{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lung-nodule-classification-using-deep-local","title":"Lung Nodule Classification using Deep Local-Global Networks","arxiv_id":"1904.10126","date":"2019-04-23","proceeding":null,"authors":["Mundher Al-Shabi","Boon Leong Lan","Wai Yee Chan","Kwan-Hoong Ng","Maxine Tan"],"abstract":"Purpose: Lung nodules have very diverse shapes and sizes, which makes\nclassifying them as benign/malignant a challenging problem. In this paper, we\npropose a novel method to predict the malignancy of nodules that have the\ncapability to analyze the shape and size of a nodule using a global feature\nextractor, as well as the density and structure of the nodule using a local\nfeature extractor. Methods: We propose to use Residual Blocks with a 3x3 kernel\nsize for local feature extraction, and Non-Local Blocks to extract the global\nfeatures. The Non-Local Block has the ability to extract global features\nwithout using a huge number of parameters. The key idea behind the Non-Local\nBlock is to apply matrix multiplications between features on the same feature\nmaps. Results: We trained and validated the proposed method on the LIDC-IDRI\ndataset which contains 1,018 computed tomography (CT) scans. We followed a\nrigorous procedure for experimental setup namely, 10-fold cross-validation and\nignored the nodules that had been annotated by less than 3 radiologists. The\nproposed method achieved state-of-the-art results with AUC=95.62%, while\nsignificantly outperforming other baseline methods. Conclusions: Our proposed\nDeep Local-Global network has the capability to accurately extract both local\nand global features. Our new method outperforms state-of-the-art architecture\nincluding Densenet and Resnet with transfer learning.","url_abs":"http://arxiv.org/abs/1904.10126v1","url_pdf":"http://arxiv.org/pdf/1904.10126v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lung-nodule-classification-using-deep-local","repo_url":"https://github.com/mundher/local-global","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"lung-nodule-classification","task_name":"Lung Nodule Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lung-nodule-classification-on-lidc-idri","task":"Lung Nodule Classification","dataset":"LIDC-IDRI","model":"Local-Global","rank_in_archive_order":6,"of":8,"metrics":{"AUC":"95.62","Accuracy":"88.46","Accuracy(10-fold)":"88.46"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}