Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images
In biomedical research, cell analysis is important to assess physiological and pathophysiological information. Virtual microscopy offers the unique possibility to study the compositions of tissues at a cellular scale. However, images acquired at such high spatial resolution are massive, contain comp...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-12-01
|
| Series: | Frontiers in Neuroanatomy |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnana.2019.00098/full |
| _version_ | 1818555719387971584 |
|---|---|
| author | Zhenzhen You Zhenzhen You Yaël Balbastre Clément Bouvier Anne-Sophie Hérard Pauline Gipchtein Philippe Hantraye Caroline Jan Nicolas Souedet Thierry Delzescaux |
| author_facet | Zhenzhen You Zhenzhen You Yaël Balbastre Clément Bouvier Anne-Sophie Hérard Pauline Gipchtein Philippe Hantraye Caroline Jan Nicolas Souedet Thierry Delzescaux |
| author_sort | Zhenzhen You |
| collection | DOAJ |
| description | In biomedical research, cell analysis is important to assess physiological and pathophysiological information. Virtual microscopy offers the unique possibility to study the compositions of tissues at a cellular scale. However, images acquired at such high spatial resolution are massive, contain complex information, and are therefore difficult to analyze automatically. In this article, we address the problem of individualization of size-varying and touching neurons in optical microscopy two-dimensional (2-D) images. Our approach is based on a series of processing steps that incorporate increasingly more information. (1) After a step of segmentation of neuron class using a Random Forest classifier, a novel min-max filter is used to enhance neurons’ centroids and boundaries, enabling the use of region growing process based on a contour-based model to drive it to neuron boundary and achieve individualization of touching neurons. (2) Taking into account size-varying neurons, an adaptive multiscale procedure aiming at individualizing touching neurons is proposed. This protocol was evaluated in 17 major anatomical regions from three NeuN-stained macaque brain sections presenting diverse and comprehensive neuron densities. Qualitative and quantitative analyses demonstrate that the proposed method provides satisfactory results in most regions (e.g., caudate, cortex, subiculum, and putamen) and outperforms a baseline Watershed algorithm. Neuron counts obtained with our method show high correlation with an adapted stereology technique performed by two experts (respectively, 0.983 and 0.975 for the two experts). Neuron diameters obtained with our method ranged between 2 and 28.6 μm, matching values reported in the literature. Further works will aim to evaluate the impact of staining and interindividual variability on our protocol. |
| first_indexed | 2024-12-12T09:57:16Z |
| format | Article |
| id | doaj.art-042b13b49ccc40798480ca78b1c024b8 |
| institution | Directory Open Access Journal |
| issn | 1662-5129 |
| language | English |
| last_indexed | 2024-12-12T09:57:16Z |
| publishDate | 2019-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroanatomy |
| spelling | doaj.art-042b13b49ccc40798480ca78b1c024b82022-12-22T00:28:06ZengFrontiers Media S.A.Frontiers in Neuroanatomy1662-51292019-12-011310.3389/fnana.2019.00098487271Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic ImagesZhenzhen You0Zhenzhen You1Yaël Balbastre2Clément Bouvier3Anne-Sophie Hérard4Pauline Gipchtein5Philippe Hantraye6Caroline Jan7Nicolas Souedet8Thierry Delzescaux9CEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceSchool of Computer Science and Engineering, Xi’an University of Technology, Xi’an, ChinaCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceCEA-CNRS-UMR 9199, Laboratoire des Maladies Neurodégénératives, MIRCen, Université Paris-Saclay, Fontenay-aux-Roses, FranceIn biomedical research, cell analysis is important to assess physiological and pathophysiological information. Virtual microscopy offers the unique possibility to study the compositions of tissues at a cellular scale. However, images acquired at such high spatial resolution are massive, contain complex information, and are therefore difficult to analyze automatically. In this article, we address the problem of individualization of size-varying and touching neurons in optical microscopy two-dimensional (2-D) images. Our approach is based on a series of processing steps that incorporate increasingly more information. (1) After a step of segmentation of neuron class using a Random Forest classifier, a novel min-max filter is used to enhance neurons’ centroids and boundaries, enabling the use of region growing process based on a contour-based model to drive it to neuron boundary and achieve individualization of touching neurons. (2) Taking into account size-varying neurons, an adaptive multiscale procedure aiming at individualizing touching neurons is proposed. This protocol was evaluated in 17 major anatomical regions from three NeuN-stained macaque brain sections presenting diverse and comprehensive neuron densities. Qualitative and quantitative analyses demonstrate that the proposed method provides satisfactory results in most regions (e.g., caudate, cortex, subiculum, and putamen) and outperforms a baseline Watershed algorithm. Neuron counts obtained with our method show high correlation with an adapted stereology technique performed by two experts (respectively, 0.983 and 0.975 for the two experts). Neuron diameters obtained with our method ranged between 2 and 28.6 μm, matching values reported in the literature. Further works will aim to evaluate the impact of staining and interindividual variability on our protocol.https://www.frontiersin.org/article/10.3389/fnana.2019.00098/fullneuron individualizationtouching neuronssize-varying neuronsmicroscopic imagesmacaque brain |
| spellingShingle | Zhenzhen You Zhenzhen You Yaël Balbastre Clément Bouvier Anne-Sophie Hérard Pauline Gipchtein Philippe Hantraye Caroline Jan Nicolas Souedet Thierry Delzescaux Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images Frontiers in Neuroanatomy neuron individualization touching neurons size-varying neurons microscopic images macaque brain |
| title | Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images |
| title_full | Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images |
| title_fullStr | Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images |
| title_full_unstemmed | Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images |
| title_short | Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images |
| title_sort | automated individualization of size varying and touching neurons in macaque cerebral microscopic images |
| topic | neuron individualization touching neurons size-varying neurons microscopic images macaque brain |
| url | https://www.frontiersin.org/article/10.3389/fnana.2019.00098/full |
| work_keys_str_mv | AT zhenzhenyou automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT zhenzhenyou automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT yaelbalbastre automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT clementbouvier automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT annesophieherard automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT paulinegipchtein automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT philippehantraye automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT carolinejan automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT nicolassouedet automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages AT thierrydelzescaux automatedindividualizationofsizevaryingandtouchingneuronsinmacaquecerebralmicroscopicimages |