Ordinal Classification Using Hybrid Artificial Neural Networks with Projection and Kernel Basis Functions

Dorado-Moreno, Manuel; Gutiérrez, Pedro Antonio; Hervás-Martínez, C.

doi:10.1007/978-3-642-28931-6_31

Cited by 12 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is referred to as multiple instance learning . In addition to assigning binary labels to the final pathology, we simultaneously trained the algorithm to predict the TBSRTC category via an ordinal regression framework, in which the output of the neural network was compared with a trainable set of cutoffs to determine the correct category …”

Section: Methodsmentioning

confidence: 99%

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Range

Dov

Kovalsky

et al. 2020

Cancer Cytopathology

View full text Add to dashboard Cite

BACKGROUND:The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) comprises 6 categories used for the diagnosis of thyroid fine-needle aspiration biopsy (FNAB). Each category has an associated risk of malignancy, which is important in the management of a thyroid nodule. More accurate predictions of malignancy may help to reduce unnecessary surgery. A machine learning algorithm (MLA) was developed to evaluate thyroid FNAB via whole slide images (WSIs) to predict malignancy. METHODS: Files were searched for all thyroidectomy specimens with preceding FNAB over 8 years.All cytologic and surgical pathology diagnoses were recorded and correlated for each nodule. One representative slide from each case was scanned to create a WSI. An MLA was designed to identify follicular cells and predict the malignancy of the final pathology. The test set comprised cases blindly reviewed by a cytopathologist who assigned a TBSRTC category. The area under the receiver operating characteristic curve was used to assess the MLA performance. RESULTS: Nine hundred eight FNABs met the criteria. The MLA predicted malignancy with a sensitivity and specificity of 92.0% and 90.5%, respectively. The areas under the curve for the prediction of malignancy by the cytopathologist and the MLA were 0.931 and 0.932, respectively. CONCLUSIONS: The performance of the MLA in predicting thyroid malignancy from FNAB WSIs is comparable to the performance of an expert cytopathologist. When the MLA and electronic medical record diagnoses are combined, the performance is superior to the performance of either alone. An MLA may be used as an adjunct to FNAB to assist in refining the indeterminate categories. Cancer Cytopathol 2020;128:287-295.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Range

Dov

Kovalsky

et al. 2020

Cancer Cytopathology

View full text Add to dashboard Cite

show abstract

“…Gradient descent techniques with proper constraints for the biases serve this purpose. This nonlinear generalisation of the POM model based on neural networks was considered in [86], where an evolutionary algorithm was applied to optimise all the parameters considered. Linear ordinal logistic regression was also combined with nonlinear kernel machines using primaldual relations from Nystrom sampling [87].…”

Section: Cumulative Link Modelsmentioning

confidence: 99%

Ordinal Regression Methods: Survey and Experimental Study

Gutiérrez

Pérez-Ortiz

Sánchez‐Monedero

et al. 2016

IEEE Trans. Knowl. Data Eng.

374

269

View full text Add to dashboard Cite

“…• Ordinal neural NETwork (ORNET). The original algorithm presented in [18], where the fitness function is the one presented in Section 3.2 without considering the cost I M(C j ).…”

Section: Evaluated Methodologiesmentioning

confidence: 99%

“…In our case, because of the complexity of the dataset, we propose to combine these two common approaches in imbalanced learning: a cost-sensitive method and an over-sampling technique (both of which are focused on ordinal classification problems). More specifically, a new fitness function is proposed for an evolutionary ordinal classification algorithm [18], which dynamically updates the weights of the classes considering the worst classified class in each generation. This classifier is used in conjunction with a recently proposed algorithm for data over-sampling in ordinal domains [19].…”

Section: Introductionmentioning

confidence: 99%

Dynamically weighted evolutionary ordinal neural network for solving an imbalanced liver transplantation problem

Dorado-Moreno¹,

Prez-Ortiz

Gutirrez³

et al. 2017

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

The combination of the proposed cost-sensitive evolutionary algorithm together with the application of an over-sampling technique improves the predictive capability of our model in a significant way (especially for minority classes), which can help the surgeons make more informed decisions about the most appropriate recipient for an specific donor organ, in order to maximize the probability of survival after the transplantation and therefore the fairness principle.

show abstract

Ordinal Classification Using Hybrid Artificial Neural Networks with Projection and Kernel Basis Functions

Cited by 12 publications

References 19 publications

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Ordinal Regression Methods: Survey and Experimental Study

Dynamically weighted evolutionary ordinal neural network for solving an imbalanced liver transplantation problem

Contact Info

Product

Resources

About