Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images
The Dicentric Chromosome Assay (DCA) is widely used in biological dosimetry, where the number of dicentric chromosomes induced by ionizing radiation (IR) exposure is quantified to estimate the absorbed radiation dose an individual has received. Dicentric chromosome scoring is a laborious and time-co...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/22/10440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267741426024448 |
|---|---|
| author | Ignacio Atencia-Jiménez Adayabalam S. Balajee Miguel J. Ruiz-Gómez Francisco Sendra-Portero Alegría Montoro Miguel A. Molina-Cabello |
| author_facet | Ignacio Atencia-Jiménez Adayabalam S. Balajee Miguel J. Ruiz-Gómez Francisco Sendra-Portero Alegría Montoro Miguel A. Molina-Cabello |
| author_sort | Ignacio Atencia-Jiménez |
| collection | DOAJ |
| description | The Dicentric Chromosome Assay (DCA) is widely used in biological dosimetry, where the number of dicentric chromosomes induced by ionizing radiation (IR) exposure is quantified to estimate the absorbed radiation dose an individual has received. Dicentric chromosome scoring is a laborious and time-consuming process which is performed manually in most cytogenetic biodosimetry laboratories. Further, dicentric chromosome scoring constitutes a bottleneck when several hundreds of samples need to be analyzed for dose estimation in the aftermath of large-scale radiological/nuclear incident(s). Recently, much interest has focused on automating dicentric chromosome scoring using Artificial Intelligence (AI) tools to reduce analysis time and improve the accuracy of dicentric chromosome detection. Our study aims to detect dicentric chromosomes in metaphase plate images using an ensemble of artificial neural network detectors suitable for datasets that present a low number of samples (in this work, only 50 images). In our approach, the input image is first processed by several operators, each producing a transformed image. Then, each transformed image is transferred to a specific detector trained with a training set processed by the same operator that transformed the image. Following this, the detectors provide their predictions about the detected chromosomes. Finally, all predictions are combined using a consensus function. Regarding the operators used, images were binarized separately applying Otsu and Spline techniques, while morphological opening and closing filters with different sizes were used to eliminate noise, isolate specific components, and enhance the structures of interest (chromosomes) within the image. Consensus-based decisions are typically more precise than those made by individual networks, as the consensus method can rectify certain misclassifications, assuming that individual network results are correct. The results indicate that our methodology worked satisfactorily in detecting a majority of chromosomes, with remarkable classification performance even with the low number of training samples utilized. AI-based dicentric chromosome detection will be beneficial for a rapid triage by improving the detection of dicentric chromosomes and thereby the dose prediction accuracy. |
| format | Article |
| id | doaj-art-58114c35d33344ff8a254dc40c0a32fd |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-58114c35d33344ff8a254dc40c0a32fd2025-08-20T01:53:40ZengMDPI AGApplied Sciences2076-34172024-11-0114221044010.3390/app142210440Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase ImagesIgnacio Atencia-Jiménez0Adayabalam S. Balajee1Miguel J. Ruiz-Gómez2Francisco Sendra-Portero3Alegría Montoro4Miguel A. Molina-Cabello5ITIS Software, University of Málaga, 29071 Málaga, SpainCytogenetic Biodosimetry Laboratory, Radiation Emergency Assistance Center, Training Site, Oak Ridge Institute for Science and Education, Oak Ridge Associated Universities, Oak Ridge, TN 37830, USADepartamento de Radiología y Medicina Física, Facultad de Medicina, Universidad de Málaga, 29010 Málaga, SpainDepartamento de Radiología y Medicina Física, Facultad de Medicina, Universidad de Málaga, 29010 Málaga, SpainLaboratorio de Biodosimetría, Servicio de Protección Radiológica, Hospital Universitario y Politécnico la Fe, 46026 Valencia, SpainITIS Software, University of Málaga, 29071 Málaga, SpainThe Dicentric Chromosome Assay (DCA) is widely used in biological dosimetry, where the number of dicentric chromosomes induced by ionizing radiation (IR) exposure is quantified to estimate the absorbed radiation dose an individual has received. Dicentric chromosome scoring is a laborious and time-consuming process which is performed manually in most cytogenetic biodosimetry laboratories. Further, dicentric chromosome scoring constitutes a bottleneck when several hundreds of samples need to be analyzed for dose estimation in the aftermath of large-scale radiological/nuclear incident(s). Recently, much interest has focused on automating dicentric chromosome scoring using Artificial Intelligence (AI) tools to reduce analysis time and improve the accuracy of dicentric chromosome detection. Our study aims to detect dicentric chromosomes in metaphase plate images using an ensemble of artificial neural network detectors suitable for datasets that present a low number of samples (in this work, only 50 images). In our approach, the input image is first processed by several operators, each producing a transformed image. Then, each transformed image is transferred to a specific detector trained with a training set processed by the same operator that transformed the image. Following this, the detectors provide their predictions about the detected chromosomes. Finally, all predictions are combined using a consensus function. Regarding the operators used, images were binarized separately applying Otsu and Spline techniques, while morphological opening and closing filters with different sizes were used to eliminate noise, isolate specific components, and enhance the structures of interest (chromosomes) within the image. Consensus-based decisions are typically more precise than those made by individual networks, as the consensus method can rectify certain misclassifications, assuming that individual network results are correct. The results indicate that our methodology worked satisfactorily in detecting a majority of chromosomes, with remarkable classification performance even with the low number of training samples utilized. AI-based dicentric chromosome detection will be beneficial for a rapid triage by improving the detection of dicentric chromosomes and thereby the dose prediction accuracy.https://www.mdpi.com/2076-3417/14/22/10440deep learningneural networkobject detectionensemblebiological dosimetrydicentric chromosome |
| spellingShingle | Ignacio Atencia-Jiménez Adayabalam S. Balajee Miguel J. Ruiz-Gómez Francisco Sendra-Portero Alegría Montoro Miguel A. Molina-Cabello Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images Applied Sciences deep learning neural network object detection ensemble biological dosimetry dicentric chromosome |
| title | Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images |
| title_full | Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images |
| title_fullStr | Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images |
| title_full_unstemmed | Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images |
| title_short | Neural Network Ensemble to Detect Dicentric Chromosomes in Metaphase Images |
| title_sort | neural network ensemble to detect dicentric chromosomes in metaphase images |
| topic | deep learning neural network object detection ensemble biological dosimetry dicentric chromosome |
| url | https://www.mdpi.com/2076-3417/14/22/10440 |
| work_keys_str_mv | AT ignacioatenciajimenez neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages AT adayabalamsbalajee neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages AT migueljruizgomez neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages AT franciscosendraportero neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages AT alegriamontoro neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages AT miguelamolinacabello neuralnetworkensembletodetectdicentricchromosomesinmetaphaseimages |