TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification

Ilyas, Talha; Mannan, Zubaer Ibna; Khan, Abbas; Azam, Sami; Kim, Hyongsuk; Boer, Friso De

doi:10.1016/j.neunet.2022.02.020

Cited by 31 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All methods were implemented using the ResNet-50-FPN backbone network in the MMDetection framework [42]. Besides, for the nuclei segmentation task, we also compared our method to the Hover-Net [21] and TSFD-Net [22] that tailored to the nuclei in histopathological images. These methods separate nuclei by predicting centroids along with contours or distance maps.…”

Section: A Comparison With Sota Is Methodsmentioning

confidence: 99%

“…Table VII summarizes some SOTA studies [20], [21], [50]- [52], [22], [23], [25], [27], [46]- [49] that are related to nuclei or chromosome segmentation in MS images. Because different studies focused on different tasks and utilized diverse datasets and metrics for evaluation, it is hard to compare these methods fairly.…”

Section: Review Of Sota Studies On Microscopy Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Medicine-Engineering Interdisciplinary Research Based on Bibliometric Analysis: A Case Study on Medicine-Engineering Institutional Cooperation of Shanghai Jiao Tong University

Wang

Cui

Deng

2022

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

This article aims to provide reference for medicine-engineering interdisciplinary research. Targeted at the scientific literature and patent literature published by Shanghai Jiao Tong University, this article attempts to set up co-occurrence matrix of medicine-engineering institutional information which was extracted from address fields of the papers, so as to construct the medicine-engineering intersection datasets. The dataset of scientific literature was analyzed using bibliometrics and visualization methods from multiple dimensions, and the most active factors, such as trends of output, journal and subject distribution, were identified from the indicators of category normalized citation impact (CNCI), times cited, keywords, citation topics and the degree of medicine-engineering interdisplinary. Research on hotspots and trends was discussed in detail. Analyses of the dataset of patent literature showed research themes and measured the degree for technology convergence of medicine-engineering.

show abstract

Section: A Comparison With Sota Is Methodsmentioning

confidence: 99%

Section: Review Of Sota Studies On Microscopy Segmentationmentioning

confidence: 99%

Medicine-Engineering Interdisciplinary Research Based on Bibliometric Analysis: A Case Study on Medicine-Engineering Institutional Cooperation of Shanghai Jiao Tong University

Wang

Cui

Deng

2022

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

show abstract

“…We compare our proposed approach with the state-of-the-art nuclei classification methods HoVer-Net [7], Triple U-net [41], MCSpatNet [5], TSFD-net [8], and Mask2former [42]. Among them, HoVer-Net, MCSpatNet, and Mask2former support nuclei classification, TSFD-net is a semantic segmentation method and Triple U-net is an instance segmentation method.…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

Lou

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

“…After channel reduction, these multiscaled features are sent to the bREGt al., 2020) for weighted feature fusion. As different-level features contribute unequally to the output feature map ( Ilyas et al., 2022 ), therefore, at each level BiFPN recalibrates the features according to their importance and fuse them together. Each BiFPN outputs P l -recalibrated feature maps, where l is the number of the pyramid level.…”

Section: System Overviewmentioning

confidence: 99%

DIANA: A deep learning-based paprika plant disease and pest phenotyping system with disease severity analysis

Ilyas

Jin²,

Siddique³

et al. 2022

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

The emergence of deep neural networks has allowed the development of fully automated and efficient diagnostic systems for plant disease and pest phenotyping. Although previous approaches have proven to be promising, they are limited, especially in real-life scenarios, to properly diagnose and characterize the problem. In this work, we propose a framework which besides recognizing and localizing various plant abnormalities also informs the user about the severity of the diseases infecting the plant. By taking a single image as input, our algorithm is able to generate detailed descriptive phrases (user-defined) that display the location, severity stage, and visual attributes of all the abnormalities that are present in the image. Our framework is composed of three main components. One of them is a detector that accurately and efficiently recognizes and localizes the abnormalities in plants by extracting region-based anomaly features using a deep neural network-based feature extractor. The second one is an encoder–decoder network that performs pixel-level analysis to generate abnormality-specific severity levels. Lastly is an integration unit which aggregates the information of these units and assigns unique IDs to all the detected anomaly instances, thus generating descriptive sentences describing the location, severity, and class of anomalies infecting plants. We discuss two possible ways of utilizing the abovementioned units in a single framework. We evaluate and analyze the efficacy of both approaches on newly constructed diverse paprika disease and pest recognition datasets, comprising six anomaly categories along with 11 different severity levels. Our algorithm achieves mean average precision of 91.7% for the abnormality detection task and a mean panoptic quality score of 70.78% for severity level prediction. Our algorithm provides a practical and cost-efficient solution to farmers that facilitates proper handling of crops.

show abstract

TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification

Cited by 31 publications

References 30 publications

Medicine-Engineering Interdisciplinary Research Based on Bibliometric Analysis: A Case Study on Medicine-Engineering Institutional Cooperation of Shanghai Jiao Tong University

Medicine-Engineering Interdisciplinary Research Based on Bibliometric Analysis: A Case Study on Medicine-Engineering Institutional Cooperation of Shanghai Jiao Tong University

Which Pixel to Annotate: A Label-Efficient Nuclei Segmentation Framework

DIANA: A deep learning-based paprika plant disease and pest phenotyping system with disease severity analysis

Contact Info

Product

Resources

About