{"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/applying-faster-r-cnn-for-object-detection-on","title":"Applying Faster R-CNN for Object Detection on Malaria Images","arxiv_id":"1804.09548","date":"2018-04-25","proceeding":null,"authors":["Jane Hung","Deepali Ravel","Stefanie C. P. Lopes","Gabriel Rangel","Odailton Amaral Nery","Benoit Malleret","Francois Nosten","Marcus V. G. Lacerda","Marcelo U. Ferreira","Laurent Rénia","Manoj T. Duraisingh","Fabio T. M. Costa","Matthias Marti","Anne E. Carpenter"],"abstract":"Deep learning based models have had great success in object detection, but\nthe state of the art models have not yet been widely applied to biological\nimage data. We apply for the first time an object detection model previously\nused on natural images to identify cells and recognize their stages in\nbrightfield microscopy images of malaria-infected blood. Many micro-organisms\nlike malaria parasites are still studied by expert manual inspection and hand\ncounting. This type of object detection task is challenging due to factors like\nvariations in cell shape, density, and color, and uncertainty of some cell\nclasses. In addition, annotated data useful for training is scarce, and the\nclass distribution is inherently highly imbalanced due to the dominance of\nuninfected red blood cells. We use Faster Region-based Convolutional Neural\nNetwork (Faster R-CNN), one of the top performing object detection models in\nrecent years, pre-trained on ImageNet but fine tuned with our data, and compare\nit to a baseline, which is based on a traditional approach consisting of cell\nsegmentation, extraction of several single-cell features, and classification\nusing random forests. To conduct our initial study, we collect and label a\ndataset of 1300 fields of view consisting of around 100,000 individual cells.\nWe demonstrate that Faster R-CNN outperforms our baseline and put the results\nin context of human performance.","url_abs":"http://arxiv.org/abs/1804.09548v2","url_pdf":"http://arxiv.org/pdf/1804.09548v2.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":"applying-faster-r-cnn-for-object-detection-on","repo_url":"https://github.com/ErickDiaz/bioinformatic_thesis_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"applying-faster-r-cnn-for-object-detection-on","repo_url":"https://github.com/sriluk9/MalariaCells-ObjectDetection-Using-FasterRCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"cell-segmentation","task_name":"Cell Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}