Texture analysis of routine T2 weighted fat-saturated images can identify head and neck paragangliomas - A pilot study
© 2020 The Author(s)..
PURPOSE: To evaluate the role of the first and second-order texture parameters obtained from T2-weighted fat-saturated DIXON images in differentiating paragangliomas from other neck masses, and to develop a statistical model to classify them.
METHOD: We retrospectively evaluated 38 paragangliomas, 18 nerve-sheath tumours and 14 other miscellaneous neck lesions obtained from an IRB approved study conducted between January 2016 and June 2019; using a composite gold standard of histopathology, cytology and DOTANOC PET CT (A total of 70 lesions in 63 patients). Fat-suppressed T2weighted-DIXON axial images were used. First and second-order texture-parameters were calculated from the original and filtered images. Feature selection using F-statistics and collinearity analysis provided 14 texture parameters for further analysis. Mann-Whitney-U test was used to compare between the groups and p-values were adjusted for multiple comparisons. ROC curve analysis was used to obtain optimal cut-offs.
RESULTS: A total of ten texture features were found to be significantly different between paragangliomas and non-paraganglioma lesions. Minimum from the histogram of grey levels was lower in paragangliomas with a cut off of ≤113.462 obtaining 62.9 % sensitivity and 77.27 % specificity in differentiating paragangliomas from non-paragangliomas. Logistic regression model was trained (n-49) using forward feature selection, which when evaluated on the validation set(n-21)- obtained an AUC of 0.855(95 %CI, 0.633 to 0.968) with a positive likelihood ratio of 4.545 (95 %CI, 1.298-15.923) in differentiating paragangliomas from non-paragangliomas.
CONCLUSION: Texture analysis of a routine imaging sequence can identify paragangliomas with high accuracy. Further development of texture analysis would enable better imaging workflow, resource utilisation and imaging cost reductions.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:7 |
---|---|
Enthalten in: |
European journal of radiology open - 7(2020) vom: 14., Seite 100248 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Ghosh, Adarsh [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Revised 17.04.2022 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1016/j.ejro.2020.100248 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM315551623 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM315551623 | ||
003 | DE-627 | ||
005 | 20231225155147.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.ejro.2020.100248 |2 doi | |
028 | 5 | 2 | |a pubmed24n1051.xml |
035 | |a (DE-627)NLM315551623 | ||
035 | |a (NLM)32984446 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Ghosh, Adarsh |e verfasserin |4 aut | |
245 | 1 | 0 | |a Texture analysis of routine T2 weighted fat-saturated images can identify head and neck paragangliomas - A pilot study |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 17.04.2022 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a © 2020 The Author(s). | ||
520 | |a PURPOSE: To evaluate the role of the first and second-order texture parameters obtained from T2-weighted fat-saturated DIXON images in differentiating paragangliomas from other neck masses, and to develop a statistical model to classify them | ||
520 | |a METHOD: We retrospectively evaluated 38 paragangliomas, 18 nerve-sheath tumours and 14 other miscellaneous neck lesions obtained from an IRB approved study conducted between January 2016 and June 2019; using a composite gold standard of histopathology, cytology and DOTANOC PET CT (A total of 70 lesions in 63 patients). Fat-suppressed T2weighted-DIXON axial images were used. First and second-order texture-parameters were calculated from the original and filtered images. Feature selection using F-statistics and collinearity analysis provided 14 texture parameters for further analysis. Mann-Whitney-U test was used to compare between the groups and p-values were adjusted for multiple comparisons. ROC curve analysis was used to obtain optimal cut-offs | ||
520 | |a RESULTS: A total of ten texture features were found to be significantly different between paragangliomas and non-paraganglioma lesions. Minimum from the histogram of grey levels was lower in paragangliomas with a cut off of ≤113.462 obtaining 62.9 % sensitivity and 77.27 % specificity in differentiating paragangliomas from non-paragangliomas. Logistic regression model was trained (n-49) using forward feature selection, which when evaluated on the validation set(n-21)- obtained an AUC of 0.855(95 %CI, 0.633 to 0.968) with a positive likelihood ratio of 4.545 (95 %CI, 1.298-15.923) in differentiating paragangliomas from non-paragangliomas | ||
520 | |a CONCLUSION: Texture analysis of a routine imaging sequence can identify paragangliomas with high accuracy. Further development of texture analysis would enable better imaging workflow, resource utilisation and imaging cost reductions | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a AUC, area under the curve | |
650 | 4 | |a FDG-PET, fluorodeoxy-glucose positron emission tomography | |
650 | 4 | |a GLCM, grey level co-occurrence matrix | |
650 | 4 | |a Head neck | |
650 | 4 | |a ID, inverse difference | |
650 | 4 | |a IDM, inverse difference moment | |
650 | 4 | |a IDMN, inverse difference moment normalized | |
650 | 4 | |a IDN, inverse difference normalized | |
650 | 4 | |a IMC1, informational measure of correlation 1 | |
650 | 4 | |a IMC2, informational measure of correlation 2 | |
650 | 4 | |a LoG, laplacian of gaussian | |
650 | 4 | |a MCC, maximal correlation coefficient | |
650 | 4 | |a NST, nerve sheath tumour | |
650 | 4 | |a Nerve sheath tumour | |
650 | 4 | |a Paraganglioma | |
650 | 4 | |a ROC, receiver operator characteristics | |
650 | 4 | |a Radiomics | |
650 | 4 | |a Schwannoma | |
650 | 4 | |a Texture analysis | |
700 | 1 | |a Malla, Soumya Ranjan |e verfasserin |4 aut | |
700 | 1 | |a Bhalla, Ashu Seith |e verfasserin |4 aut | |
700 | 1 | |a Manchanda, Smita |e verfasserin |4 aut | |
700 | 1 | |a Kandasamy, Devasenathipathy |e verfasserin |4 aut | |
700 | 1 | |a Kumar, Rakesh |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t European journal of radiology open |d 2014 |g 7(2020) vom: 14., Seite 100248 |w (DE-627)NLM246467290 |x 2352-0477 |7 nnns |
773 | 1 | 8 | |g volume:7 |g year:2020 |g day:14 |g pages:100248 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.ejro.2020.100248 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 7 |j 2020 |b 14 |h 100248 |