1
|
Zeng S, Li X, Liu Y, Huang Q, He Y. Automatic Annotation Diagnostic Framework for Nasopharyngeal Carcinoma via Pathology-Fidelity GAN and Prior-Driven Classification. Bioengineering (Basel) 2024; 11:739. [PMID: 39061821 PMCID: PMC11273917 DOI: 10.3390/bioengineering11070739] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2024] [Revised: 07/17/2024] [Accepted: 07/18/2024] [Indexed: 07/28/2024] Open
Abstract
Non-keratinizing carcinoma is the most common subtype of nasopharyngeal carcinoma (NPC). Its poorly differentiated tumor cells and complex microenvironment present challenges to pathological diagnosis. AI-based pathological models have demonstrated potential in diagnosing NPC, but the reliance on costly manual annotation hinders development. To address the challenges, this paper proposes a deep learning-based framework for diagnosing NPC without manual annotation. The framework includes a novel unpaired generative network and a prior-driven image classification system. With pathology-fidelity constraints, the generative network achieves accurate digital staining from H&E to EBER images. The classification system leverages staining specificity and pathological prior knowledge to annotate training data automatically and to classify images for NPC diagnosis. This work used 232 cases for study. The experimental results show that the classification system reached a 99.59% accuracy in classifying EBER images, which closely matched the diagnostic results of pathologists. Utilizing PF-GAN as the backbone of the framework, the system attained a specificity of 0.8826 in generating EBER images, markedly outperforming that of other GANs (0.6137, 0.5815). Furthermore, the F1-Score of the framework for patch level diagnosis was 0.9143, exceeding those of fully supervised models (0.9103, 0.8777). To further validate its clinical efficacy, the framework was compared with experienced pathologists at the WSI level, showing comparable NPC diagnosis performance. This low-cost and precise diagnostic framework optimizes the early pathological diagnosis method for NPC and provides an innovative strategic direction for AI-based cancer diagnosis.
Collapse
Affiliation(s)
- Siqi Zeng
- Medical Optical Technology R&D Center, Research Institute of Tsinghua, Pearl River Delta, Guangzhou 510700, China;
| | - Xinwei Li
- School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China;
| | - Yiqing Liu
- Institute of Biopharmaceutical and Health Engineering, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China;
| | - Qiang Huang
- Shenzhen Shengqiang Technology Co., Ltd., Shenzhen 518055, China;
| | - Yonghong He
- Institute of Biopharmaceutical and Health Engineering, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China;
| |
Collapse
|
2
|
Zong R, Ma X, Shi Y, Geng L. Can Machine Learning Models Based on Computed Tomography Radiomics and Clinical Characteristics Provide Diagnostic Value for Epstein-Barr Virus-Associated Gastric Cancer? J Comput Assist Tomogr 2024:00004728-990000000-00333. [PMID: 38924393 DOI: 10.1097/rct.0000000000001636] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/28/2024]
Abstract
OBJECTIVE The aim of this study was to explore whether machine learning model based on computed tomography (CT) radiomics and clinical characteristics can differentiate Epstein-Barr virus-associated gastric cancer (EBVaGC) from non-EBVaGC. METHODS Contrast-enhanced CT images were collected from 158 patients with GC (46 EBV-positive, 112 EBV-negative) between April 2018 and February 2023. Radiomics features were extracted from the volumes of interest. A radiomics signature was built based on radiomics features by the least absolute shrinkage and selection operator logistic regression algorithm. Multivariate analyses were used to identify significant clinicoradiological variables. We developed 6 ML models for EBVaGC, including logistic regression, Extreme Gradient Boosting, random forest (RF), support vector machine, Gaussian Naive Bayes, and K-nearest neighbor algorithm. The area under the receiver operating characteristic curve (AUC), the area under the precision-recall curves (AP), calibration plots, and decision curve analysis were applied to assess the effectiveness of each model. RESULTS Six ML models achieved AUC of 0.706-0.854 and AP of 0.480-0.793 for predicting EBV status in GC. With an AUC of 0.854 and an AP of 0.793, the RF model performed the best. The forest plot of the AUC score revealed that the RF model had the most stable performance, with a standard deviation of 0.003 for AUC score. RF also performed well in the testing dataset, with an AUC of 0.832 (95% confidence interval: 0.679-0.951), accuracy of 0.833, sensitivity of 0.857, and specificity of 0.824, respectively. CONCLUSIONS The RF model based on clinical variables and Rad_score can serve as a noninvasive tool to evaluate the EBV status of gastric cancer.
Collapse
Affiliation(s)
- Ruilong Zong
- From the Department of Radiology, Xuzhou Central Hospital, Xuzhou, China
| | - Xijuan Ma
- From the Department of Radiology, Xuzhou Central Hospital, Xuzhou, China
| | - Yibing Shi
- From the Department of Radiology, Xuzhou Central Hospital, Xuzhou, China
| | - Li Geng
- Department of Radiology, The Affiliated Hospital of Xuzhou Medical University
| |
Collapse
|
3
|
Yang J, Chen L, Liu E, Wang B, Driman DK, Zhang Q, Ling C. Deep learning system for true- and pseudo-invasion in colorectal polyps. Sci Rep 2024; 14:426. [PMID: 38172166 PMCID: PMC10764718 DOI: 10.1038/s41598-023-50681-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2023] [Accepted: 12/22/2023] [Indexed: 01/05/2024] Open
Abstract
Over 15 million colonoscopies were performed yearly in North America, during which biopsies were taken for pathological examination to identify abnormalities. Distinguishing between true- and pseudo-invasion in colon polyps is critical in treatment planning. Surgical resection of the colon is often the treatment option for true invasion, whereas observation is recommended for pseudo-invasion. The task of identifying true- vs pseudo-invasion, however, could be highly challenging. There is no specialized software tool for this task, and no well-annotated dataset is available. In our work, we obtained (only) 150 whole-slide images (WSIs) from the London Health Science Centre. We built three deep neural networks representing different magnifications in WSIs, mimicking the workflow of pathologists. We also built an online tool for pathologists to annotate WSIs to train our deep neural networks. Results showed that our novel system classifies tissue types with 95.3% accuracy and differentiates true- and pseudo-invasions with 83.9% accuracy. The system's efficiency is comparable to an expert pathologist. Our system can also be easily adjusted to serve as a confirmatory or screening tool. Our system (available at http://ai4path.ca ) will lead to better, faster patient care and reduced healthcare costs.
Collapse
Affiliation(s)
- Joe Yang
- Department of Computer Science, Western University, London, N6A 3K7, Canada
| | - Lina Chen
- Sunnybrook Health Sciences Centre, University of Toronto, Toronto, M4N 3M5, Canada
| | - Eric Liu
- Department of Computer Science, Western University, London, N6A 3K7, Canada
| | - Boyu Wang
- Department of Computer Science, Western University, London, N6A 3K7, Canada
| | - David K Driman
- Department of Pathology and Laboratory Medicine, Western University, London, N6A 3K7, Canada
| | - Qi Zhang
- Department of Pathology and Laboratory Medicine, Western University, London, N6A 3K7, Canada.
| | - Charles Ling
- Department of Computer Science, Western University, London, N6A 3K7, Canada.
| |
Collapse
|
4
|
Yousif M, Pantanowitz L. Artificial Intelligence-Enabled Gastric Cancer Interpretations: Are We There yet? Surg Pathol Clin 2023; 16:673-686. [PMID: 37863559 DOI: 10.1016/j.path.2023.05.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2023]
Abstract
The integration of digital pathology and artificial intelligence (AI) is revolutionizing pathology by providing pathologists with new tools to improve workflow, enhance diagnostic accuracy, and undertake novel discovery. The capability of AI to recognize patterns and features in digital images beyond human perception is particularly valuable, thereby providing additional information for prognostic and predictive purposes. AI-based tools diagnose gastric carcinoma in digital images, detect gastric carcinoma metastases in lymph nodes, automate Ki-67 scoring in gastric neuroendocrine tumors, and quantify tumor-infiltrating lymphocytes. This article provides an overview of all of these applications of AI pertaining to gastric cancer.
Collapse
Affiliation(s)
- Mustafa Yousif
- Department of Pathology, University of Michigan, NCRC Building 35, 2800 Plymouth Road, Ann Arbor, MI 48109, USA.
| | - Liron Pantanowitz
- Department of Pathology, UPMC Shadyside Hospital, 5150 Centre Avenue Cancer Pavilion, POB2, Suite 3B, Room 347, Pittsburgh, PA 15232, USA
| |
Collapse
|
5
|
Choi S, Kim S. Artificial Intelligence in the Pathology of Gastric Cancer. J Gastric Cancer 2023; 23:410-427. [PMID: 37553129 PMCID: PMC10412971 DOI: 10.5230/jgc.2023.23.e25] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Revised: 07/09/2023] [Accepted: 07/14/2023] [Indexed: 08/10/2023] Open
Abstract
Recent advances in artificial intelligence (AI) have provided novel tools for rapid and precise pathologic diagnosis. The introduction of digital pathology has enabled the acquisition of scanned slide images that are essential for the application of AI. The application of AI for improved pathologic diagnosis includes the error-free detection of potentially negligible lesions, such as a minute focus of metastatic tumor cells in lymph nodes, the accurate diagnosis of potentially controversial histologic findings, such as very well-differentiated carcinomas mimicking normal epithelial tissues, and the pathological subtyping of the cancers. Additionally, the utilization of AI algorithms enables the precise decision of the score of immunohistochemical markers for targeted therapies, such as human epidermal growth factor receptor 2 and programmed death-ligand 1. Studies have revealed that AI assistance can reduce the discordance of interpretation between pathologists and more accurately predict clinical outcomes. Several approaches have been employed to develop novel biomarkers from histologic images using AI. Moreover, AI-assisted analysis of the cancer microenvironment showed that the distribution of tumor-infiltrating lymphocytes was related to the response to the immune checkpoint inhibitor therapy, emphasizing its value as a biomarker. As numerous studies have demonstrated the significance of AI-assisted interpretation and biomarker development, the AI-based approach will advance diagnostic pathology.
Collapse
Affiliation(s)
- Sangjoon Choi
- Department of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Seokhwi Kim
- Department of Pathology, Ajou University School of Medicine, Suwon, Korea
- Department of Biomedical Sciences, Ajou University Graduate School of Medicine, Suwon, Korea.
| |
Collapse
|
6
|
Al-Khreisat MJ, Ismail NH, Tabnjh A, Hussain FA, Mohamed Yusoff AA, Johan MF, Islam MA. Worldwide Prevalence of Epstein-Barr Virus in Patients with Burkitt Lymphoma: A Systematic Review and Meta-Analysis. Diagnostics (Basel) 2023; 13:2068. [PMID: 37370963 DOI: 10.3390/diagnostics13122068] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 05/28/2023] [Accepted: 06/07/2023] [Indexed: 06/29/2023] Open
Abstract
Burkitt lymphoma (BL) is a form of B-cell malignancy that progresses aggressively and is most often seen in children. While Epstein-Barr virus (EBV) is a double-stranded DNA virus that has been linked to a variety of cancers, it can transform B lymphocytes into immortalized cells, as shown in BL. Therefore, the estimated prevalence of EBV in a population may assist in the prediction of whether this population has a high risk of increased BL cases. This systematic review and meta-analysis aimed to estimate the prevalence of Epstein-Barr virus in patients with Burkitt lymphoma. Using the appropriate keywords, four electronic databases were searched. The quality of the included studies was assessed using the Joanna Briggs Institute's critical appraisal tool. The results were reported as percentages with a 95% confidence interval using a random-effects model (CI). PROSPERO was used to register the protocol (CRD42022372293), and 135 studies were included. The prevalence of Epstein-Barr virus in patients with Burkitt lymphoma was 57.5% (95% CI: 51.5 to 63.4, n = 4837). The sensitivity analyses demonstrated consistent results, and 65.2% of studies were of high quality. Egger's test revealed that there was a significant publication bias. EBV was found in a significantly high proportion of BL patients (more than 50% of BL patients). This study recommends EBV testing as an alternative for predictions and the assessment of the clinical disease status of BL.
Collapse
Affiliation(s)
- Mutaz Jamal Al-Khreisat
- Department of Haematology, School of Medical Sciences, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia
| | - Nor Hayati Ismail
- Department of Haematology, School of Medical Sciences, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia
| | - Abedelmalek Tabnjh
- Department of Applied Dental Sciences, Faculty of Applied Medical Sciences, Jordan University of Science and Technology, Irbid 22110, Jordan
| | - Faezahtul Arbaeyah Hussain
- Department of Pathology, School of Medical Sciences, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia
| | - Abdul Aziz Mohamed Yusoff
- Department of Neurosciences, School of Medical Sciences, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia
| | - Muhammad Farid Johan
- Department of Haematology, School of Medical Sciences, Universiti Sains Malaysia, Kubang Kerian 16150, Kelantan, Malaysia
| | - Md Asiful Islam
- WHO Collaborating Centre for Global Women's Health, Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham B15 2TT, UK
| |
Collapse
|