SwePub
Sök i LIBRIS databas

  Utökad sökning

onr:"swepub:oai:gup.ub.gu.se/306609"
 

Sökning: onr:"swepub:oai:gup.ub.gu.se/306609" > Artificial intellig...

LIBRIS Formathandbok  (Information om MARC21)
FältnamnIndikatorerMetadata
00006175naa a2200697 4500
001oai:gup.ub.gu.se/306609
003SwePub
008240719s2021 | |||||||||||000 ||eng|
009oai:research.chalmers.se:a8579cf3-00ca-4509-80bf-c8e12cdca426
009oai:lup.lub.lu.se:d92f3b81-03cc-40a7-9f32-872248f3d924
0247 a https://gup.ub.gu.se/publication/3066092 URI
0247 a https://doi.org/10.1186/s41747-021-00210-82 DOI
0247 a https://research.chalmers.se/publication/5228802 URI
0247 a https://lup.lub.lu.se/record/d92f3b81-03cc-40a7-9f32-872248f3d9242 URI
040 a (SwePub)gud (SwePub)cthd (SwePub)lu
041 a eng
042 9 SwePub
072 7a ref2 swepub-contenttype
072 7a art2 swepub-publicationtype
1001 a Borrelli, P.u Sahlgrenska universitetssjukhuset,Sahlgrenska University Hospital4 aut
2451 0a Artificial intelligence-aided CT segmentation for body composition analysis: a validation study
264 c 2021-03-11
264 1b Springer Science and Business Media LLC,c 2021
520 a BackgroundBody composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images.MethodsEthical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations.ResultsThe accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p <0.001) for SAT and 1.9% versus 3.9% (p < 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of 20%.Conclusions The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.
650 7a MEDICIN OCH HÄLSOVETENSKAPx Hälsovetenskapx Folkhälsovetenskap, global hälsa, socialmedicin och epidemiologi0 (SwePub)303022 hsv//swe
650 7a MEDICAL AND HEALTH SCIENCESx Health Sciencesx Public Health, Global Health, Social Medicine and Epidemiology0 (SwePub)303022 hsv//eng
650 7a TEKNIK OCH TEKNOLOGIERx Medicinteknikx Annan medicinteknik0 (SwePub)206992 hsv//swe
650 7a ENGINEERING AND TECHNOLOGYx Medical Engineeringx Other Medical Engineering0 (SwePub)206992 hsv//eng
650 7a MEDICIN OCH HÄLSOVETENSKAPx Klinisk medicinx Radiologi och bildbehandling0 (SwePub)302082 hsv//swe
650 7a MEDICAL AND HEALTH SCIENCESx Clinical Medicinex Radiology, Nuclear Medicine and Medical Imaging0 (SwePub)302082 hsv//eng
650 7a TEKNIK OCH TEKNOLOGIERx Medicinteknikx Medicinsk bildbehandling0 (SwePub)206032 hsv//swe
650 7a ENGINEERING AND TECHNOLOGYx Medical Engineeringx Medical Image Processing0 (SwePub)206032 hsv//eng
653 a Body composition
653 a Muscles
653 a Neural networks (computer)
653 a Subcutaneous fat
653 a Tomography (x-ray
653 a computed)
653 a visceral adipose-tissue
653 a tomography
653 a sarcopenia
653 a software
653 a cancer
653 a Radiology
653 a Nuclear Medicine & Medical Imaging
653 a Muscles
7001 a Kaboteh, R.u Sahlgrenska universitetssjukhuset,Sahlgrenska University Hospital4 aut
7001 a Enqvist, Olof,d 1981u Chalmers University of Technology,Eigenvision AB4 aut0 (Swepub:cth)enolof
7001 a Ulén, Johannesu Chalmers University of Technology4 aut0 (Swepub:lu)math-jsu
7001 a Trägårdh, Elinu Lund University,Lunds universitet,Nuklearmedicin, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Nuclear medicine, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Skåne University Hospital4 aut0 (Swepub:lu)klin-etr
7001 a Kjölhede, Henrik,d 1981u Gothenburg University,Göteborgs universitet,Institutionen för kliniska vetenskaper, Avdelningen för urologi,Institute of Clinical Sciences, Department of Urology,University of Gothenburg,Sahlgrenska universitetssjukhuset,Sahlgrenska University Hospital4 aut0 (Swepub:lu)med-hrk
7001 a Edenbrandt, Lars,d 1957u Gothenburg University,Göteborgs universitet,Institutionen för medicin, avdelningen för molekylär och klinisk medicin,Institute of Medicine, Department of Molecular and Clinical Medicine,Sahlgrenska universitetssjukhuset,Sahlgrenska University Hospital,University of Gothenburg4 aut0 (Swepub:lu)klfy-led
7102 a Sahlgrenska universitetssjukhusetb Sahlgrenska University Hospital4 org
7730 t European Radiology Experimentald : Springer Science and Business Media LLCg 5:1q 5:1x 2509-9280
8564 u https://eurradiolexp.springeropen.com/track/pdf/10.1186/s41747-021-00210-8
8564 u https://research.chalmers.se/publication/522880/file/522880_Fulltext.pdfx primaryx freey FULLTEXT
8564 u http://dx.doi.org/10.1186/s41747-021-00210-8x freey FULLTEXT
8564 8u https://gup.ub.gu.se/publication/306609
8564 8u https://doi.org/10.1186/s41747-021-00210-8
8564 8u https://research.chalmers.se/publication/522880
8564 8u https://lup.lub.lu.se/record/d92f3b81-03cc-40a7-9f32-872248f3d924

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy