Classification of Multiple H&E Images via an Ensemble Computational Scheme
In this work, a computational scheme is proposed to identify the main combinations of handcrafted descriptors and deep-learned features capable of classifying histological images stained with hematoxylin and eosin. The handcrafted descriptors were those representatives of multiscale and multidimensi...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/26/1/34 |
| _version_ | 1797344106509238272 |
|---|---|
| author | Leonardo H. da Costa Longo Guilherme F. Roberto Thaína A. A. Tosta Paulo R. de Faria Adriano M. Loyola Sérgio V. Cardoso Adriano B. Silva Marcelo Z. do Nascimento Leandro A. Neves |
| author_facet | Leonardo H. da Costa Longo Guilherme F. Roberto Thaína A. A. Tosta Paulo R. de Faria Adriano M. Loyola Sérgio V. Cardoso Adriano B. Silva Marcelo Z. do Nascimento Leandro A. Neves |
| author_sort | Leonardo H. da Costa Longo |
| collection | DOAJ |
| description | In this work, a computational scheme is proposed to identify the main combinations of handcrafted descriptors and deep-learned features capable of classifying histological images stained with hematoxylin and eosin. The handcrafted descriptors were those representatives of multiscale and multidimensional fractal techniques (fractal dimension, lacunarity and percolation) applied to quantify the histological images with the corresponding representations via explainable artificial intelligence (xAI) approaches. The deep-learned features were obtained from different convolutional neural networks (DenseNet-121, EfficientNet-b2, Inception-V3, ResNet-50 and VGG-19). The descriptors were investigated through different associations. The most relevant combinations, defined through a ranking algorithm, were analyzed via a heterogeneous ensemble of classifiers with the support vector machine, naive Bayes, random forest and K-nearest neighbors algorithms. The proposed scheme was applied to histological samples representative of breast cancer, colorectal cancer, oral dysplasia and liver tissue. The best results were accuracy rates of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>94.83</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>100</mn><mo>%</mo></mrow></semantics></math></inline-formula>, with the identification of pattern ensembles for classifying multiple histological images. The computational scheme indicated solutions exploring a reduced number of features (a maximum of 25 descriptors) and with better performance values than those observed in the literature. The presented information in this study is useful to complement and improve the development of computer-aided diagnosis focused on histological images. |
| first_indexed | 2024-03-08T10:57:33Z |
| format | Article |
| id | doaj.art-bcf92e1138cd4e548b96ba5f5b736388 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-08T10:57:33Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-bcf92e1138cd4e548b96ba5f5b7363882024-01-26T16:23:03ZengMDPI AGEntropy1099-43002023-12-012613410.3390/e26010034Classification of Multiple H&E Images via an Ensemble Computational SchemeLeonardo H. da Costa Longo0Guilherme F. Roberto1Thaína A. A. Tosta2Paulo R. de Faria3Adriano M. Loyola4Sérgio V. Cardoso5Adriano B. Silva6Marcelo Z. do Nascimento7Leandro A. Neves8Department of Computer Science and Statistics (DCCE), São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265, São José do Rio Preto 15054-000, SP, BrazilDepartment of Informatics Engineering, Faculty of Engineering, University of Porto, Dr. Roberto Frias, sn, 4200-465 Porto, PortugalScience and Technology Institute, Federal University of São Paulo (UNIFESP), Avenida Cesare Mansueto Giulio Lattes, 1201, São José dos Campos 12247-014, SP, BrazilDepartment of Histology and Morphology, Institute of Biomedical Science, Federal University of Uberlândia (UFU), Av. Amazonas, S/N, Uberlândia 38405-320, MG, BrazilArea of Oral Pathology, School of Dentistry, Federal University of Uberlândia (UFU), R. Ceará—Umuarama, Uberlândia 38402-018, MG, BrazilArea of Oral Pathology, School of Dentistry, Federal University of Uberlândia (UFU), R. Ceará—Umuarama, Uberlândia 38402-018, MG, BrazilFaculty of Computer Science (FACOM), Federal University of Uberlândia (UFU), Avenida João Naves de Ávila 2121, Bl.B, Uberlândia 38400-902, MG, BrazilFaculty of Computer Science (FACOM), Federal University of Uberlândia (UFU), Avenida João Naves de Ávila 2121, Bl.B, Uberlândia 38400-902, MG, BrazilDepartment of Computer Science and Statistics (DCCE), São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265, São José do Rio Preto 15054-000, SP, BrazilIn this work, a computational scheme is proposed to identify the main combinations of handcrafted descriptors and deep-learned features capable of classifying histological images stained with hematoxylin and eosin. The handcrafted descriptors were those representatives of multiscale and multidimensional fractal techniques (fractal dimension, lacunarity and percolation) applied to quantify the histological images with the corresponding representations via explainable artificial intelligence (xAI) approaches. The deep-learned features were obtained from different convolutional neural networks (DenseNet-121, EfficientNet-b2, Inception-V3, ResNet-50 and VGG-19). The descriptors were investigated through different associations. The most relevant combinations, defined through a ranking algorithm, were analyzed via a heterogeneous ensemble of classifiers with the support vector machine, naive Bayes, random forest and K-nearest neighbors algorithms. The proposed scheme was applied to histological samples representative of breast cancer, colorectal cancer, oral dysplasia and liver tissue. The best results were accuracy rates of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>94.83</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>100</mn><mo>%</mo></mrow></semantics></math></inline-formula>, with the identification of pattern ensembles for classifying multiple histological images. The computational scheme indicated solutions exploring a reduced number of features (a maximum of 25 descriptors) and with better performance values than those observed in the literature. The presented information in this study is useful to complement and improve the development of computer-aided diagnosis focused on histological images.https://www.mdpi.com/1099-4300/26/1/34classificationhistological imagesdeep-learned featuresfractal techniquesxAI representationensembles |
| spellingShingle | Leonardo H. da Costa Longo Guilherme F. Roberto Thaína A. A. Tosta Paulo R. de Faria Adriano M. Loyola Sérgio V. Cardoso Adriano B. Silva Marcelo Z. do Nascimento Leandro A. Neves Classification of Multiple H&E Images via an Ensemble Computational Scheme Entropy classification histological images deep-learned features fractal techniques xAI representation ensembles |
| title | Classification of Multiple H&E Images via an Ensemble Computational Scheme |
| title_full | Classification of Multiple H&E Images via an Ensemble Computational Scheme |
| title_fullStr | Classification of Multiple H&E Images via an Ensemble Computational Scheme |
| title_full_unstemmed | Classification of Multiple H&E Images via an Ensemble Computational Scheme |
| title_short | Classification of Multiple H&E Images via an Ensemble Computational Scheme |
| title_sort | classification of multiple h e images via an ensemble computational scheme |
| topic | classification histological images deep-learned features fractal techniques xAI representation ensembles |
| url | https://www.mdpi.com/1099-4300/26/1/34 |
| work_keys_str_mv | AT leonardohdacostalongo classificationofmultipleheimagesviaanensemblecomputationalscheme AT guilhermefroberto classificationofmultipleheimagesviaanensemblecomputationalscheme AT thainaaatosta classificationofmultipleheimagesviaanensemblecomputationalscheme AT paulordefaria classificationofmultipleheimagesviaanensemblecomputationalscheme AT adrianomloyola classificationofmultipleheimagesviaanensemblecomputationalscheme AT sergiovcardoso classificationofmultipleheimagesviaanensemblecomputationalscheme AT adrianobsilva classificationofmultipleheimagesviaanensemblecomputationalscheme AT marcelozdonascimento classificationofmultipleheimagesviaanensemblecomputationalscheme AT leandroaneves classificationofmultipleheimagesviaanensemblecomputationalscheme |