1naresh2naresh<pre>Array
(
    [urn:ac.highwire.org:guest:identity] => Array
        (
            [runtime-id] => urn:ac.highwire.org:guest:identity
            [type] => guest
            [service-id] => ajnr-ac.highwire.org
            [access-type] => FreeToRead
            [privilege] => Array
                (
                    [urn:ac.highwire.org:guest:privilege] => Array
                        (
                            [runtime-id] => urn:ac.highwire.org:guest:privilege
                            [type] => privilege-set
                            [privilege-set] => GUEST
                        )

                )

            [credentials] => Array
                (
                    [method] => guest
                )

        )

    [ed5d5ca4-1d89-44f8-aa57-a2f3a8b5b174] => Array
        (
            [runtime-id] => ed5d5ca4-1d89-44f8-aa57-a2f3a8b5b174
            [type] => toll-free-key
            [service-id] => ajnr-ac.highwire.org
            [access-type] => FreeToRead
            [privilege] => Array
                (
                    [0e4a156b-49d0-4a52-a65c-7e8a8b311a93] => Array
                        (
                            [runtime-id] => 0e4a156b-49d0-4a52-a65c-7e8a8b311a93
                            [type] => toll-free-key
                        )

                )

            [credentials] => Array
                (
                    [method] => toll-free-key
                    [value] => tf_ipsecsha;f475341c9ad35b5b7bfe771c8bb727c675d40b16
                )

        )

)
1naresh2naresh<pre>Array
(
    [urn:ac.highwire.org:guest:identity] => Array
        (
            [runtime-id] => urn:ac.highwire.org:guest:identity
            [type] => guest
            [service-id] => ajnr-ac.highwire.org
            [access-type] => Controlled
            [privilege] => Array
                (
                    [urn:ac.highwire.org:guest:privilege] => Array
                        (
                            [runtime-id] => urn:ac.highwire.org:guest:privilege
                            [type] => privilege-set
                            [privilege-set] => GUEST
                        )

                )

            [credentials] => Array
                (
                    [method] => guest
                )

        )

    [ec819fae-fdd1-48d2-9b7d-ef5f85ecdadd] => Array
        (
            [runtime-id] => ec819fae-fdd1-48d2-9b7d-ef5f85ecdadd
            [type] => toll-free-key
            [service-id] => ajnr-ac.highwire.org
            [access-type] => Controlled
            [privilege] => Array
                (
                    [87e17f57-9c91-4d38-a9b8-082d7ced5e26] => Array
                        (
                            [runtime-id] => 87e17f57-9c91-4d38-a9b8-082d7ced5e26
                            [type] => toll-free-key
                        )

                )

            [credentials] => Array
                (
                    [method] => toll-free-key
                    [value] => tf_ipsecsha;f475341c9ad35b5b7bfe771c8bb727c675d40b16
                )

        )

)
Comment on “Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study”
==================================================================================================================================================================

* A. Larroza
* D. Moratal
* A. Paredes-Sánchez
* E. Soria-Olivas
* M.L. Chust
* L.A. Arribas
* E. Arana

We have read with great interest the article published by Tiwari et al, “Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study.”1

In their article, they refer to our work regarding brain metastasis differentiation from radionecrosis.2 They mention that our results may have been affected by the classifier being contaminated by sections from the same patient being used in both the training and testing sets during classification.

As stated in our article, 115 lesions from 73 patients were analyzed.2 There were more lesions than patients because some of the patients showed 2 or 3 lesions in different brain regions. For each lesion, only the MR imaging section depicting the most solid component was used for analysis. Therefore, only 1 section per lesion was used for classification and training, while testing sets were independent. These latter statements were probably misinterpreted by Tiwari et al1 regarding our methodology.

## References

1.  1. Tiwari P, Prasanna P, Wolansky L, et al. Computer-extracted texture features to distinguish cerebral radionecrosis from recurrent brain tumors on multiparametric MRI: a feasibility study. AJNR Am J Neuroradiol 2016;37:2231–36 doi:10.3174/ajnr.A4931 pmid:27633806
    
    [Abstract/FREE Full Text](http://www.ajnr.org/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NDoiYWpuciI7czo1OiJyZXNpZCI7czoxMDoiMzcvMTIvMjIzMSI7czo0OiJhdG9tIjtzOjE5OiIvYWpuci8zOC8zL0UyMS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=) 

2.  2. Larroza A, Moratal D, Paredes-Sánchez A, et al. Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI. J Magn Reson Imaging 2015;42:1362–68 doi:10.1002/jmri.24913 pmid:25865833
    
    [CrossRef](http://www.ajnr.org/lookup/external-ref?access_num=10.1002/jmri.24913&link_type=DOI) 
    
    [PubMed](http://www.ajnr.org/lookup/external-ref?access_num=25865833&link_type=MED&atom=%2Fajnr%2F38%2F3%2FE21.atom) 

*   © 2017 by American Journal of Neuroradiology