext\">Select Flair type:<\/p>\n<\/td>\n<td class=\"inputtablesecondcolumn\"><select class=\"inputformtext\" name=\"flair_type\" required=\"\">\n<option value=\"\">Select&#8230;<\/option>\n<option value=\"3D\">3D<\/option>\n<option value=\"2D\">2D<\/option>\n<\/select><\/td>\n<\/tr>\n<tr>\n<td class=\"inputtablefirstcolumn\">\n<p class=\"inputformtext\">Select image FLAIR to upload:<\/p>\n<\/td>\n<td class=\"inputtablesecondcolumn\"><input id=\"fileToUpload1\" class=\"inputformtext\" name=\"fileToUpload1\" required=\"\" type=\"file\" \/><\/td>\n<\/tr>\n<tr>\n<td class=\"inputtablefirstcolumn\">\n<p class=\"inputformtext\">Select image T13D to upload:<\/p>\n<\/td>\n<td class=\"inputtablesecondcolumn\"><input id=\"fileToUpload2\" class=\"inputformtext\" name=\"fileToUpload2\" required=\"\" type=\"file\" \/><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><input class=\"submit\" type=\"submit\" value=\"Submit\" \/><\/p>\n<hr \/><\/form>\n<p class=\"pipelinedescription\"> LST-AI \u2013 Deep Learning Ensemble for Accurate MS Lesion Segmentation \u2013 segments T2 hyperintense lesions in FLAIR images. LST-AI is an advanced deep learning-based extension of the original LST toolbox. LST-AI was trained using an ensemble network model with data from 491 Multiple Sclerosis patients with severe lesion patterns. It also labels lesions such as periventricular, infratentorial, juxtacortical, and subcortical according to the 2017 McDonald criteria. Further information on the algorithm can be found in the publication by <a href=\"https:\/\/doi.org\/10.1016\/j.nicl.2024.103611\" target=\"_blank\" rel=\"noopener noreferrer\">Wiltgen, 2024<\/a>.<\/p>\n<p class=\"pipelinedescription\">The LST-AI pipeline implemented in neuGRID requires FLAIR and T13D images of the subject. Lesion volume values are corrected by dividing by the subject\u2019s Total Intracranial Volume, calculated by SPM12, and multiplying by a constant.<\/p>\n<p class=\"pipelinedescription\">Once the LST-AI algorithm execution is complete, the outputs are stored in a PDF report showing the number and volume of lesions, the segmentation of lesions in relevant brain scans, and the subject\u2019s position in the Prediction Percentile plot for white matter lesion volume. Each coloured line in the normative plot represents the Prediction Percentile for white matter lesion volume of a non-pathological subject; each number in the legend indicates the percentage of non-pathological subjects with a white matter lesion volume below the respective coloured line. If the subject is located above the 95% coloured line, the subject should be considered pathological.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-5249\" src=\"https:\/\/www.neugrid2.eu\/wp-content\/uploads\/2025\/04\/lpa.jpg\" alt=\"\" width=\"227\" height=\"250\" \/><\/p>\n<p class=\"pipelinecaption\">Probabilistic lesion volume map generated by LST-AI on a FLAIR image in axial view.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Welcome to the LST-AI segmentation service in neuGRID! How to run the segmentation on MRI scans: You have to upload: i. Zip file containing DICOMS or ii. nii.gz archive Then provide the following information: Age of the patient Sex of the patient (Male or Female) Flair type (2D or 3D) and click the submit button! [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-5461","page","type-page","status-publish","hentry","post"],"_links":{"self":[{"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/pages\/5461","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/comments?post=5461"}],"version-history":[{"count":6,"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/pages\/5461\/revisions"}],"predecessor-version":[{"id":5551,"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/pages\/5461\/revisions\/5551"}],"wp:attachment":[{"href":"https:\/\/www.neugrid2.eu\/index.php\/wp-json\/wp\/v2\/media?parent=5461"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}