{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:28:23Z","timestamp":1760146103820,"version":"build-2065373602"},"reference-count":24,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Positron Emission Tomography\/Computed Tomography (PET\/CT) using Fluorodeoxyglucose (FDG) is an important imaging modality for assessing treatment outcomes in patients with pulmonary malignant neoplasms undergoing radiation therapy. However, distinguishing between benign post-radiation changes and residual or recurrent malignancies on PET\/CT images is challenging. Leveraging the potential of artificial intelligence (AI), we aimed to develop a hybrid fusion model integrating radiomics and Convolutional Neural Network (CNN) architectures to improve differentiation between benign post-radiation changes and residual or recurrent malignancies on PET\/CT images. We retrospectively collected post-radiation PET\/CTs with identified labels for benign changes or residual\/recurrent malignant lesions from 95 lung cancer patients who received radiation therapy. Firstly, we developed separate radiomics and CNN models using handcrafted and self-learning features, respectively. Then, to build a more reliable model, we fused the probabilities from the two models through an evidential reasoning approach to derive the final prediction probability. Five-folder cross-validation was performed to evaluate the proposed radiomics, CNN, and fusion models. Overall, the hybrid fusion model outperformed the other two models in terms of sensitivity, specificity, accuracy, and the area under the curve (AUC) with values of 0.67, 0.72, 0.69, and 0.72, respectively. Evaluation results on the three AI models we developed suggest that handcrafted features and learned features may provide complementary information for residual or recurrent malignancy identification in PET\/CT.<\/jats:p>","DOI":"10.3390\/a17100435","type":"journal-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T03:57:52Z","timestamp":1727755072000},"page":"435","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Early Detection of Residual\/Recurrent Lung Malignancies on Post-Radiation FDG PET\/CT"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5345-0086","authenticated-orcid":false,"given":"Liyuan","family":"Chen","sequence":"first","affiliation":[{"name":"The Department of Radiation Oncology, The University of Texas Southwestern Medical Center, 2280 Inwood Road, Dallas, TX 75235, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5931-9735","authenticated-orcid":false,"given":"Avanka","family":"Lowe","sequence":"additional","affiliation":[{"name":"The Department of Medical Imaging, The University of Arizona College of Medicine, Tucson and Banner University Medical Center, 1501 N Cambell Ave, Tucson, AZ 85724, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8491-4146","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"The Department of Radiation Oncology, The University of Texas Southwestern Medical Center, 2280 Inwood Road, Dallas, TX 75235, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1097\/CM9.0000000000001474","article-title":"Changing profiles of cancer burden worldwide and in China: A secondary analysis of the Global cancer statistics 2020","volume":"134","author":"Cao","year":"2021","journal-title":"Chin. Med. J."},{"key":"ref_2","first-page":"181S","article-title":"Treatment of stage I non-small cell lung carcinoma","volume":"123","author":"Smythe","year":"2003","journal-title":"Chest"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/0277-5379(89)90266-6","article-title":"Radiation sensitivity of human lung cancer cell lines","volume":"25","author":"Carmichael","year":"1989","journal-title":"Eur. J. Cancer Clin. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.ijrobp.2004.03.036","article-title":"Early FDG-PET imaging after radical radiotherapy for non\u2013small-cell lung cancer: Inflammatory changes in normal tissues correlate with tumor response and do not confound therapeutic response evaluation","volume":"60","author":"Hicks","year":"2004","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1148\/rg.313105096","article-title":"Lung abnormalities at multimodality imaging after radiation therapy for non\u2013small cell lung cancer","volume":"31","author":"Larici","year":"2011","journal-title":"Radiographics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.radonc.2007.01.007","article-title":"Time trends in the maximal uptake of FDG on PET scan during thoracic radiotherapy. A prospective study in locally advanced non-small cell lung cancer (NSCLC) patients","volume":"82","author":"Bosmans","year":"2007","journal-title":"Radiother. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"855","DOI":"10.2967\/jnumed.115.165480","article-title":"18F-FDG PET\/CT: Therapy response assessment interpretation (Hopkins criteria) and survival outcomes in lung cancer patients","volume":"57","author":"Sheikhbahaei","year":"2016","journal-title":"J. Nucl. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s40644-023-00567-6","article-title":"PET\/CT reading for relapse in non-small cell lung cancer after chemoradiotherapy in the PET-Plan trial cohort","volume":"23","author":"Brose","year":"2023","journal-title":"Cancer Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s13014-024-02402-z","article-title":"A PET\/CT radiomics model for predicting distant metastasis in early-stage non\u2013small cell lung cancer patients treated with stereotactic body radiotherapy: A multicentric study","volume":"19","author":"Yu","year":"2024","journal-title":"Radiat. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bianconi, F., Palumbo, I., Spanu, A., Nuvoli, S., Fravolini, M.L., and Palumbo, B. (2020). PET\/CT radiomics in lung cancer: An overview. Appl. Sci., 10.","DOI":"10.3390\/app10051718"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1016\/j.ijrobp.2015.12.369","article-title":"Detection of Local Cancer Recurrence after Stereotactic Ablative Radiation Therapy for Lung Cancer: Physician Performance versus Radiomic Assessment","volume":"94","author":"Mattonen","year":"2016","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1016\/j.ijrobp.2021.02.004","article-title":"Attention guided lymph node malignancy prediction in head and neck cancer","volume":"110","author":"Chen","year":"2021","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhou, Z., Sher, D., Zhang, Q., Shah, J., Pham, N.-L., Jiang, S., and Wang, J. (2019). Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer. Phys. Med. Biol., 64.","DOI":"10.1088\/1361-6560\/ab083a"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.compbiomed.2018.04.009","article-title":"Accurate segmenting of cervical tumors in PET imaging based on similarity between adjacent slices","volume":"97","author":"Chen","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","article-title":"Textural features for image classification","volume":"SMC-3","author":"Haralick","year":"1973","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_16","unstructured":"Xinli, W., Albregtsen, F., and Foyn, B. (1994, January 13\u201315). Texture Features from Gray Level Gap Length Matrix. Proceedings of the MVA\u201994 IAPR Workshop on Machine Vision Applications, Kawasaki, Japan."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/TBME.2013.2284600","article-title":"Advanced statistical matrices for texture characterization: Application to cell classification","volume":"61","author":"Thibault","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/21.44046","article-title":"Textural features corresponding to textural properties","volume":"19","author":"Amadasun","year":"1989","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1016\/j.ejor.2004.09.059","article-title":"Environmental impact assessment using the evidential reasoning approach","volume":"174","author":"Wang","year":"2006","journal-title":"Eur. J. Oper. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s13550-023-00977-4","article-title":"The predictive value of [18F] FDG PET\/CT radiomics combined with clinical features for EGFR mutation status in different clinical staging of lung adenocarcinoma","volume":"13","author":"Gao","year":"2023","journal-title":"EJNMMI Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1001\/jama.2010.261","article-title":"Stereotactic body radiation therapy for inoperable early stage lung cancer","volume":"303","author":"Timmerman","year":"2010","journal-title":"JAMA"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1007\/s002590000258","article-title":"Use of PET to monitor the response of lung cancer to radiation treatment","volume":"27","author":"Erdi","year":"2000","journal-title":"Eur. J. Nucl. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"033502","DOI":"10.1118\/1.4866219","article-title":"Early prediction of tumor recurrence based on CT texture changes after stereotactic ablative radiotherapy (SABR) for lung cancer","volume":"41","author":"Mattonen","year":"2014","journal-title":"Med. Phys."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"100195","DOI":"10.1016\/j.health.2023.100195","article-title":"A novel hybrid deep learning method for early detection of lung cancer using neural networks","volume":"3","author":"Wankhade","year":"2023","journal-title":"Healthc. Anal."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/10\/435\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:08:23Z","timestamp":1760112503000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/10\/435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":24,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["a17100435"],"URL":"https:\/\/doi.org\/10.3390\/a17100435","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2024,10,1]]}}}