A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis
Abstract Colorectal cancer (CRC) constitutes the third most commonly diagnosed cancer in males and the second in females. Precise histopathological classification of CRC tissue pathology is the cornerstone not only for diagnosis but also for patients’ management decision making. An automated system...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/c3ed0f888ecf4796aa5bdfd8a73f82b8 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:c3ed0f888ecf4796aa5bdfd8a73f82b8 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:c3ed0f888ecf4796aa5bdfd8a73f82b82021-12-02T16:31:02ZA neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis10.1038/s41598-021-94781-62045-2322https://doaj.org/article/c3ed0f888ecf4796aa5bdfd8a73f82b82021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94781-6https://doaj.org/toc/2045-2322Abstract Colorectal cancer (CRC) constitutes the third most commonly diagnosed cancer in males and the second in females. Precise histopathological classification of CRC tissue pathology is the cornerstone not only for diagnosis but also for patients’ management decision making. An automated system able to accurately classify different CRC tissue regions may increase diagnostic precision and alleviate clinical workload. However, tissue classification is a challenging task due to the variability in morphological and textural characteristics present in histopathology images. In this study, an artificial neural network was trained to classify between eight classes of CRC tissue image patches derived from a public dataset with 5000 CRC histopathology image tiles. A total of 532 multi-level pathomics features examined at different scales were extracted by visual descriptors such as local binary patterns, wavelet transforms and Gabor filters. An exhaustive evaluation involving a variety of wavelet families and parameters was performed in order to shed light on the impact of scale on pathomics based CRC tissue differentiation. Our model achieved a performance accuracy of 95.3% with tenfold cross validation demonstrating superior performance compared to 87.4% reported in recent studies. Furthermore, we experimentally showed that the first and the second levels of the wavelet approximations can be used without compromising classification performance.Eleftherios TrivizakisGeorgios S. IoannidisIoannis SouglakosApostolos H. KarantanasMaria TzardiKostas MariasNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Eleftherios Trivizakis Georgios S. Ioannidis Ioannis Souglakos Apostolos H. Karantanas Maria Tzardi Kostas Marias A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| description |
Abstract Colorectal cancer (CRC) constitutes the third most commonly diagnosed cancer in males and the second in females. Precise histopathological classification of CRC tissue pathology is the cornerstone not only for diagnosis but also for patients’ management decision making. An automated system able to accurately classify different CRC tissue regions may increase diagnostic precision and alleviate clinical workload. However, tissue classification is a challenging task due to the variability in morphological and textural characteristics present in histopathology images. In this study, an artificial neural network was trained to classify between eight classes of CRC tissue image patches derived from a public dataset with 5000 CRC histopathology image tiles. A total of 532 multi-level pathomics features examined at different scales were extracted by visual descriptors such as local binary patterns, wavelet transforms and Gabor filters. An exhaustive evaluation involving a variety of wavelet families and parameters was performed in order to shed light on the impact of scale on pathomics based CRC tissue differentiation. Our model achieved a performance accuracy of 95.3% with tenfold cross validation demonstrating superior performance compared to 87.4% reported in recent studies. Furthermore, we experimentally showed that the first and the second levels of the wavelet approximations can be used without compromising classification performance. |
| format |
article |
| author |
Eleftherios Trivizakis Georgios S. Ioannidis Ioannis Souglakos Apostolos H. Karantanas Maria Tzardi Kostas Marias |
| author_facet |
Eleftherios Trivizakis Georgios S. Ioannidis Ioannis Souglakos Apostolos H. Karantanas Maria Tzardi Kostas Marias |
| author_sort |
Eleftherios Trivizakis |
| title |
A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| title_short |
A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| title_full |
A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| title_fullStr |
A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| title_full_unstemmed |
A neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| title_sort |
neural pathomics framework for classifying colorectal cancer histopathology images based on wavelet multi-scale texture analysis |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/c3ed0f888ecf4796aa5bdfd8a73f82b8 |
| work_keys_str_mv |
AT eleftheriostrivizakis aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT georgiossioannidis aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT ioannissouglakos aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT apostoloshkarantanas aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT mariatzardi aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT kostasmarias aneuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT eleftheriostrivizakis neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT georgiossioannidis neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT ioannissouglakos neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT apostoloshkarantanas neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT mariatzardi neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis AT kostasmarias neuralpathomicsframeworkforclassifyingcolorectalcancerhistopathologyimagesbasedonwaveletmultiscaletextureanalysis |
| _version_ |
1718383898494238720 |