{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T11:26:04Z","timestamp":1784114764826,"version":"3.55.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Catholic Medical Center Research Foundation","award":["5-2020-B0001-00262"],"award-info":[{"award-number":["5-2020-B0001-00262"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Purpose<\/jats:title>\n<jats:p>Radical surgery is the primary treatment for early-stage resectable lung cancer, yet recurrence after curative surgery is not uncommon. Identifying patients at high risk of recurrence using preoperative computed tomography (CT) images could enable more aggressive surgical approaches, shorter surveillance intervals, and intensified adjuvant treatments. This study aims to analyze lung cancer sites in CT images to predict potential recurrences in high-risk individuals.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We retrieved anonymized imaging and clinical data from an institutional database, focusing on patients who underwent curative pulmonary resections for non-small cell lung cancers. Our study used a deep learning model, the Mask Region-based Convolutional Neural Network (MRCNN), to predict cancer locations and assign recurrence classification scores. To find optimized trained weighted values in the model, we developed preprocessing python codes, adjusted dynamic learning rate, and modifying hyper parameter in the model.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>The model training completed; we performed classifications using the validation dataset. The results, including the confusion matrix, demonstrated performance metrics: bounding box (0.390), classification (0.034), mask (0.266), Region Proposal Network (RPN) bounding box (0.341), and RPN classification (0.054). The model successfully identified lung cancer recurrence sites, which were then accurately mapped onto chest CT images to highlight areas of primary concern.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The trained model allows clinicians to focus on lung regions where cancer recurrence is more likely, acting as a significant aid in the detection and diagnosis of lung cancer. Serving as a clinical decision support system, it offers substantial support in managing lung cancer patients.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0300442","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T17:28:23Z","timestamp":1720805303000},"page":"e0300442","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhanced deep learning model for precise nodule localization and recurrence risk prediction following curative-intent surgery for lung cancer"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4027-1038","authenticated-orcid":true,"given":"Jihwan","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mi Jung","family":"Rho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2799-4570","authenticated-orcid":true,"given":"Mi Hyoung","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"pone.0300442.ref001","first-page":"72","article-title":"Cancer statistics, 2022.","author":"RL Siegel","year":"2022","journal-title":"CA: A Cancer J Clin"},{"key":"pone.0300442.ref002","doi-asserted-by":"crossref","first-page":"9567","DOI":"10.2147\/IJGM.S338250","article-title":"Prognosis and survival analysis of 922,317 lung cancer patients from the US based on the most recent data from the SEER database (April 15, 2021).","volume":"14","author":"S Hu","year":"2021","journal-title":"Int J Gen Med"},{"issue":"4","key":"pone.0300442.ref003","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1016\/j.ccm.2011.08.005","volume":"32","author":"WD Travis","year":"2011","journal-title":"Pathology of lung cancer Clin Chest Med"},{"issue":"12","key":"pone.0300442.ref004","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.1001\/jamaoncol.2021.4932","article-title":"Update of Incidence, Prevalence, Survival, and Initial Treatment in Patients With Non\u2013Small Cell Lung Cancer in the US.","volume":"7","author":"AK Ganti","year":"2021","journal-title":"JAMA Oncol"},{"issue":"5","key":"pone.0300442.ref005","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1164\/rccm.200504-531OE","article-title":"One hundred years of lung cancer","volume":"172","author":"GS Spiro","year":"2005","journal-title":"Am J Respir Crit Care Med"},{"key":"pone.0300442.ref006","first-page":"2023","article-title":"Non-small cell lung cancer (Version 3.2023)","volume":"13","author":"National Comprehensive Cancer NEtwork"},{"issue":"4","key":"pone.0300442.ref007","first-page":"242","volume":"3","author":"H Uramoto","year":"2013","journal-title":"Recurrence after surgery in patients with NSCKC Transl Lung Cacner Res"},{"issue":"4","key":"pone.0300442.ref008","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1097\/JTO.0b013e31824a9022","article-title":"Recurrence dynamics for non-small-cell lung cancer: effect of surgery on the development of metastases","volume":"7","author":"R Demicheli","year":"2012","journal-title":"J Thorac Oncol"},{"issue":"8","key":"pone.0300442.ref009","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1097\/JTO.0b013e31825cca6e","article-title":"Pathological Vascular Invasion and Tumor Differentiation Predict Cancer Recurrence in Stage ia Non\u2013Small-Cell Lung Cancer After Complete Surgical Resection.","volume":"7","author":"Y Shimada","year":"2012","journal-title":"J Thorac Oncol"},{"issue":"3","key":"pone.0300442.ref010","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1378\/chest.122.3.1037","article-title":"Prognostic factors in non-small cell lung cancer: a decade of progress","volume":"122","author":"MD Brundage","year":"2002","journal-title":"Chest"},{"issue":"6","key":"pone.0300442.ref011","doi-asserted-by":"crossref","first-page":"1494","DOI":"10.1378\/chest.10-3279","article-title":"Risk factors for tumor recurrence in patients with early-stage (stage I and II) non-small cell lung cancer: patient selection criteria for adjuvant chemotherapy according to the seventh edition TNM classification.","volume":"140","author":"R Maeda","year":"2011","journal-title":"Chest"},{"issue":"8","key":"pone.0300442.ref012","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1055\/s-0029-1185734","article-title":"Early recurrence after surgical resection in patients with pathological stage I non-small cell lung cancer","volume":"57","author":"R Kawachi","year":"2009","journal-title":"Thorac Cardiovasc Surg"},{"issue":"2","key":"pone.0300442.ref013","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/S0169-5002(02)00040-5","article-title":"Late events and clinical prognostic factors in stage I non small cell lung cancer","volume":"37","author":"F Pasini","year":"2002","journal-title":"Lung Cancer"},{"issue":"1","key":"pone.0300442.ref014","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1097\/JTO.0b013e3181f9abca","article-title":"Positron emission tomography\/computed tomography and lymphovascular invasion predict recurrence in stage I lung cancers","volume":"6","author":"S Shiono","year":"2011","journal-title":"J Thorac Oncol"},{"issue":"1","key":"pone.0300442.ref015","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1007\/s00330-018-5561-5","article-title":"Risk of pleural recurrence after percutaneous transthoracic needle biopsy in stage I non-small-cell lung cancer","volume":"29","author":"SY Ahn","year":"2019","journal-title":"Eur Radiol"},{"issue":"8","key":"pone.0300442.ref016","doi-asserted-by":"crossref","first-page":"e42043","DOI":"10.1371\/journal.pone.0042043","article-title":"Incidence of Pleural Recurrence after Computed Tomography-Guided Needle Biopsy in Stage I Lung Cancer.","volume":"7","author":"K Asakura","year":"2021","journal-title":"PLoS one"},{"issue":"2","key":"pone.0300442.ref017","doi-asserted-by":"crossref","first-page":"e2513","DOI":"10.1097\/MD.0000000000002513","article-title":"Preoperative CT Predicting Recurrence of Surgically Resected Adenocarcinoma of the Lung.","volume":"95","author":"HJ Koo","year":"2016","journal-title":"Medicine"},{"key":"pone.0300442.ref018","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1186\/s13019-021-01476-0","article-title":"Predicting recurrence of non-small cell lung cancer based on mean computed tomography value","volume":"16","author":"M Tamura","year":"2021","journal-title":"J Cardiothorac Surg"},{"key":"pone.0300442.ref019","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1007\/s11548-022-02694-0","article-title":"Use of deep learning to predict postoperative recurrence of lung adenocarcinoma from preoperative CT","volume":"17","author":"Y Sasaki","year":"2022","journal-title":"Int J CARDS"},{"key":"pone.0300442.ref020","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-38319-4","volume-title":"Clinical decision support systems","author":"ES Berner","year":"2007","edition":"3"},{"key":"pone.0300442.ref021","volume-title":"Machine Learning for OpenCV","author":"M. Beyeler","year":"2017"},{"key":"pone.0300442.ref022","article-title":"Mask r-cnn.","author":"K He","year":"2017","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"pone.0300442.ref023","article-title":"Deep residual learning for image recognition","author":"K He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0300442.ref024","article-title":"Feature pyramid networks for object detection","author":"T-Y Lin","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"issue":"4","key":"pone.0300442.ref025","article-title":"Interpretation and visualization techniques for deep learning models in medical imaging","volume":"66","author":"DT Huff","year":"2021","journal-title":"Phys Med Biol"},{"issue":"19","key":"pone.0300442.ref026","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges","volume":"27","author":"R Miotto","year":"2018","journal-title":"Brief Bioinform"},{"issue":"4","key":"pone.0300442.ref027","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1002\/cac2.12012","article-title":"Emerging role of deep learning-based artificial intelligence in tumor pathology","volume":"40","author":"Y Jiang","year":"2020","journal-title":"Cancer Coun"},{"issue":"6","key":"pone.0300442.ref028","doi-asserted-by":"crossref","first-page":"e567","DOI":"10.1016\/j.jtcvs.2023.01.022","article-title":"EpiCard investigators. Clinical utility of a deep-learning mortality prediction model for cardiac surgery decision making","volume":"166","author":"N Allou","year":"2023","journal-title":"J Thorac Cardiovasc Surg"},{"issue":"2","key":"pone.0300442.ref029","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1111\/joim.13483","article-title":"Predictive models for clinical decision making: Deep dives in practical machine learning","volume":"292","author":"S Eloranta","year":"2022","journal-title":"J Intern Med"},{"issue":"4","key":"pone.0300442.ref030","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1109\/TMI.2015.2508280","article-title":"Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching","volume":"35","author":"Y Guo","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0300442.ref031","doi-asserted-by":"crossref","DOI":"10.1016\/B978-0-12-810408-8.00018-3","volume-title":"Chest Radiograph Pathology Categorization via Transfer Learning","author":"I Diamant","year":"2017"},{"key":"pone.0300442.ref032","doi-asserted-by":"crossref","DOI":"10.1016\/B978-0-12-810408-8.00006-7","article-title":"Multi-instance multi-stage deep learning for medical image recognition","author":"Z Yan","year":"2017","journal-title":"Deep Learning for Medical Image Analysis.: Elsevier"},{"key":"pone.0300442.ref033","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-42999-1_10","article-title":"Fully convolutional networks in medical imaging: Applications to image enhancement and recognition.","author":"CF Baumgartner","year":"2017","journal-title":"Deep Learning and Convolutional Neural Networks for Medical Image Computing: Precision Medicine, High Performance and Large-Scale Datasets"},{"key":"pone.0300442.ref034","author":"M Gao","journal-title":"Interstitial lung diseases via deep convolutional neural networks: Segmentation label propagation"},{"key":"pone.0300442.ref035","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-42999-1_12","article-title":"Fully automated segmentation using distance regularised level set and deep-structured learning and inference.","author":"TA Ngo","year":"2017","journal-title":"Deep Learning and Convolutional Neural Networks for Medical Image Computing: Precision Medicine, High Performance and Large-Scale Datasets"},{"key":"pone.0300442.ref036","volume-title":"Automatic pancreas segmentation using coarse-to-fine Superpixel labeling, in Deep Learning and Convolutional Neural Networks for Medical Image Computing: Precision Medicine, High Performance and Large-Scale Datasets","author":"A Farag","year":"2017"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0300442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T17:28:56Z","timestamp":1720805336000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0300442"}},"subtitle":[],"editor":[{"given":"Xiaohui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0300442","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]}}}