Publication

Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI

View document

Bibliographic Details
Summary:BACKGROUND: Whole-body diffusion weighted imaging (WB-DWI) has proven value to detect multiple myeloma (MM) lesions. However, the large volume of imaging data and the presence of numerous lesions makes the reading process challenging. The aim of the current study was to develop a semi-automatic lesion segmentation algorithm for WB-DWI images in MM patients and to evaluate this smart-algorithm (SA) performance by comparing it to the manual segmentations performed by radiologists. METHODS: An atlas-based segmentation was developed to remove the high-signal intensity normal tissues on WB-DWI and to restrict the lesion area to the skeleton. Then, an outlier threshold-based segmentation was applied to WB-DWI images, and the segmented area's signal intensity was compared to the average signal intensity of a low-fat muscle on T1-weighted images. This method was validated in 22 whole-body DWI images of patients diagnosed with MM. Dice similarity coefficient (DSC), sensitivity and positive predictive value (PPV) were computed to evaluate the SA performance against the gold standard (GS) and to compare with the radiologists. A non-parametric Wilcoxon test was also performed. Apparent diffusion coefficient (ADC) histogram metrics and lesion volume were extracted for the GS segmentation and for the correctly identified lesions by SA and their correlation was assessed. RESULTS: The mean inter-radiologists DSC was 0.323 ± 0.268. The SA vs GS achieved a DSC of 0.274 ± 0.227, sensitivity of 0.764 ± 0.276 and PPV 0.217 ± 0.207. Its distribution was not significantly different from the mean DSC of inter-radiologist segmentation (p = 0.108, Wilcoxon test). ADC and lesion volume intraclass correlation coefficient (ICC) of the GS and of the correctly identified lesions by the SA was 0.996 for the median and 0.894 for the lesion volume (p < 0.001). The duration of the lesion volume segmentation by the SA was, on average, 10.22 ± 0.86 min, per patient. CONCLUSIONS: The SA provides equally reproducible segmentation results when compared to the manual segmentation of radiologists. Thus, the proposed method offers robust and efficient segmentation of MM lesions on WB-DWI. This method may aid accurate assessment of tumor burden and therefore provide insights to treatment response assessment.
Main Authors:Almeida, Sílvia D.
Other Authors:Santinha, João; Oliveira, Francisco P.M.; Ip, Joana; Lisitskaya, Maria; Lourenço, João; Uysal, Aycan; Matos, Celso; João, Cristina; Papanikolaou, Nikolaos
Subject:Atlas-based segmentation Diffusion weighted imaging Multiple myeloma Semi-automatic segmentation Total lesion burden Radiological and Ultrasound Technology Oncology Radiology Nuclear Medicine and imaging
Year:2020
Country:Portugal
Document type:article
Access type:open access
Associated institution:Universidade Nova de Lisboa
Language:English
Origin:Repositório Institucional da UNL
_version_ 1868984041029500928
author Almeida, Sílvia D.
author2 Santinha, João
Oliveira, Francisco P.M.
Ip, Joana
Lisitskaya, Maria
Lourenço, João
Uysal, Aycan
Matos, Celso
João, Cristina
Papanikolaou, Nikolaos
author2_role author
author
author
author
author
author
author
author
author
author_facet Almeida, Sílvia D.
Santinha, João
Oliveira, Francisco P.M.
Ip, Joana
Lisitskaya, Maria
Lourenço, João
Uysal, Aycan
Matos, Celso
João, Cristina
Papanikolaou, Nikolaos
author_role author
contributor_name_str_mv NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)
BioMed Central (BMC)
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Almeida, Sílvia D.\"},{\"Person.name\":\"Santinha, João\"},{\"Person.name\":\"Oliveira, Francisco P.M.\"},{\"Person.name\":\"Ip, Joana\"},{\"Person.name\":\"Lisitskaya, Maria\"},{\"Person.name\":\"Lourenço, João\"},{\"Person.name\":\"Uysal, Aycan\"},{\"Person.name\":\"Matos, Celso\"},{\"Person.name\":\"João, Cristina\"},{\"Person.name\":\"Papanikolaou, Nikolaos\"}]
datacite.contributors.contributor.contributorName.fl_str_mv NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)
BioMed Central (BMC)
RUN
datacite.creators.creator.creatorName.fl_str_mv Almeida, Sílvia D.
Santinha, João
Oliveira, Francisco P.M.
Ip, Joana
Lisitskaya, Maria
Lourenço, João
Uysal, Aycan
Matos, Celso
João, Cristina
Papanikolaou, Nikolaos
datacite.date.Accepted.fl_str_mv 2020-01-13T00:00:00Z
datacite.date.available.fl_str_mv 2020-01-27T23:30:12Z
datacite.date.embargoed.fl_str_mv 2020-01-27T23:30:12Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
datacite.titles.title.fl_str_mv Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
dc.contributor.none.fl_str_mv NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)
BioMed Central (BMC)
RUN
dc.creator.none.fl_str_mv Almeida, Sílvia D.
Santinha, João
Oliveira, Francisco P.M.
Ip, Joana
Lisitskaya, Maria
Lourenço, João
Uysal, Aycan
Matos, Celso
João, Cristina
Papanikolaou, Nikolaos
dc.date.Accepted.fl_str_mv 2020-01-13T00:00:00Z
dc.date.available.fl_str_mv 2020-01-27T23:30:12Z
dc.date.embargoed.fl_str_mv 2020-01-27T23:30:12Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/91871
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
dc.title.fl_str_mv Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description BACKGROUND: Whole-body diffusion weighted imaging (WB-DWI) has proven value to detect multiple myeloma (MM) lesions. However, the large volume of imaging data and the presence of numerous lesions makes the reading process challenging. The aim of the current study was to develop a semi-automatic lesion segmentation algorithm for WB-DWI images in MM patients and to evaluate this smart-algorithm (SA) performance by comparing it to the manual segmentations performed by radiologists. METHODS: An atlas-based segmentation was developed to remove the high-signal intensity normal tissues on WB-DWI and to restrict the lesion area to the skeleton. Then, an outlier threshold-based segmentation was applied to WB-DWI images, and the segmented area's signal intensity was compared to the average signal intensity of a low-fat muscle on T1-weighted images. This method was validated in 22 whole-body DWI images of patients diagnosed with MM. Dice similarity coefficient (DSC), sensitivity and positive predictive value (PPV) were computed to evaluate the SA performance against the gold standard (GS) and to compare with the radiologists. A non-parametric Wilcoxon test was also performed. Apparent diffusion coefficient (ADC) histogram metrics and lesion volume were extracted for the GS segmentation and for the correctly identified lesions by SA and their correlation was assessed. RESULTS: The mean inter-radiologists DSC was 0.323 ± 0.268. The SA vs GS achieved a DSC of 0.274 ± 0.227, sensitivity of 0.764 ± 0.276 and PPV 0.217 ± 0.207. Its distribution was not significantly different from the mean DSC of inter-radiologist segmentation (p = 0.108, Wilcoxon test). ADC and lesion volume intraclass correlation coefficient (ICC) of the GS and of the correctly identified lesions by the SA was 0.996 for the median and 0.894 for the lesion volume (p < 0.001). The duration of the lesion volume segmentation by the SA was, on average, 10.22 ± 0.86 min, per patient. CONCLUSIONS: The SA provides equally reproducible segmentation results when compared to the manual segmentation of radiologists. Thus, the proposed method offers robust and efficient segmentation of MM lesions on WB-DWI. This method may aid accurate assessment of tumor burden and therefore provide insights to treatment response assessment.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/6ea9fab5-aad2-4cac-ac5d-ebfbd3da21af/download
id run_e6e52a85cca856439e97595afc0f5c42
identifier.url.fl_str_mv http://hdl.handle.net/10362/91871
inst_facet_str urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/91871
organization_str_mv urn:organizationAcronym:unl
person_str_mv Almeida, Sílvia D.
Santinha, João
Oliveira, Francisco P.M.
Ip, Joana
Lisitskaya, Maria
Lourenço, João
Uysal, Aycan
Matos, Celso
João, Cristina
Papanikolaou, Nikolaos
publishDate 2020
repo_facet_str urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engenBACKGROUND: Whole-body diffusion weighted imaging (WB-DWI) has proven value to detect multiple myeloma (MM) lesions. However, the large volume of imaging data and the presence of numerous lesions makes the reading process challenging. The aim of the current study was to develop a semi-automatic lesion segmentation algorithm for WB-DWI images in MM patients and to evaluate this smart-algorithm (SA) performance by comparing it to the manual segmentations performed by radiologists. METHODS: An atlas-based segmentation was developed to remove the high-signal intensity normal tissues on WB-DWI and to restrict the lesion area to the skeleton. Then, an outlier threshold-based segmentation was applied to WB-DWI images, and the segmented area's signal intensity was compared to the average signal intensity of a low-fat muscle on T1-weighted images. This method was validated in 22 whole-body DWI images of patients diagnosed with MM. Dice similarity coefficient (DSC), sensitivity and positive predictive value (PPV) were computed to evaluate the SA performance against the gold standard (GS) and to compare with the radiologists. A non-parametric Wilcoxon test was also performed. Apparent diffusion coefficient (ADC) histogram metrics and lesion volume were extracted for the GS segmentation and for the correctly identified lesions by SA and their correlation was assessed. RESULTS: The mean inter-radiologists DSC was 0.323 ± 0.268. The SA vs GS achieved a DSC of 0.274 ± 0.227, sensitivity of 0.764 ± 0.276 and PPV 0.217 ± 0.207. Its distribution was not significantly different from the mean DSC of inter-radiologist segmentation (p = 0.108, Wilcoxon test). ADC and lesion volume intraclass correlation coefficient (ICC) of the GS and of the correctly identified lesions by the SA was 0.996 for the median and 0.894 for the lesion volume (p < 0.001). The duration of the lesion volume segmentation by the SA was, on average, 10.22 ± 0.86 min, per patient. CONCLUSIONS: The SA provides equally reproducible segmentation results when compared to the manual segmentation of radiologists. Thus, the proposed method offers robust and efficient segmentation of MM lesions on WB-DWI. This method may aid accurate assessment of tumor burden and therefore provide insights to treatment response assessment.application/pdfenQuantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWIAlmeida, Sílvia D.Santinha, JoãoOliveira, Francisco P.M.Ip, JoanaLisitskaya, MariaLourenço, JoãoUysal, AycanMatos, CelsoJoão, CristinaPapanikolaou, NikolaosNOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)BioMed Central (BMC)HostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptISSNIsPartOf1470-7330URNIsPartOfPURE: 16530209URNIsPartOfPURE UUID: 66ee9d89-ffa8-4976-af5e-40a56a00246dURNIsPartOfScopus: 85077786257URNIsPartOfPubMed: 31931880URNIsPartOfWOS: 000521263800002DOIIsPartOf10.1186/s40644-020-0286-52020-01-27T23:30:12Z2020-01-132020-01-13T00:00:00ZHandlehttp://hdl.handle.net/10362/91871http://purl.org/coar/access_right/c_abf2open accessAtlas-based segmentationDiffusion weighted imagingMultiple myelomaSemi-automatic segmentationTotal lesion burdenRadiological and Ultrasound TechnologyOncologyRadiology Nuclear Medicine and imaging2489392 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/6ea9fab5-aad2-4cac-ac5d-ebfbd3da21af/download
spellingShingle Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
Almeida, Sílvia D.
Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
status SINGLETON
subject.fl_str_mv Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
title Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
title_full Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
title_fullStr Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
title_full_unstemmed Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
title_short Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
title_sort Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI
topic Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
topic_facet Atlas-based segmentation
Diffusion weighted imaging
Multiple myeloma
Semi-automatic segmentation
Total lesion burden
Radiological and Ultrasound Technology
Oncology
Radiology Nuclear Medicine and imaging
url http://hdl.handle.net/10362/91871
visible 1