Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images

Microscopy Res & Technique

et al. 2021

Self Cite

Accurate cerebral neuron segmentation is required before neuron counting and neuron morphological analysis. Numerous algorithms for neuron segmentation have been published, but they are mainly evaluated using limited subsets from a specific anatomical region, targeting neurons of clear contrast and/or neurons with similar staining intensity. It is thus unclear how these algorithms perform on cerebral neurons in diverse anatomical regions. In this article, we introduce and reliably evaluate existing machine learning algorithms using a data set of microscopy images of macaque brain. This data set highlights various anatomical regions (e.g., cortex, caudate, thalamus, claustrum, putamen, hippocampus, subiculum, lateral geniculate, globus pallidus, etc.), poor contrast, and staining intensity differences of neurons. The evaluation was performed using 10 architectures of six classic machine learning algorithms in terms of typical Recall, Precision, F‐score, aggregated Jaccard index (AJI), as well as a performance ranking of algorithms. F‐score of most of the algorithms is superior to 0.7. Deep learning algorithms facilitate generally higher F‐scores. U‐net with suitable layer depth has been evaluated to be excellent classifiers with F‐score of 0.846 and 0.837 when performing cross validation. The evaluation and analysis indicate the performance gap among algorithms in various anatomical regions and the strengths and limitations of each algorithm. The comparative result highlights at the same time the importance and difficulty of neuron segmentation and provides clues for future improvement. To the best of our knowledge, this work is the first comprehensive study for neuron segmentation in such large‐scale anatomical regions. Neuron segmentation plays a critical role in extracting cerebral information, such as neuron counting and neuron morphological analysis. Accurate automated cerebral neuron segmentation is a challenging task due to different kinds, poor contrast, staining intensity differences, and fuzzy boundaries of neurons. The comprehensive evaluation and analysis of performance among existing machine learning algorithms in diverse anatomical regions allows to make clear of the strengths and limitations of state‐of‐the‐art algorithm. The comprehensive study provides clues for future improvement and creation of automated methods.

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of automated segmentation algorithms for neurons in macaque cerebral microscopic images

Microscopy Res & Technique

et al. 2021

Self Cite

“…Centroids marked by white points are postprocessed based on b1-b9). Red contours are obtained by applying competitive region growing method You et al (2019). d1-d9) Individualization results obtained based on You et al (2019).…”

Section: Qualitative Visual Inspectionmentioning

confidence: 99%

Macaque Neuron Instance Segmentation only with Point Annotations based on Multiscale Fully Convolutional Regression Neural Network

et al. 2021

Preprint

Self Cite

In the field of biomedicine, instance segmentation / individualization is important in analyzing the number, the morphology and the distribution of neurons for the whole slide images. Traditionally, biologists apply stereology technique to manually count the number of neurons in the regions of interest and estimate the number in anatomical regions or the entire brain. This is very tedious and time-consuming. In this paper, we propose a multiscale fully convolutional regression neural network combined with competitive region growing technique to individualize size-varying and touching neurons in major anatomical regions of macaque brain. Given that neuron instance or contour annotations are infeasible to obtain in certain regions, such as dentate gyrus where thousands of touching neurons are present, we ask expert to perform point annotations in the center location of neurons (noted as neuron centroids) for training. Thanks to the multiscale resolution achieved by parallel multiple receptive fields and different network depths, our proposed network succeeds in detecting the centroids of size-varying and touching neurons. Competitive region growing is then applied on these centroids to achieve neuron instance segmentation. Experiments on macaque brain data suggest that our proposed method outperform the state-of-the-art methods in terms of neuron instance segmentation performance. To our knowledge, this is the first deep learning research work to individualize size-varying and touching neurons only using point annotations in major anatomical regions in the macaque brain. The cartographic representation of the number and the average orientation of neurons illustrates the synthesis of multi-gigabyte image information in the form of cartography, and shows the characteristics of different anatomical regions from mesoscopic level.

Multiscale segmentation‐ and error‐guided iterative convolutional neural network for cerebral neuron segmentation in microscopic images

Microscopy Res & Technique

et al. 2022

Self Cite

This article uses microscopy images obtained from diverse anatomical regions of macaque brain for neuron semantic segmentation. The complex structure of brain, the large intra‐class staining intensity difference within neuron class, the small inter‐class staining intensity difference between neuron and tissue class, and the unbalanced dataset increase the difficulty of neuron semantic segmentation. To address this problem, we propose a multiscale segmentation‐ and error‐guided iterative convolutional neural network (MSEG‐iCNN) to improve the semantic segmentation performance in major anatomical regions of the macaque brain. After evaluating microscopic images from 17 anatomical regions, the semantic segmentation performance of neurons is improved by 10.6%, 4.0%, 1.5%, and 1.2% compared with Random Forest, FCN‐8s, U‐Net, and UNet++, respectively. Especially for neurons with brighter staining intensity in the anatomical regions such as lateral geniculate, globus pallidus and hypothalamus, the performance is improved by 66.1%, 23.9%, 11.2%, and 6.7%, respectively. Experiments show that our proposed method can efficiently segment neurons with a wide range of staining intensities. The semantic segmentation results are of great significance and can be further used for neuron instance segmentation, morphological analysis and disease diagnosis. Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra‐class staining intensity difference within neuron class, the small inter‐class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation‐ and error‐guided iterative convolutional neural network (MSEG‐iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain. Highlights Cell segmentation plays a critical role in extracting cerebral information, such as cell counting, cell morphometry and distribution analysis. Accurate automated neuron segmentation is challenging due to the complex structure of brain, the large intra‐class staining intensity difference within neuron class, the small inter‐class staining intensity difference between neuron and tissue class, and the unbalanced dataset. The proposed multiscale segmentation‐ and error‐guided iterative convolutional neural network (MSEG‐iCNN) improve the segmentation performance in 17 major anatomical regions of the macaque brain.