Keras R-CNN: library for cell detection in biological images using deep neural networks
Abstract Background A common yet still manual task in basic biology research, high-throughput drug screening and digital pathology is identifying the number, location, and type of individual cells in images. Object detection methods can be useful for identifying individual cells as well as their...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2021
|
| Online Access: | https://hdl.handle.net/1721.1/131732 |
| _version_ | 1826210997687287808 |
|---|---|
| author | Hung, Jane Goodman, Allen Ravel, Deepali Lopes, Stefanie C P Rangel, Gabriel W Nery, Odailton A Malleret, Benoit Nosten, Francois Lacerda, Marcus V G Ferreira, Marcelo U Rénia, Laurent Duraisingh, Manoj T Costa, Fabio T M Marti, Matthias Carpenter, Anne E |
| author2 | Massachusetts Institute of Technology. Department of Chemical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Chemical Engineering Hung, Jane Goodman, Allen Ravel, Deepali Lopes, Stefanie C P Rangel, Gabriel W Nery, Odailton A Malleret, Benoit Nosten, Francois Lacerda, Marcus V G Ferreira, Marcelo U Rénia, Laurent Duraisingh, Manoj T Costa, Fabio T M Marti, Matthias Carpenter, Anne E |
| author_sort | Hung, Jane |
| collection | MIT |
| description | Abstract
Background
A common yet still manual task in basic biology research, high-throughput drug screening and digital pathology is identifying the number, location, and type of individual cells in images. Object detection methods can be useful for identifying individual cells as well as their phenotype in one step. State-of-the-art deep learning for object detection is poised to improve the accuracy and efficiency of biological image analysis.
Results
We created Keras R-CNN to bring leading computational research to the everyday practice of bioimage analysts. Keras R-CNN implements deep learning object detection techniques using Keras and Tensorflow (
https://github.com/broadinstitute/keras-rcnn
). We demonstrate the command line tool’s simplified Application Programming Interface on two important biological problems, nucleus detection and malaria stage classification, and show its potential for identifying and classifying a large number of cells. For malaria stage classification, we compare results with expert human annotators and find comparable performance.
Conclusions
Keras R-CNN is a Python package that performs automated cell identification for both brightfield and fluorescence images and can process large image sets. Both the package and image datasets are freely available on GitHub and the Broad Bioimage Benchmark Collection. |
| first_indexed | 2024-09-23T14:59:07Z |
| format | Article |
| id | mit-1721.1/131732 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:59:07Z |
| publishDate | 2021 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | mit-1721.1/1317322023-03-15T19:25:11Z Keras R-CNN: library for cell detection in biological images using deep neural networks Hung, Jane Goodman, Allen Ravel, Deepali Lopes, Stefanie C P Rangel, Gabriel W Nery, Odailton A Malleret, Benoit Nosten, Francois Lacerda, Marcus V G Ferreira, Marcelo U Rénia, Laurent Duraisingh, Manoj T Costa, Fabio T M Marti, Matthias Carpenter, Anne E Massachusetts Institute of Technology. Department of Chemical Engineering Abstract Background A common yet still manual task in basic biology research, high-throughput drug screening and digital pathology is identifying the number, location, and type of individual cells in images. Object detection methods can be useful for identifying individual cells as well as their phenotype in one step. State-of-the-art deep learning for object detection is poised to improve the accuracy and efficiency of biological image analysis. Results We created Keras R-CNN to bring leading computational research to the everyday practice of bioimage analysts. Keras R-CNN implements deep learning object detection techniques using Keras and Tensorflow ( https://github.com/broadinstitute/keras-rcnn ). We demonstrate the command line tool’s simplified Application Programming Interface on two important biological problems, nucleus detection and malaria stage classification, and show its potential for identifying and classifying a large number of cells. For malaria stage classification, we compare results with expert human annotators and find comparable performance. Conclusions Keras R-CNN is a Python package that performs automated cell identification for both brightfield and fluorescence images and can process large image sets. Both the package and image datasets are freely available on GitHub and the Broad Bioimage Benchmark Collection. 2021-09-20T17:30:01Z 2021-09-20T17:30:01Z 2020-07-11 2020-07-12T03:48:08Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/131732 BMC Bioinformatics. 2020 Jul 11;21(1):300 PUBLISHER_CC en https://doi.org/10.1186/s12859-020-03635-x Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf BioMed Central BioMed Central |
| spellingShingle | Hung, Jane Goodman, Allen Ravel, Deepali Lopes, Stefanie C P Rangel, Gabriel W Nery, Odailton A Malleret, Benoit Nosten, Francois Lacerda, Marcus V G Ferreira, Marcelo U Rénia, Laurent Duraisingh, Manoj T Costa, Fabio T M Marti, Matthias Carpenter, Anne E Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title | Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title_full | Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title_fullStr | Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title_full_unstemmed | Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title_short | Keras R-CNN: library for cell detection in biological images using deep neural networks |
| title_sort | keras r cnn library for cell detection in biological images using deep neural networks |
| url | https://hdl.handle.net/1721.1/131732 |
| work_keys_str_mv | AT hungjane kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT goodmanallen kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT raveldeepali kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT lopesstefaniecp kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT rangelgabrielw kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT neryodailtona kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT malleretbenoit kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT nostenfrancois kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT lacerdamarcusvg kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT ferreiramarcelou kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT renialaurent kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT duraisinghmanojt kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT costafabiotm kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT martimatthias kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks AT carpenterannee kerasrcnnlibraryforcelldetectioninbiologicalimagesusingdeepneuralnetworks |