{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T05:29:28Z","timestamp":1734067768946,"version":"3.30.2"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T00:00:00Z","timestamp":1733961600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science KAKENHI","doi-asserted-by":"crossref","award":["18K12095"],"award-info":[{"award-number":["18K12095"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Joint Usage\/Research Center for Interdisciplinary Large-Scale Information Infrastructures and High-Performance Computing Infrastructure Projects in Japan","award":["jh170036-DAH, jh180073-DAH, jh190047-DAH and jh200042-DAH"],"award-info":[{"award-number":["jh170036-DAH, jh180073-DAH, jh190047-DAH and jh200042-DAH"]}]},{"name":"Siemens Healthcare KK"},{"name":"HIMEDIC Inc.","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>A general-purpose method of emphasizing abnormal lesions in chest radiographs, named EGGPALE (Extrapolative, Generative and General-Purpose Abnormal Lesion Emphasizer), is presented. The proposed EGGPALE method is composed of a flow-based generative model and L-infinity-distance-based extrapolation in a latent space. The flow-based model is trained using only normal chest radiographs, and an invertible mapping function from the image space to the latent space is determined. In the latent space, a given unseen image is extrapolated so that the image point moves away from the normal chest X-ray hyperplane. Finally, the moved point is mapped back to the image space and the corresponding emphasized image is created. The proposed method was evaluated by an image interpretation experiment with nine radiologists and 1,000 chest radiographs, of which positive suspected lung cancer cases and negative cases were validated by computed tomography examinations. The sensitivity of EGGPALE-processed images showed +0.0559 average improvement compared with that of the original images, with -0.0192 deterioration of average specificity. The area under the receiver operating characteristic curve of the ensemble of nine radiologists showed a statistically significant improvement. From these results, the feasibility of EGGPALE for enhancing abnormal lesions was validated. Our code is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/utrad-ical\/Eggpale\" xlink:type=\"simple\">https:\/\/github.com\/utrad-ical\/Eggpale<\/jats:ext-link>.<\/jats:p>","DOI":"10.1371\/journal.pone.0315646","type":"journal-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T18:40:20Z","timestamp":1734028820000},"page":"e0315646","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep generative abnormal lesion emphasization validated by nine radiologists and 1000 chest X-rays with lung nodules"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7496-1651","authenticated-orcid":true,"given":"Shouhei","family":"Hanaoka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6471-9936","authenticated-orcid":true,"given":"Yukihiro","family":"Nomura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoto","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Issei","family":"Sato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soichiro","family":"Miki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeharu","family":"Yoshikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisaichi","family":"Shibata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9498-7501","authenticated-orcid":true,"given":"Takahiro","family":"Nakao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomomi","family":"Takenaga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"Koyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinichi","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noriko","family":"Kanemaru","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kotaro","family":"Fujimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoya","family":"Sakamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoya","family":"Nishiyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8688-3005","authenticated-orcid":true,"given":"Hirotaka","family":"Matsuzaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobutake","family":"Yamamichi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1180-2629","authenticated-orcid":true,"given":"Osamu","family":"Abe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,12,12]]},"reference":[{"key":"pone.0315646.ref001","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1038\/sj.bjc.6604351","article-title":"Sensitivity and specificity of lung cancer screening using chest low-dose computed tomography","volume":"98","author":"Y Toyoda","year":"2008","journal-title":"Br J Cancer"},{"key":"pone.0315646.ref002","article-title":"Diagnostic accuracy of chest radiography for the diagnosis of tuberculosis (TB) and its role in the detection of latent TB infection: a systematic review","author":"R Piccazzo","year":"2014","journal-title":"J Rheumatol"},{"key":"pone.0315646.ref003","doi-asserted-by":"crossref","first-page":"e0204155","DOI":"10.1371\/journal.pone.0204155","article-title":"Deep learning in chest radiography: Detection of findings and presence of change","volume":"13","author":"R Singh","year":"2018","journal-title":"PLoS One"},{"key":"pone.0315646.ref004","first-page":"485","article-title":"Radiologic errors in patients with lung cancer","volume":"134","author":"JV Forrest","year":"1981","journal-title":"West J Med"},{"key":"pone.0315646.ref005","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1378\/chest.115.3.720","article-title":"Miss rate of lung cancer on the chest radiograph in clinical practice","volume":"115","author":"LG Quekel","year":"1999","journal-title":"Chest"},{"key":"pone.0315646.ref006","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/S0009-9260(97)80280-2","article-title":"An assessment of inter-observer agreement and accuracy when reporting plain radiographs","volume":"52","author":"GR Tudor","year":"1997","journal-title":"Clin Radiol"},{"key":"pone.0315646.ref007","volume-title":"Digital image processing","author":"RC Gonzalez","year":"2002"},{"key":"pone.0315646.ref008","doi-asserted-by":"crossref","unstructured":"Hummel R. Image enhancement by histogram transformation. comp. graph. 1977.","DOI":"10.1016\/S0146-664X(77)80011-7"},{"key":"pone.0315646.ref009","first-page":"8577","article-title":"Triad histogram to enhance chest X-ray image","author":"R. Senthilkumar","year":"2014","journal-title":"nternational j adv res comput commun eng"},{"key":"pone.0315646.ref010","first-page":"590","article-title":"Improved lung nodule visualization on chest radiographs using digital filtering and contrast enhancement","volume":"110","author":"BY Kwan","year":"2011","journal-title":"Proc World Acad of Sci Eng Technol"},{"key":"pone.0315646.ref011","doi-asserted-by":"crossref","unstructured":"Bao C, Sheng C. A parameterized logarithmic image processing method based on Laplacian of Gaussian filtering for lung nodules enhancement in chest radiographs. 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA). ieeexplore.ieee.org; 2013. pp. 649\u2013652.","DOI":"10.1109\/IMSNA.2013.6743360"},{"key":"pone.0315646.ref012","first-page":"1987","article-title":"Hessian-LoG: a novel dot enhancement filter","volume":"6","author":"Z Shi","year":"2012","journal-title":"ICIC Exp Lett"},{"key":"pone.0315646.ref013","doi-asserted-by":"crossref","first-page":"59","DOI":"10.4103\/2228-7477.150435","article-title":"Multi-scale Morphological Image Enhancement of Chest Radiographs by a Hybrid Scheme","volume":"5","author":"FS Alavijeh","year":"2015","journal-title":"J Med Signals Sens"},{"key":"pone.0315646.ref014","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1148\/radiol.11100153","article-title":"Lung nodules: improved detection with software that suppresses the rib and clavicle on chest radiographs","volume":"260","author":"MT Freedman","year":"2011","journal-title":"Radiology"},{"key":"pone.0315646.ref015","doi-asserted-by":"crossref","first-page":"W397","DOI":"10.2214\/AJR.09.2431","article-title":"Performance of radiologists in detection of small pulmonary nodules on chest radiographs: effect of rib suppression with a massive-training artificial neural network","volume":"193","author":"S Oda","year":"2009","journal-title":"AJR Am J Roentgenol"},{"key":"pone.0315646.ref016","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1109\/TMI.2006.871549","article-title":"Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN)","volume":"25","author":"K Suzuki","year":"2006","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0315646.ref017","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"pone.0315646.ref018","doi-asserted-by":"crossref","first-page":"568","DOI":"10.2214\/AJR.19.21512","article-title":"Tackling the Radiological Society of North America Pneumonia Detection Challenge","volume":"213","author":"I Pan","year":"2019","journal-title":"AJR Am J Roentgenol"},{"key":"pone.0315646.ref019","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.5588\/ijtld.15.0926","article-title":"Computer-aided detection of pulmonary tuberculosis on digital chest radiographs: a systematic review","volume":"20","author":"T Pande","year":"2016","journal-title":"Int J Tuberc Lung Dis"},{"key":"pone.0315646.ref020","first-page":"e180041","article-title":"Augmenting the National Institutes of Health Chest Radiograph Dataset with Expert Annotations of Possible Pneumonia","volume":"1","author":"G Shih","year":"2019","journal-title":"Radiology: Artificial Intelligence"},{"key":"pone.0315646.ref021","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1186\/s12938-018-0544-y","article-title":"Computer-aided detection in chest radiography based on artificial intelligence: a survey","volume":"17","author":"C Qin","year":"2018","journal-title":"Biomed Eng Online"},{"key":"pone.0315646.ref022","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-Ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2017.","DOI":"10.1109\/CVPR.2017.369"},{"key":"pone.0315646.ref023","unstructured":"Nalisnick E, Matsukawa A, Teh YW, Gorur D, Lakshminarayanan B. Do Deep Generative Models Know What They Don\u2019t Know? arXiv [stat.ML]. 2018. http:\/\/arxiv.org\/abs\/1810.09136"},{"key":"pone.0315646.ref024","unstructured":"Kingma DP, Welling M. Auto-Encoding Variational Bayes. arXiv [stat.ML]. 2013. http:\/\/arxiv.org\/abs\/1312.6114v10"},{"key":"pone.0315646.ref025","volume-title":"Advances in Neural Information Processing Systems","author":"I Goodfellow","year":"2014"},{"key":"pone.0315646.ref026","doi-asserted-by":"crossref","first-page":"101552","DOI":"10.1016\/j.media.2019.101552","article-title":"Generative adversarial network in medical imaging: A review","volume":"58","author":"X Yi","year":"2019","journal-title":"Med Image Anal"},{"key":"pone.0315646.ref027","unstructured":"Kingma DP, Dhariwal P. Glow: Generative Flow with Invertible 1x1 Convolutions. arXiv [stat.ML]. 2018. http:\/\/arxiv.org\/abs\/1807.03039"},{"key":"pone.0315646.ref028","first-page":"105751P","article-title":"A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes. Medical Imaging 2018: Computer-Aided Diagnosis","author":"D Sato","year":"2018","journal-title":"International Society for Optics and Photonics"},{"key":"pone.0315646.ref029","unstructured":"Chen X, Konukoglu E. Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders. arXiv [cs.CV]. 2018. http:\/\/arxiv.org\/abs\/1806.04972"},{"key":"pone.0315646.ref030","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1007\/978-3-319-59050-9_12","article-title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","author":"T Schlegl","year":"2017","journal-title":"Information Processing in Medical Imaging. Springer International Publishing"},{"key":"pone.0315646.ref031","doi-asserted-by":"crossref","unstructured":"Zenati H, Romain M, Foo C-S, Lecouat B, Chandrasekhar V. Adversarially Learned Anomaly Detection. 2018 IEEE International Conference on Data Mining (ICDM). 2018. pp. 727\u2013736.","DOI":"10.1109\/ICDM.2018.00088"},{"key":"pone.0315646.ref032","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1007\/s10278-020-00413-2","article-title":"Unsupervised Deep Anomaly Detection in Chest Radiographs","volume":"34","author":"T Nakao","year":"2021","journal-title":"J Digit Imaging"},{"key":"pone.0315646.ref033","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks","volume":"54","author":"T Schlegl","year":"2019","journal-title":"Med Image Anal"},{"key":"pone.0315646.ref034","article-title":"A versatile anomaly detection method for medical images with a flow-based generative model in semi-supervision setting","author":"H Shibata","year":"2021","journal-title":"Int J CARS (In Press)"},{"key":"pone.0315646.ref035","doi-asserted-by":"crossref","first-page":"101839","DOI":"10.1016\/j.media.2020.101839","article-title":"A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis","volume":"67","author":"Y Tang","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0315646.ref036","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1109\/TMI.2018.2881415","article-title":"Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural Networks","volume":"38","author":"H Salehinejad","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0315646.ref037","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s42979-021-00720-7","article-title":"Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs","volume":"2","author":"B Segal","year":"2021","journal-title":"SN Computer Science"},{"key":"pone.0315646.ref038","unstructured":"Dinh L, Krueger D, Bengio Y. NICE: Non-linear Independent Components Estimation. arXiv [cs.LG]. 2014. http:\/\/arxiv.org\/abs\/1410.8516"},{"key":"pone.0315646.ref039","unstructured":"Dinh L, Sohl-Dickstein J, Bengio S. Density estimation using Real NVP. arXiv [cs.LG]. 2016. http:\/\/arxiv.org\/abs\/1605.08803"},{"key":"pone.0315646.ref040","volume-title":"Optimization Online","author":"Christoph Brauer"},{"key":"pone.0315646.ref041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0010-4655(96)00017-3","article-title":"ScaLAPACK: a portable linear algebra library for distributed memory computers\u2014design issues and performance","volume":"97","author":"J Choi","year":"1996","journal-title":"Comput Phys Commun"},{"key":"pone.0315646.ref042","unstructured":"Ch\u01b0\u01a1ng HM. ML-BoneSuppression. Github https:\/\/github.com\/hmchuong\/ML-BoneSuppression; https:\/\/github.com\/hmchuong\/ML-BoneSuppression"},{"key":"pone.0315646.ref043","doi-asserted-by":"crossref","first-page":"2941","DOI":"10.1007\/s00330-007-0667-1","article-title":"Comparison of sensitivity and reading time for the use of computer-aided detection (CAD) of pulmonary nodules at MDCT as concurrent or second reader","author":"F Beyer","year":"2007","journal-title":"European Radiology"},{"key":"pone.0315646.ref044","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1148\/radiol.2019182465","article-title":"Deep Convolutional Neural Network\u2013based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs","volume":"294","author":"Y Sim","year":"2020","journal-title":"Radiology"},{"key":"pone.0315646.ref045","unstructured":"aicentral. In: aicentral [Internet]. [cited 10 Jun 2022]. https:\/\/aicentral.acrdsi.org\/"},{"key":"pone.0315646.ref046","unstructured":"grand-challenge.org. In: grand-challenge.org [Internet]. [cited 10 Jun 2022]. https:\/\/grand-challenge.org\/aiforradiology\/"},{"key":"pone.0315646.ref047","doi-asserted-by":"crossref","first-page":"2399","DOI":"10.1016\/j.ejrad.2013.09.016","article-title":"Bone suppressed images improve radiologists\u2019 detection performance for pulmonary nodules in chest radiographs","volume":"82","author":"S Schalekamp","year":"2013","journal-title":"Eur J Radiol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T18:40:49Z","timestamp":1734028849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315646"}},"subtitle":[],"editor":[{"given":"Asadullah","family":"Shaikh","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,12]]},"references-count":47,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0315646","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,12]]}}}