1
|
Shi J, Shu T, Wu K, Jiang Z, Zheng L, Wang W, Wu H, Zheng Y. Masked hypergraph learning for weakly supervised histopathology whole slide image classification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 253:108237. [PMID: 38820715 DOI: 10.1016/j.cmpb.2024.108237] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/06/2024] [Revised: 05/16/2024] [Accepted: 05/20/2024] [Indexed: 06/02/2024]
Abstract
BACKGROUND AND OBJECTIVES Graph neural network (GNN) has been extensively used in histopathology whole slide image (WSI) analysis due to the efficiency and flexibility in modelling relationships among entities. However, most existing GNN-based WSI analysis methods only consider the pairwise correlation of patches from one single perspective (e.g. spatial affinity or embedding similarity) yet ignore the intrinsic non-pairwise relationships present in gigapixel WSI, which are likely to contribute to feature learning and downstream tasks. The objective of this study is therefore to explore the non-pairwise relationships in histopathology WSI and exploit them to guide the learning of slide-level representations for better classification performance. METHODS In this paper, we propose a novel Masked HyperGraph Learning (MaskHGL) framework for weakly supervised histopathology WSI classification. Compared with most GNN-based WSI classification methods, MaskHGL exploits the non-pairwise correlations between patches with hypergraph and global message passing conducted by hypergraph convolution. Concretely, multi-perspective hypergraphs are first built for each WSI, then hypergraph attention is introduced into the jointed hypergraph to propagate the non-pairwise relationships and thus yield more discriminative node representation. More importantly, a masked hypergraph reconstruction module is devised to guide the hypergraph learning which can generate more powerful robustness and generalization than the method only using hypergraph modelling. Additionally, a self-attention-based node aggregator is also applied to explore the global correlation of patches in WSI and produce the slide-level representation for classification. RESULTS The proposed method is evaluated on two public TCGA benchmark datasets and one in-house dataset. On the public TCGA-LUNG (1494 WSIs) and TCGA-EGFR (696 WSIs) test set, the area under receiver operating characteristic (ROC) curve (AUC) were 0.9752±0.0024 and 0.7421±0.0380, respectively. On the USTC-EGFR (754 WSIs) dataset, MaskHGL achieved significantly better performance with an AUC of 0.8745±0.0100, which surpassed the second-best state-of-the-art method SlideGraph+ 2.64%. CONCLUSIONS MaskHGL shows a great improvement, brought by considering the intrinsic non-pairwise relationships within WSI, in multiple downstream WSI classification tasks. In particular, the designed masked hypergraph reconstruction module promisingly alleviates the data scarcity and greatly enhances the robustness and classification ability of our MaskHGL. Notably, it has shown great potential in cancer subtyping and fine-grained lung cancer gene mutation prediction from hematoxylin and eosin (H&E) stained WSIs.
Collapse
Affiliation(s)
- Jun Shi
- School of Software, Hefei University of Technology, Hefei, 230601, Anhui Province, China
| | - Tong Shu
- School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, Anhui Province, China
| | - Kun Wu
- Image Processing Center, School of Astronautics, Beihang University, Beijing, 102206, China
| | - Zhiguo Jiang
- Image Processing Center, School of Astronautics, Beihang University, Beijing, 102206, China; Tianmushan Laboratory, Hangzhou, 311115, Zhejiang Province, China
| | - Liping Zheng
- School of Software, Hefei University of Technology, Hefei, 230601, Anhui Province, China
| | - Wei Wang
- Department of Pathology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230036, Anhui Province, China; Intelligent Pathology Institute, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230036, Anhui Province, China
| | - Haibo Wu
- Department of Pathology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230036, Anhui Province, China; Intelligent Pathology Institute, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230036, Anhui Province, China
| | - Yushan Zheng
- School of Engineering Medicine, Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100191, China.
| |
Collapse
|
2
|
Abel J, Jain S, Rajan D, Padigela H, Leidal K, Prakash A, Conway J, Nercessian M, Kirkup C, Javed SA, Biju R, Harguindeguy N, Shenker D, Indorf N, Sanghavi D, Egger R, Trotter B, Gerardin Y, Brosnan-Cashman JA, Dhoot A, Montalto MC, Parmar C, Wapinski I, Khosla A, Drage MG, Yu L, Taylor-Weiner A. AI powered quantification of nuclear morphology in cancers enables prediction of genome instability and prognosis. NPJ Precis Oncol 2024; 8:134. [PMID: 38898127 PMCID: PMC11187064 DOI: 10.1038/s41698-024-00623-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Accepted: 06/04/2024] [Indexed: 06/21/2024] Open
Abstract
While alterations in nucleus size, shape, and color are ubiquitous in cancer, comprehensive quantification of nuclear morphology across a whole-slide histologic image remains a challenge. Here, we describe the development of a pan-tissue, deep learning-based digital pathology pipeline for exhaustive nucleus detection, segmentation, and classification and the utility of this pipeline for nuclear morphologic biomarker discovery. Manually-collected nucleus annotations were used to train an object detection and segmentation model for identifying nuclei, which was deployed to segment nuclei in H&E-stained slides from the BRCA, LUAD, and PRAD TCGA cohorts. Interpretable features describing the shape, size, color, and texture of each nucleus were extracted from segmented nuclei and compared to measurements of genomic instability, gene expression, and prognosis. The nuclear segmentation and classification model trained herein performed comparably to previously reported models. Features extracted from the model revealed differences sufficient to distinguish between BRCA, LUAD, and PRAD. Furthermore, cancer cell nuclear area was associated with increased aneuploidy score and homologous recombination deficiency. In BRCA, increased fibroblast nuclear area was indicative of poor progression-free and overall survival and was associated with gene expression signatures related to extracellular matrix remodeling and anti-tumor immunity. Thus, we developed a powerful pan-tissue approach for nucleus segmentation and featurization, enabling the construction of predictive models and the identification of features linking nuclear morphology with clinically-relevant prognostic biomarkers across multiple cancer types.
Collapse
|
3
|
Koriakina N, Sladoje N, Bašić V, Lindblad J. Deep multiple instance learning versus conventional deep single instance learning for interpretable oral cancer detection. PLoS One 2024; 19:e0302169. [PMID: 38687694 PMCID: PMC11060593 DOI: 10.1371/journal.pone.0302169] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 03/28/2024] [Indexed: 05/02/2024] Open
Abstract
The current medical standard for setting an oral cancer (OC) diagnosis is histological examination of a tissue sample taken from the oral cavity. This process is time-consuming and more invasive than an alternative approach of acquiring a brush sample followed by cytological analysis. Using a microscope, skilled cytotechnologists are able to detect changes due to malignancy; however, introducing this approach into clinical routine is associated with challenges such as a lack of resources and experts. To design a trustworthy OC detection system that can assist cytotechnologists, we are interested in deep learning based methods that can reliably detect cancer, given only per-patient labels (thereby minimizing annotation bias), and also provide information regarding which cells are most relevant for the diagnosis (thereby enabling supervision and understanding). In this study, we perform a comparison of two approaches suitable for OC detection and interpretation: (i) conventional single instance learning (SIL) approach and (ii) a modern multiple instance learning (MIL) method. To facilitate systematic evaluation of the considered approaches, we, in addition to a real OC dataset with patient-level ground truth annotations, also introduce a synthetic dataset-PAP-QMNIST. This dataset shares several properties of OC data, such as image size and large and varied number of instances per bag, and may therefore act as a proxy model of a real OC dataset, while, in contrast to OC data, it offers reliable per-instance ground truth, as defined by design. PAP-QMNIST has the additional advantage of being visually interpretable for non-experts, which simplifies analysis of the behavior of methods. For both OC and PAP-QMNIST data, we evaluate performance of the methods utilizing three different neural network architectures. Our study indicates, somewhat surprisingly, that on both synthetic and real data, the performance of the SIL approach is better or equal to the performance of the MIL approach. Visual examination by cytotechnologist indicates that the methods manage to identify cells which deviate from normality, including malignant cells as well as those suspicious for dysplasia. We share the code as open source.
Collapse
Affiliation(s)
- Nadezhda Koriakina
- Centre for Image Analysis, Department of Information Technology, Uppsala University, Uppsala, Sweden
| | - Nataša Sladoje
- Centre for Image Analysis, Department of Information Technology, Uppsala University, Uppsala, Sweden
| | - Vladimir Bašić
- Department of Natural Science and Biomedicine, School of Health and Welfare, Jönköping University, Jönköping, Sweden
- Clinical Research Center Dalarna, Uppsala University, Falun, Sweden
| | - Joakim Lindblad
- Centre for Image Analysis, Department of Information Technology, Uppsala University, Uppsala, Sweden
| |
Collapse
|
4
|
Katayama A, Aoki Y, Watanabe Y, Horiguchi J, Rakha EA, Oyama T. Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers. Int J Clin Oncol 2024:10.1007/s10147-024-02513-3. [PMID: 38619651 DOI: 10.1007/s10147-024-02513-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2024] [Accepted: 03/12/2024] [Indexed: 04/16/2024]
Abstract
Breast cancer is the most prevalent cancer among women, and its diagnosis requires the accurate identification and classification of histological features for effective patient management. Artificial intelligence, particularly through deep learning, represents the next frontier in cancer diagnosis and management. Notably, the use of convolutional neural networks and emerging Vision Transformers (ViT) has been reported to automate pathologists' tasks, including tumor detection and classification, in addition to improving the efficiency of pathology services. Deep learning applications have also been extended to the prediction of protein expression, molecular subtype, mutation status, therapeutic efficacy, and outcome prediction directly from hematoxylin and eosin-stained slides, bypassing the need for immunohistochemistry or genetic testing. This review explores the current status and prospects of deep learning in breast cancer diagnosis with a focus on whole-slide image analysis. Artificial intelligence applications are increasingly applied to many tasks in breast pathology ranging from disease diagnosis to outcome prediction, thus serving as valuable tools for assisting pathologists and supporting breast cancer management.
Collapse
Affiliation(s)
- Ayaka Katayama
- Diagnostic Pathology, Gunma University Graduate School of Medicine, 3-39-22 Showamachi, Maebashi, Gunma, 371-8511, Japan.
| | - Yuki Aoki
- Center for Mathematics and Data Science, Gunma University, Maebashi, Japan
| | - Yukako Watanabe
- Clinical Training Center, Gunma University Hospital, Maebashi, Japan
| | - Jun Horiguchi
- Department of Breast Surgery, International University of Health and Welfare, Narita, Japan
| | - Emad A Rakha
- Department of Histopathology School of Medicine, University of Nottingham, University Park, Nottingham, UK
- Department of Pathology, Hamad Medical Corporation, Doha, Qatar
| | - Tetsunari Oyama
- Diagnostic Pathology, Gunma University Graduate School of Medicine, 3-39-22 Showamachi, Maebashi, Gunma, 371-8511, Japan
| |
Collapse
|
5
|
Aalam SW, Ahanger AB, Masoodi TA, Bhat AA, Akil ASAS, Khan MA, Assad A, Macha MA, Bhat MR. Deep learning-based identification of esophageal cancer subtypes through analysis of high-resolution histopathology images. Front Mol Biosci 2024; 11:1346242. [PMID: 38567100 PMCID: PMC10985197 DOI: 10.3389/fmolb.2024.1346242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Accepted: 02/23/2024] [Indexed: 04/04/2024] Open
Abstract
Esophageal cancer (EC) remains a significant health challenge globally, with increasing incidence and high mortality rates. Despite advances in treatment, there remains a need for improved diagnostic methods and understanding of disease progression. This study addresses the significant challenges in the automatic classification of EC, particularly in distinguishing its primary subtypes: adenocarcinoma and squamous cell carcinoma, using histopathology images. Traditional histopathological diagnosis, while being the gold standard, is subject to subjectivity and human error and imposes a substantial burden on pathologists. This study proposes a binary class classification system for detecting EC subtypes in response to these challenges. The system leverages deep learning techniques and tissue-level labels for enhanced accuracy. We utilized 59 high-resolution histopathological images from The Cancer Genome Atlas (TCGA) Esophageal Carcinoma dataset (TCGA-ESCA). These images were preprocessed, segmented into patches, and analyzed using a pre-trained ResNet101 model for feature extraction. For classification, we employed five machine learning classifiers: Support Vector Classifier (SVC), Logistic Regression (LR), Decision Tree (DT), AdaBoost (AD), Random Forest (RF), and a Feed-Forward Neural Network (FFNN). The classifiers were evaluated based on their prediction accuracy on the test dataset, yielding results of 0.88 (SVC and LR), 0.64 (DT and AD), 0.82 (RF), and 0.94 (FFNN). Notably, the FFNN classifier achieved the highest Area Under the Curve (AUC) score of 0.92, indicating its superior performance, followed closely by SVC and LR, with a score of 0.87. This suggested approach holds promising potential as a decision-support tool for pathologists, particularly in regions with limited resources and expertise. The timely and precise detection of EC subtypes through this system can substantially enhance the likelihood of successful treatment, ultimately leading to reduced mortality rates in patients with this aggressive cancer.
Collapse
Affiliation(s)
- Syed Wajid Aalam
- Department of Computer Science, Islamic University of Science and Technology, Awantipora, India
| | - Abdul Basit Ahanger
- Department of Computer Science, Islamic University of Science and Technology, Awantipora, India
| | - Tariq A. Masoodi
- Human Immunology Department, Research Branch, Sidra Medicine, Doha, Qatar
| | - Ajaz A. Bhat
- Department of Human Genetics-Precision Medicine in Diabetes, Obesity and Cancer Program, Sidra Medicine, Doha, Qatar
| | - Ammira S. Al-Shabeeb Akil
- Department of Human Genetics-Precision Medicine in Diabetes, Obesity and Cancer Program, Sidra Medicine, Doha, Qatar
| | | | - Assif Assad
- Department of Computer Science and Engineering, Islamic University of Science and Technology, Awantipora, India
| | - Muzafar A. Macha
- Watson-Crick Centre for Molecular Medicine, Islamic University of Science and Technology, Awantipora, India
| | - Muzafar Rasool Bhat
- Department of Computer Science, Islamic University of Science and Technology, Awantipora, India
| |
Collapse
|
6
|
Hölscher DL, Goedertier M, Klinkhammer BM, Droste P, Costa IG, Boor P, Bülow RD. tRigon: an R package and Shiny App for integrative (path-)omics data analysis. BMC Bioinformatics 2024; 25:98. [PMID: 38443821 PMCID: PMC10916305 DOI: 10.1186/s12859-024-05721-w] [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: 11/21/2023] [Accepted: 02/26/2024] [Indexed: 03/07/2024] Open
Abstract
BACKGROUND Pathomics facilitates automated, reproducible and precise histopathology analysis and morphological phenotyping. Similar to molecular omics, pathomics datasets are high-dimensional, but also face large outlier variability and inherent data missingness, making quick and comprehensible data analysis challenging. To facilitate pathomics data analysis and interpretation as well as support a broad implementation we developed tRigon (Toolbox foR InteGrative (path-)Omics data aNalysis), a Shiny application for fast, comprehensive and reproducible pathomics analysis. RESULTS tRigon is available via the CRAN repository ( https://cran.r-project.org/web/packages/tRigon ) with its source code available on GitLab ( https://git-ce.rwth-aachen.de/labooratory-ai/trigon ). The tRigon package can be installed locally and its application can be executed from the R console via the command 'tRigon::run_tRigon()'. Alternatively, the application is hosted online and can be accessed at https://labooratory.shinyapps.io/tRigon . We show fast computation of small, medium and large datasets in a low- and high-performance hardware setting, indicating broad applicability of tRigon. CONCLUSIONS tRigon allows researchers without coding abilities to perform exploratory feature analyses of pathomics and non-pathomics datasets on their own using a variety of hardware.
Collapse
Affiliation(s)
- David L Hölscher
- Institute of Pathology, RWTH Aachen University Clinic, Aachen, Germany
- Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany
| | - Michael Goedertier
- Institute of Pathology, RWTH Aachen University Clinic, Aachen, Germany
- Institute for Computational Genomics, RWTH Aachen University Clinic, Aachen, Germany
| | | | - Patrick Droste
- Institute of Pathology, RWTH Aachen University Clinic, Aachen, Germany
- Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany
| | - Ivan G Costa
- Institute for Computational Genomics, RWTH Aachen University Clinic, Aachen, Germany
| | - Peter Boor
- Institute of Pathology, RWTH Aachen University Clinic, Aachen, Germany
- Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany
| | - Roman D Bülow
- Institute of Pathology, RWTH Aachen University Clinic, Aachen, Germany.
| |
Collapse
|
7
|
Escobar Díaz Guerrero R, Oliveira JL, Popp J, Bocklitz T. MMIR: an open-source software for the registration of multimodal histological images. BMC Med Inform Decis Mak 2024; 24:65. [PMID: 38443881 PMCID: PMC10916274 DOI: 10.1186/s12911-024-02424-3] [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: 09/12/2023] [Accepted: 01/11/2024] [Indexed: 03/07/2024] Open
Abstract
BACKGROUND Multimodal histology image registration is a process that transforms into a common coordinate system two or more images obtained from different microscopy modalities. The combination of information from various modalities can contribute to a comprehensive understanding of tissue specimens, aiding in more accurate diagnoses, and improved research insights. Multimodal image registration in histology samples presents a significant challenge due to the inherent differences in characteristics and the need for tailored optimization algorithms for each modality. RESULTS We developed MMIR a cloud-based system for multimodal histological image registration, which consists of three main modules: a project manager, an algorithm manager, and an image visualization system. CONCLUSION Our software solution aims to simplify image registration tasks with a user-friendly approach. It facilitates effective algorithm management, responsive web interfaces, supports multi-resolution images, and facilitates batch image registration. Moreover, its adaptable architecture allows for the integration of custom algorithms, ensuring that it aligns with the specific requirements of each modality combination. Beyond image registration, our software enables the conversion of segmented annotations from one modality to another.
Collapse
Affiliation(s)
- Rodrigo Escobar Díaz Guerrero
- BMD Software, PCI - Creative Science Park, 3830-352, Ilhavo, Portugal.
- DETI/IEETA, University of Aveiro, 3810-193, Aveiro, Portugal.
- Leibniz Institute of Photonic Technology Jena, Member of Leibniz research alliance 'Health technologies', Albert-Einstein-Straße 9, 07745, Jena, Germany.
| | | | - Juergen Popp
- Leibniz Institute of Photonic Technology Jena, Member of Leibniz research alliance 'Health technologies', Albert-Einstein-Straße 9, 07745, Jena, Germany
- Institute of Physical Chemistry and Abbe Center of Photonics (IPC), Friedrich-Schiller-University, Helmholtzweg 4, 07743, Jena, Germany
| | - Thomas Bocklitz
- Leibniz Institute of Photonic Technology Jena, Member of Leibniz research alliance 'Health technologies', Albert-Einstein-Straße 9, 07745, Jena, Germany
- Institute of Physical Chemistry and Abbe Center of Photonics (IPC), Friedrich-Schiller-University, Helmholtzweg 4, 07743, Jena, Germany
- Institute of Computer Science, Faculty of Mathematics, Physics & Computer Science, University Bayreuth, Universitätsstraße 30, 95447, Bayreuth, Germany
| |
Collapse
|
8
|
Pytlarz M, Wojnicki K, Pilanc P, Kaminska B, Crimi A. Deep Learning Glioma Grading with the Tumor Microenvironment Analysis Protocol for Comprehensive Learning, Discovering, and Quantifying Microenvironmental Features. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01008-x. [PMID: 38413460 DOI: 10.1007/s10278-024-01008-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 12/17/2023] [Accepted: 12/21/2023] [Indexed: 02/29/2024]
Abstract
Gliomas are primary brain tumors that arise from neural stem cells, or glial precursors. Diagnosis of glioma is based on histological evaluation of pathological cell features and molecular markers. Gliomas are infiltrated by myeloid cells that accumulate preferentially in malignant tumors, and their abundance inversely correlates with survival, which is of interest for cancer immunotherapies. To avoid time-consuming and laborious manual examination of images, a deep learning approach for automatic multiclass classification of tumor grades was proposed. As an alternative way of investigating characteristics of brain tumor grades, we implemented a protocol for learning, discovering, and quantifying tumor microenvironment elements on our glioma dataset. Using only single-stained biopsies we derived characteristic differentiating tumor microenvironment phenotypic neighborhoods. The study was complicated by the small size of the available human leukocyte antigen stained on glioma tissue microarray dataset - 206 images of 5 classes - as well as imbalanced data distribution. This challenge was addressed by image augmentation for underrepresented classes. In practice, we considered two scenarios, a whole slide supervised learning classification, and an unsupervised cell-to-cell analysis looking for patterns of the microenvironment. In the supervised learning investigation, we evaluated 6 distinct model architectures. Experiments revealed that a DenseNet121 architecture surpasses the baseline's accuracy by a significant margin of 9% for the test set, achieving a score of 69%, increasing accuracy in discerning challenging WHO grade 2 and 3 cases. All experiments have been carried out in a cross-validation manner. The tumor microenvironment analysis suggested an important role for myeloid cells and their accumulation in the context of characterizing glioma grades. Those promising approaches can be used as an additional diagnostic tool to improve assessment during intraoperative examination or subtyping tissues for treatment selection, potentially easing the workflow of pathologists and oncologists.
Collapse
Affiliation(s)
- M Pytlarz
- Sano - Centre for Computational Personalised Medicine, Czarnowiejska 36, Kraków, 30-054, Poland.
| | - K Wojnicki
- Nencki Institute of Experimental Biology of the Polish Academy of Sciences, 3 Pasteur Street, Warszawa, 02-093, Poland
| | - P Pilanc
- Nencki Institute of Experimental Biology of the Polish Academy of Sciences, 3 Pasteur Street, Warszawa, 02-093, Poland
| | - B Kaminska
- Nencki Institute of Experimental Biology of the Polish Academy of Sciences, 3 Pasteur Street, Warszawa, 02-093, Poland
| | - A Crimi
- Sano - Centre for Computational Personalised Medicine, Czarnowiejska 36, Kraków, 30-054, Poland
| |
Collapse
|
9
|
Wagner SJ, Matek C, Shetab Boushehri S, Boxberg M, Lamm L, Sadafi A, Winter DJE, Marr C, Peng T. Built to Last? Reproducibility and Reusability of Deep Learning Algorithms in Computational Pathology. Mod Pathol 2024; 37:100350. [PMID: 37827448 DOI: 10.1016/j.modpat.2023.100350] [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] [Received: 02/10/2023] [Revised: 10/02/2023] [Accepted: 10/03/2023] [Indexed: 10/14/2023]
Abstract
Recent progress in computational pathology has been driven by deep learning. While code and data availability are essential to reproduce findings from preceding publications, ensuring a deep learning model's reusability is more challenging. For that, the codebase should be well-documented and easy to integrate into existing workflows and models should be robust toward noise and generalizable toward data from different sources. Strikingly, only a few computational pathology algorithms have been reused by other researchers so far, let alone employed in a clinical setting. To assess the current state of reproducibility and reusability of computational pathology algorithms, we evaluated peer-reviewed articles available in PubMed, published between January 2019 and March 2021, in 5 use cases: stain normalization; tissue type segmentation; evaluation of cell-level features; genetic alteration prediction; and inference of grading, staging, and prognostic information. We compiled criteria for data and code availability and statistical result analysis and assessed them in 160 publications. We found that only one-quarter (41 of 160 publications) made code publicly available. Among these 41 studies, three-quarters (30 of 41) analyzed their results statistically, half of them (20 of 41) released their trained model weights, and approximately a third (16 of 41) used an independent cohort for evaluation. Our review is intended for both pathologists interested in deep learning and researchers applying algorithms to computational pathology challenges. We provide a detailed overview of publications with published code in the field, list reusable data handling tools, and provide criteria for reproducibility and reusability.
Collapse
Affiliation(s)
- Sophia J Wagner
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; School of Computation, Information and Technology, Technical University of Munich, Garching, Germany
| | - Christian Matek
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Institute of Pathology, University Hospital Erlangen, Erlangen, Germany
| | - Sayedali Shetab Boushehri
- School of Computation, Information and Technology, Technical University of Munich, Garching, Germany; Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Data & Analytics (D&A), Roche Pharma Research and Early Development (pRED), Roche Innovation Center Munich, Germany
| | - Melanie Boxberg
- Institute of Pathology, Technical University Munich, Munich, Germany; Institute of Pathology Munich-North, Munich, Germany
| | - Lorenz Lamm
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; Helmholtz Pioneer Campus, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany
| | - Ario Sadafi
- School of Computation, Information and Technology, Technical University of Munich, Garching, Germany; Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany
| | - Dominik J E Winter
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany; School of Life Sciences, Technical University of Munich, Weihenstephan, Germany
| | - Carsten Marr
- Institute of AI for Health, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany.
| | - Tingying Peng
- Helmholtz AI, Helmholtz Munich-German Research Center for Environmental Health, Neuherberg, Germany.
| |
Collapse
|
10
|
Iorgulescu JB, Ruthen N, Ahn R, Panagioti E, Gokhale PC, Neagu M, Speranza MC, Eschle BK, Soroko KM, Piranlioglu R, Datta M, Krishnan S, Yates KB, Baker GJ, Jain RK, Suvà ML, Neuberg D, White FM, Chiocca EA, Freeman GJ, Sharpe AH, Wu CJ, Reardon DA. Antigen presentation deficiency, mesenchymal differentiation, and resistance to immunotherapy in the murine syngeneic CT2A tumor model. Front Immunol 2023; 14:1297932. [PMID: 38213329 PMCID: PMC10782385 DOI: 10.3389/fimmu.2023.1297932] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Accepted: 12/11/2023] [Indexed: 01/13/2024] Open
Abstract
Background The GL261 and CT2A syngeneic tumor lines are frequently used as immunocompetent orthotopic mouse models of human glioblastoma (huGBM) but demonstrate distinct differences in their responses to immunotherapy. Methods To decipher the cell-intrinsic mechanisms that drive immunotherapy resistance in CT2A-luc and to define the aspects of human cancer biology that these lines can best model, we systematically compared their characteristics using whole exome and transcriptome sequencing, and protein analysis through immunohistochemistry, Western blot, flow cytometry, immunopeptidomics, and phosphopeptidomics. Results The transcriptional profiles of GL261-luc2 and CT2A-luc tumors resembled those of some huGBMs, despite neither line sharing the essential genetic or histologic features of huGBM. Both models exhibited striking hypermutation, with clonal hotspot mutations in RAS genes (Kras p.G12C in GL261-luc2 and Nras p.Q61L in CT2A-luc). CT2A-luc distinctly displayed mesenchymal differentiation, upregulated angiogenesis, and multiple defects in antigen presentation machinery (e.g. Tap1 p.Y488C and Psmb8 p.A275P mutations) and interferon response pathways (e.g. copy number losses of loci including IFN genes and reduced phosphorylation of JAK/STAT pathway members). The defect in MHC class I expression could be overcome in CT2A-luc by interferon-γ treatment, which may underlie the modest efficacy of some immunotherapy combinations. Additionally, CT2A-luc demonstrated substantial baseline secretion of the CCL-2, CCL-5, and CCL-22 chemokines, which play important roles as myeloid chemoattractants. Conclusion Although the clinical contexts that can be modeled by GL261 and CT2A for huGBM are limited, CT2A may be an informative model of immunotherapy resistance due to its deficits in antigen presentation machinery and interferon response pathways.
Collapse
Affiliation(s)
- J. Bryan Iorgulescu
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
- Department of Pathology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- The Eli and Edythe L. Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - Neil Ruthen
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Ryuhjin Ahn
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States
- Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Eleni Panagioti
- Department of Neurosurgery, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA, United States
| | - Prafulla C. Gokhale
- Experimental Therapeutics Core and Belfer Center for Applied Cancer Science, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Martha Neagu
- Department of Immunology, Blavatnik Institute, Harvard Medical School, Boston, MA, United States
| | - Maria C. Speranza
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Benjamin K. Eschle
- Experimental Therapeutics Core and Belfer Center for Applied Cancer Science, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Kara M. Soroko
- Experimental Therapeutics Core and Belfer Center for Applied Cancer Science, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Raziye Piranlioglu
- Department of Neurosurgery, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA, United States
| | - Meenal Datta
- Edwin L. Steele Laboratories for Tumor Biology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
- Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Shanmugarajan Krishnan
- Edwin L. Steele Laboratories for Tumor Biology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Kathleen B. Yates
- The Eli and Edythe L. Broad Institute of MIT and Harvard, Cambridge, MA, United States
- Center for Cancer Research, Massachusetts General Hospital, Boston, MA, United States
| | - Gregory J. Baker
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, United States
- Ludwig Center for Cancer Research at Harvard, Harvard Medical School, Boston, MA, United States
| | - Rakesh K. Jain
- Edwin L. Steele Laboratories for Tumor Biology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Mario L. Suvà
- The Eli and Edythe L. Broad Institute of MIT and Harvard, Cambridge, MA, United States
- Center for Cancer Research, Massachusetts General Hospital, Boston, MA, United States
- Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Donna Neuberg
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Forest M. White
- Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States
- Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - E. Antonio Chiocca
- Department of Neurosurgery, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA, United States
| | - Gordon J. Freeman
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
| | - Arlene H. Sharpe
- Department of Pathology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- The Eli and Edythe L. Broad Institute of MIT and Harvard, Cambridge, MA, United States
- Department of Immunology, Blavatnik Institute, Harvard Medical School, Boston, MA, United States
| | - Catherine J. Wu
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
- The Eli and Edythe L. Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - David A. Reardon
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, United States
| |
Collapse
|
11
|
Lin TP, Yang CY, Liu KJ, Huang MY, Chen YL. Immunohistochemical Stain-Aided Annotation Accelerates Machine Learning and Deep Learning Model Development in the Pathologic Diagnosis of Nasopharyngeal Carcinoma. Diagnostics (Basel) 2023; 13:3685. [PMID: 38132269 PMCID: PMC10743164 DOI: 10.3390/diagnostics13243685] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Revised: 12/04/2023] [Accepted: 12/05/2023] [Indexed: 12/23/2023] Open
Abstract
Nasopharyngeal carcinoma (NPC) is an epithelial cancer originating in the nasopharynx epithelium. Nevertheless, annotating pathology slides remains a bottleneck in the development of AI-driven pathology models and applications. In the present study, we aim to demonstrate the feasibility of using immunohistochemistry (IHC) for annotation by non-pathologists and to develop an efficient model for distinguishing NPC without the time-consuming involvement of pathologists. For this study, we gathered NPC slides from 251 different patients, comprising hematoxylin and eosin (H&E) slides, pan-cytokeratin (Pan-CK) IHC slides, and Epstein-Barr virus-encoded small RNA (EBER) slides. The annotation of NPC regions in the H&E slides was carried out by a non-pathologist trainee who had access to corresponding Pan-CK IHC slides, both with and without EBER slides. The training process utilized ResNeXt, a deep neural network featuring a residual and inception architecture. In the validation set, NPC exhibited an AUC of 0.896, with a sensitivity of 0.919 and a specificity of 0.878. This study represents a significant breakthrough: the successful application of deep convolutional neural networks to identify NPC without the need for expert pathologist annotations. Our results underscore the potential of laboratory techniques to substantially reduce the workload of pathologists.
Collapse
Affiliation(s)
- Tai-Pei Lin
- Department of Life Sciences, National Chung Hsing University, Taichung 402, Taiwan;
| | - Chiou-Ying Yang
- Institute of Molecular Biology, National Chung Hsing University, Taichung 402, Taiwan;
| | - Ko-Jiunn Liu
- National Institute of Cancer Research, National Health Research Institutes, Tainan 704, Taiwan;
- Graduate Institute of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung 807, Taiwan
- Institute of Clinical Pharmacy and Pharmaceutical Sciences and Institute of Clinical Medicine, National Cheng Kung University, Tainan 701, Taiwan
| | - Meng-Yuan Huang
- Department of Life Sciences, National Chung Hsing University, Taichung 402, Taiwan;
| | - Yen-Lin Chen
- Department of Pathology, Tri-Service General Hospital, National Defense Medical Center, Taipei 114, Taiwan
| |
Collapse
|
12
|
Sun X, Li W, Fu B, Peng Y, He J, Wang L, Yang T, Meng X, Li J, Wang J, Huang P, Wang R. TGMIL: A hybrid multi-instance learning model based on the Transformer and the Graph Attention Network for whole-slide images classification of renal cell carcinoma. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 242:107789. [PMID: 37722310 DOI: 10.1016/j.cmpb.2023.107789] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Revised: 08/30/2023] [Accepted: 09/01/2023] [Indexed: 09/20/2023]
Abstract
BACKGROUND AND OBJECTIVES The pathological diagnosis of renal cell carcinoma is crucial for treatment. Currently, the multi-instance learning method is commonly used for whole-slide image classification of renal cell carcinoma, which is mainly based on the assumption of independent identical distribution. But this is inconsistent with the need to consider the correlation between different instances in the diagnosis process. Furthermore, the problem of high resource consumption of pathology images is still urgent to be solved. Therefore, we propose a new multi-instance learning method to solve this problem. METHODS In this study, we proposed a hybrid multi-instance learning model based on the Transformer and the Graph Attention Network, called TGMIL, to achieve whole-slide image of renal cell carcinoma classification without pixel-level annotation or region of interest extraction. Our approach is divided into three steps. First, we designed a feature pyramid with the multiple low magnifications of whole-slide image named MMFP. It makes the model incorporates richer information, and reduces memory consumption as well as training time compared to the highest magnification. Second, TGMIL amalgamates the Transformer and the Graph Attention's capabilities, adeptly addressing the loss of instance contextual and spatial. Within the Graph Attention network stream, an easy and efficient approach employing max pooling and mean pooling yields the graph adjacency matrix, devoid of extra memory consumption. Finally, the outputs of two streams of TGMIL are aggregated to achieve the classification of renal cell carcinoma. RESULTS On the TCGA-RCC validation set, a public dataset for renal cell carcinoma, the area under a receiver operating characteristic (ROC) curve (AUC) and accuracy of TGMIL were 0.98±0.0015,0.9191±0.0062, respectively. It showcased remarkable proficiency on the private validation set of renal cell carcinoma pathology images, attaining AUC of 0.9386±0.0162 and ACC of 0.9197±0.0124. Furthermore, on the public breast cancer whole-slide image test dataset, CAMELYON 16, our model showed good classification performance with an accuracy of 0.8792. CONCLUSIONS TGMIL models the diagnostic process of pathologists and shows good classification performance on multiple datasets. Concurrently, the MMFP module efficiently diminishes resource requirements, offering a novel angle for exploring computational pathology images.
Collapse
Affiliation(s)
- Xinhuan Sun
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, 550025, China; Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Wuchao Li
- Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Bangkang Fu
- Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Yunsong Peng
- Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Junjie He
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, 550025, China; Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Lihui Wang
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, 550025, China
| | - Tongyin Yang
- Department of Pathology, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Xue Meng
- Department of Pathology, Affiliated Hospital of Zunyi Medical University, Zunyi, 563000, China
| | - Jin Li
- Department of Pathology, Affiliated Hospital of Zunyi Medical University, Zunyi, 563000, China
| | - Jinjing Wang
- Department of Pathology, Affiliated Hospital of Zunyi Medical University, Zunyi, 563000, China
| | - Ping Huang
- Department of Pathology, Guizhou Provincial People's Hospital, Guiyang, 550002, China
| | - Rongpin Wang
- Department of Radiology, International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment, Guizhou Provincial People's Hospital, Guiyang, 550002, China.
| |
Collapse
|
13
|
Meng X, Zou T. Clinical applications of graph neural networks in computational histopathology: A review. Comput Biol Med 2023; 164:107201. [PMID: 37517325 DOI: 10.1016/j.compbiomed.2023.107201] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 06/10/2023] [Accepted: 06/19/2023] [Indexed: 08/01/2023]
Abstract
Pathological examination is the optimal approach for diagnosing cancer, and with the advancement of digital imaging technologies, it has spurred the emergence of computational histopathology. The objective of computational histopathology is to assist in clinical tasks through image processing and analysis techniques. In the early stages, the technique involved analyzing histopathology images by extracting mathematical features, but the performance of these models was unsatisfactory. With the development of artificial intelligence (AI) technologies, traditional machine learning methods were applied in this field. Although the performance of the models improved, there were issues such as poor model generalization and tedious manual feature extraction. Subsequently, the introduction of deep learning techniques effectively addressed these problems. However, models based on traditional convolutional architectures could not adequately capture the contextual information and deep biological features in histopathology images. Due to the special structure of graphs, they are highly suitable for feature extraction in tissue histopathology images and have achieved promising performance in numerous studies. In this article, we review existing graph-based methods in computational histopathology and propose a novel and more comprehensive graph construction approach. Additionally, we categorize the methods and techniques in computational histopathology according to different learning paradigms. We summarize the common clinical applications of graph-based methods in computational histopathology. Furthermore, we discuss the core concepts in this field and highlight the current challenges and future research directions.
Collapse
Affiliation(s)
- Xiangyan Meng
- Xi'an Technological University, Xi'an, Shaanxi, 710021, China.
| | - Tonghui Zou
- Xi'an Technological University, Xi'an, Shaanxi, 710021, China.
| |
Collapse
|
14
|
Chitnis SR, Liu S, Dash T, Verlekar TT, Di Ieva A, Berkovsky S, Vig L, Srinivasan A. Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083343 DOI: 10.1109/embc40787.2023.10340659] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Whole Slide Images (WSIs) or histopathology images are used in digital pathology. WSIs pose great challenges to deep learning models for clinical diagnosis, owing to their size and lack of pixel-level annotations. With the recent advancements in computational pathology, newer multiple-instance learning-based models have been proposed. Multiple-instance learning for WSIs necessitates creating patches and uses the encoding of these patches for diagnosis. These models use generic pre-trained models (ResNet-50 pre-trained on ImageNet) for patch encoding. The recently proposed KimiaNet, a DenseNet121 model pre-trained on TCGA slides, is a domain-specific pre-trained model. This paper shows the effect of domain-specific pre-training on WSI classification. To investigate the effect of domain-specific pre-training, we considered the current state-of-the-art multiple-instance learning models, 1) CLAM, an attention-based model, and 2) TransMIL, a self-attention-based model, and evaluated the models' confidence and predictive performance in detecting primary brain tumors - gliomas. Domain-specific pre-training improves the confidence of the models and also achieves a new state-of-the-art performance of WSI-based glioma subtype classification, showing a high clinical applicability in assisting glioma diagnosis. We will publicly share our code and experimental results at https://github.com/soham-chitnis10/WSI-domain-specific.
Collapse
|
15
|
Hu W, Li X, Li C, Li R, Jiang T, Sun H, Huang X, Grzegorzek M, Li X. A state-of-the-art survey of artificial neural networks for Whole-slide Image analysis: From popular Convolutional Neural Networks to potential visual transformers. Comput Biol Med 2023; 161:107034. [PMID: 37230019 DOI: 10.1016/j.compbiomed.2023.107034] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Revised: 04/13/2023] [Accepted: 05/10/2023] [Indexed: 05/27/2023]
Abstract
In recent years, with the advancement of computer-aided diagnosis (CAD) technology and whole slide image (WSI), histopathological WSI has gradually played a crucial aspect in the diagnosis and analysis of diseases. To increase the objectivity and accuracy of pathologists' work, artificial neural network (ANN) methods have been generally needed in the segmentation, classification, and detection of histopathological WSI. However, the existing review papers only focus on equipment hardware, development status and trends, and do not summarize the art neural network used for full-slide image analysis in detail. In this paper, WSI analysis methods based on ANN are reviewed. Firstly, the development status of WSI and ANN methods is introduced. Secondly, we summarize the common ANN methods. Next, we discuss publicly available WSI datasets and evaluation metrics. These ANN architectures for WSI processing are divided into classical neural networks and deep neural networks (DNNs) and then analyzed. Finally, the application prospect of the analytical method in this field is discussed. The important potential method is Visual Transformers.
Collapse
Affiliation(s)
- Weiming Hu
- Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Xintong Li
- Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Chen Li
- Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
| | - Rui Li
- Microscopic Image and Medical Image Analysis Group, College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
| | - Tao Jiang
- School of Intelligent Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu, China; International Joint Institute of Robotics and Intelligent Systems, Chengdu University of Information Technology, Chengdu, China
| | - Hongzan Sun
- Shengjing Hospital of China Medical University, Shenyang, China
| | - Xinyu Huang
- Institute for Medical Informatics, University of Luebeck, Luebeck, Germany
| | - Marcin Grzegorzek
- Institute for Medical Informatics, University of Luebeck, Luebeck, Germany; Department of Knowledge Engineering, University of Economics in Katowice, Katowice, Poland
| | - Xiaoyan Li
- Cancer Hospital of China Medical University, Shenyang, China.
| |
Collapse
|
16
|
Dehkharghanian T, Bidgoli AA, Riasatian A, Mazaheri P, Campbell CJV, Pantanowitz L, Tizhoosh HR, Rahnamayan S. Biased data, biased AI: deep networks predict the acquisition site of TCGA images. Diagn Pathol 2023; 18:67. [PMID: 37198691 DOI: 10.1186/s13000-023-01355-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Accepted: 05/07/2023] [Indexed: 05/19/2023] Open
Abstract
BACKGROUND Deep learning models applied to healthcare applications including digital pathology have been increasing their scope and importance in recent years. Many of these models have been trained on The Cancer Genome Atlas (TCGA) atlas of digital images, or use it as a validation source. One crucial factor that seems to have been widely ignored is the internal bias that originates from the institutions that contributed WSIs to the TCGA dataset, and its effects on models trained on this dataset. METHODS 8,579 paraffin-embedded, hematoxylin and eosin stained, digital slides were selected from the TCGA dataset. More than 140 medical institutions (acquisition sites) contributed to this dataset. Two deep neural networks (DenseNet121 and KimiaNet were used to extract deep features at 20× magnification. DenseNet was pre-trained on non-medical objects. KimiaNet has the same structure but trained for cancer type classification on TCGA images. The extracted deep features were later used to detect each slide's acquisition site, and also for slide representation in image search. RESULTS DenseNet's deep features could distinguish acquisition sites with 70% accuracy whereas KimiaNet's deep features could reveal acquisition sites with more than 86% accuracy. These findings suggest that there are acquisition site specific patterns that could be picked up by deep neural networks. It has also been shown that these medically irrelevant patterns can interfere with other applications of deep learning in digital pathology, namely image search. This study shows that there are acquisition site specific patterns that can be used to identify tissue acquisition sites without any explicit training. Furthermore, it was observed that a model trained for cancer subtype classification has exploited such medically irrelevant patterns to classify cancer types. Digital scanner configuration and noise, tissue stain variation and artifacts, and source site patient demographics are among factors that likely account for the observed bias. Therefore, researchers should be cautious of such bias when using histopathology datasets for developing and training deep networks.
Collapse
Affiliation(s)
- Taher Dehkharghanian
- University Health Network, Toronto, ON, Canada
- Department of Pathology and Molecular Medicine, Faculty of Health Science, McMaster University, Hamilton, ON, Canada
| | - Azam Asilian Bidgoli
- Nature Inspired Computational Intelligence (NICI), Ontario Tech University, Oshawa, ON, Canada
- Nature Inspired Computational Intelligence (NICI) Lab, Department of Engineering, Brock University, 1812 Sir Isaac Brock Way, St. Catharines, ON, L2S 3A1, Canada
- Bharti School of Engineering and Computer Science, Laurentian University, Sudbury, ON, Canada
| | | | - Pooria Mazaheri
- Nature Inspired Computational Intelligence (NICI), Ontario Tech University, Oshawa, ON, Canada
| | - Clinton J V Campbell
- Department of Pathology and Molecular Medicine, Faculty of Health Science, McMaster University, Hamilton, ON, Canada
- William Osler Health System, Brampton, ON, Canada
| | | | - H R Tizhoosh
- KIMIA Lab, University of Waterloo, Waterloo, ON, Canada
- Rhazes Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
| | - Shahryar Rahnamayan
- Nature Inspired Computational Intelligence (NICI), Ontario Tech University, Oshawa, ON, Canada.
- Nature Inspired Computational Intelligence (NICI) Lab, Department of Engineering, Brock University, 1812 Sir Isaac Brock Way, St. Catharines, ON, L2S 3A1, Canada.
| |
Collapse
|
17
|
Holub P, Müller H, Bíl T, Pireddu L, Plass M, Prasser F, Schlünder I, Zatloukal K, Nenutil R, Brázdil T. Privacy risks of whole-slide image sharing in digital pathology. Nat Commun 2023; 14:2577. [PMID: 37142591 PMCID: PMC10160114 DOI: 10.1038/s41467-023-37991-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 04/11/2023] [Indexed: 05/06/2023] Open
Abstract
Access to large volumes of so-called whole-slide images-high-resolution scans of complete pathological slides-has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education/training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle "as open as possible and as closed as necessary" is still lacking. In this article, we develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective. We introduce a taxonomy of whole-slide images with respect to privacy risks and mathematical model for risk assessment and design . Based on this risk assessment model and the taxonomy, we conduct a series of experiments to demonstrate the risks using real-world imaging data. Finally, we develop guidelines for risk assessment and recommendations for low-risk sharing of whole-slide image data.
Collapse
Affiliation(s)
- Petr Holub
- BBMRI-ERIC, Graz, Austria.
- Institute of Computer Science, Masaryk University, Brno, Czech Republic.
| | - Heimo Müller
- BBMRI.at & Diagnostic & Research Center for Molecular BioMedicine, Medical University of Graz, Graz, A-8010, Austria
| | - Tomáš Bíl
- Institute of Computer Science, Masaryk University, Brno, Czech Republic
| | - Luca Pireddu
- Visual and Data-intensive Computing Group, CRS4, Pula, Italy
| | - Markus Plass
- BBMRI.at & Diagnostic & Research Center for Molecular BioMedicine, Medical University of Graz, Graz, A-8010, Austria
| | - Fabian Prasser
- Berlin Institute of Health @ Charité - Universitätsmedizin Berlin, Berlin, Germany
| | | | - Kurt Zatloukal
- BBMRI.at & Diagnostic & Research Center for Molecular BioMedicine, Medical University of Graz, Graz, A-8010, Austria
| | - Rudolf Nenutil
- BBMRI.cz & Masaryk Memorial Cancer Institute, Brno, Czech Republic
| | - Tomáš Brázdil
- Faculty of Informatics, Masaryk University, Brno, Czech Republic
| |
Collapse
|
18
|
Wu Q, Tian R, He X, Liu J, Ou C, Li Y, Fu X. Machine learning-based integration develops an immune-related risk model for predicting prognosis of high-grade serous ovarian cancer and providing therapeutic strategies. Front Immunol 2023; 14:1164408. [PMID: 37090728 PMCID: PMC10113544 DOI: 10.3389/fimmu.2023.1164408] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2023] [Accepted: 03/28/2023] [Indexed: 04/08/2023] Open
Abstract
BackgroundHigh-grade serous ovarian cancer (HGSOC) is a highly lethal gynecological cancer that requires accurate prognostic models and personalized treatment strategies. The tumor microenvironment (TME) is crucial for disease progression and treatment. Machine learning-based integration is a powerful tool for identifying predictive biomarkers and developing prognostic models. Hence, an immune-related risk model developed using machine learning-based integration could improve prognostic prediction and guide personalized treatment for HGSOC.MethodsDuring the bioinformatic study in HGSOC, we performed (i) consensus clustering to identify immune subtypes based on signatures of immune and stromal cells, (ii) differentially expressed genes and univariate Cox regression analysis to derive TME- and prognosis-related genes, (iii) machine learning-based procedures constructed by ten independent machine learning algorithms to screen and construct a TME-related risk score (TMErisk), and (iv) evaluation of the effect of TMErisk on the deconstruction of TME, indication of genomic instability, and guidance of immunotherapy and chemotherapy.ResultsWe identified two different immune microenvironment phenotypes and a robust and clinically practicable prognostic scoring system. TMErisk demonstrated superior performance over most clinical features and other published signatures in predicting HGSOC prognosis across cohorts. The low TMErisk group with a notably favorable prognosis was characterized by BRCA1 mutation, activation of immunity, and a better immune response. Conversely, the high TMErisk group was significantly associated with C-X-C motif chemokine ligands deletion and carcinogenic activation pathways. Additionally, low TMErisk group patients were more responsive to eleven candidate agents.ConclusionOur study developed a novel immune-related risk model that predicts the prognosis of ovarian cancer patients using machine learning-based integration. Additionally, the study not only depicts the diversity of cell components in the TME of HGSOC but also guides the development of potential therapeutic techniques for addressing tumor immunosuppression and enhancing the response to cancer therapy.
Collapse
Affiliation(s)
- Qihui Wu
- Department of Gynecology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Changsha, China
| | - Ruotong Tian
- Department of Pharmacology, School of Basic Medical Sciences, Shanghai Medical College, Fudan University, Shanghai, China
| | - Xiaoyun He
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Changsha, China
- Departments of Ultrasound Imaging, Xiangya Hospital, Central South University, Changsha, Hunan, China
| | - Jiaxin Liu
- Department of Pathology, School of Basic Medical Sciences, Central South University, Changsha, China
| | - Chunlin Ou
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Changsha, China
- Department of Pathology, Xiangya Hospital, Central South University, Changsha, China
- *Correspondence: Xiaodan Fu, ; ; Yimin Li, ; Chunlin Ou,
| | - Yimin Li
- Department of Pathology, Fudan University Shanghai Cancer Center, Shanghai, China
- Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China
- *Correspondence: Xiaodan Fu, ; ; Yimin Li, ; Chunlin Ou,
| | - Xiaodan Fu
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Changsha, China
- Department of Pathology, Xiangya Hospital, Central South University, Changsha, China
- *Correspondence: Xiaodan Fu, ; ; Yimin Li, ; Chunlin Ou,
| |
Collapse
|
19
|
Kang H, Yang M, Zhang F, Xu H, Ren S, Li J, Chen D, Wang F, Li D, Chen X. Identification lymph node metastasis in esophageal squamous cell carcinoma using whole slide images and a hybrid network of multiple instance and transfer learning. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/18/2023]
|
20
|
Bias reduction in representation of histopathology images using deep feature selection. Sci Rep 2022; 12:19994. [PMID: 36411301 PMCID: PMC9678861 DOI: 10.1038/s41598-022-24317-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Accepted: 11/14/2022] [Indexed: 11/22/2022] Open
Abstract
Appearing traces of bias in deep networks is a serious reliability issue which can play a significant role in ethics and generalization related concerns. Recent studies report that the deep features extracted from the histopathology images of The Cancer Genome Atlas (TCGA), the largest publicly available archive, are surprisingly able to accurately classify the whole slide images (WSIs) based on their acquisition site while these features are extracted to primarily discriminate cancer types. This is clear evidence that the utilized Deep Neural Networks (DNNs) unexpectedly detect the specific patterns of the source site, i.e, the hospital of origin, rather than histomorphologic patterns, a biased behavior resulting in degraded trust and generalization. This observation motivated us to propose a method to alleviate the destructive impact of hospital bias through a novel feature selection process. To this effect, we have proposed an evolutionary strategy to select a small set of optimal features to not only accurately represent the histological patterns of tissue samples but also to eliminate the features contributing to internal bias toward the institution. The defined objective function for an optimal subset selection of features is to minimize the accuracy of the model to classify the source institutions which is basically defined as a bias indicator. By the conducted experiments, the selected features extracted by the state-of-the-art network trained on TCGA images (i.e., the KimiaNet), considerably decreased the institutional bias, while improving the quality of features to discriminate the cancer types. In addition, the selected features could significantly improve the results of external validation compared to the entire set of features which has been negatively affected by bias. The proposed scheme is a model-independent approach which can be employed when it is possible to define a bias indicator as a participating objective in a feature selection process; even with unknown bias sources.
Collapse
|
21
|
Shen A, Wang F, Paul S, Bhuvanapalli D, Alayof J, Farris AB, Teodoro G, Brat DJ, Kong J. An integrative web-based software tool for multi-dimensional pathology whole-slide image analytics. Phys Med Biol 2022; 67:10.1088/1361-6560/ac8fde. [PMID: 36067783 PMCID: PMC10039615 DOI: 10.1088/1361-6560/ac8fde] [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: 04/02/2022] [Accepted: 09/06/2022] [Indexed: 11/12/2022]
Abstract
Objective.In the era of precision medicine, human tumor atlas-oriented studies have been significantly facilitated by high-resolution, multi-modal tissue based microscopic pathology image analytics. To better support such tissue-based investigations, we have developed Digital Pathology Laboratory (DPLab), a publicly available web-based platform, to assist biomedical research groups, non-technical end users, and clinicians for pathology whole-slide image visualization, annotation, analysis, and sharing via web browsers.Approach.A major advancement of this work is the easy-to-follow methods to reconstruct three-dimension (3D) tissue image volumes by registering two-dimension (2D) whole-slide pathology images of serial tissue sections stained by hematoxylin and eosin (H&E), and immunohistochemistry (IHC). The integration of these serial slides stained by different methods provides cellular phenotype and pathophysiologic states in the context of a 3D tissue micro-environment. DPLab is hosted on a publicly accessible server and connected to a backend computational cluster for intensive image analysis computations, with results visualized, downloaded, and shared via a web interface.Main results.Equipped with an analysis toolbox of numerous image processing algorithms, DPLab supports continued integration of community-contributed algorithms and presents an effective solution to improve the accessibility and dissemination of image analysis algorithms by research communities.Significance.DPLab represents the first step in making next generation tissue investigation tools widely available to the research community, enabling and facilitating discovery of clinically relevant disease mechanisms in a digital 3D tissue space.
Collapse
Affiliation(s)
- Alice Shen
- School of Medicine, University of California at San Diego, San Diego, CA USA
| | - Fusheng Wang
- Department of Computer Science, Stony Brook University, Stony Brook, NY USA
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY USA
| | - Saptarshi Paul
- Department of Computer Science, Georgia State University, Atlanta, GA USA
| | - Divya Bhuvanapalli
- Department of Computer Science, Georgia State University, Atlanta, GA USA
| | | | - Alton B. Farris
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GA USA
| | - George Teodoro
- Department of Computer Science in University of Brasilia, Brasília, DF Brazil
| | - Daniel J. Brat
- Department of Pathology, Northwestern University, Chicago, IL USA
| | - Jun Kong
- Department of Computer Science, Georgia State University, Atlanta, GA USA
- Department of Mathematics and Statistics, Georgia State University, Atlanta, GA USA
- Winship Cancer Institute, Emory University, Atlanta, GA USA
| |
Collapse
|
22
|
Ahmed AA, Abouzid M, Kaczmarek E. Deep Learning Approaches in Histopathology. Cancers (Basel) 2022; 14:5264. [PMID: 36358683 PMCID: PMC9654172 DOI: 10.3390/cancers14215264] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2022] [Revised: 10/10/2022] [Accepted: 10/24/2022] [Indexed: 10/06/2023] Open
Abstract
The revolution of artificial intelligence and its impacts on our daily life has led to tremendous interest in the field and its related subtypes: machine learning and deep learning. Scientists and developers have designed machine learning- and deep learning-based algorithms to perform various tasks related to tumor pathologies, such as tumor detection, classification, grading with variant stages, diagnostic forecasting, recognition of pathological attributes, pathogenesis, and genomic mutations. Pathologists are interested in artificial intelligence to improve the diagnosis precision impartiality and to minimize the workload combined with the time consumed, which affects the accuracy of the decision taken. Regrettably, there are already certain obstacles to overcome connected to artificial intelligence deployments, such as the applicability and validation of algorithms and computational technologies, in addition to the ability to train pathologists and doctors to use these machines and their willingness to accept the results. This review paper provides a survey of how machine learning and deep learning methods could be implemented into health care providers' routine tasks and the obstacles and opportunities for artificial intelligence application in tumor morphology.
Collapse
Affiliation(s)
- Alhassan Ali Ahmed
- Department of Bioinformatics and Computational Biology, Poznan University of Medical Sciences, 60-812 Poznan, Poland
- Doctoral School, Poznan University of Medical Sciences, 60-812 Poznan, Poland
| | - Mohamed Abouzid
- Doctoral School, Poznan University of Medical Sciences, 60-812 Poznan, Poland
- Department of Physical Pharmacy and Pharmacokinetics, Faculty of Pharmacy, Poznan University of Medical Sciences, Rokietnicka 3 St., 60-806 Poznan, Poland
| | - Elżbieta Kaczmarek
- Department of Bioinformatics and Computational Biology, Poznan University of Medical Sciences, 60-812 Poznan, Poland
| |
Collapse
|
23
|
Orsulic S, John J, Walts AE, Gertych A. Computational pathology in ovarian cancer. Front Oncol 2022; 12:924945. [PMID: 35965569 PMCID: PMC9372445 DOI: 10.3389/fonc.2022.924945] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2022] [Accepted: 06/27/2022] [Indexed: 11/30/2022] Open
Abstract
Histopathologic evaluations of tissue sections are key to diagnosing and managing ovarian cancer. Pathologists empirically assess and integrate visual information, such as cellular density, nuclear atypia, mitotic figures, architectural growth patterns, and higher-order patterns, to determine the tumor type and grade, which guides oncologists in selecting appropriate treatment options. Latent data embedded in pathology slides can be extracted using computational imaging. Computers can analyze digital slide images to simultaneously quantify thousands of features, some of which are visible with a manual microscope, such as nuclear size and shape, while others, such as entropy, eccentricity, and fractal dimensions, are quantitatively beyond the grasp of the human mind. Applications of artificial intelligence and machine learning tools to interpret digital image data provide new opportunities to explore and quantify the spatial organization of tissues, cells, and subcellular structures. In comparison to genomic, epigenomic, transcriptomic, and proteomic patterns, morphologic and spatial patterns are expected to be more informative as quantitative biomarkers of complex and dynamic tumor biology. As computational pathology is not limited to visual data, nuanced subvisual alterations that occur in the seemingly “normal” pre-cancer microenvironment could facilitate research in early cancer detection and prevention. Currently, efforts to maximize the utility of computational pathology are focused on integrating image data with other -omics platforms that lack spatial information, thereby providing a new way to relate the molecular, spatial, and microenvironmental characteristics of cancer. Despite a dire need for improvements in ovarian cancer prevention, early detection, and treatment, the ovarian cancer field has lagged behind other cancers in the application of computational pathology. The intent of this review is to encourage ovarian cancer research teams to apply existing and/or develop additional tools in computational pathology for ovarian cancer and actively contribute to advancing this important field.
Collapse
Affiliation(s)
- Sandra Orsulic
- Veterans Affairs Greater Los Angeles Healthcare System, Los Angeles, CA, United States
- Department of Obstetrics and Gynecology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, United States
- Jonsson Comprehensive Cancer Center, University of California Los Angeles, Los Angeles, CA, United States
- *Correspondence: Sandra Orsulic,
| | - Joshi John
- Veterans Affairs Greater Los Angeles Healthcare System, Los Angeles, CA, United States
- Department of Psychiatry, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, United States
| | - Ann E. Walts
- Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, United States
| | - Arkadiusz Gertych
- Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, United States
- Department of Surgery, Cedars-Sinai Medical Center, Los Angeles, CA, United States
- Faculty of Biomedical Engineering, Silesian University of Technology, Zabrze, Poland
| |
Collapse
|
24
|
Bidgoli AA, Rahnamayan S, Dehkharghanian T, Riasatian A, Kalra S, Zaveri M, Campbell CJ, Parwani A, Pantanowitz L, Tizhoosh H. Evolutionary deep feature selection for compact representation of gigapixel images in digital pathology. Artif Intell Med 2022; 132:102368. [DOI: 10.1016/j.artmed.2022.102368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2021] [Revised: 06/13/2022] [Accepted: 07/14/2022] [Indexed: 11/26/2022]
|
25
|
Software tools and platforms in Digital Pathology: a review for clinicians and computer scientists. J Pathol Inform 2022; 13:100103. [PMID: 36268075 PMCID: PMC9576980 DOI: 10.1016/j.jpi.2022.100103] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 05/12/2022] [Accepted: 05/17/2022] [Indexed: 11/20/2022] Open
Abstract
At the end of the twentieth century, a new technology was developed that allowed an entire tissue section to be scanned on an objective slide. Originally called virtual microscopy, this technology is now known as Whole Slide Imaging (WSI). WSI presents new challenges for reading, visualization, storage, and analysis. For this reason, several technologies have been developed to facilitate the handling of these images. In this paper, we analyze the most widely used technologies in the field of digital pathology, ranging from specialized libraries for the reading of these images to complete platforms that allow reading, visualization, and analysis. Our aim is to provide the reader, whether a pathologist or a computational scientist, with the knowledge to choose the technologies to use for new studies, development, or research.
Collapse
|
26
|
Automatic Recognition of Ragged Red Fibers in Muscle Biopsy from Patients with Mitochondrial Disorders. Healthcare (Basel) 2022; 10:healthcare10030574. [PMID: 35327052 PMCID: PMC8949467 DOI: 10.3390/healthcare10030574] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2022] [Revised: 03/14/2022] [Accepted: 03/17/2022] [Indexed: 11/16/2022] Open
Abstract
Mitochondrial dysfunction is considered to be a major cause of primary mitochondrial myopathy in children and adults, as reduced mitochondrial respiration and morphological changes such as ragged red fibers (RRFs) are observed in muscle biopsies. However, it is also possible to hypothesize the role of mitochondrial dysfunction in aging muscle or in secondary mitochondrial dysfunctions. The recognition of true histological patterns of mitochondrial myopathy can avoid unnecessary genetic investigations. The aim of our study was to develop and validate machine-learning methods for RRF detection in light microscopy images of skeletal muscle tissue. We used image sets of 489 color images captured from representative areas of Gomori’s trichrome-stained tissue retrieved from light microscopy images at a 20× magnification. We compared the performance of random forest, gradient boosting machine, and support vector machine classifiers. Our results suggested that the advent of scanning technologies, combined with the development of machine-learning models for image classification, make neuromuscular disorders’ automated diagnostic systems a concrete possibility.
Collapse
|
27
|
A comprehensive review of computer-aided whole-slide image analysis: from datasets to feature extraction, segmentation, classification and detection approaches. Artif Intell Rev 2022. [DOI: 10.1007/s10462-021-10121-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
|
28
|
Vizcarra JC, Burlingame EA, Hug CB, Goltsev Y, White BS, Tyson DR, Sokolov A. A community-based approach to image analysis of cells, tissues and tumors. Comput Med Imaging Graph 2022; 95:102013. [PMID: 34864359 PMCID: PMC8761177 DOI: 10.1016/j.compmedimag.2021.102013] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2021] [Revised: 11/09/2021] [Accepted: 11/09/2021] [Indexed: 01/03/2023]
Abstract
Emerging multiplexed imaging platforms provide an unprecedented view of an increasing number of molecular markers at subcellular resolution and the dynamic evolution of tumor cellular composition. As such, they are capable of elucidating cell-to-cell interactions within the tumor microenvironment that impact clinical outcome and therapeutic response. However, the rapid development of these platforms has far outpaced the computational methods for processing and analyzing the data they generate. While being technologically disparate, all imaging assays share many computational requirements for post-collection data processing. As such, our Image Analysis Working Group (IAWG), composed of researchers in the Cancer Systems Biology Consortium (CSBC) and the Physical Sciences - Oncology Network (PS-ON), convened a workshop on "Computational Challenges Shared by Diverse Imaging Platforms" to characterize these common issues and a follow-up hackathon to implement solutions for a selected subset of them. Here, we delineate these areas that reflect major axes of research within the field, including image registration, segmentation of cells and subcellular structures, and identification of cell types from their morphology. We further describe the logistical organization of these events, believing our lessons learned can aid others in uniting the imaging community around self-identified topics of mutual interest, in designing and implementing operational procedures to address those topics and in mitigating issues inherent in image analysis (e.g., sharing exemplar images of large datasets and disseminating baseline solutions to hackathon challenges through open-source code repositories).
Collapse
Affiliation(s)
- Juan Carlos Vizcarra
- Department of Biomedical Engineering, Georgia Institute of Technology & Emory University, Atlanta, GA, USA
| | - Erik A Burlingame
- Computational Biology Program, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR, USA
| | - Clemens B Hug
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Science, Boston, MA, USA
| | - Yury Goltsev
- Department of Microbiology & Immunology, Stanford University School of Medicine, Stanford, CA, USA
| | - Brian S White
- Computational Oncology, Sage Bionetworks, Seattle, WA, USA
| | - Darren R Tyson
- Department of Biochemistry, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Artem Sokolov
- Laboratory of Systems Pharmacology, Harvard Program in Therapeutic Science, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
29
|
Thennavan A, Beca F, Xia Y, Recio SG, Allison K, Collins LC, Tse GM, Chen YY, Schnitt SJ, Hoadley KA, Beck A, Perou CM. Molecular analysis of TCGA breast cancer histologic types. CELL GENOMICS 2021; 1. [PMID: 35465400 DOI: 10.1016/j.xgen.2021.100067] [Citation(s) in RCA: 33] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
Breast cancer is classified into multiple distinct histologic types, and many of the rarer types have limited characterization. Here, we extend The Cancer Genome Atlas Breast Cancer (TCGA-BRCA) dataset with additional histologic type annotations, in a total of 1063 breast cancers. We analyze this extended dataset to define transcriptomic and genomic profiles of six rare special histologic types: cribriform, micropapillary, mucinous, papillary, metaplastic, and invasive carcinoma with medullary pattern. We show the broader applicability of our constructed special histologic type gene signatures in the TCGA Pan-Cancer Atlas dataset with a predictive model that detects mucinous histologic type across cancers of other organ systems. Using a normal mammary cell differentiation score analysis, we order histologic types into a continuum from stem cell-like to luminal progenitor-like to mature luminal-like. Finally, we classify TCGA-BRCA into 12 consensus groups based on integrated genomic and histological features. We present a rich openly accessible resource of histologic and genomic characterization of TCGA-BRCA to enable studies of the range of breast cancers.
Collapse
Affiliation(s)
- Aatish Thennavan
- Oral and Craniofacial Biomedicine Program, School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.,Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Francisco Beca
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA
| | - Youli Xia
- Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.,Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Susana Garcia Recio
- Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.,Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA
| | - Kimberly Allison
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA
| | - Laura C Collins
- Department of Pathology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, MA, USA
| | - Gary M Tse
- Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong
| | - Yunn-Yi Chen
- Department of Pathology and Laboratory Medicine, University of California, San Francisco, CA, 94143, USA
| | - Stuart J Schnitt
- Department of Pathology, Brigham and Women's Hospital and Harvard Medical School; Breast Oncology Program, Dana-Farber/Brigham and Women's Cancer Center, Boston, MA 02115, USA
| | - Katherine A Hoadley
- Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.,Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA
| | | | - Charles M Perou
- Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.,Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.,Department of Pathology & Laboratory Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| |
Collapse
|
30
|
Gondal MN, Chaudhary SU. Navigating Multi-Scale Cancer Systems Biology Towards Model-Driven Clinical Oncology and Its Applications in Personalized Therapeutics. Front Oncol 2021; 11:712505. [PMID: 34900668 PMCID: PMC8652070 DOI: 10.3389/fonc.2021.712505] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2021] [Accepted: 10/26/2021] [Indexed: 12/19/2022] Open
Abstract
Rapid advancements in high-throughput omics technologies and experimental protocols have led to the generation of vast amounts of scale-specific biomolecular data on cancer that now populates several online databases and resources. Cancer systems biology models built using this data have the potential to provide specific insights into complex multifactorial aberrations underpinning tumor initiation, development, and metastasis. Furthermore, the annotation of these single- and multi-scale models with patient data can additionally assist in designing personalized therapeutic interventions as well as aid in clinical decision-making. Here, we have systematically reviewed the emergence and evolution of (i) repositories with scale-specific and multi-scale biomolecular cancer data, (ii) systems biology models developed using this data, (iii) associated simulation software for the development of personalized cancer therapeutics, and (iv) translational attempts to pipeline multi-scale panomics data for data-driven in silico clinical oncology. The review concludes that the absence of a generic, zero-code, panomics-based multi-scale modeling pipeline and associated software framework, impedes the development and seamless deployment of personalized in silico multi-scale models in clinical settings.
Collapse
Affiliation(s)
- Mahnoor Naseer Gondal
- Biomedical Informatics Research Laboratory, Department of Biology, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, United States
| | - Safee Ullah Chaudhary
- Biomedical Informatics Research Laboratory, Department of Biology, Syed Babar Ali School of Science and Engineering, Lahore University of Management Sciences, Lahore, Pakistan
| |
Collapse
|
31
|
Huang J, Tseng LH, Parini V, Lokhandwala PM, Pallavajjala A, Rodriguez E, Xian R, Chen L, Gocke CD, Eshleman JR, Lin MT. IDH1 and IDH2 Mutations in Colorectal Cancers. Am J Clin Pathol 2021; 156:777-786. [PMID: 33929516 DOI: 10.1093/ajcp/aqab023] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
OBJECTIVES To elucidate clinicopathologic and molecular characteristics of IDH1 and IDH2 (IDH1/2) mutations in colorectal cancers (CRCs). METHODS We evaluated IDH1/2 mutations in 1,623 CRCs using a next-generation sequencing assay. RESULTS IDH1/2 mutations, predominantly IDH1 p.R132C, were detected in 15 (0.9%) CRCs and in 5 (3.0%) of 167 BRAF p.V600E-mutated CRCs. Three IDH1/2-mutated CRCs were associated with inflammatory bowel disease. They were significantly associated with old age, mucinous or signet ring cell adenocarcinoma, and high-grade histomorphology. Concordance of variant allele frequency between IDH1/2 mutants and other trunk drivers in CRCs and presence of IDH1/2 mutation in the adenoma and early adenocarcinoma indicated IDH1/2 mutations could be trunk drivers suitable for targeted therapy. CONCLUSIONS IDH1/2 mutations in CRCs were uncommon but enriched in BRAF p.V600E-mutated CRCs and perhaps colitis-associated CRCs. Further studies on IDH1/2-mutated CRCs are needed to clarify their clinicopathologic features and implications for targeted therapy.
Collapse
Affiliation(s)
- Jialing Huang
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Department of Pathology, Thomas Jefferson University, Philadelphia, PA, USA
| | - Li-Hui Tseng
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Graduate Institute of Medical Genomics and Proteomics, National Taiwan University, Taipei, Taiwan
| | - Vamsi Parini
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Parvez M Lokhandwala
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Aparna Pallavajjala
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Erika Rodriguez
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Rena Xian
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Liam Chen
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Christopher D Gocke
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - James R Eshleman
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Ming-Tseh Lin
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
32
|
Corvo A, Caballero HSG, Westenberg MA, van Driel MA, van Wijk JJ. Visual Analytics for Hypothesis-Driven Exploration in Computational Pathology. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2021; 27:3851-3866. [PMID: 32340951 DOI: 10.1109/tvcg.2020.2990336] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Recent advances in computational and algorithmic power are evolving the field of medical imaging rapidly. In cancer research, many new directions are sought to characterize patients with additional imaging features derived from radiology and pathology images. The emerging field of Computational Pathology targets the high-throughput extraction and analysis of the spatial distribution of cells from digital histopathology images. The associated morphological and architectural features allow researchers to quantify and characterize new imaging biomarkers for cancer diagnosis, prognosis, and treatment decisions. However, while the image feature space grows, exploration and analysis become more difficult and ineffective. There is a need for dedicated interfaces for interactive data manipulation and visual analysis of computational pathology and clinical data. For this purpose, we present IIComPath, a visual analytics approach that enables clinical researchers to formulate hypotheses and create computational pathology pipelines involving cohort construction, spatial analysis of image-derived features, and cohort analysis. We demonstrate our approach through use cases that investigate the prognostic value of current diagnostic features and new computational pathology biomarkers.
Collapse
|
33
|
Su K, Yu Q, Shen R, Sun SY, Moreno CS, Li X, Qin ZS. Pan-cancer analysis of pathway-based gene expression pattern at the individual level reveals biomarkers of clinical prognosis. CELL REPORTS METHODS 2021; 1:100050. [PMID: 34671755 PMCID: PMC8525796 DOI: 10.1016/j.crmeth.2021.100050] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Revised: 05/07/2021] [Accepted: 06/16/2021] [Indexed: 02/08/2023]
Abstract
Identifying biomarkers to predict the clinical outcomes of individual patients is a fundamental problem in clinical oncology. Multiple single-gene biomarkers have already been identified and used in clinics. However, multiple oncogenes or tumor-suppressor genes are involved during the process of tumorigenesis. Additionally, the efficacy of single-gene biomarkers is limited by the extensively variable expression levels measured by high-throughput assays. In this study, we hypothesize that in individual tumor samples, the disruption of transcription homeostasis in key pathways or gene sets plays an important role in tumorigenesis and has profound implications for the patient's clinical outcome. We devised a computational method named iPath to identify, at the individual-sample level, which pathways or gene sets significantly deviate from their norms. We conducted a pan-cancer analysis and demonstrated that iPath is capable of identifying highly predictive biomarkers for clinical outcomes, including overall survival, tumor subtypes, and tumor-stage classifications.
Collapse
Affiliation(s)
- Kenong Su
- Department of Computer Science, Emory University, Atlanta, GA 30322, USA
| | - Qi Yu
- Department of Biostatistics and Bioinformatics, Emory University, Atlanta, GA 30322, USA
| | - Ronglai Shen
- Department of Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY 10017, USA
| | - Shi-Yong Sun
- Department of Hematology & Medical Oncology, Emory University School of Medicine, Atlanta, GA 30322, USA
| | - Carlos S. Moreno
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA 30322, USA
| | - Xiaoxian Li
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA 30322, USA
| | - Zhaohui S. Qin
- Department of Computer Science, Emory University, Atlanta, GA 30322, USA
- Department of Biostatistics and Bioinformatics, Emory University, Atlanta, GA 30322, USA
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA 30322, USA
| |
Collapse
|
34
|
Howard FM, Dolezal J, Kochanny S, Schulte J, Chen H, Heij L, Huo D, Nanda R, Olopade OI, Kather JN, Cipriani N, Grossman RL, Pearson AT. The impact of site-specific digital histology signatures on deep learning model accuracy and bias. Nat Commun 2021; 12:4423. [PMID: 34285218 PMCID: PMC8292530 DOI: 10.1038/s41467-021-24698-1] [Citation(s) in RCA: 88] [Impact Index Per Article: 29.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2020] [Accepted: 07/01/2021] [Indexed: 12/20/2022] Open
Abstract
The Cancer Genome Atlas (TCGA) is one of the largest biorepositories of digital histology. Deep learning (DL) models have been trained on TCGA to predict numerous features directly from histology, including survival, gene expression patterns, and driver mutations. However, we demonstrate that these features vary substantially across tissue submitting sites in TCGA for over 3,000 patients with six cancer subtypes. Additionally, we show that histologic image differences between submitting sites can easily be identified with DL. Site detection remains possible despite commonly used color normalization and augmentation methods, and we quantify the image characteristics constituting this site-specific digital histology signature. We demonstrate that these site-specific signatures lead to biased accuracy for prediction of features including survival, genomic mutations, and tumor stage. Furthermore, ethnicity can also be inferred from site-specific signatures, which must be accounted for to ensure equitable application of DL. These site-specific signatures can lead to overoptimistic estimates of model performance, and we propose a quadratic programming method that abrogates this bias by ensuring models are not trained and validated on samples from the same site.
Collapse
Affiliation(s)
- Frederick M Howard
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - James Dolezal
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - Sara Kochanny
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - Jefree Schulte
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | - Heather Chen
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | - Lara Heij
- Department of Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany
- Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany
| | - Dezheng Huo
- Department of Public Health Sciences, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Rita Nanda
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Olufunmilayo I Olopade
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Jakob N Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
- Medical Oncology, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
| | - Nicole Cipriani
- Department of Pathology, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Robert L Grossman
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA.
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA.
| | - Alexander T Pearson
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA.
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA.
| |
Collapse
|
35
|
Riasatian A, Babaie M, Maleki D, Kalra S, Valipour M, Hemati S, Zaveri M, Safarpoor A, Shafiei S, Afshari M, Rasoolijaberi M, Sikaroudi M, Adnan M, Shah S, Choi C, Damaskinos S, Campbell CJ, Diamandis P, Pantanowitz L, Kashani H, Ghodsi A, Tizhoosh HR. Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides. Med Image Anal 2021; 70:102032. [PMID: 33773296 DOI: 10.1016/j.media.2021.102032] [Citation(s) in RCA: 49] [Impact Index Per Article: 16.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2019] [Revised: 01/21/2021] [Accepted: 03/02/2021] [Indexed: 02/07/2023]
Abstract
Feature vectors provided by pre-trained deep artificial neural networks have become a dominant source for image representation in recent literature. Their contribution to the performance of image analysis can be improved through fine-tuning. As an ultimate solution, one might even train a deep network from scratch with the domain-relevant images, a highly desirable option which is generally impeded in pathology by lack of labeled images and the computational expense. In this study, we propose a new network, namely KimiaNet, that employs the topology of the DenseNet with four dense blocks, fine-tuned and trained with histopathology images in different configurations. We used more than 240,000 image patches with 1000×1000 pixels acquired at 20× magnification through our proposed "high-cellularity mosaic" approach to enable the usage of weak labels of 7126 whole slide images of formalin-fixed paraffin-embedded human pathology samples publicly available through The Cancer Genome Atlas (TCGA) repository. We tested KimiaNet using three public datasets, namely TCGA, endometrial cancer images, and colorectal cancer images by evaluating the performance of search and classification when corresponding features of different networks are used for image representation. As well, we designed and trained multiple convolutional batch-normalized ReLU (CBR) networks. The results show that KimiaNet provides superior results compared to the original DenseNet and smaller CBR networks when used as feature extractor to represent histopathology images.
Collapse
Affiliation(s)
- Abtin Riasatian
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Morteza Babaie
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada.
| | - Danial Maleki
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Shivam Kalra
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Mojtaba Valipour
- School of Computer Science, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Sobhan Hemati
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Manit Zaveri
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Amir Safarpoor
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Sobhan Shafiei
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Mehdi Afshari
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Maral Rasoolijaberi
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Milad Sikaroudi
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Mohd Adnan
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Sultaan Shah
- Huron Digital Pathology, 1620 King Street North, St. Jacobs, ON, Canada
| | - Charles Choi
- Huron Digital Pathology, 1620 King Street North, St. Jacobs, ON, Canada
| | - Savvas Damaskinos
- Huron Digital Pathology, 1620 King Street North, St. Jacobs, ON, Canada
| | - Clinton Jv Campbell
- Department of Pathology and Molecular Medicine, McMaster University, Hamilton, Canada
| | - Phedias Diamandis
- Laboratory Medicine and Pathobiology, University of Toronto, ON, Canada
| | - Liron Pantanowitz
- Department of Pathology, University of Pittsburgh Medical Center, PA, USA
| | - Hany Kashani
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada
| | - Ali Ghodsi
- School of Computer Science, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada; Vector Institute, 661 University Ave Suite 710, Toronto, ON, Canada
| | - H R Tizhoosh
- Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada; Vector Institute, 661 University Ave Suite 710, Toronto, ON, Canada.
| |
Collapse
|
36
|
Farris AB, Vizcarra J, Amgad M, Cooper LAD, Gutman D, Hogan J. Artificial intelligence and algorithmic computational pathology: an introduction with renal allograft examples. Histopathology 2021; 78:791-804. [PMID: 33211332 DOI: 10.1111/his.14304] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
Whole slide imaging, which is an important technique in the field of digital pathology, has recently been the subject of increased interest and avenues for utilisation, and with more widespread whole slide image (WSI) utilisation, there will also be increased interest in and implementation of image analysis (IA) techniques. IA includes artificial intelligence (AI) and targeted or hypothesis-driven algorithms. In the overall pathology field, the number of citations related to these topics has increased in recent years. Renal pathology is one anatomical pathology subspecialty that has utilised WSIs and IA algorithms; it can be argued that renal transplant pathology could be particularly suited for whole slide imaging and IA, as renal transplant pathology is frequently classified by use of the semiquantitative Banff classification of renal allograft pathology. Hypothesis-driven/targeted algorithms have been used in the past for the assessment of a variety of features in the kidney (e.g. interstitial fibrosis, tubular atrophy, inflammation); in recent years, the amount of research has particularly increased in the area of AI/machine learning for the identification of glomeruli, for histological segmentation, and for other applications. Deep learning is the form of machine learning that is most often used for such AI approaches to the 'big data' of pathology WSIs, and deep learning methods such as artificial neural networks (ANNs)/convolutional neural networks (CNNs) are utilised. Unsupervised and supervised AI algorithms can be employed to accomplish image or semantic classification. In this review, AI and other IA algorithms applied to WSIs are discussed, and examples from renal pathology are covered, with an emphasis on renal transplant pathology.
Collapse
Affiliation(s)
- Alton B Farris
- Department of Pathology and Laboratory Medicine, Atlanta, GA, USA
| | - Juan Vizcarra
- Department of Bioinformatics, Emory University, Atlanta, GA, USA
| | - Mohamed Amgad
- Department of Pathology and Center for Computational Imaging and Signal Analytics, Northwestern University, Chicago, IL, USA
| | - Lee A D Cooper
- Department of Pathology and Center for Computational Imaging and Signal Analytics, Northwestern University, Chicago, IL, USA
| | - David Gutman
- Department of Bioinformatics, Emory University, Atlanta, GA, USA
| | - Julien Hogan
- Department of Surgery, Emory University, Atlanta, GA, USA
| |
Collapse
|
37
|
Zhou C, Jin Y, Chen Y, Huang S, Huang R, Wang Y, Zhao Y, Chen Y, Guo L, Liao J. Histopathology classification and localization of colorectal cancer using global labels by weakly supervised deep learning. Comput Med Imaging Graph 2021; 88:101861. [PMID: 33497891 DOI: 10.1016/j.compmedimag.2021.101861] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2020] [Revised: 12/22/2020] [Accepted: 12/28/2020] [Indexed: 01/19/2023]
Abstract
Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide. In coping with it, histopathology image analysis (HIA) provides key information for clinical diagnosis of CRC. Nowadays, the deep learning methods are widely used in improving cancer classification and localization of tumor-regions in HIA. However, these efforts are both time-consuming and labor-intensive due to the manual annotation of tumor-regions in the whole slide images (WSIs). Furthermore, classical deep learning methods to analyze thousands of patches extracted from WSIs may cause loss of integrated information of image. Herein, a novel method was developed, which used only global labels to achieve WSI classification and localization of carcinoma by combining features from different magnifications of WSIs. The model was trained and tested using 1346 colorectal cancer WSIs from the Cancer Genome Atlas (TCGA). Our method classified colorectal cancer with an accuracy of 94.6 %, which slightly outperforms most of the existing methods. Its cancerous-location probability maps were in good agreement with annotations from three individual expert pathologists. Independent tests on 50 newly-collected colorectal cancer WSIs from hospitals produced 92.0 % accuracy and cancerous-location probability maps were in good agreement with the three pathologists. The results thereby demonstrated that the method sufficiently achieved WSI classification and localization utilizing only global labels. This weakly supervised deep learning method is effective in time and cost, as it delivered a better performance in comparison with the state-of-the-art methods.
Collapse
Affiliation(s)
- Changjiang Zhou
- School of Science, China Pharmaceutical University, Nanjing, China
| | - Yi Jin
- School of Science, China Pharmaceutical University, Nanjing, China
| | - Yuzong Chen
- School of Science, China Pharmaceutical University, Nanjing, China; Bioinformatics and Drug Design Group, Department of Pharmacy, National University of Singapore, Singapore, Singapore
| | - Shan Huang
- Department of Pathology, The First Affiliated Hospital of Soochow University, Soochow, China
| | - Rengpeng Huang
- Department of Pathology, The First Affiliated Hospital of Soochow University, Soochow, China
| | - Yuhong Wang
- Department of Pathology, The First Affiliated Hospital of Soochow University, Soochow, China
| | - Youcai Zhao
- Department of Pathology, Nanjing First Hospital, Nanjing, China
| | - Yao Chen
- School of Science, China Pharmaceutical University, Nanjing, China
| | - Lingchuan Guo
- Department of Pathology, The First Affiliated Hospital of Soochow University, Soochow, China.
| | - Jun Liao
- School of Science, China Pharmaceutical University, Nanjing, China.
| |
Collapse
|
38
|
Kalra S, Tizhoosh HR, Choi C, Shah S, Diamandis P, Campbell CJV, Pantanowitz L. Yottixel - An Image Search Engine for Large Archives of Histopathology Whole Slide Images. Med Image Anal 2020; 65:101757. [PMID: 32623275 DOI: 10.1016/j.media.2020.101757] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2019] [Revised: 06/11/2020] [Accepted: 06/16/2020] [Indexed: 01/21/2023]
Abstract
With the emergence of digital pathology, searching for similar images in large archives has gained considerable attention. Image retrieval can provide pathologists with unprecedented access to the evidence embodied in already diagnosed and treated cases from the past. This paper proposes a search engine specialized for digital pathology, called Yottixel, a portmanteau for "one yotta pixel," alluding to the big-data nature of histopathology images. The most impressive characteristic of Yottixel is its ability to represent whole slide images (WSIs) in a compact manner. Yottixel can perform millions of searches in real-time with a high search accuracy and low storage profile. Yottixel uses an intelligent indexing algorithm capable of representing WSIs with a mosaic of patches which are then converted into barcodes, called "Bunch of Barcodes" (BoB), the most prominent performance enabler of Yottixel. The performance of the prototype platform is qualitatively tested using 300 WSIs from the University of Pittsburgh Medical Center (UPMC) and 2,020 WSIs from The Cancer Genome Atlas Program (TCGA) provided by the National Cancer Institute. Both datasets amount to more than 4,000,000 patches of 1000 × 1000 pixels. We report three sets of experiments that show that Yottixel can accurately retrieve organs and malignancies, and its semantic ordering shows good agreement with the subjective evaluation of human observers.
Collapse
Affiliation(s)
- Shivam Kalra
- Kimia Lab, University of Waterloo, Ontario, Canada; Huron Digital Pathology, St. Jacobs, ON, Canada
| | - H R Tizhoosh
- Kimia Lab, University of Waterloo, Ontario, Canada; Vector Institute, MaRS Centre, Toronto, Canada.
| | | | | | | | | | - Liron Pantanowitz
- University of Pittsburgh Medical Center, Department of Pathology, PA, USA
| |
Collapse
|
39
|
Rodriguez EF, De Marchi F, Lokhandwala PM, Belchis D, Xian R, Gocke CD, Eshleman JR, Illei P, Li MT. IDH1 and IDH2 mutations in lung adenocarcinomas: Evidences of subclonal evolution. Cancer Med 2020; 9:4386-4394. [PMID: 32333643 PMCID: PMC7300411 DOI: 10.1002/cam4.3058] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2019] [Revised: 03/24/2020] [Accepted: 03/30/2020] [Indexed: 12/19/2022] Open
Abstract
Background Selective IDH1 and IDH2 inhibitors have been approved for targeted therapy of acute myeloid leukemia. Clinical trials for solid tumors with IDH1 and IDH2 (IDH1/2) mutations are ongoing. Reports of IDH1/2‐mutated non–small cell lung cancers (NSCLCs), however, are limited. Methods We evaluated IDH1/2 mutations in 1,924 NSCLC specimens (92% adenocarcinoma) using a next‐generation sequencing assay. Results Retrospective quality assessments identified false detection of IDH1 c.395G>A (p.R132H) resulting from cytosine deamination (C:G→T:A) artifact in one specimen. IDH1/2 mutations were detected in 9 (0.5%) adenocarcinomas taken by fine‐needle aspiration (n = 3), thoracentesis (n = 2) or core biopsy (n = 4). All nine adenocarcinomas showed high‐grade features. Extensive clear cell change, however, was not observed. High expression (50% or greater) of PD‐L1 was observed in two of five specimens examined. IDH1/2 mutations were associated with old age, smoking history, and coexisting KRAS mutation. Lower than expected variant allele frequency of IDH1/2 mutants and coexistence of IDH1/2 mutations with known trunk drivers in the BRAF, EGFR, and KRAS genes suggest they could be branching drivers leading to subclonal evolution in lung adenocarcinomas. Multiregional analysis of an adenocarcinoma harboring two IDH2 mutations revealed parallel evolution originating from a KRAS‐mutated lineage, further supporting subclonal evolution promoted by IDH1/2 mutations. Conclusions IDH1/2 mutations in NSCLCs are uncommon. They occur in adenocarcinomas with high‐grade features and may be branching drivers leading to subclonal evolution. Accumulation of more IDH1/2‐mutated NSCLCs is needed to clarify their clinicopathological characteristics and implications for targeted therapy.
Collapse
Affiliation(s)
- Erika F Rodriguez
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Federico De Marchi
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Parvez M Lokhandwala
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Deborah Belchis
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Rena Xian
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.,Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Christopher D Gocke
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.,Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - James R Eshleman
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.,Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Peter Illei
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Ming-Tseh Li
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| |
Collapse
|
40
|
Zhang Z, Li H, Jiang S, Li R, Li W, Chen H, Bo X. A survey and evaluation of Web-based tools/databases for variant analysis of TCGA data. Brief Bioinform 2020; 20:1524-1541. [PMID: 29617727 PMCID: PMC6781580 DOI: 10.1093/bib/bby023] [Citation(s) in RCA: 35] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2017] [Revised: 02/22/2018] [Indexed: 12/28/2022] Open
Abstract
The Cancer Genome Atlas (TCGA) is a publicly funded project that aims to catalog and discover major cancer-causing genomic alterations with the goal of creating a comprehensive ‘atlas’ of cancer genomic profiles. The availability of this genome-wide information provides an unprecedented opportunity to expand our knowledge of tumourigenesis. Computational analytics and mining are frequently used as effective tools for exploring this byzantine series of biological and biomedical data. However, some of the more advanced computational tools are often difficult to understand or use, thereby limiting their application by scientists who do not have a strong computational background. Hence, it is of great importance to build user-friendly interfaces that allow both computational scientists and life scientists without a computational background to gain greater biological and medical insights. To that end, this survey was designed to systematically present available Web-based tools and facilitate the use TCGA data for cancer research.
Collapse
Affiliation(s)
- Zhuo Zhang
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Hao Li
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Shuai Jiang
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Ruijiang Li
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Wanying Li
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Hebing Chen
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| | - Xiaochen Bo
- Beijing Institute of Radiation Medicine, Beijing 100850, China
| |
Collapse
|
41
|
Jiang Y, Yang M, Wang S, Li X, Sun Y. Emerging role of deep learning-based artificial intelligence in tumor pathology. Cancer Commun (Lond) 2020; 40:154-166. [PMID: 32277744 PMCID: PMC7170661 DOI: 10.1002/cac2.12012] [Citation(s) in RCA: 150] [Impact Index Per Article: 37.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2020] [Accepted: 02/06/2020] [Indexed: 12/11/2022] Open
Abstract
The development of digital pathology and progression of state-of-the-art algorithms for computer vision have led to increasing interest in the use of artificial intelligence (AI), especially deep learning (DL)-based AI, in tumor pathology. The DL-based algorithms have been developed to conduct all kinds of work involved in tumor pathology, including tumor diagnosis, subtyping, grading, staging, and prognostic prediction, as well as the identification of pathological features, biomarkers and genetic changes. The applications of AI in pathology not only contribute to improve diagnostic accuracy and objectivity but also reduce the workload of pathologists and subsequently enable them to spend additional time on high-level decision-making tasks. In addition, AI is useful for pathologists to meet the requirements of precision oncology. However, there are still some challenges relating to the implementation of AI, including the issues of algorithm validation and interpretability, computing systems, the unbelieving attitude of pathologists, clinicians and patients, as well as regulators and reimbursements. Herein, we present an overview on how AI-based approaches could be integrated into the workflow of pathologists and discuss the challenges and perspectives of the implementation of AI in tumor pathology.
Collapse
Affiliation(s)
- Yahui Jiang
- Department of PathologyKey Laboratory of Cancer Prevention and TherapyTianjin's Clinical Research Center for CancerNational Clinical Research Center for CancerTianjin Cancer Institute and HospitalTianjin Medical UniversityTianjin300060P. R. China
| | - Meng Yang
- Department Epidemiology and BiostatisticsKey Laboratory of Cancer Prevention and TherapyTianjin's Clinical Research Center for CancerNational Clinical Research Center for CancerTianjin Cancer Institute and HospitalTianjin Medical UniversityTianjin300060P.R. China
| | - Shuhao Wang
- Institute for Interdisciplinary Information SciencesTsinghua UniversityBeijing100084P. R. China
| | - Xiangchun Li
- Department Epidemiology and BiostatisticsKey Laboratory of Cancer Prevention and TherapyTianjin's Clinical Research Center for CancerNational Clinical Research Center for CancerTianjin Cancer Institute and HospitalTianjin Medical UniversityTianjin300060P.R. China
| | - Yan Sun
- Department of PathologyKey Laboratory of Cancer Prevention and TherapyTianjin's Clinical Research Center for CancerNational Clinical Research Center for CancerTianjin Cancer Institute and HospitalTianjin Medical UniversityTianjin300060P. R. China
| |
Collapse
|
42
|
Herrera-Merchan A, Cuadros M, Rodriguez MI, Rodriguez S, Torres R, Estecio M, Coira IF, Loidi C, Saiz M, Carmona-Saez P, Medina PP. The value of lncRNA FENDRR and FOXF1 as a prognostic factor for survival of lung adenocarcinoma. Oncotarget 2020; 11:1172-1185. [PMID: 32284793 PMCID: PMC7138163] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2017] [Accepted: 10/02/2017] [Indexed: 11/25/2022] Open
Abstract
It is increasingly evident that non-coding RNAs play a significant role in tumour development. However, we still have a limited knowledge of the clinical significance of long non-coding RNAs (lncRNAs) in lung cancer. The FENDRR is a long coding RNA (also named FOXF1-AS1) located in the vicinity of the protein-coding gene FOXF1 at 16q24.1 chromosomal region. The present study aimed to define the clinic pathological significance of the long-non-coding RNA FENDRR in lung adenocarcinomas. FENDRR expression measured by quantitative PCR was found significantly downregulated (p<0.001) in lung adenocarcinoma samples in comparison with their normal adjacent tissues (n=70). RNA in situ hybridization (RNA-FISH) corroborated independently the down-regulation of FENDRR. Interestingly, the expression of FENDRR correlated positively (p<0.001) with the expression of its protein-coding neighbor gene FOXF1. Additionally, FOXF1 expression was also found downregulated in adenocarcinomas compared to normal samples (p<0.001) and its expression was significantly correlated with overall survival alone (p=0.003) or in combination with FENDRR expression (p=0.01). In conclusion, our data support that FENDRR and FOXF1 expression is decreased in lung adenocarcinoma and should be considered as new potential diagnostic/prognosis biomarkers.
Collapse
Affiliation(s)
- Antonio Herrera-Merchan
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
- Department of Biochemistry and Molecular Biology I, University of Granada, Granada, Spain
| | - Marta Cuadros
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
- Department of Biochemistry and Molecular Biology III and Immunology, University of Granada, Granada, Spain
| | - Maria Isabel Rodriguez
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
- Department of Biochemistry and Molecular Biology I, University of Granada, Granada, Spain
| | - Sandra Rodriguez
- Molecular Cytogenetics Group, Human Cancer Genetics Program, Spanish National Cancer Research Centre-CNIO, Madrid, Spain
| | - Raul Torres
- Molecular Cytogenetics Group, Human Cancer Genetics Program, Spanish National Cancer Research Centre-CNIO, Madrid, Spain
| | - Marcos Estecio
- Department of Epigenetics and Molecular Carcinogenesis, UT MD Anderson Cancer Center, Houston, TX, USA
| | - Isabel F. Coira
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
- Department of Biochemistry and Molecular Biology I, University of Granada, Granada, Spain
| | - Claudia Loidi
- Pathological Anatomy, University Hospital Cruces, University of Pais Vasco, Spain
| | - Monica Saiz
- Pathological Anatomy, University Hospital Cruces, University of Pais Vasco, Spain
| | - Pedro Carmona-Saez
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
| | - Pedro P. Medina
- Centre for Genomics and Oncological Research, PTS Granada, Centro Pfizer - Universidad de Granada - Junta de Andalucía de Genómica e Investigación Oncológica (GENYO), Granada, Spain
- Department of Biochemistry and Molecular Biology I, University of Granada, Granada, Spain
| |
Collapse
|
43
|
Barsoum I, Tawedrous E, Faragalla H, Yousef GM. Histo-genomics: digital pathology at the forefront of precision medicine. ACTA ACUST UNITED AC 2020; 6:203-212. [PMID: 30827078 DOI: 10.1515/dx-2018-0064] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2018] [Accepted: 09/28/2018] [Indexed: 12/26/2022]
Abstract
The toughest challenge OMICs face is that they provide extremely high molecular resolution but poor spatial information. Understanding the cellular/histological context of the overwhelming genetic data is critical for a full understanding of the clinical behavior of a malignant tumor. Digital pathology can add an extra layer of information to help visualize in a spatial and microenvironmental context the molecular information of cancer. Thus, histo-genomics provide a unique chance for data integration. In the era of a precision medicine, a four-dimensional (4D) (temporal/spatial) analysis of cancer aided by digital pathology can be a critical step to understand the evolution/progression of different cancers and consequently tailor individual treatment plans. For instance, the integration of molecular biomarkers expression into a three-dimensional (3D) image of a digitally scanned tumor can offer a better understanding of its subtype, behavior, host immune response and prognosis. Using advanced digital image analysis, a larger spectrum of parameters can be analyzed as potential predictors of clinical behavior. Correlation between morphological features and host immune response can be also performed with therapeutic implications. Radio-histomics, or the interface of radiological images and histology is another emerging exciting field which encompasses the integration of radiological imaging with digital pathological images, genomics, and clinical data to portray a more holistic approach to understating and treating disease. These advances in digital slide scanning are not without technical challenges, which will be addressed carefully in this review with quick peek at its future.
Collapse
Affiliation(s)
- Ivraym Barsoum
- Department of Pathology and Molecular Medicine, Faculty of Health Sciences, Queen's University, Kingston, Ontario, Canada
| | - Eriny Tawedrous
- Department of Laboratory Medicine, and the Keenan Research Centre for Biomedical Science at the Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, Canada
| | - Hala Faragalla
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada
| | - George M Yousef
- Department of Laboratory Medicine, and the Keenan Research Centre for Biomedical Science at the Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, Canada.,Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada.,Department of Pediatric Laboratory Medicine, The Hospital for Sick Children, 555 University Avenue, Toronto, ON M5G 1X8, Canada
| |
Collapse
|
44
|
Ning Z, Pan W, Chen Y, Xiao Q, Zhang X, Luo J, Wang J, Zhang Y. Integrative analysis of cross-modal features for the prognosis prediction of clear cell renal cell carcinoma. Bioinformatics 2020; 36:2888-2895. [DOI: 10.1093/bioinformatics/btaa056] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2019] [Revised: 01/14/2020] [Accepted: 01/20/2020] [Indexed: 12/19/2022] Open
Abstract
Abstract
Motivation
As a highly heterogeneous disease, clear cell renal cell carcinoma (ccRCC) has quite variable clinical behaviors. The prognostic biomarkers play a crucial role in stratifying patients suffering from ccRCC to avoid over- and under-treatment. Researches based on hand-crafted features and single-modal data have been widely conducted to predict the prognosis of ccRCC. However, these experience-dependent methods, neglecting the synergy among multimodal data, have limited capacity to perform accurate prediction. Inspired by complementary information among multimodal data and the successful application of convolutional neural networks (CNNs) in medical image analysis, a novel framework was proposed to improve prediction performance.
Results
We proposed a cross-modal feature-based integrative framework, in which deep features extracted from computed tomography/histopathological images by using CNNs were combined with eigengenes generated from functional genomic data, to construct a prognostic model for ccRCC. Results showed that our proposed model can stratify high- and low-risk subgroups with significant difference (P-value < 0.05) and outperform the predictive performance of those models based on single-modality features in the independent testing cohort [C-index, 0.808 (0.728–0.888)]. In addition, we also explored the relationship between deep image features and eigengenes, and make an attempt to explain deep image features from the view of genomic data. Notably, the integrative framework is available to the task of prognosis prediction of other cancer with matched multimodal data.
Availability and implementation
https://github.com/zhang-de-lab/zhang-lab? from=singlemessage
Supplementary information
Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Zhenyuan Ning
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| | - Weihao Pan
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| | - Yuting Chen
- Department of Radiotherapy Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong 510515, China
| | - Qing Xiao
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| | - Xinsen Zhang
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| | - Jiaxiu Luo
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| | - Jian Wang
- School of Biomedical Engineering
- Department of Radiotherapy Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong 510515, China
| | - Yu Zhang
- School of Biomedical Engineering
- Guangdong Provincial Key Laboratory of Medical Image Processing
| |
Collapse
|
45
|
Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A. Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nat Rev Clin Oncol 2019; 16:703-715. [PMID: 31399699 PMCID: PMC6880861 DOI: 10.1038/s41571-019-0252-y] [Citation(s) in RCA: 642] [Impact Index Per Article: 128.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/04/2019] [Indexed: 02/06/2023]
Abstract
In the past decade, advances in precision oncology have resulted in an increased demand for predictive assays that enable the selection and stratification of patients for treatment. The enormous divergence of signalling and transcriptional networks mediating the crosstalk between cancer, stromal and immune cells complicates the development of functionally relevant biomarkers based on a single gene or protein. However, the result of these complex processes can be uniquely captured in the morphometric features of stained tissue specimens. The possibility of digitizing whole-slide images of tissue has led to the advent of artificial intelligence (AI) and machine learning tools in digital pathology, which enable mining of subvisual morphometric phenotypes and might, ultimately, improve patient management. In this Perspective, we critically evaluate various AI-based computational approaches for digital pathology, focusing on deep neural networks and 'hand-crafted' feature-based methodologies. We aim to provide a broad framework for incorporating AI and machine learning tools into clinical oncology, with an emphasis on biomarker development. We discuss some of the challenges relating to the use of AI, including the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies. Finally, we present potential future opportunities for precision oncology.
Collapse
Affiliation(s)
- Kaustav Bera
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Kurt A Schalper
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA
| | - David L Rimm
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA
| | - Vamsidhar Velcheti
- Thoracic Medical Oncology, Perlmutter Cancer Center, New York University, New York, NY, USA
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
- Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, OH, USA.
| |
Collapse
|
46
|
Tian K, Rubadue CA, Lin DI, Veta M, Pyle ME, Irshad H, Heng YJ. Automated clear cell renal carcinoma grade classification with prognostic significance. PLoS One 2019; 14:e0222641. [PMID: 31581201 PMCID: PMC6776313 DOI: 10.1371/journal.pone.0222641] [Citation(s) in RCA: 26] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2019] [Accepted: 09/04/2019] [Indexed: 01/31/2023] Open
Abstract
We developed an automated 2-tiered Fuhrman's grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman's grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21-3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.
Collapse
Affiliation(s)
- Katherine Tian
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
- The Harker School, San Jose, CA, United States of America
| | - Christopher A. Rubadue
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
| | - Douglas I. Lin
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
| | - Mitko Veta
- Medical Image Analysis Group, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Michael E. Pyle
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
| | - Humayun Irshad
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
| | - Yujing J. Heng
- Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America
- Cancer Research Institute, Beth Israel Deaconess Cancer Center, Boston, MA, United States of America
| |
Collapse
|
47
|
Amgad M, Elfandy H, Hussein H, Atteya LA, Elsebaie MAT, Abo Elnasr LS, Sakr RA, Salem HSE, Ismail AF, Saad AM, Ahmed J, Elsebaie MAT, Rahman M, Ruhban IA, Elgazar NM, Alagha Y, Osman MH, Alhusseiny AM, Khalaf MM, Younes AAF, Abdulkarim A, Younes DM, Gadallah AM, Elkashash AM, Fala SY, Zaki BM, Beezley J, Chittajallu DR, Manthey D, Gutman DA, Cooper LAD. Structured crowdsourcing enables convolutional segmentation of histology images. Bioinformatics 2019; 35:3461-3467. [PMID: 30726865 PMCID: PMC6748796 DOI: 10.1093/bioinformatics/btz083] [Citation(s) in RCA: 75] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2018] [Revised: 12/30/2018] [Accepted: 02/05/2019] [Indexed: 01/17/2023] Open
Abstract
MOTIVATION While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. RESULTS We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. AVAILABILITY AND IMPLEMENTATION Dataset is freely available at: https://goo.gl/cNM4EL. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Mohamed Amgad
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, USA
| | - Habiba Elfandy
- Department of Pathology, National Cancer Institute, Cairo, Egypt
| | - Hagar Hussein
- Department of Medicine, Cairo University, Cairo, Egypt
| | | | | | | | - Rokia A Sakr
- Department of Medicine, Menoufia University, Menoufia, Egypt
| | | | - Ahmed F Ismail
- Department of Pathology, Medical Research Institute, Alexandria University, Alexandria, Egypt
| | - Anas M Saad
- Department of Medicine, Ain Shams University, Cairo, Egypt
| | - Joumana Ahmed
- Department of Medicine, Cairo University, Cairo, Egypt
| | | | - Mustafijur Rahman
- Department of Medicine, Chittagong University, Chittagong, Bangladesh
| | - Inas A Ruhban
- Department of Medicine, Damascus University, Damascus, Syria
| | - Nada M Elgazar
- Department of Medicine, Mansoura University, Mansoura, Egypt
| | - Yahya Alagha
- Department of Medicine, Cairo University, Cairo, Egypt
| | | | | | - Mariam M Khalaf
- Department of Medicine, Batterjee Medical College, Jeddah, Saudi Arabia
| | | | | | - Duaa M Younes
- Department of Medicine, Ain Shams University, Cairo, Egypt
| | | | | | - Salma Y Fala
- Department of Medicine, Suez Canal University, Ismailia, Egypt
| | - Basma M Zaki
- Department of Medicine, Suez Canal University, Ismailia, Egypt
| | | | | | | | - David A Gutman
- Department of Neurology, Emory University School of Medicine, Atlanta, GA, USA
| | - Lee A D Cooper
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, USA
- Department of Biomedical Engineering, Emory University, Atlanta, GA, USA
| |
Collapse
|
48
|
Chen PHC, Gadepalli K, MacDonald R, Liu Y, Kadowaki S, Nagpal K, Kohlberger T, Dean J, Corrado GS, Hipp JD, Mermel CH, Stumpe MC. An augmented reality microscope with real-time artificial intelligence integration for cancer diagnosis. Nat Med 2019; 25:1453-1457. [PMID: 31406351 DOI: 10.1038/s41591-019-0539-7] [Citation(s) in RCA: 110] [Impact Index Per Article: 22.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2019] [Accepted: 07/02/2019] [Indexed: 12/17/2022]
Abstract
The microscopic assessment of tissue samples is instrumental for the diagnosis and staging of cancer, and thus guides therapy. However, these assessments demonstrate considerable variability and many regions of the world lack access to trained pathologists. Though artificial intelligence (AI) promises to improve the access and quality of healthcare, the costs of image digitization in pathology and difficulties in deploying AI solutions remain as barriers to real-world use. Here we propose a cost-effective solution: the augmented reality microscope (ARM). The ARM overlays AI-based information onto the current view of the sample in real time, enabling seamless integration of AI into routine workflows. We demonstrate the utility of ARM in the detection of metastatic breast cancer and the identification of prostate cancer, with latency compatible with real-time use. We anticipate that the ARM will remove barriers towards the use of AI designed to improve the accuracy and efficiency of cancer diagnosis.
Collapse
Affiliation(s)
| | | | | | - Yun Liu
- Google Health, Mountain View, CA, USA
| | | | | | | | | | | | - Jason D Hipp
- Google Health, Mountain View, CA, USA.,AstraZeneca, Gaithersburg, MD, USA
| | | | - Martin C Stumpe
- Google Health, Mountain View, CA, USA. .,Tempus Labs Inc., Chicago, IL, USA.
| |
Collapse
|
49
|
Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning. Sci Rep 2019; 9:10509. [PMID: 31324828 PMCID: PMC6642160 DOI: 10.1038/s41598-019-46718-3] [Citation(s) in RCA: 88] [Impact Index Per Article: 17.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2019] [Accepted: 06/28/2019] [Indexed: 02/07/2023] Open
Abstract
Histopathological images contain morphological markers of disease progression that have diagnostic and predictive values. In this study, we demonstrate how deep learning framework can be used for an automatic classification of Renal Cell Carcinoma (RCC) subtypes, and for identification of features that predict survival outcome from digital histopathological images. Convolutional neural networks (CNN's) trained on whole-slide images distinguish clear cell and chromophobe RCC from normal tissue with a classification accuracy of 93.39% and 87.34%, respectively. Further, a CNN trained to distinguish clear cell, chromophobe and papillary RCC achieves a classification accuracy of 94.07%. Here, we introduced a novel support vector machine-based method that helped to break the multi-class classification task into multiple binary classification tasks which not only improved the performance of the model but also helped to deal with data imbalance. Finally, we extracted the morphological features from high probability tumor regions identified by the CNN to predict patient survival outcome of most common clear cell RCC. The generated risk index based on both tumor shape and nuclei features are significantly associated with patient survival outcome. These results highlight that deep learning can play a role in both cancer diagnosis and prognosis.
Collapse
|
50
|
Tabibu S, Vinod PK, Jawahar CV. Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning. Sci Rep 2019. [DOI: 10.1038/s41598-019-46718-3 [internet]] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
|