{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T02:12:01Z","timestamp":1787883121266,"version":"build-2784847793"},"reference-count":38,"publisher":"IOP Publishing","issue":"23","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"the Key Research and Development Projects of Shaanxi","award":["Program No.2022GY-315"],"award-info":[{"award-number":["Program No.2022GY-315"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876138 and 61203311"],"award-info":[{"award-number":["61876138 and 61203311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2023,12,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate response prediction allows for personalized cancer treatment of locally advanced rectal cancer (LARC) with neoadjuvant chemoradiation. In this work, we designed a convolutional neural network (CNN) feature extractor with switchable 3D and 2D convolutional kernels to extract deep learning features for response prediction. Compared with radiomics features, convolutional kernels may adaptively extract local or global image features from multi-modal MR sequences without the need of feature predefinition. We then developed an unsupervised clustering based evaluation method to improve the feature selection operation in the feature space formed by the combination of CNN features and radiomics features. While normal process of feature selection generally includes the operations of classifier training and classification execution, the process needs to be repeated many times after new feature combinations were found to evaluate the model performance, which incurs a significant time cost. To address this issue, we proposed a cost effective process to use a constructed unsupervised clustering analysis indicator to replace the classifier training process by indirectly evaluating the quality of new found feature combinations in feature selection process. We evaluated the proposed method using 43 LARC patients underwent neoadjuvant chemoradiation. Our prediction model achieved accuracy, area-under-curve (AUC), sensitivity and specificity of 0.852, 0.871, 0.868, and 0.735 respectively. Compared with traditional radiomics methods, the prediction models (AUC = 0.846) based on deep learning-based feature sets are significantly better than traditional radiomics methods (AUC = 0.714). The experiments also showed following findings: (1) the features with higher predictive power are mainly from high-order abstract features extracted by CNN on ADC images and T2 images; (2) both ADC_Radiomics and ADC_CNN features are more advantageous for predicting treatment responses than the radiomics and CNN features extracted from T2 images; (3) 3D CNN features are more effective than 2D CNN features in the treatment response prediction. The proposed unsupervised clustering indicator is feasible with low computational cost, which facilitates the discovery of valuable solutions by highlighting the correlation and complementarity between different types of features.<\/jats:p>","DOI":"10.1088\/1361-6560\/ad0d46","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T17:44:56Z","timestamp":1700156696000},"page":"235012","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Feature selection based on unsupervised clustering evaluation for predicting neoadjuvant chemoradiation response for patients with locally advanced rectal cancer"],"prefix":"10.1088","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6418-3043","authenticated-orcid":true,"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"Xi\u2019an University of Posts and Telecommunications"},{"name":"Xi\u2019an University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Li","sequence":"additional","affiliation":[{"name":"Xi\u2019an University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoying","family":"Pan","sequence":"additional","affiliation":[{"name":"Xi\u2019an University of Posts and Telecommunications"},{"name":"Xi\u2019an University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqian","family":"Qiang","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital of Xi\u2019an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"X Sharon","family":"Qi","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,12,1]]},"reference":[{"key":"pmbad0d46bib1","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/j.media.2007.12.003","type":"journal-article","article-title":"Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI","volume":"12","author":"Andreopoulos","year":"2008","journal-title":"Med. Image Anal."},{"key":"pmbad0d46bib2","doi-asserted-by":"publisher","first-page":"874","DOI":"10.6004\/jnccn.2018.0061","type":"journal-article","article-title":"Rectal cancer, version 2.2018, NCCN clinical practice guidelines in oncology","volume":"16","author":"Benson","year":"2018","journal-title":"J. Natl Comprehensive Cancer Netw."},{"key":"pmbad0d46bib3","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1056\/NEJMoa060829","type":"journal-article","article-title":"Chemotherapy with preoperative radiotherapy in rectal cancer","volume":"355","author":"Bosset","year":"2006","journal-title":"New Engl. J. Med."},{"key":"pmbad0d46bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2020.100223","type":"journal-article","article-title":"Diffusion weighted imaging improves diagnostic ability of MRI for determining complete response to neoadjuvant therapy in locally advanced rectal cancer","volume":"7","author":"Chandramohan","year":"2020","journal-title":"Eur. J. Radiol. Open"},{"key":"pmbad0d46bib5","first-page":"200","type":"journal-article","article-title":"Diffusion weighted imaging combined with magnetic resonance conventional sequences for the diagnosis of rectal cancer","volume":"31","author":"Cong","year":"2009","journal-title":"Zhongguo yi xue ke xue Yuan xue bao Acta Acad. Med. Sinicae"},{"key":"pmbad0d46bib6","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.629321","type":"journal-article","article-title":"Improving the prediction of benign or malignant breast masses using a combination of image biomarkers and clinical parameters","volume":"11","author":"Cui","year":"2021","journal-title":"Front. Oncol."},{"key":"pmbad0d46bib7","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1148\/radiol.11102467","type":"journal-article","article-title":"Rectal cancer: assessment of complete response to preoperative combined radiation therapy with chemotherapy\u2014conventional MR volumetry versus diffusion-weighted MR imaging","volume":"260","author":"Curvo-Semedo","year":"2011","journal-title":"Radiology"},{"key":"pmbad0d46bib8","doi-asserted-by":"publisher","first-page":"e524","DOI":"10.1016\/j.crad.2013.05.094","type":"journal-article","article-title":"Apparent diffusion coefficient as a non-invasive predictor of treatment response and recurrence in locally advanced rectal cancer","volume":"68","author":"Elmi","year":"2013","journal-title":"Clin. Radiol."},{"key":"pmbad0d46bib9","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21492","type":"journal-article","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Freddie","year":"2018","journal-title":"CA: A Cancer J. for Clinicians"},{"key":"pmbad0d46bib10","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab7970","type":"journal-article","article-title":"Deep learning-based radiomics features for improving neoadjuvant chemoradiation response prediction in locally advanced rectal cancer","volume":"65","author":"Fu","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbad0d46bib11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s10350-004-6106-3","type":"journal-article","article-title":"Accuracy of endorectal ultrasonography in preoperative staging of rectal tumors","volume":"45","author":"Garcia-Aguilar","year":"2002","journal-title":"Dis. Colon Rectum"},{"key":"pmbad0d46bib12","first-page":"563","type":"journal-article","article-title":"Radiomics: images are more than pictures","volume":"278","author":"Ggillies","year":"2016","journal-title":"They Are Data Radiol."},{"key":"pmbad0d46bib13","doi-asserted-by":"publisher","first-page":"363","DOI":"10.21037\/jgo.2017.10.10","type":"journal-article","article-title":"Management of locally advanced rectal cancer in the elderly: a critical review and algorithm","volume":"9","author":"Hathout","year":"2018","journal-title":"J. Gastrointest. Oncol."},{"key":"pmbad0d46bib14","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1007\/s00330-011-2220-5","type":"journal-article","article-title":"Tumour ADC measurements in rectal cancer: effect of ROI methods on ADC values and interobserver variability","volume":"21","author":"Lambregts","year":"2011","journal-title":"Eur. Radiol."},{"key":"pmbad0d46bib15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-10649-8","type":"journal-article","article-title":"A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme","volume":"7","author":"Lao","year":"2017","journal-title":"Sci. Rep."},{"key":"pmbad0d46bib16","doi-asserted-by":"publisher","first-page":"140438","DOI":"10.1109\/ACCESS.2019.2937739","type":"journal-article","article-title":"Unsupervised feature selection and clustering optimization based on improved differential evolution","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"pmbad0d46bib17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12880-021-00560-0","type":"journal-article","article-title":"Evaluating treatment response to neoadjuvant chemoradiotherapy in rectal cancer using various MRI-based radiomics models","volume":"21","author":"Li","year":"2021","journal-title":"BMC Med. Imaging"},{"key":"pmbad0d46bib18","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1016\/S1470-2045(10)70172-8","type":"journal-article","article-title":"Long-term outcome in patients with a pathological complete response after chemoradiation for rectal cancer: a pooled analysis of individual patient data","volume":"11","author":"Maas","year":"2010","journal-title":"Lancet Oncol."},{"key":"pmbad0d46bib19","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.23813","type":"journal-article","article-title":"MRI texture analysis in predicting treatment response to neoadjuvant chemoradiotherapy in rectal cancer","volume":"9","author":"Meng","year":"2018","journal-title":"Oncotarget"},{"key":"pmbad0d46bib20","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s12293-018-0254-9","type":"journal-article","article-title":"PSO with surrogate models for feature selection: static and dynamic clustering-based methods","volume":"10","author":"Nguyen","year":"2018","journal-title":"Memetic Comput."},{"key":"pmbad0d46bib21","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.3390\/cancers12071894","type":"journal-article","article-title":"Pre-treatment T2-WI based radiomics features for prediction of locally advanced rectal cancer non-response to neoadjuvant chemoradiotherapy: a preliminary study","volume":"12","author":"Petresc","year":"2020","journal-title":"Cancers"},{"key":"pmbad0d46bib22","doi-asserted-by":"publisher","first-page":"306","DOI":"10.4240\/wjgs.v7.i11.306","type":"journal-article","article-title":"Watch and wait approach to rectal cancer: A review","volume":"7","author":"Pozo","year":"2015","journal-title":"World J. Gastrointest. Surg."},{"key":"pmbad0d46bib23","doi-asserted-by":"publisher","first-page":"89","DOI":"10.5114\/pg.2018.81072","type":"journal-article","article-title":"Epidemiology of colorectal cancer: incidence, mortality, survival, and risk factors","volume":"14","author":"Rawla","year":"2019","journal-title":"Przeglad Gastroenterologiczny"},{"key":"pmbad0d46bib24","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1148\/radiol.2322030778","type":"journal-article","article-title":"High-b-value diffusion-weighted MR imaging for pretreatment prediction and early monitoring of tumor response to therapy in mice","volume":"232","author":"Roth","year":"2004","journal-title":"Radiology"},{"key":"pmbad0d46bib25","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.radonc.2018.03.033","type":"journal-article","article-title":"Tracking tumor biology with radiomics: a systematic review utilizing a radiomics quality score","volume":"127","author":"Sanduleanu","year":"2018","journal-title":"Radiother. Oncol."},{"key":"pmbad0d46bib26","doi-asserted-by":"publisher","first-page":"3775","DOI":"10.1007\/s00261-019-01971-y","type":"journal-article","article-title":"Prediction of efficacy of neoadjuvant chemoradiotherapy for rectal cancer: the value of texture analysis of magnetic resonance images","volume":"44","author":"Shu","year":"2019","journal-title":"Abdominal Radiol."},{"key":"pmbad0d46bib27","doi-asserted-by":"publisher","first-page":"145","DOI":"10.3322\/caac.21601","type":"journal-article","article-title":"Colorectal cancer statistics, 2020","volume":"70","author":"Siegel","year":"2020","journal-title":"CA: A Cancer J. Clinicians"},{"key":"pmbad0d46bib28","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1016\/j.neucom.2016.07.026","type":"journal-article","article-title":"A new hybrid filter\u2013wrapper feature selection method for clustering based on ranking","volume":"214","author":"Solorio-Fern\u00e1ndez","year":"2016","journal-title":"Neurocomputing"},{"key":"pmbad0d46bib29","doi-asserted-by":"crossref","first-page":"2537","DOI":"10.1016\/S0140-6736(18)31078-X","type":"journal-article","article-title":"Long-term outcomes of clinical complete responders after neoadjuvant treatment for rectal cancer in the international Watch and Wait Database (IWWD): an international multicentre registry study","volume":"391","author":"Van Der Valk","year":"2018","journal-title":"Lancet"},{"key":"pmbad0d46bib30","doi-asserted-by":"publisher","first-page":"194","DOI":"10.3390\/s19010194","type":"journal-article","article-title":"An appraisal of lung nodules automatic classification algorithms for CT images","volume":"19","author":"Wang","year":"2019","journal-title":"Sensors"},{"key":"pmbad0d46bib31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.21037\/jmai.2019.04.01","type":"journal-article","article-title":"A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques","volume":"2","author":"Wu","year":"2019","journal-title":"J. Med. Artif. Intell."},{"key":"pmbad0d46bib32","doi-asserted-by":"publisher","first-page":"6350","DOI":"10.3390\/cancers13246350","type":"journal-article","article-title":"Prediction of neoadjuvant chemoradiotherapy response in rectal cancer with metric learning using pretreatment 18F-Fluorodeoxyglucose positron emission tomography","volume":"13","author":"Wu","year":"2021","journal-title":"Cancers"},{"key":"pmbad0d46bib33","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2019.00552","type":"journal-article","article-title":"MRI-based radiomics predicts tumor response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer","volume":"9","author":"Yi","year":"2019","journal-title":"Front. Oncol."},{"key":"pmbad0d46bib34","doi-asserted-by":"crossref","DOI":"10.1117\/1.JMI.7.5.051202","type":"journal-article","article-title":"2D CNN versus 3D CNN for false-positive reduction in lung cancer screening","volume":"7","author":"Yu","year":"2020","journal-title":"J. Med. Imaging"},{"key":"pmbad0d46bib35","doi-asserted-by":"publisher","first-page":"55483","DOI":"10.1109\/ACCESS.2020.2980079","type":"journal-article","article-title":"Unsupervised detection of abnormal electricity consumption behavior based on feature engineering","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"pmbad0d46bib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-80998-y","type":"journal-article","article-title":"Improving prognostic performance in resectable pancreatic ductal adenocarcinoma using radiomics and deep learning features fusion in CT images","volume":"11","author":"Zhang","year":"2021","journal-title":"Sci. Rep."},{"key":"pmbad0d46bib37","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1245\/s10434-019-07300-3","type":"journal-article","article-title":"Radiomics-based pretherapeutic prediction of non-response to neoadjuvant therapy in locally advanced rectal cancer","volume":"26","author":"Zhou","year":"2019","journal-title":"Ann. Surg. Oncol."},{"key":"pmbad0d46bib38","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.574337","type":"journal-article","article-title":"A deep learning model to predict the response to neoadjuvant chemoradiotherapy by the pretreatment apparent diffusion coefficient images of locally advanced rectal cancer","volume":"10","author":"Zhu","year":"2020","journal-title":"Front. Oncol."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:24:53Z","timestamp":1778775893000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad0d46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":38,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12,1]]},"published-print":{"date-parts":[[2023,12,7]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad0d46","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,1]]},"assertion":[{"value":"Feature selection based on unsupervised clustering evaluation for predicting neoadjuvant chemoradiation response for patients with locally advanced rectal cancer","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2023-06-14","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-11-16","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-01","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}