Segmentation of Tissue Regions in Whole Slide Images Using Hand-Crafted Image Features DOI
Samuel J. Clark, Richard Green

Опубликована: Ноя. 29, 2023

This paper proposes a method to address the need for accurate and explainable tissue segmentation in whole slide images (WSIs) computational pathology. The research focuses on developing machine learning algorithm using hand-crafted image features random forest classifier segment regions WSIs. Three questions were formulated investigated. (RQ1) Can be used as primary an ML accurately WSIsƒ (RQ2) What are dominant classifying whether WSI tiles within regionƒ (RQ3) post-processing techniques required improve accuracy of algorithmƒ proposed achieved average 98.05%. results revealed significant influence specific features, such saturation channel mean standard deviation, grey level co-occurrence matrix measures, More-over, incorporating morphological operations thresholding improved segmentation. 98.05% outperformed existing solutions demonstrated effectiveness reliably segmenting from background presents valuable pre-processing step that can support future related cancer region

Язык: Английский

Automatic Segmentation with Deep Learning in Radiotherapy DOI Open Access
Lars Johannes Isaksson, Paul Summers, Federico Mastroleo

и другие.

Cancers, Год журнала: 2023, Номер 15(17), С. 4389 - 4389

Опубликована: Сен. 1, 2023

This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), methods. We collect key statistics about the to uncover commonalities, trends, methods, identify areas where more research might be needed. Moreover, we analyzed corpus by posing explicit questions aimed at providing high-quality actionable insights, including: “What should researchers think when starting study?”, “How can practices medical improved?”, is missing from corpus?”, more. allowed us provide practical guidelines on how conduct good study today’s competitive environment will useful for future within field, regardless specific radiotherapeutic subfield. To aid our analysis, used large language model ChatGPT condense information.

Язык: Английский

Процитировано

20
Deep learning techniques in PET/CT imaging: A comprehensive review from sinogram to image space DOI

Maryam Fallahpoor,

Subrata Chakraborty, Biswajeet Pradhan

и другие.

Computer Methods and Programs in Biomedicine, Год журнала: 2023, Номер 243, С. 107880 - 107880

Опубликована: Окт. 21, 2023

Язык: Английский

Процитировано

20
CNNM-FDI: Novel Convolutional Neural Network Model for Fire Detection in Images DOI
Arvind Kumar Vishwakarma, Maroti Deshmukh

IETE Journal of Research, Год журнала: 2025, Номер unknown, С. 1 - 14

Опубликована: Янв. 29, 2025

Язык: Английский

Процитировано

1
Intelligent tumor tissue classification for Hybrid Health Care Units DOI Creative Commons
Muhammad Hassaan Farooq Butt, Jianping Li, Jiancheng Ji

и другие.

Frontiers in Medicine, Год журнала: 2024, Номер 11

Опубликована: Июнь 26, 2024

Introduction In the evolving healthcare landscape, we aim to integrate hyperspectral imaging into Hybrid Health Care Units advance diagnosis of medical diseases through effective fusion cutting-edge technology. The scarcity data limits use in disease classification. Methods Our study innovatively integrates characterize tumor tissues across diverse body locations, employing Sharpened Cosine Similarity framework for classification and subsequent recommendation. efficiency proposed model is evaluated using Cohen's kappa, overall accuracy, f1-score metrics. Results demonstrates remarkable efficiency, with kappa 91.76%, an accuracy 95.60%, 96%. These metrics indicate superior performance our over existing state-of-the-art methods, even limited training data. Conclusion This marks a milestone hybrid informatics, improving personalized care advancing recommendations.

Язык: Английский

Процитировано

4
Spatio-temporal collaborative multiple-stream transformer network for liver lesion classification on multiple-sequence magnetic resonance imaging DOI
Shuangping Huang,

Z. R. Hong,

Bianzhe Wu

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 142, С. 109933 - 109933

Опубликована: Янв. 5, 2025

Язык: Английский

Процитировано

0
Dual prototypes contrastive learning based semi-supervised segmentation method for intelligent medical applications DOI
Tao Yue, Rongtao Xu,

Jingqian Wu

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 154, С. 110905 - 110905

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
A Transformer-Guided Cross-Modality Adaptive Feature Fusion Framework for Esophageal Gross Tumor Volume Segmentation DOI

Yaoting Yue,

Nan Li,

Gaobo Zhang

и другие.

Computer Methods and Programs in Biomedicine, Год журнала: 2024, Номер 251, С. 108216 - 108216

Опубликована: Май 12, 2024

Язык: Английский

Процитировано

2
Segmentation of Tissue Regions in Whole Slide Images Using Hand-Crafted Image Features DOI
Samuel J. Clark, Richard Green

Опубликована: Ноя. 29, 2023

This paper proposes a method to address the need for accurate and explainable tissue segmentation in whole slide images (WSIs) computational pathology. The research focuses on developing machine learning algorithm using hand-crafted image features random forest classifier segment regions WSIs. Three questions were formulated investigated. (RQ1) Can be used as primary an ML accurately WSIsƒ (RQ2) What are dominant classifying whether WSI tiles within regionƒ (RQ3) post-processing techniques required improve accuracy of algorithmƒ proposed achieved average 98.05%. results revealed significant influence specific features, such saturation channel mean standard deviation, grey level co-occurrence matrix measures, More-over, incorporating morphological operations thresholding improved segmentation. 98.05% outperformed existing solutions demonstrated effectiveness reliably segmenting from background presents valuable pre-processing step that can support future related cancer region

Язык: Английский

Процитировано

0