{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:47:21Z","timestamp":1764402441802,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2009,11,16]],"date-time":"2009-11-16T00:00:00Z","timestamp":1258329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The goal of this study was to develop a computer-aided therapeutic response (CADrx) system for early prediction of drug treatment response for glioblastoma multiforme (GBM) brain tumors with diffusion weighted (DW) MR images. In conventional Macdonald assessment, tumor response is assessed nine weeks or more post-treatment. However, we will investigate the ability of DW-MRI to assess response earlier, at five weeks post treatment. The apparent diffusion coefficient (ADC) map, calculated from DW images, has been shown to reveal changes in the tumor\u2019s microenvironment preceding morphologic tumor changes. ADC values in treated brain tumors could theoretically both increase due to the cell kill (and thus reduced cell density) and decrease due to inhibition of edema. In this study, we investigated the effectiveness of features that quantify changes from pre- and post-treatment tumor ADC histograms to detect treatment response. There are three parts to this study: first, tumor regions were segmented on T1w contrast enhanced images by Otsu\u2019s thresholding method, and mapped from T1w images onto ADC images by a 3D region of interest (ROI) mapping tool using DICOM header information; second, ADC histograms of the tumor region were extracted from both pre- and five weeks post-treatment scans, and fitted by a two-component Gaussian mixture model (GMM). The GMM features as well as standard histogram-based features were extracted. Finally, supervised machine learning techniques were applied for classification of responders or non-responders. The approach was evaluated with a dataset of 85 patients with GBM under chemotherapy, in which 39 responded and 46 did not, based on tumor volume reduction. We compared adaBoost, random forest and support vector machine classification algorithms, using ten-fold cross validation, resulting in the best accuracy of 69.41% and the corresponding area under the curve (Az) of 0.70.<\/jats:p>","DOI":"10.3390\/a2041350","type":"journal-article","created":{"date-parts":[[2009,11,16]],"date-time":"2009-11-16T07:29:38Z","timestamp":1258356578000},"page":"1350-1367","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["CADrx for GBM Brain Tumors: Predicting Treatment Response from Changes in Diffusion-Weighted MRI"],"prefix":"10.3390","volume":"2","author":[{"given":"Jing","family":"Huo","sequence":"first","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]},{"given":"Kazunori","family":"Okada","sequence":"additional","affiliation":[{"name":"San Francisco State University Computer Science Department, Thornton Hall 911, 1600 Holloway Avenue, San Francisco, CA 94132-4163, USA"}]},{"given":"Hyun J.","family":"Kim","sequence":"additional","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]},{"given":"Whitney B.","family":"Pope","sequence":"additional","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]},{"given":"Jonathan G.","family":"Goldin","sequence":"additional","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]},{"given":"Jeffrey R.","family":"Alger","sequence":"additional","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]},{"given":"Matthew S.","family":"Brown","sequence":"additional","affiliation":[{"name":"UCLA Department of Radiological Sciences, 924 Westwood Blvd., Suite 650, Los Angeles, CA 90024, USA"}]}],"member":"1968","published-online":{"date-parts":[[2009,11,16]]},"reference":[{"key":"ref_1","unstructured":"Giger, M.L. (2000). Computer-aided diagnosis in medical imaging \u2014 A new era in image interpretation, World Markets Research Centre. Technical Report."},{"key":"ref_2","first-page":"581","article-title":"Evaluation of cancer therapy using diffusion magnetic resonance imaging","volume":"2","author":"Ross","year":"2003","journal-title":"Mol. Cancer Ther."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1593\/neo.81328","article-title":"Diffusion-weighted magnetic imaging as a cancer biomarker: consensus and recommendations","volume":"11","author":"Padhani","year":"2009","journal-title":"Neoplasia"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/0730-725X(94)00093-I","article-title":"Applications of fuzzy C-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme","volume":"13","author":"Phillips","year":"1995","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1109\/42.700731","article-title":"Automatic tumor segmentation using knowledge-based techniques","volume":"17","author":"Clark","year":"1998","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/S0933-3657(00)00073-7","article-title":"Automatic segmentation of non-enhancing brain tumors in magnetic resonance images","volume":"21","author":"Hall","year":"2001","journal-title":"Artif. Intell. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1016\/S1076-6332(03)00506-3","article-title":"Automatic brain tumor segmentation by subject specific modification of atlas priors","volume":"10","author":"Prastawa","year":"2003","journal-title":"Acad. Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1148\/radiology.218.2.r01fe44586","article-title":"Automated segmentation of mr images of brain tumors","volume":"218","author":"Kaus","year":"2001","journal-title":"Radiology"},{"key":"ref_9","unstructured":"Ho, S., Bullitt, E., and Gerig, G. (, January August,). Level set evolution with region competition: Automatic 3-d segmentation of brain tumors. Proceedings of International Conference on Pattern Recognition, Quebec, Canada."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1002\/(SICI)1522-2586(199906)9:6<768::AID-JMRI3>3.0.CO;2-2","article-title":"Fast tissue segmentation based on a 4D feature map in characterization of intracranial lesions fast tissue segmentation based on a 4D feature map in characterization of intracranial lesions","volume":"9","author":"Vinitski","year":"1999","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_11","unstructured":"Lee, C.H., Schmidt, M., Murtha, A., Bistritz, A., Sander, J., and Greiner, R. (, January October,). Segmenting brain tumor with conditional random fields and support vector machines. Proceedings of Workshop on Computer Vision for Biomedical Image Applications at International Conference on Computer Vision, Beijing, China."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/42.552055","article-title":"Computerized tumor boundary detection using a hopfield neural network","volume":"16","author":"Zhu","year":"1997","journal-title":"LEEE Trans. Med. Imaging"},{"key":"ref_13","unstructured":"Zhang, J., Ma, K., Er, M.H., and Chong, V. (, January January,). Tumor segmentation from magnetic resonance imaging by learning via one-class support vector machine. Proceedings of International Workshop on Advanced Image Technology, Singapore."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/j.compmedimag.2009.04.006","article-title":"Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field","volume":"33","author":"Niea","year":"2009","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/TMI.2007.912817","article-title":"Efficient Multilevel Brain Tumor Segmentation with Integrated Bayesian Model Classification","volume":"27","author":"Corso","year":"2008","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.compmedimag.2004.07.008","article-title":"A system for brain tumor volume estimation via mr imaging and fuzzy connectedness","volume":"29","author":"Liu","year":"2005","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"69143Y","DOI":"10.1117\/12.770769","article-title":"Hierarchical Segmentation of Malignant Gliomas via Integrated Contextual Filter Response","volume":"6914","author":"Dube","year":"2008","journal-title":"Proc. SPIE"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1063\/1.2817354","article-title":"Automated MR image processing and analysis of malignant brain tumors: enabling technology for data mining","volume":"Vol. 953","author":"Dube","year":"2007","journal-title":"Data Mining Systems Analysis and Optimization in Biomedicine"},{"key":"ref_19","unstructured":"US Food and Drug Administration (2007). Guidance for industry: clinical trial endpoints for the approval of cancer drugs and biologics. Federal Register, 72, No. 94."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1093\/jnci\/92.24.2029","article-title":"Diffusion magnetic resonance imaging: an early surrogate marker of therapeutic efficacy in brain tumors","volume":"92","author":"Chenevert","year":"2000","journal-title":"J. Natl. Cancer Inst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1200\/JCO.2003.05.069","article-title":"Early detection of response to radiation therapy in patients with brain malignancies using conventional and high b-value diffusion-weighted magnetic resonance imaging","volume":"21","author":"Mardor","year":"2003","journal-title":"J. Clin. Oncol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5524","DOI":"10.1073\/pnas.0501532102","article-title":"The functional diffusion map: a noninvasive MRI biomarker for early stratification of clinical brain tumor response","volume":"102","author":"Moffat","year":"2005","journal-title":"PANS"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16759","DOI":"10.1073\/pnas.0508347102","article-title":"Evaluation of the functional diffusion map as an early biomarker of time-to-progression and overall survival in high-grade glioma","volume":"102","author":"Hamstra","year":"2005","journal-title":"PNAS"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"72601Y","DOI":"10.1117\/12.812923","article-title":"Histogram-based classification with Gaussian mixture modeling for GBM tumor treatment response using ADC map","volume":"7260","author":"Huo","year":"2009","journal-title":"Proc. SPIE"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1148\/radiol.2521081534","article-title":"Recurrent glioblastoma multiforme: ADC histogram analysis predicts response to bevacizumab treatment","volume":"252","author":"Pope","year":"2009","journal-title":"Radiology"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1146\/annurev.bioeng.8.061505.095802","article-title":"Machine learning for detection and diagnosis of disease","volume":"8","author":"Sajda","year":"2006","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref_27","first-page":"771","article-title":"A short introduction to boosting","volume":"14","author":"Freund","year":"1999","journal-title":"J. Jpn. Soc. For. Artif. Intell."},{"key":"ref_28","unstructured":"Duda, R.O., Hart, P.E., and Stork, D.H. (2000). Pattern classification, Wiley Interscience."},{"key":"ref_29","unstructured":"Ho, T.K. (, January August,). Random decision forest. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random decision forest","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_31","unstructured":"Vapnik, V. (1979). Estimation of Dependencies Based on Empirical Data, Nauka."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bishop, C. (1995). Neural Networks for Pattern Recognition, Clarendon Press.","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref_33","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Support_vector_machine."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0097-8485(01)00094-8","article-title":"Drug design by machine learning: support vector machines for pharmaceutical data analysis","volume":"26","author":"Burbidge","year":"2001","journal-title":"Comput. And. Chem"},{"key":"ref_35","unstructured":"Huo, J., Alger, J.R., Kim, H.J., Pope, W.B., Okada, K., Goldin, J.G., and Brown, M.S. (2009). Between-scanner variation in normal white matter ADC in the setting of a multi-center clinical trial. Ismrm, (in press)."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","article-title":"A threshold selection method from gray level histograms","volume":"9","year":"1979","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"ref_37","first-page":"641","article-title":"Seeded region growing","volume":"16","author":"Adams","year":"1994","journal-title":"IEEE Trans. Syst. Man. Cybern. Int."},{"key":"ref_38","unstructured":"Rubner, Y., Tomasi, C., and Guibas, L.J. (, January January,). A metric for distributions with applications to image databases. Proceedings of ICCV, Bombay, India."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1109\/TPAMI.2007.1058","article-title":"An efficient Earth mover's distance algorithm for robust histogram comparison","volume":"29","author":"Ling","year":"2007","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"ref_40","unstructured":"Witten, I.H., and Frank, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann."},{"key":"ref_41","unstructured":"Yamasaki, F., Sugiyama, K., Ohtaki, M., Takeshima, Y., Abed, N., Akiyamad, Y., Takabad, J., Amatyac, V.J., Saitoa, T., Kajiwaraa, Y., Hanayaa, R., and Kurisua, K. (2009). Glioblastoma treated with postoperative radio-chemotherapy: Prognostic value of apparent diffusion coefficient at MR imaging. Eur.J. Aiol., (in press)."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1175\/825.1","article-title":"The ROC curve and the area under it as a performance measure","volume":"19","author":"Marzban","year":"2004","journal-title":"Weather Forecast."},{"key":"ref_43","first-page":"1435","article-title":"Chromosomal abnormalities in glioblastoma multiforme by comparative genomic hybridization: correlation with radiation treatment outcome","volume":"5","author":"Huhn","year":"1999","journal-title":"Clin. Cancer Res."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/2\/4\/1350\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T22:11:39Z","timestamp":1760220699000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/2\/4\/1350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,11,16]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2009,12]]}},"alternative-id":["a2041350"],"URL":"https:\/\/doi.org\/10.3390\/a2041350","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2009,11,16]]}}}