A Fast and Accurate Algorithm for Nuclei Instance Segmentation in Microscopy Images

Cheng, Zhiming; Qu, Ang

doi:10.1109/access.2020.3020393

Cited by 25 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hao Liang et al [36] integrated the Guided Anchoring (GA) with the Region Proposal Network (RPN) to implement a GA-RPN module that generates candidate proposals for nuclei detection, then the Mask R-CNN was applied on the extracted ROI, for nuclear instance segmentation. A fast and accurate region-based nuclei instance segmentation algorithm was presented by Cheng et al [37]. The architecture consists of detection and segmentation blocks.…”

Section: Related Workmentioning

confidence: 99%

“…The testing set consists of 14 images of different patients that were taken from 7 organs, where three of them (stomach, bladder and colon) are not included in the training set. The third and fourth models, listed in Table 5, were re-implemented by Z. Cheng et al [37], using the same training and testing sets, mentioned in this section, and the same GPU, used in [37]. For direct comparison with some alternative methods that are listed in Table 5, in terms of the segmentation quality, the Average Intersection over Union at threshold α (AIoU@ α), defined by ( 12) [53], was calculated beside the AJI and F1-score.…”

Section: Comparison With State-of-the-art Approachesmentioning

confidence: 99%

“…N denotes the total number of predicted nuclei that satisfies IoU i ≥ α (α = 0.5 and 0.7). Based on the architectures, introduced in [34,37,38,45] the computational complexity in terms of the number of convolution layers (that represents the number of layers of the neural network) has been approximately counted and listed in Table 5; this is to achieve a fair comparison, since the architectures were implemented on different GPUs. From Table 5 it can be noticed that the proposed architecture consists of the lowest number of convolution layers while its segmentation quality outperforms the first approach and is comparable to the other alternative methods, whose architectures are more complicated than itself.…”

Section: Comparison With State-of-the-art Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Real-time and accurate deep learning-based multi-organ nucleus segmentation in histology images

Ahmed

2024

J Real-Time Image Proc

View full text Add to dashboard Cite

Automated nucleus segmentation is considered the gold standard for diagnosing some severe diseases. Accurate instance segmentation of nuclei is still very challenging because of the large number of clustered nuclei, and the different appearance of nuclei for different tissue types. In this paper, a neural network is proposed for fast and accurate instance segmentation of nuclei in histopathology images. The network is inspired by the Unet and residual nets. The main contribution of the proposed model is enhancing the classification accuracy of nuclear boundaries by moderately preserving the spatial features by relatively d the size of feature maps. Then, a proposed 2D convolution layer is used instead of the conventional 3D convolution layer, the core of CNN-based architectures, where the feature maps are first compacted before being convolved by 2D kernel filters. This significantly reduces the processing time and avoids the out of memory problem of the GPU. Also, more features are extracted when getting deeper into the network without degrading the spatial features dramatically. Hence, the number of layers, required to compensate the loss of spatial features, is reduced that also reduces the processing time. The proposed approach is applied to two multi-organ datasets and evaluated by the Aggregated Jaccard Index (AJI), F1-score and the number of frames per second. Also, the formula of AJI is modified to reflect the object- and pixel-level errors more accurately. The proposed model is compared to some state-of-the-art architectures, and it shows better performance in terms of the segmentation speed and accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Comparison With State-of-the-art Approachesmentioning

confidence: 99%

Section: Comparison With State-of-the-art Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Real-time and accurate deep learning-based multi-organ nucleus segmentation in histology images

Ahmed

2024

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…For instance, radioactive material was divided into several categories and nuclear sites were found using a multi-scale deep residual aggregation network [ 22 ]. Clustered nuclei were divided using the Feature Pyramid Network (FPN) [ 23 ] and U-Net architecture. Deep learning models [ 24 ] were used to identify nuclei outlines, and segmentation was conducted using an iterative region expanding technique.…”

Section: Background and Related Workmentioning

confidence: 99%

A Novel Heteromorphous Convolutional Neural Network for Automated Assessment of Tumors in Colon and Lung Histopathology Images

et al. 2023

View full text Add to dashboard Cite

The automated assessment of tumors in medical image analysis encounters challenges due to the resemblance of colon and lung tumors to non-mitotic nuclei and their heteromorphic characteristics. An accurate assessment of tumor nuclei presence is crucial for determining tumor aggressiveness and grading. This paper proposes a new method called ColonNet, a heteromorphous convolutional neural network (CNN) with a feature grafting methodology categorically configured for analyzing mitotic nuclei in colon and lung histopathology images. The ColonNet model consists of two stages: first, identifying potential mitotic patches within the histopathological imaging areas, and second, categorizing these patches into squamous cell carcinomas, adenocarcinomas (lung), benign (lung), benign (colon), and adenocarcinomas (colon) based on the model’s guidelines. We develop and employ our deep CNNs, each capturing distinct structural, textural, and morphological properties of tumor nuclei, to construct the heteromorphous deep CNN. The execution of the proposed ColonNet model is analyzed by its comparison with state-of-the-art CNNs. The results demonstrate that our model surpasses others on the test set, achieving an impressive F1 score of 0.96, sensitivity and specificity of 0.95, and an area under the accuracy curve of 0.95. These outcomes underscore our hybrid model’s superior performance, excellent generalization, and accuracy, highlighting its potential as a valuable tool to support pathologists in diagnostic activities.

show abstract

“…However, adding attention mechanisms to both the detection and segmentation modules complicates the model and impairs inference speed. Cheng [21] et al proposed a fast and stable nucleus instance segmentation method (Nucleiseg), which adopts a fusion module based on the feature pyramid network on the basis of ANCIS to combine the complementary information of shallow and deep layers, and pass the boundary box-cropped feature maps to guide segmentation. Yi et al [22] proposed a context-refined neural cell instance segmentation method (CRNIS), which aims to make the network pay more attention to foreground information and suppress background information.…”

Section: Nuclei Instance Segmentationmentioning

confidence: 99%

Improved BlendMask: Nuclei instance segmentation for medical microscopy images

Wang

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Nuclei instance segmentation is an important task in medical image analysis involving cell‐level pathological analysis, which is of great significance for many biomedical applications. Nuclei segmentation is a challenging task due to edge adhesions and the distribution of numerous tiny dense nuclei. In this work, a nuclei instance segmentation framework, namely, the improved BlendMask is proposed. In this framework, in order to improve the performance of detection and segmentation of dense small objects and adhering nuclei, two components, including dilated convolution aggregation module (DCA) and context information aggregation module (CIA), are designed. The DCA constructs multi‐path parallel dilated convolution, which greatly increases the receptive field of the network and the ability to capture multi‐scale contextual information. The CIA reduces the information loss in the channel by endowing the network with high‐level multi‐scale spatial context information. In addition, a novel distributional ranking loss function is given that can effectively alleviate the imbalance between the target and the background. The proposed method is validated on the DSB2018 dataset. Compared to BlendMask, this network improves by 3.6% on AP segmentation metric, and the segmentation performance of this network is superior to that of several recent classic open‐source nuclei instance segmentation methods.

show abstract

A Fast and Accurate Algorithm for Nuclei Instance Segmentation in Microscopy Images

Cited by 25 publications

References 34 publications

Real-time and accurate deep learning-based multi-organ nucleus segmentation in histology images

Real-time and accurate deep learning-based multi-organ nucleus segmentation in histology images

A Novel Heteromorphous Convolutional Neural Network for Automated Assessment of Tumors in Colon and Lung Histopathology Images

Improved BlendMask: Nuclei instance segmentation for medical microscopy images

Contact Info

Product

Resources

About