{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:09:58Z","timestamp":1791839398437,"version":"4.3.4"},"reference-count":90,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T00:00:00Z","timestamp":1624924800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004035","name":"Jordan University of Science and Technology","doi-asserted-by":"crossref","award":["20190180"],"award-info":[{"award-number":["20190180"]}],"id":[{"id":"10.13039\/501100004035","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NVIDIA Corporation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Medical imaging refers to visualization techniques to provide valuable information about the internal structures of the human body for clinical applications, diagnosis, treatment, and scientific research. Segmentation is one of the primary methods for analyzing and processing medical images, which helps doctors diagnose accurately by providing detailed information on the body\u2019s required part. However, segmenting medical images faces several challenges, such as requiring trained medical experts and being time-consuming and error-prone. Thus, it appears necessary for an automatic medical image segmentation system. Deep learning algorithms have recently shown outstanding performance for segmentation tasks, especially semantic segmentation networks that provide pixel-level image understanding. By introducing the first fully convolutional network (FCN) for semantic image segmentation, several segmentation networks have been proposed on its basis. One of the state-of-the-art convolutional networks in the medical image field is U-Net. This paper presents a novel end-to-end semantic segmentation model, named Ens4B-UNet, for medical images that ensembles four U-Net architectures with pre-trained backbone networks. Ens4B-UNet utilizes U-Net\u2019s success with several significant improvements by adapting powerful and robust convolutional neural networks (CNNs) as backbones for U-Nets encoders and using the nearest-neighbor up-sampling in the decoders. Ens4B-UNet is designed based on the weighted average ensemble of four encoder-decoder segmentation models. The backbone networks of all ensembled models are pre-trained on the ImageNet dataset to exploit the benefit of transfer learning. For improving our models, we apply several techniques for training and predicting, including stochastic weight averaging (SWA), data augmentation, test-time augmentation (TTA), and different types of optimal thresholds. We evaluate and test our models on the 2019 Pneumothorax Challenge dataset, which contains 12,047 training images with 12,954 masks and 3,205 test images. Our proposed segmentation network achieves a 0.8608 mean Dice similarity coefficient (DSC) on the test set, which is among the top one-percent systems in the Kaggle competition.<\/jats:p>","DOI":"10.7717\/peerj-cs.607","type":"journal-article","created":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T04:41:17Z","timestamp":1624941677000},"page":"e607","source":"Crossref","is-referenced-by-count":120,"title":["Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures"],"prefix":"10.7717","volume":"7","author":[{"given":"Ayat","family":"Abedalla","sequence":"first","affiliation":[{"name":"Computer Science, Jordan University of Science and Technology, Irbid, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malak","family":"Abdullah","sequence":"additional","affiliation":[{"name":"Computer Science, Jordan University of Science and Technology, Irbid, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9372-9076","authenticated-orcid":true,"given":"Mahmoud","family":"Al-Ayyoub","sequence":"additional","affiliation":[{"name":"Computer Science, Jordan University of Science and Technology, Irbid, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elhadj","family":"Benkhelifa","sequence":"additional","affiliation":[{"name":"Smart Systems, AI and Cybersecurity Research Centre, Staffordshire University, Stoke on Trent, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2021,6,29]]},"reference":[{"key":"10.7717\/peerj-cs.607\/ref-1","article-title":"Research in medical imaging using image processing techniques","author":"Abdallah","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-2","first-page":"1","article-title":"2st-unet: 2-stage training model using u-net for pneumothorax segmentation in chest x-rays","author":"Abedalla","year":"2020"},{"key":"10.7717\/peerj-cs.607\/ref-3","doi-asserted-by":"publisher","first-page":"101406","DOI":"10.1109\/ACCESS.2020.2998601","article-title":"Httu-net: hybrid two track u-net for automatic brain tumor segmentation","volume":"8","author":"Aboelenein","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.607\/ref-4","article-title":"Understanding deep neural networks with rectified linear units","author":"Arora","year":"2016"},{"issue":"12","key":"10.7717\/peerj-cs.607\/ref-5","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.607\/ref-6","first-page":"404","article-title":"Surf: speeded up robust features","author":"Bay","year":"2006"},{"key":"10.7717\/peerj-cs.607\/ref-7","first-page":"77","article-title":"Fully convolutional network for liver segmentation and lesions detection","author":"Ben-Cohen","year":"2016"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-8","first-page":"125","article-title":"Albumentations: fast and flexible image augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information-An International Interdisciplinary Journal"},{"key":"10.7717\/peerj-cs.607\/ref-9","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFS","author":"Chen","year":"2014"},{"issue":"4","key":"10.7717\/peerj-cs.607\/ref-10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.607\/ref-11","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.7717\/peerj-cs.607\/ref-12","first-page":"2843","article-title":"Deep neural networks segment neuronal membranes in electron microscopy images","author":"Ciresan","year":"2012"},{"key":"10.7717\/peerj-cs.607\/ref-13","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.7717\/peerj-cs.607\/ref-14","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1109\/BMEI.2010.5639536","article-title":"MRI brain tumor segmentation with region growing method based on the gradients and variances along and inside of the boundary curve","volume-title":"2010 3rd International Conference on Biomedical Engineering and Informatics","volume":"1","author":"Deng","year":"2010"},{"issue":"3","key":"10.7717\/peerj-cs.607\/ref-15","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"10.7717\/peerj-cs.607\/ref-16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60964-5_44","article-title":"Automatic brain tumor detection and segmentation using u-net based fully convolutional networks","volume-title":"Medical Image Understanding and Analysis. MIUA 2017. Communications in Computer and Information Science","volume":"723","author":"Dong","year":"2017"},{"issue":"1","key":"10.7717\/peerj-cs.607\/ref-17","doi-asserted-by":"publisher","first-page":"e358","DOI":"10.7717\/peerj-cs.358","article-title":"Covid-19: a new deep learning computer-aided model for classification","volume":"7","author":"Elzeki","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.607\/ref-18","article-title":"A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms","author":"Fardo","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-19","first-page":"803","article-title":"Overview of current biomedical image segmentation methods","author":"Fasihi","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-20","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-21","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-22","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"Graves","year":"2014"},{"key":"10.7717\/peerj-cs.607\/ref-23","first-page":"747","article-title":"Cardiac MR image segmentation using deformable models","author":"Gupta","year":"1993"},{"key":"10.7717\/peerj-cs.607\/ref-24","first-page":"195","article-title":"The influence of the sigmoid function parameters on the speed of backpropagation learning","author":"Han","year":"1995"},{"key":"10.7717\/peerj-cs.607\/ref-25","first-page":"14","article-title":"Introduction to magnetic resonance imaging techniques","author":"Hanson","year":"2009","journal-title":"Danish Research Centre for Magnetic Resonance (DRCMR)"},{"issue":"4","key":"10.7717\/peerj-cs.607\/ref-26","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","article-title":"Brain tumor segmentation with deep neural networks","volume":"35","author":"Havaei","year":"2017","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.607\/ref-27","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-28","first-page":"144","article-title":"Sketch-based editing tools for tumour segmentation in 3d medical images","volume-title":"Computer Graphics Forum","volume":"32","author":"Heckel","year":"2013"},{"issue":"8","key":"10.7717\/peerj-cs.607\/ref-29","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.7717\/peerj-cs.607\/ref-30","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.7717\/peerj-cs.607\/ref-31","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.7717\/peerj-cs.607\/ref-32","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v33i01.3301590","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","author":"Irvin","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-34","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-35","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","article-title":"The distribution of the flora in the alpine zone. 1","volume":"11","author":"Jaccard","year":"1912","journal-title":"New Phytologist"},{"issue":"6","key":"10.7717\/peerj-cs.607\/ref-36","first-page":"475","article-title":"Two public chest x-ray datasets for computer-aided screening of pulmonary diseases","volume":"4","author":"Jaeger","year":"2014","journal-title":"Quantitative Imaging in Medicine and Surgery"},{"key":"10.7717\/peerj-cs.607\/ref-37","article-title":"Pneumothorax segmentation: deep learning image segmentation to predict pneumothorax","author":"Jakhar","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-38","article-title":"Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images","author":"Jun","year":"2018"},{"key":"10.7717\/peerj-cs.607\/ref-39","doi-asserted-by":"crossref","first-page":"1262","DOI":"10.1109\/ICIP.2005.1530292","article-title":"A classification approach for anatomical regions segmentation","volume-title":"IEEE International Conference on Image Processing 2005","volume":"2","author":"Kalinin","year":"2005"},{"key":"10.7717\/peerj-cs.607\/ref-40","first-page":"1","article-title":"Evaluation of deep learning-based approaches for covid-19 classification based on chest x-ray images","volume-title":"Signal, Image and Video Processing","author":"Kamal","year":"2021"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-41","first-page":"980","article-title":"MRI brain abnormalities segmentation using k-nearest neighbors (k-nn)","volume":"3","author":"Khalid","year":"2011","journal-title":"International Journal on Computer Science and Engineering"},{"key":"10.7717\/peerj-cs.607\/ref-42","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.7717\/peerj-cs.607\/ref-43","first-page":"3503","article-title":"U-segnet: fully convolutional neural network based automated brain tissue segmentation tool","author":"Kumar","year":"2018"},{"issue":"11","key":"10.7717\/peerj-cs.607\/ref-44","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"issue":"12","key":"10.7717\/peerj-cs.607\/ref-45","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","article-title":"H-denseunet: hybrid densely connected unet for liver and tumor segmentation from CT volumes","volume":"37","author":"Li","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.607\/ref-46","doi-asserted-by":"publisher","first-page":"5805","DOI":"10.1109\/ACCESS.2019.2963472","article-title":"Multi-task refined boundary-supervision U-Net (MRBSU-Net) for gastrointestinal stromal tumor segmentation in endoscopic ultrasound (EUS) images","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.607\/ref-47","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-48","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"10.7717\/peerj-cs.607\/ref-49","doi-asserted-by":"publisher","first-page":"202459","DOI":"10.1109\/ACCESS.2020.3035772","article-title":"Esophagus segmentation in computed tomography images using a U-Net neural network with a semiautomatic labeling method","volume":"8","author":"Lou","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.607\/ref-50","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1109\/ICCV.1999.790410","article-title":"Object recognition from local scale-invariant features","volume-title":"Proceedings of the Seventh IEEE International Conference on Computer Vision","volume":"2","author":"Lowe","year":"1999"},{"key":"10.7717\/peerj-cs.607\/ref-51","first-page":"805","article-title":"Thoracic disorders","author":"Lugo","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-52","first-page":"1551","article-title":"Fully convolutional multi-scale SCSE-Densenet for automatic pneumothorax segmentation in chest radiographs","author":"Luo","year":"2019"},{"issue":"5","key":"10.7717\/peerj-cs.607\/ref-53","doi-asserted-by":"publisher","first-page":"2002697","DOI":"10.1183\/13993003.02697-2020","article-title":"Covid-19 and pneumothorax: a multicentre retrospective case series","volume":"56","author":"Martinelli","year":"2020","journal-title":"European Respiratory Journal"},{"issue":"6Part10","key":"10.7717\/peerj-cs.607\/ref-54","doi-asserted-by":"publisher","first-page":"3493","DOI":"10.1118\/1.3611983","article-title":"SU-E-T-33: pydicom: an open source dicom library","volume":"38","author":"Mason","year":"2011","journal-title":"Medical Physics"},{"issue":"1","key":"10.7717\/peerj-cs.607\/ref-55","doi-asserted-by":"publisher","first-page":"3","DOI":"10.2174\/157340561101150423103441","article-title":"A survey on medical image segmentation","volume":"11","author":"Masood","year":"2015","journal-title":"Current Medical Imaging Reviews"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-56","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/S1361-8415(96)80007-7","article-title":"Deformable models in medical image analysis: a survey","volume":"1","author":"McInerney","year":"1996","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.607\/ref-57","first-page":"698","article-title":"Content-adaptive u-net architecture for medical image segmentation","author":"Mostayed","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-58","first-page":"1","article-title":"Brain tumor segmentation using thresholding, morphological operations and extraction of features of tumor","author":"Murthy","year":"2014"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-59","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1159\/000135932","article-title":"Pneumothorax","volume":"76","author":"Noppen","year":"2008","journal-title":"Respiration"},{"key":"10.7717\/peerj-cs.607\/ref-60","first-page":"238","article-title":"A new approach for model-based adaptive region growing in medical image analysis","author":"Pohle","year":"2001"},{"key":"10.7717\/peerj-cs.607\/ref-61","doi-asserted-by":"publisher","first-page":"2003308","DOI":"10.1183\/13993003.03308-2020","article-title":"Pleural diseases and COVID-19: ubi fumus, ibi ignis","volume":"56","author":"Porcel","year":"2020","journal-title":"European Respiratory Journal"},{"issue":"3","key":"10.7717\/peerj-cs.607\/ref-62","doi-asserted-by":"crossref","first-page":"1","DOI":"10.12928\/telkomnika.v18i3.14753","article-title":"Unet-vgg16 with transfer learning for MRI-based brain tumor segmentation","volume":"18","author":"Pravitasari","year":"2020","journal-title":"Telkomnika"},{"key":"10.7717\/peerj-cs.607\/ref-63","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science","volume":"9351","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-65","first-page":"4510","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.7717\/peerj-cs.607\/ref-66","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"Saon","year":"2017"},{"issue":"1","key":"10.7717\/peerj-cs.607\/ref-67","first-page":"1","article-title":"Image segmentation by using thresholding techniques for medical images","volume":"6","author":"Senthilkumaran","year":"2016","journal-title":"Computer Science & Engineering: An International Journal"},{"issue":"3","key":"10.7717\/peerj-cs.607\/ref-68","doi-asserted-by":"publisher","first-page":"2885","DOI":"10.1016\/j.aej.2021.01.011","article-title":"Developing an efficient deep neural network for automatic detection of covid-19 using chest x-ray images","volume":"60","author":"Sheykhivand","year":"2021","journal-title":"Alexandria Engineering Journal"},{"key":"10.7717\/peerj-cs.607\/ref-69","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"issue":"1","key":"10.7717\/peerj-cs.607\/ref-70","doi-asserted-by":"publisher","first-page":"241","DOI":"10.2214\/ajr.164.1.7998549","article-title":"The first clinical x-ray made in america-100 years","volume":"164","author":"Spiegel","year":"1995","journal-title":"American Journal of Roentgenology"},{"key":"10.7717\/peerj-cs.607\/ref-71","first-page":"11166","article-title":"Pixel-adaptive convolutional neural networks","author":"Su","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-72","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014"},{"key":"10.7717\/peerj-cs.607\/ref-73","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-74","first-page":"2820","article-title":"Mnasnet: platform-aware neural architecture search for mobile","author":"Tan","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-75","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-76","first-page":"1195","article-title":"Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017"},{"key":"10.7717\/peerj-cs.607\/ref-77","article-title":"A fully convolutional neural network for cardiac segmentation in short-axis MRI","author":"Tran","year":"2016"},{"issue":"8","key":"10.7717\/peerj-cs.607\/ref-78","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.compmedimag.2008.08.004","article-title":"A modified FCM algorithm for MRI brain image segmentation using both local and non-local spatial constraints","volume":"32","author":"Wang","year":"2008","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"10.7717\/peerj-cs.607\/ref-79","article-title":"Training deeper convolutional networks with deep supervision","author":"Wang","year":"2015"},{"key":"10.7717\/peerj-cs.607\/ref-80","article-title":"Test-time augmentation with uncertainty estimation for deep learning-based medical image segmentation","author":"Wang","year":"2018"},{"key":"10.7717\/peerj-cs.607\/ref-81","first-page":"2097","article-title":"Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017a"},{"key":"10.7717\/peerj-cs.607\/ref-82","first-page":"2097","article-title":"Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017b"},{"key":"10.7717\/peerj-cs.607\/ref-83","article-title":"Transformers: state-of-the-art natural language processing","author":"Wolf","year":"2019"},{"key":"10.7717\/peerj-cs.607\/ref-84","first-page":"3","article-title":"Cbam: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.7717\/peerj-cs.607\/ref-85","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1109\/ICPR.1998.712005","article-title":"An effective entropic thresholding for ultrasonic images","volume-title":"Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No. 98EX170)","volume":"2","author":"Wu","year":"1998"},{"key":"10.7717\/peerj-cs.607\/ref-86","first-page":"1492","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"10.7717\/peerj-cs.607\/ref-87","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","author":"Xu","year":"2015"},{"issue":"2","key":"10.7717\/peerj-cs.607\/ref-88","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/S0730-725X(02)00477-0","article-title":"Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms","volume":"20","author":"Yang","year":"2002","journal-title":"Magnetic Resonance Imaging"},{"issue":"Suppl 4","key":"10.7717\/peerj-cs.607\/ref-89","first-page":"S372","article-title":"Pneumothorax: from definition to diagnosis and treatment","volume":"6","author":"Zarogoulidis","year":"2014","journal-title":"Journal of Thoracic Disease"},{"key":"10.7717\/peerj-cs.607\/ref-90","first-page":"2881","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-607.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-607.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-607.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-607.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T04:41:55Z","timestamp":1624941715000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-607"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,29]]},"references-count":90,"alternative-id":["10.7717\/peerj-cs.607"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.607","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{"has-review":[{"id-type":"doi","id":"10.7287\/peerj-cs.607v0.1\/reviews\/3","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.607v0.1\/reviews\/2","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.607v0.1\/reviews\/1","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.607v0.2\/reviews\/2","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.607v0.2\/reviews\/3","asserted-by":"object"}]},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,29]]},"article-number":"e607"}}