基于CT放射和模糊分类的治疗引起的腮腺收缩和毒性的早期预测(英文)

2017-03-18 16:17:08 admin 11

Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomicsand fuzzy classification.

Artif Intell Med. 2017 Mar 18

Pota M1, Scalco E2, Sanguineti G3, Farneti A3, Cattaneo GM4, Rizzo G2, Esposito M5.

Author information

    1.National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR), Via P. Castellino 111, 80131 Naples, Italy. Electronic address: marco.pota@na.icar.cnr.it.

    2.National Research Council of Italy - Institute of Molecular Bioimaging and Physiology (IBFM), Via F.lli Cervi 93, 20090 Segrate, MI, Italy.

    3.Radiotherapy, Istituto Nazionale Tumori Regina Elena, Roma, Italy.

    4.Medical Physics Department, San Raffaele Scientific Institute, Milano, Italy.

    5.National Research Council of Italy - Institute for High Performance Computing and Networking (ICAR), Via P. Castellino 111, 80131 Naples, Italy.

Abstract

MOTIVATION


Patients under radiotherapy for head-and-neck cancer often suffer of long-term xerostomia, and/or consistent shrinkage of parotid glands. In order to avoid these drawbacks, adaptive therapy can be planned for patients at risk, if the prediction is obtained timely, before or during the early phase of treatment. Artificial intelligence can address the problem, by learning from examples and building classification models. In particular, fuzzy logic has shown its suitability for medical applications, in order to manage uncertain data, and to build transparent rule-based classifiers. In previous works, clinical, dosimetric and image-based features were considered separately, to find different possible predictors of parotid shrinkage. On the other hand, a few works reported possible image-based predictors of xerostomia, while the combination of different types of features has been little addressed.

OBJECTIVE


This paper proposes the application of a novel machine learning approach, based on both statistics and fuzzy logic, aimed at the classification of patients at risk of i) parotid gland shrinkage and ii) 12-months xerostomia. Both problems are addressed with the aim of individuating predictors and models to classify respective outcomes.

METHODS


Knowledge is extracted from a real dataset of radiotherapy patients, by means of a recently developed method named Likelihood-Fuzzy Analysis, based on the representation of statistical information by fuzzy rule-based models. This method enables to manage heterogeneous variables and missing data, and to obtain interpretable fuzzy models presenting good generalization power (thus high performance), and to measure classification confidence. Numerous features are extracted to characterize patients, coming from different sources, i.e. clinical features, dosimetric parameters, and radiomics-based measures obtained by texture analysis of Computed Tomography images. A learning approach based on the composition of simple models in a more complicated one allows to consider the features separately, in order to identify predictors and models to use when only some data source is available, and obtaining more accurate results when more information can be combined.

RESULTS

Regarding parotid shrinkage, a number of good predictors is detected, some already known and confirmed here, and some others found here, in particular among radiomics-based features. A number of models are also designed, some using single features and others involving models composition to improve classification accuracy. In particular, the best model to be used at the initial treatment stage, and another one applicable at the half treatment stage are identified. Regarding 12-months toxicity, some possible predictors are detected, in particular among radiomics-based features. Moreover, the relation between final parotid shrinkage rate and 12-months xerostomia is evaluated. The method is compared to the naïve Bayes classifier, which reveals similar results in terms of classification accuracy and best predictors. The interpretable fuzzy rule-based models are explicitly presented, and the dependence between predictors and outcome is explained, thus furnishing in some cases helpful insights about the considered problems.

CONCLUSION


Thanks to the performance and interpretability of the fuzzy classification method employed, predictors of both parotidshrinkage and xerostomia are detected, and their influence on each outcome is revealed. Moreover, models for predicting parotid shrinkageat initial and half radiotherapy stages are found.

KEYWORDS


Classification; Fuzzy logic; Parotid gland; Radiomics; Rule-based systems; Xerostomia


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片
  • 人工智能诊断云平台