1
|
Ferrero A, Ghelichkhan E, Manoochehri H, Ho MM, Albertson DJ, Brintz BJ, Tasdizen T, Whitaker RT, Knudsen BS. HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification. Mod Pathol 2024; 37:100447. [PMID: 38369187 DOI: 10.1016/j.modpat.2024.100447] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 01/06/2024] [Accepted: 02/06/2024] [Indexed: 02/20/2024]
Abstract
Pathologists have, over several decades, developed criteria for diagnosing and grading prostate cancer. However, this knowledge has not, so far, been included in the design of convolutional neural networks (CNN) for prostate cancer detection and grading. Further, it is not known whether the features learned by machine-learning algorithms coincide with diagnostic features used by pathologists. We propose a framework that enforces algorithms to learn the cellular and subcellular differences between benign and cancerous prostate glands in digital slides from hematoxylin and eosin-stained tissue sections. After accurate gland segmentation and exclusion of the stroma, the central component of the pipeline, named HistoEM, utilizes a histogram embedding of features from the latent space of the CNN encoder. Each gland is represented by 128 feature-wise histograms that provide the input into a second network for benign vs cancer classification of the whole gland. Cancer glands are further processed by a U-Net structured network to separate low-grade from high-grade cancer. Our model demonstrates similar performance compared with other state-of-the-art prostate cancer grading models with gland-level resolution. To understand the features learned by HistoEM, we first rank features based on the distance between benign and cancer histograms and visualize the tissue origins of the 2 most important features. A heatmap of pixel activation by each feature is generated using Grad-CAM and overlaid on nuclear segmentation outlines. We conclude that HistoEM, similar to pathologists, uses nuclear features for the detection of prostate cancer. Altogether, this novel approach can be broadly deployed to visualize computer-learned features in histopathology images.
Collapse
Affiliation(s)
- Alessandro Ferrero
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | - Elham Ghelichkhan
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | - Hamid Manoochehri
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | - Man Minh Ho
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | | | | | - Tolga Tasdizen
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | - Ross T Whitaker
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah
| | | |
Collapse
|
2
|
Lin Z, Shen H, Liu X, Ma W, Wang M, Ruan J, Yu H, Ma S, Sun X. Recent advances of artificial intelligence in melanoma clinical practice. Melanoma Res 2023; 33:454-461. [PMID: 37696256 DOI: 10.1097/cmr.0000000000000922] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/13/2023]
Abstract
Skin melanoma is a lethal cancer. The incidence of melanoma is increasing rapidly in all regions of the world. Despite significant breakthroughs in melanoma treatment in recent years, precise diagnosis of melanoma is still a challenge in some cases. Even specialized physicians may need time and effort to make accurate judgments. As artificial intelligence (AI) technology advances into medical practice, it may bring new solutions to this problem based on its efficiency, accuracy, and speed. This paper summarizes the recent progress of AI in melanoma-related applications, including melanoma diagnosis and classification, the discovery of new medication, guiding treatment, and prognostic assessment. The paper also compares the effectiveness of various algorithms in melanoma application and suggests future research directions for AI in melanoma clinical practice.
Collapse
Affiliation(s)
- Zijun Lin
- Guangdong Provincial Key Laboratory of Medical Molecular Diagnostics, The First Dongguan Affiliated Hospital, Guangdong Medical University
- Institute of Aging Research, School of Medical Technology, Guangdong Medical University
| | - Haoyan Shen
- School of Biomedical Engineering, Guangdong Medical University
| | - Xinguang Liu
- Guangdong Provincial Key Laboratory of Medical Molecular Diagnostics, The First Dongguan Affiliated Hospital, Guangdong Medical University
- Institute of Aging Research, School of Medical Technology, Guangdong Medical University
| | - Wanrui Ma
- Department of General Medicine, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan
| | - Mingfa Wang
- Department of Pathology, The Second Affiliated Hospital of Hainan Medical University, Haikou
| | - Jie Ruan
- Institute of Aging Research, School of Medical Technology, Guangdong Medical University
| | - Hongbin Yu
- Guangdong Provincial Key Laboratory of Medical Molecular Diagnostics, Chinese American Tumor Institute, Guangdong Medical University, Dongguan, China
| | - Sha Ma
- School of Biomedical Engineering, Guangdong Medical University
| | - Xuerong Sun
- Guangdong Provincial Key Laboratory of Medical Molecular Diagnostics, The First Dongguan Affiliated Hospital, Guangdong Medical University
- Institute of Aging Research, School of Medical Technology, Guangdong Medical University
| |
Collapse
|
3
|
Kuang X, Zhong Z, Liang W, Huang S, Luo R, Luo H, Li Y. Bibliometric analysis of 100 top cited articles of heart failure-associated diseases in combination with machine learning. Front Cardiovasc Med 2023; 10:1158509. [PMID: 37304963 PMCID: PMC10248156 DOI: 10.3389/fcvm.2023.1158509] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Accepted: 05/03/2023] [Indexed: 06/13/2023] Open
Abstract
Objective The aim of this paper is to analyze the application of machine learning in heart failure-associated diseases using bibliometric methods and to provide a dynamic and longitudinal bibliometric analysis of heart failure-related machine learning publications. Materials and methods Web of Science was screened to gather the articles for the study. Based on bibliometric indicators, a search strategy was developed to screen the title for eligibility. Intuitive data analysis was employed to analyze the top-100 cited articles and VOSViewer was used to analyze the relevance and impact of all articles. The two analysis methods were then compared to get conclusions. Results The search identified 3,312 articles. In the end, 2,392 papers were included in the study, which were published between 1985 and 2023. All articles were analyzed using VOSViewer. Key points of the analysis included the co-authorship map of authors, countries and organizations, the citation map of journal and documents and a visualization of keyword co-occurrence analysis. Among these 100 top-cited papers, with a mean of 122.9 citations, the most-cited article had 1,189, and the least cited article had 47. Harvard University and the University of California topped the list among all institutes with 10 papers each. More than one-ninth of the authors of these 100 top-cited papers wrote three or more articles. The 100 articles came from 49 journals. The articles were divided into seven areas according to the type of machine learning approach employed: Support Vector Machines, Convolutional Neural Networks, Logistic Regression, Recurrent Neural Networks, Random Forest, Naive Bayes, and Decision Tree. Support Vector Machines were the most popular method. Conclusions This analysis provides a comprehensive overview of the artificial intelligence (AI)-related research conducted in the field of heart failure, which helps healthcare institutions and researchers better understand the prospects of AI in heart failure and formulate more scientific and effective research plans. In addition, our bibliometric evaluation can assist healthcare institutions and researchers in determining the advantages, sustainability, risks, and potential impacts of AI technology in heart failure.
Collapse
Affiliation(s)
- Xuyuan Kuang
- Department of Hyperbaric Oxygen, Xiangya Hospital, Changsha, China
- National Research Center of Geriatic Diseases (Xiangya Hospital), Changsha, China
| | - Zihao Zhong
- Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business, Changsha, China
| | - Wei Liang
- Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business, Changsha, China
| | - Suzhen Huang
- The Big Data Institute, Central South University, Changsha, China
| | - Renji Luo
- Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business, Changsha, China
| | - Hui Luo
- National Research Center of Geriatic Diseases (Xiangya Hospital), Changsha, China
- Department of Anesthesiology, Xiangya Hospital, Changsha, China
| | - Yongheng Li
- Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business, Changsha, China
| |
Collapse
|
4
|
Wang S, Deng P, Sun X, Han J, Yang S, Chen Z. Global research trends and hotspots analysis of hallux valgus: A bibliometric analysis from 2004 to 2021. Front Surg 2023; 10:1093000. [PMID: 36998596 PMCID: PMC10044137 DOI: 10.3389/fsurg.2023.1093000] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 02/13/2023] [Indexed: 03/09/2023] Open
Abstract
BackgroundHallux valgus (HV) is a common foot and ankle surgery disease. The correction of HV deformity relies on a highly challenging surgical treatment. Thus, widely adopted evidence-based clinical guidelines are still needed to guide the selection of the most appropriate interventions. Recently, the study of HV has been growing and scholars are increasingly paying particular attention to this area. However, bibliometric literature remains lacking. Therefore, this study aims to reveal the hotspots and future research trends in HV via bibliometric analysis to fill this knowledge gap.MethodsLiterature related to HV from 2004 to 2021 was retrieved from the Science Citation Index Expanded (SCI-expanded) of the Web of Science Core Collection (WoSCC). Quantitative and qualitative analyses of scientific data are performed using software such as CiteSpace, R-bibliometrix, and VOSviewer.ResultsA total of 1,904 records were identified for analysis. The United States had the most number of published articles and total citations. Thus, the United States has made an essential contribution to the field of HV. Meanwhile, La Trobe University in Australia was the most productive institution. Menz HB and Foot & Ankle International were the most influential authors and the most popular journals among researchers, respectively. In addition, “older people,” “chevron osteotomy,” “Lapidus,” and “hallux rigidus” have always been the hotspots of attention. Changes and developments in the surgery of HV have gained researchers' interest. Future research trends are more focused on “radiographic measurement,” “recurrence,” “outcome,” “rotation,” “pronation,” and “minimally invasive surgery.” Thus, focusing on these subject directions can facilitate academic progress and provide the possibility of better treatments for HV.ConclusionThis study summarizes the hotspots and trends in the field of HV from 2004 to 2021, which will provide researchers with an updated view of essential information and somehow guide future research.
Collapse
Affiliation(s)
- Shulong Wang
- School of Graduates, Beijing University of Chinese Medicine, Beijing, China
- Department of Hand and Foot Surgery, Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing, China
| | - Ping Deng
- School of Graduates, Beijing University of Chinese Medicine, Beijing, China
- Department of Hand and Foot Surgery, Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing, China
| | - Xiaojie Sun
- School of Graduates, Beijing University of Chinese Medicine, Beijing, China
- Department of Hand and Foot Surgery, Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing, China
| | - Jinglu Han
- School of Graduates, Beijing University of Chinese Medicine, Beijing, China
- Department of Hand and Foot Surgery, Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing, China
| | - Shanshan Yang
- School of Graduates, Beijing University of Chinese Medicine, Beijing, China
| | - Zhaojun Chen
- Department of Hand and Foot Surgery, Beijing University of Chinese Medicine Third Affiliated Hospital, Beijing, China
- Correspondence: Zhaojun Chen
| |
Collapse
|