{"id":3804,"date":"2022-10-21T13:03:55","date_gmt":"2022-10-21T11:03:55","guid":{"rendered":"https:\/\/staging.mediaire.ai\/?p=3804"},"modified":"2025-09-03T09:10:30","modified_gmt":"2025-09-03T07:10:30","slug":"segmentation-of-ms-lesions-accuracy-of-mdbrain","status":"publish","type":"post","link":"https:\/\/mediaire.ai\/en\/segmentation-of-ms-lesions-accuracy-of-mdbrain\/","title":{"rendered":"Segmentation of MS Lesions Accuracy of mdbrain 4.5 versus a pool of human experts"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Presented at<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

<\/p>\n

Congress of the European Society of Radiology<\/span> (2022)<\/p>\n

<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Authors<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

<\/p>\n

Dalbis T., Grilo J., Hitziger S., Ling W. X., Opalka J., Lemke A.<\/p>\n

<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Abstract<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Purpose<\/strong><\/p>\n

The diagnosis of multiple sclerosis (MS) requires the assessment of lesion load from brain MRIs. Traditionally, MS lesions are manually annotated by radiologists, a process that is inefficient and error prone. The AI-software mdbrain leverages deep-learning to automatically segment MS lesions. Here, we assess the accuracy of the lesion-segmentation algorithm to be released in mdbrain 4.5 compared to SPM-SLS (http:\/\/atc.udg.edu\/salem\/slsToolbox\/) and to the inter-rater performance of 4 experts.<\/p>\n

Materials & Methods<\/strong><\/p>\n

mdbrain uses a deep neural network to segment lesions from a FLAIR scan. The network was trained using 280 annotated FLAIRs. Performances were tested on a separate dataset of 30 FLAIRs annotated by 4 experts. To assess segmentation accuracy, we computed the lesion-wise F1 score between each algorithm (mdbrain and SPM-SLS) and rater, averaged across raters. The inter-rater F1 was computed by comparing the annotation of each rater against the remaining 3. F1 scores were also computed for different lesion classes separately.<\/p>\n

Results<\/strong><\/p>\n

mdbrain achieved an F1 score of 0.72, which was larger than SPM-SLS (F1=0.55) but slightly smaller than the inter-rater (F1=0.75). F1 scores of mdbrain were larger than the inter-rater for juxtacortical (mdbrain F1=0.75; inter-rater F1=0.72) and infratentorial lesions (mdbrain F1=0.58; inter-rater F1=0.55), but smaller for periventricular (mdbrain F1=0.74; inter-rater F1=0.77) and deep-white matter lesions (mdbrain F1=0.70; inter-rater F1=0.76). An average time of 2 minutes was required by mdbrain to process a single scan (GPU-equipped machine).<\/p>\n

Discussion<\/strong><\/p>\n

The AI-software mdbrain 4.5 achieved a lesion-segmentation accuracy comparable to a pool of human experts and considerably higher than SPM-SLS.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
Performance of lesion segmentationof mdbrain v4.5 against SPM v12 for F1 and DICE score. Benchmark = interrater accuracy (dashed line).<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

The diagnosis of multiple sclerosis (MS) requires the assessment of lesion load from brain MRIs. Traditionally, MS lesions are manually annotated by radiologists, a process that is inefficient and error prone. The AI-software mdbrain leverages deep-learning to automatically segment MS lesions.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[14],"tags":[],"class_list":["post-3804","post","type-post","status-publish","format-standard","hentry","category-publications"],"acf":[],"_links":{"self":[{"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/posts\/3804","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/comments?post=3804"}],"version-history":[{"count":5,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/posts\/3804\/revisions"}],"predecessor-version":[{"id":21637,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/posts\/3804\/revisions\/21637"}],"wp:attachment":[{"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/media?parent=3804"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/categories?post=3804"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mediaire.ai\/en\/wp-json\/wp\/v2\/tags?post=3804"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}