Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning
Ultrasound has been considered a safe and accurate alternative to radiography and computerized tomography to diagnose lung diseases such as pneumonia. However, speckle noise, artifacts or certain conditions can difficult image interpretation. For example, in some cases, the pleura line cannot be obs...
- Autores:
-
Contreras Ojeda, Sara
Domínguez Jiménez, Juan Antonio
Contreras Ortiz, Sonia Helena
- Tipo de recurso:
- Fecha de publicación:
- 2020
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/9949
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/9949
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11583/0000/Analysis-and-classification-of-lung-and-muscular-tissues-in-ultrasound/10.1117/12.2576368.short
- Palabra clave:
- Bioinformatics
Biological organs
Computerized tomography
Discrete wavelet transforms
Feature extraction
Histology
Image classification
Machine learning
Nearest neighbor search
Tissue
Ultrasonics
LEMB
- Rights
- closedAccess
- License
- http://purl.org/coar/access_right/c_14cb
| id |
UTB2_7a8a4580e8ea5b955ddbce3de8f0fe84 |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/9949 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| title |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| spellingShingle |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning Bioinformatics Biological organs Computerized tomography Discrete wavelet transforms Feature extraction Histology Image classification Machine learning Nearest neighbor search Tissue Ultrasonics LEMB |
| title_short |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| title_full |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| title_fullStr |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| title_full_unstemmed |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| title_sort |
Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning |
| dc.creator.fl_str_mv |
Contreras Ojeda, Sara Domínguez Jiménez, Juan Antonio Contreras Ortiz, Sonia Helena |
| dc.contributor.author.none.fl_str_mv |
Contreras Ojeda, Sara Domínguez Jiménez, Juan Antonio Contreras Ortiz, Sonia Helena |
| dc.subject.keywords.spa.fl_str_mv |
Bioinformatics Biological organs Computerized tomography Discrete wavelet transforms Feature extraction Histology Image classification Machine learning Nearest neighbor search Tissue Ultrasonics |
| topic |
Bioinformatics Biological organs Computerized tomography Discrete wavelet transforms Feature extraction Histology Image classification Machine learning Nearest neighbor search Tissue Ultrasonics LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
Ultrasound has been considered a safe and accurate alternative to radiography and computerized tomography to diagnose lung diseases such as pneumonia. However, speckle noise, artifacts or certain conditions can difficult image interpretation. For example, in some cases, the pleura line cannot be observed. This work proposes an approach for discriminating between lung and muscular tissues in ultrasound images. We evaluated the symlet and daubechies wavelets for feature extraction, principal component analysis and recursive backward elimination for feature selection, and supervised learning methods for classification. Statistical moments and the energy of the second horizontal coefficient and peak-to-peak root mean squared ratio were the features more outstanding over the rest. The best model was obtained with recursive backward elimination for feature selection and knearest neighbor for classification. Tissue classification was possible with a mean accuracy of 97.5% and area under the curve of 99%. These results offer great insights on the recognition of lung and muscular tissues, which could improve the effectiveness of automatic segmentation and analysis algorithms. |
| publishDate |
2020 |
| dc.date.issued.none.fl_str_mv |
2020-11-03 |
| dc.date.accessioned.none.fl_str_mv |
2021-02-08T15:52:52Z |
| dc.date.available.none.fl_str_mv |
2021-02-08T15:52:52Z |
| dc.date.submitted.none.fl_str_mv |
2021-02-03 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/lecture |
| dc.type.hasversion.spa.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_8544 |
| status_str |
publishedVersion |
| dc.identifier.citation.spa.fl_str_mv |
S. L. Contreras-Ojeda, J. A. Dominguez-Jiménez, and S. H. Contreras-Ortiz "Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning", Proc. SPIE 11583, 16th International Symposium on Medical Information Processing and Analysis, 115830F (3 November 2020); https://doi.org/10.1117/12.2576368 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/9949 |
| dc.identifier.url.none.fl_str_mv |
https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11583/0000/Analysis-and-classification-of-lung-and-muscular-tissues-in-ultrasound/10.1117/12.2576368.short |
| dc.identifier.doi.none.fl_str_mv |
10.1117/12.2576368 |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
S. L. Contreras-Ojeda, J. A. Dominguez-Jiménez, and S. H. Contreras-Ortiz "Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning", Proc. SPIE 11583, 16th International Symposium on Medical Information Processing and Analysis, 115830F (3 November 2020); https://doi.org/10.1117/12.2576368 10.1117/12.2576368 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/9949 https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11583/0000/Analysis-and-classification-of-lung-and-muscular-tissues-in-ultrasound/10.1117/12.2576368.short |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/closedAccess |
| eu_rights_str_mv |
closedAccess |
| rights_invalid_str_mv |
http://purl.org/coar/access_right/c_14cb |
| dc.format.extent.none.fl_str_mv |
7 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.source.spa.fl_str_mv |
Proceedings Volume 11583, 16th International Symposium on Medical Information Processing and Analysis; 115830F (2020) |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/1/117.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/2/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/3/117.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/4/117.pdf.jpg |
| bitstream.checksum.fl_str_mv |
2661321b7f88ef3635d4b1d73997808c e20ad307a1c5f3f25af9304a7a7c86b6 000ac29bc17b4fecf07c3adf675ec742 4a65723fcda36843004369881c6834e0 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1814021663146115072 |
| spelling |
Contreras Ojeda, Sara2f78dd6b-33ca-46d8-a5a0-bc083e4cd7e2Domínguez Jiménez, Juan Antoniod2ff9be0-9c22-42f6-a0eb-ce74b44b6ab2Contreras Ortiz, Sonia Helena690f7c84-d6e0-464a-b059-47146b2f92f52021-02-08T15:52:52Z2021-02-08T15:52:52Z2020-11-032021-02-03S. L. Contreras-Ojeda, J. A. Dominguez-Jiménez, and S. H. Contreras-Ortiz "Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learning", Proc. SPIE 11583, 16th International Symposium on Medical Information Processing and Analysis, 115830F (3 November 2020); https://doi.org/10.1117/12.2576368https://hdl.handle.net/20.500.12585/9949https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11583/0000/Analysis-and-classification-of-lung-and-muscular-tissues-in-ultrasound/10.1117/12.2576368.short10.1117/12.2576368Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarUltrasound has been considered a safe and accurate alternative to radiography and computerized tomography to diagnose lung diseases such as pneumonia. However, speckle noise, artifacts or certain conditions can difficult image interpretation. For example, in some cases, the pleura line cannot be observed. This work proposes an approach for discriminating between lung and muscular tissues in ultrasound images. We evaluated the symlet and daubechies wavelets for feature extraction, principal component analysis and recursive backward elimination for feature selection, and supervised learning methods for classification. Statistical moments and the energy of the second horizontal coefficient and peak-to-peak root mean squared ratio were the features more outstanding over the rest. The best model was obtained with recursive backward elimination for feature selection and knearest neighbor for classification. Tissue classification was possible with a mean accuracy of 97.5% and area under the curve of 99%. These results offer great insights on the recognition of lung and muscular tissues, which could improve the effectiveness of automatic segmentation and analysis algorithms.7 páginasapplication/pdfengProceedings Volume 11583, 16th International Symposium on Medical Information Processing and Analysis; 115830F (2020)Analysis and classification of lung and muscular tissues in ultrasound images using 2D wavelet transform and machine learninginfo:eu-repo/semantics/lectureinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_8544http://purl.org/coar/version/c_970fb48d4fbd8a85BioinformaticsBiological organsComputerized tomographyDiscrete wavelet transformsFeature extractionHistologyImage classificationMachine learningNearest neighbor searchTissueUltrasonicsLEMBinfo:eu-repo/semantics/closedAccesshttp://purl.org/coar/access_right/c_14cbCartagena de IndiasWielpütz, M.O., Heußel, C.P., Herth, F.J.F., Kauczor, H.-U. Radiological diagnosis in lung disease: Factoring treatment options into the choice of diagnostic modality (Open Access) (2014) Deutsches Arzteblatt International, 111 (11), pp. 181-187. Cited 26 times. http://www.aerzteblatt.de/pdf.asp?id=156439 doi: 10.3238/arztebl.2014.0181Reissig, A., Copetti, R., Mathis, G., Mempel, C., Schuler, A., Zechner, P., Aliberti, S., (...), Hoyer, H. Lung ultrasound in the diagnosis and follow-up of community-acquired pneumonia: A prospective, multicenter, diagnostic accuracy study (Open Access) (2012) Chest, 142 (4), pp. 965-972. Cited 236 times. http://journal.publications.chestnet.org/data/Journals/CHEST/25163/chest_142_4_965.pdf doi: 10.1378/chest.12-0364Soldati, G., Smargiassi, A., Inchingolo, R., Buonsenso, D., Perrone, T., Briganti, D.F., Perlini, S., (...), Demi, L. Proposal for International Standardization of the Use of Lung Ultrasound for Patients With COVID-19 (Open Access) (2020) Journal of Ultrasound in Medicine, 39 (7), pp. 1413-1419. Cited 137 times. http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1550-9613 doi: 10.1002/jum.15285Buonsenso, D., Raffaelli, F., Tamburrini, E., Biasucci, D.G., Salvi, S., Smargiassi, A., Inchingolo, R., (...), Moro, F. Clinical role of lung ultrasound for diagnosis and monitoring of COVID-19 pneumonia in pregnant women (Open Access) (2020) Ultrasound in Obstetrics and Gynecology, 56 (1), pp. 106-109. Cited 44 times. http://obgyn.onlinelibrary.wiley.com/hub/journal/10.1002/(ISSN)1469-0705/ doi: 10.1002/uog.22055Zenteno, O., Castaneda, B., Lavarello, R. Spectral-based pneumonia detection tool using ultrasound data from pediatric populations (2016) Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016-October, art. no. 7591635, pp. 4129-4132. Cited 7 times. ISBN: 978-145770220-4 doi: 10.1109/EMBC.2016.7591635Organization, W.H. (2019) Pneumonia. Cited 16 times. Last accessed 18 September 2019Du, R.-H., Liang, L.-R., Yang, C.-Q., Wang, W., Cao, T.-Z., Li, M., Guo, G.-Y., (...), Shi, H.-Z. Predictors of mortality for patients with COVID-19 pneumonia caused by SARSCoV- 2: A prospective cohort study (Open Access) (2020) European Respiratory Journal, 55 (5), art. no. e2000524. Cited 277 times. https://erj.ersjournals.com/content/erj/55/5/2000524.full.pdf doi: 10.1183/13993003.00524-2020ichtenstein, D.A. Ultrasound examination of the lungs in the intensive care unit (2009) Pediatric Critical Care Medicine, 10 (6), pp. 693-698. Cited 83 times. http://journals.lww.com/pccmjournal doi: 10.1097/PCC.0b013e3181b7f637Correa, M., Zimic, M., Barrientos, F., Barrientos, R., Román-Gonzalez, A., Pajuelo, M.J., Anticona, C., (...), Oberhelman, R. Automatic classification of pediatric pneumonia based on lung ultrasound pattern recognition (Open Access) (2018) PLoS ONE, 13 (12), art. no. e0206410. Cited 18 times. https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0206410&type=printable doi: 10.1371/journal.pone.0206410Etehadtavakol, M., Ng, E.Y.K., Chandran, V., Rabbani, H. Separable and non-separable discrete wavelet transform based texture features and image classification of breast thermograms (2013) Infrared Physics and Technology, 61, pp. 274-286. Cited 45 times. doi: 10.1016/j.infrared.2013.08.009Contreras-Ojeda, S.L., Sierra-Pardo, C., Dominguez-Jimenez, J.A., Lopez-Bueno, J., Contreras-Ortiz, S.H. Texture Analysis of Ultrasound Images for Pneumonia Detection in Pediatric Patients (2019) 2019 22nd Symposium on Image, Signal Processing and Artificial Vision, STSIVA 2019 - Conference Proceedings, art. no. 8730238. Cited 4 times. http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8719845 ISBN: 978-172811491-0 doi: 10.1109/STSIVA.2019.8730238Valdes-Burgos, L., Contreras-Ojeda, S.L., Domínguez-Jiménez, J.A., López-Bueno, J., Contreras-Ortiz, S.H. Analysis and classification of lung tissue in ultrasound images for pneumonia detection (2020) Proceedings of SPIE - The International Society for Optical Engineering, 11330, art. no. 1133003. http://spie.org/x1848.xml ISBN: 978-151063427-5 doi: 10.1117/12.2542615Yelampalli, P.K.R., Nayak, J., Gaidhane, V.H. Daubechies wavelet-based local feature descriptor for multimodal medical image registration (2018) IET Image Processing, 12 (10), pp. 1692-1702. Cited 12 times. www.ietdl.org/IET-IPR doi: 10.1049/iet-ipr.2017.1305Layek, K., Samanta, S., Sadhu, A., Maity, S.P., Barui, A. Classification of sonoelastography images of prostate cancer using transformation- based feature extraction techniques (2018) Soft Computing Based Medical Image Analysis, pp. 245-269. Cited 3 times. https://sciencedirect.utb.elogim.com/book/9780128130872/soft-computing-based-medical-image-analysis#book-description ISBN: 978-012813087-2 doi: 10.1016/B978-0-12-813087-2.00013-0Akkasaligar, P.T., Biradar, S. Diagnosis of renal calculus disease in medical ultrasound images (2016) 2016 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2016, art. no. 7919642. Cited 6 times. ISBN: 978-150900611-3 doi: 10.1109/ICCIC.2016.7919642Lever, J., Krzywinski, M., Altman, N. (2017) Points of Significance: Principal Component Analysis. Cited 7 times.Li, F., Yang, Y. Analysis of recursive feature elimination methods (2005) SIGIR 2005 - Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 633-634. Cited 5 times. ISBN: 1595930345; 978-159593034-7 doi: 10.1145/1076034.1076164http://purl.org/coar/resource_type/c_c94fORIGINAL117.pdf117.pdfAbstractapplication/pdf85023https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/1/117.pdf2661321b7f88ef3635d4b1d73997808cMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/2/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD52TEXT117.pdf.txt117.pdf.txtExtracted texttext/plain1343https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/3/117.pdf.txt000ac29bc17b4fecf07c3adf675ec742MD53THUMBNAIL117.pdf.jpg117.pdf.jpgGenerated Thumbnailimage/jpeg60793https://repositorio.utb.edu.co/bitstream/20.500.12585/9949/4/117.pdf.jpg4a65723fcda36843004369881c6834e0MD5420.500.12585/9949oai:repositorio.utb.edu.co:20.500.12585/99492023-05-26 08:13:12.518Repositorio Institucional UTBrepositorioutb@utb.edu.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 |