1
|
Al-Kadi OS, Di Ieva A. Fractal-Based Analysis of Histological Features of Brain Tumors. ADVANCES IN NEUROBIOLOGY 2024; 36:501-524. [PMID: 38468050 DOI: 10.1007/978-3-031-47606-8_26] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/13/2024]
Abstract
The structural complexity of brain tumor tissue represents a major challenge for effective histopathological diagnosis. Tumor vasculature is known to be heterogeneous, and mixtures of patterns are usually present. Therefore, extracting key descriptive features for accurate quantification is not a straightforward task. Several steps are involved in the texture analysis process where tissue heterogeneity contributes to the variability of the results. One of the interesting aspects of the brain lies in its fractal nature. Many regions within the brain tissue yield similar statistical properties at different scales of magnification. Fractal-based analysis of the histological features of brain tumors can reveal the underlying complexity of tissue structure and angiostructure, also providing an indication of tissue abnormality development. It can further be used to quantify the chaotic signature of disease to distinguish between different temporal tumor stages and histopathological grades.Brain meningioma subtype classifications' improvement from histopathological images is the main focus of this chapter. Meningioma tissue texture exhibits a wide range of histological patterns whereby a single slide may show a combination of multiple patterns. Distinctive fractal patterns quantified in a multiresolution manner would be for better spatial relationship representation. Fractal features extracted from textural tissue patterns can be useful in characterizing meningioma tumors in terms of subtype classification, a challenging problem compared to histological grading, and furthermore can provide an objective measure for quantifying subtle features within subtypes that are hard to discriminate.
Collapse
Affiliation(s)
- Omar S Al-Kadi
- Artificial Intelligence Department, King Abdullah II School for Information Technology, University of Jordan, Amman, Jordan.
| | - Antonio Di Ieva
- Computational NeuroSurgery (CNS) Lab & Macquarie Neurosurgery, Macquarie Medical School, Faculty of Medicine, Human and Health Sciences, Macquarie University, Sydney, NSW, Australia
| |
Collapse
|
2
|
Hanna C, Willman M, Cole D, Mehkri Y, Liu S, Willman J, Lucke-Wold B. Review of meningioma diagnosis and management. EGYPTIAN JOURNAL OF NEUROSURGERY 2023; 38:16. [PMID: 37124311 PMCID: PMC10138329 DOI: 10.1186/s41984-023-00195-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Accepted: 06/14/2022] [Indexed: 05/02/2023] Open
Abstract
Meningiomas are the most common intracranial tumors in adult patients. Although the majority of meningiomas are diagnosed as benign, approximately 20% of cases are high-grade tumors that require significant clinical treatment. The gold standard for grading central nervous system tumors comes from the World Health Organization Classification of Tumors of the central nervous system. Treatment options also depend on the location, imaging, and histopathological features of the tumor. This review will cover diagnostic strategies for meningiomas, including 2021 updates to the World Health Organization's grading of meningiomas. Meningioma treatment plans are variable and highly dependent on tumor grading. This review will also update the reader on developments in the treatment of meningiomas, including surgery, radiation therapy and monoclonal antibody treatment.
Collapse
Affiliation(s)
- Chadwin Hanna
- Department of Neurosurgery, University of Florida, Gainesville, FL, USA
| | - Matthew Willman
- Department of Neurosurgery, University of Florida, Gainesville, FL, USA
| | - Dwayne Cole
- Department of Neurosurgery, University of Florida, Gainesville, FL, USA
| | - Yusuf Mehkri
- Department of Neurosurgery, University of Florida, Gainesville, FL, USA
| | - Sophie Liu
- Department of Neuroscience, Johns Hopkins University, Baltimore, MD, USA
| | - Jonathan Willman
- Department of Neurosurgery, University of Florida, Gainesville, FL, USA
| | | |
Collapse
|
3
|
Alzoubi I, Bao G, Zheng Y, Wang X, Graeber MB. Artificial intelligence techniques for neuropathological diagnostics and research. Neuropathology 2022. [PMID: 36443935 DOI: 10.1111/neup.12880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2022] [Revised: 10/17/2022] [Accepted: 10/23/2022] [Indexed: 12/03/2022]
Abstract
Artificial intelligence (AI) research began in theoretical neurophysiology, and the resulting classical paper on the McCulloch-Pitts mathematical neuron was written in a psychiatry department almost 80 years ago. However, the application of AI in digital neuropathology is still in its infancy. Rapid progress is now being made, which prompted this article. Human brain diseases represent distinct system states that fall outside the normal spectrum. Many differ not only in functional but also in structural terms, and the morphology of abnormal nervous tissue forms the traditional basis of neuropathological disease classifications. However, only a few countries have the medical specialty of neuropathology, and, given the sheer number of newly developed histological tools that can be applied to the study of brain diseases, a tremendous shortage of qualified hands and eyes at the microscope is obvious. Similarly, in neuroanatomy, human observers no longer have the capacity to process the vast amounts of connectomics data. Therefore, it is reasonable to assume that advances in AI technology and, especially, whole-slide image (WSI) analysis will greatly aid neuropathological practice. In this paper, we discuss machine learning (ML) techniques that are important for understanding WSI analysis, such as traditional ML and deep learning, introduce a recently developed neuropathological AI termed PathoFusion, and present thoughts on some of the challenges that must be overcome before the full potential of AI in digital neuropathology can be realized.
Collapse
Affiliation(s)
- Islam Alzoubi
- School of Computer Science The University of Sydney Sydney New South Wales Australia
| | - Guoqing Bao
- School of Computer Science The University of Sydney Sydney New South Wales Australia
| | - Yuqi Zheng
- Ken Parker Brain Tumour Research Laboratories Brain and Mind Centre, Faculty of Medicine and Health, University of Sydney Camperdown New South Wales Australia
| | - Xiuying Wang
- School of Computer Science The University of Sydney Sydney New South Wales Australia
| | - Manuel B. Graeber
- Ken Parker Brain Tumour Research Laboratories Brain and Mind Centre, Faculty of Medicine and Health, University of Sydney Camperdown New South Wales Australia
| |
Collapse
|
4
|
Forward AK, Volk HA, Cherubini GB, Harcourt-Brown T, Plessas IN, Garosi L, De Decker S. Clinical presentation, diagnostic findings and outcome of dogs undergoing surgical resection for intracranial meningioma: 101 dogs. BMC Vet Res 2022; 18:88. [PMID: 35249530 PMCID: PMC8900440 DOI: 10.1186/s12917-022-03182-y] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2021] [Accepted: 02/23/2022] [Indexed: 11/10/2022] Open
Abstract
Background Meningioma is the most common primary brain neoplasm in dogs. Further information is required regarding the expected long-term prognosis of dogs following the surgical resection of an intracranial meningioma together with the influence of adjunctive therapies. Whilst there have been several studies reporting the long-term outcome of intracranial meningioma resection following surgery alone, surgery with the use of an ultrasonic aspirator, surgery combined with radiotherapy and surgery combined with the addition of hydroxyurea, it is currently unclear which type of adjunctive therapy is associated with the most favourable outcomes. The objective of this study is to describe the presentation and outcome of dogs undergoing surgery for the resection of an intracranial meningioma and the effect of clinical factors, adjunctive therapies and meningioma histopathological subtype on the long-term outcome. Results A hundred and one dogs that had intracranial surgery for meningioma resection were investigated from four referral centres. 94% of dogs survived to hospital discharge with a median survival time of 386 days. Approximately 50% of dogs survived for less than a year, 25% survived between 1 and 2 years, 15% survived between 2 and 3 years and 10% survived for greater than 3 years following discharge from hospital. One or more adjunctive therapies were used in 75 dogs and the analysis of the data did not reveal a clear benefit of a specific type of adjunctive therapy. Those dogs that had a transfrontal approach had a significantly reduced survival time (MST 184 days) compared to those dogs that had a rostrotentorial approach (MST 646 days; p < 0.05). There was no association between meningioma subtype and survival time. Conclusions This study did not identify a clear benefit of a specific type of adjunctive therapy on the survival time. Dogs that had a transfrontal approach had a significantly reduced survival time. Intracranial surgery for meningioma resection offers an excellent prognosis for survival to discharge from hospital with a median long term survival time of 386 days.
Collapse
Affiliation(s)
| | - Holger Andreas Volk
- Department of Small Animal Medicine and Surgery, University of Veterinary Medicine Hannover, 30559, Hannover, Germany
| | - Giunio Bruto Cherubini
- Dick White Referrals, Station Farm, London Road, Six Mile Bottom, Cambridgeshire, CB8 0UH, UK
| | - Tom Harcourt-Brown
- Langford Small Animal Referral Hospital, Langford House, Langford, Bristol, BS40 5DU, UK
| | | | | | - Steven De Decker
- Department of Clinical Science and Services, Royal Veterinary College, University of London, North Mymms, AL9 7TA, UK
| |
Collapse
|
5
|
Galldiks N, Angenstein F, Werner JM, Bauer EK, Gutsche R, Fink GR, Langen KJ, Lohmann P. Use of advanced neuroimaging and artificial intelligence in meningiomas. Brain Pathol 2022; 32:e13015. [PMID: 35213083 PMCID: PMC8877736 DOI: 10.1111/bpa.13015] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2021] [Revised: 06/09/2021] [Accepted: 08/02/2021] [Indexed: 01/04/2023] Open
Abstract
Anatomical cross‐sectional imaging methods such as contrast‐enhanced MRI and CT are the standard for the delineation, treatment planning, and follow‐up of patients with meningioma. Besides, advanced neuroimaging is increasingly used to non‐invasively provide detailed insights into the molecular and metabolic features of meningiomas. These techniques are usually based on MRI, e.g., perfusion‐weighted imaging, diffusion‐weighted imaging, MR spectroscopy, and positron emission tomography. Furthermore, artificial intelligence methods such as radiomics offer the potential to extract quantitative imaging features from routinely acquired anatomical MRI and CT scans and advanced imaging techniques. This allows the linking of imaging phenotypes to meningioma characteristics, e.g., the molecular‐genetic profile. Here, we review several diagnostic applications and future directions of these advanced neuroimaging techniques, including radiomics in preclinical models and patients with meningioma.
Collapse
Affiliation(s)
- Norbert Galldiks
- Department of Neurology, Faculty of Medicine, University Hospital Cologne, University of Cologne, Cologne, Germany.,Institute of Neuroscience and Medicine (INM-3, -4), Research Center Juelich, Juelich, Germany.,Center for Integrated Oncology (CIO), Universities of Aachen, Cologne, Germany
| | - Frank Angenstein
- Functional Neuroimaging Group, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Magdeburg, Germany.,Leibniz Institute for Neurobiology (LIN), Magdeburg, Germany.,Medical Faculty, Otto von Guericke University, Magdeburg, Germany
| | - Jan-Michael Werner
- Department of Neurology, Faculty of Medicine, University Hospital Cologne, University of Cologne, Cologne, Germany
| | - Elena K Bauer
- Department of Neurology, Faculty of Medicine, University Hospital Cologne, University of Cologne, Cologne, Germany
| | - Robin Gutsche
- Institute of Neuroscience and Medicine (INM-3, -4), Research Center Juelich, Juelich, Germany
| | - Gereon R Fink
- Department of Neurology, Faculty of Medicine, University Hospital Cologne, University of Cologne, Cologne, Germany.,Institute of Neuroscience and Medicine (INM-3, -4), Research Center Juelich, Juelich, Germany
| | - Karl-Josef Langen
- Institute of Neuroscience and Medicine (INM-3, -4), Research Center Juelich, Juelich, Germany.,Center for Integrated Oncology (CIO), Universities of Aachen, Cologne, Germany.,Department of Nuclear Medicine, University Hospital Aachen, Aachen, Germany
| | - Philipp Lohmann
- Institute of Neuroscience and Medicine (INM-3, -4), Research Center Juelich, Juelich, Germany.,Department of Stereotaxy and Functional Neurosurgery, Faculty of Medicine, University Hospital Cologne, University of Cologne, Cologne, Germany
| |
Collapse
|
6
|
Abstract
Histopathological images (HIs) are the gold standard for evaluating some types of tumors for cancer diagnosis. The analysis of such images is time and resource-consuming and very challenging even for experienced pathologists, resulting in inter-observer and intra-observer disagreements. One of the ways of accelerating such an analysis is to use computer-aided diagnosis (CAD) systems. This paper presents a review on machine learning methods for histopathological image analysis, including shallow and deep learning methods. We also cover the most common tasks in HI analysis, such as segmentation and feature extraction. Besides, we present a list of publicly available and private datasets that have been used in HI research.
Collapse
|
7
|
Radiomic Analysis of Craniopharyngioma and Meningioma in the Sellar/Parasellar Area with MR Images Features and Texture Features: A Feasible Study. CONTRAST MEDIA & MOLECULAR IMAGING 2020; 2020:4837156. [PMID: 32158365 PMCID: PMC7049426 DOI: 10.1155/2020/4837156] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/17/2019] [Revised: 01/08/2020] [Accepted: 01/20/2020] [Indexed: 02/05/2023]
Abstract
Purpose To investigate the ability of qualitative Magnetic Resonance (MR) images features and quantitative Magnetic Resonance Imaging (MRI) texture features in the contrastive analysis between craniopharyngioma and meningioma. Method A total number of 127 patients were included in this study (craniopharyngioma = 63; meningioma = 64). All the features analyzed in this study were acquired from preoperative MRI images. Qualitative MR images features were evaluated with chi-square tests or Fisher exact test, while MRI texture features were evaluated with the Mann-Whitney U test with the Benjamini-Hochberg method. Then binary logistic regression analysis for texture features was performed to evaluate their ability as independent predictors, and the diagnostic accuracy was calculated next for these texture features with high abilities as independent predictors using receiver operating characteristic (ROC) curves. Results Four qualitative MR images features showed significant difference between craniopharyngioma and meningioma, but only cystic alteration could be considered as diagnostic independent predictors. Meanwhile, three quantitative parameters, histogram-based matrix- (HISTO-) Skewness, Grey-level co-occurrence matrix- (GLCM-) Contrast on contrast-enhanced images, and HISTO-Skewness on images of T2-weighted imaging (T2WI), showed promising abilities in the contrastive analysis. Besides, these texture features were found significantly to be relative to cystic alteration. Conclusion MR images features and texture features were useful in the contrastive analysis of craniopharyngioma and meningioma. Furthermore, qualitative MR images features and MRI texture features could be related to each other.
Collapse
|
8
|
Dragić M, Zarić M, Mitrović N, Nedeljković N, Grković I. Application of Gray Level Co-Occurrence Matrix Analysis as a New Method for Enzyme Histochemistry Quantification. MICROSCOPY AND MICROANALYSIS : THE OFFICIAL JOURNAL OF MICROSCOPY SOCIETY OF AMERICA, MICROBEAM ANALYSIS SOCIETY, MICROSCOPICAL SOCIETY OF CANADA 2019; 25:690-698. [PMID: 30714562 DOI: 10.1017/s1431927618016306] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Enzyme histochemistry is a valuable histological method which provides a connection between morphology, activity, and spatial localization of investigated enzymes. Even though the method relies purely on arbitrary evaluations performed by the human eye, it is still wildly accepted and used in histo(patho)logy. Texture analysis emerged as an excellent tool for image quantification of subtle differences reflected in both spatial discrepancies and gray level values of pixels. The current study of texture analysis utilizes the gray-level co-occurrence matrix as a method for quantification of differences between ecto-5'-nucleotidase activities in healthy hippocampal tissue and tissue with marked neurodegeneration. We used the angular second moment, contrast (CON), correlation, inverse difference moment (INV), and entropy for texture analysis and receiver operating characteristic analysis with immunoblot and qualitative assessment of enzyme histochemistry as a validation. Our results strongly argue that co-occurrence matrix analysis could be used for the determination of fine differences in the enzyme activities with the possibility to ascribe those differences to regions or specific cell types. In addition, it emerged that INV and CON are especially useful parameters for this type of enzyme histochemistry analysis. We concluded that texture analysis is a reliable method for quantification of this descriptive technique, thus removing biases and adding it a quantitative dimension.
Collapse
Affiliation(s)
- Milorad Dragić
- Department for General Physiology and Biophysics,Faculty of Biology,University of Belgrade,Belgrade,Studentski trg 3,11001 Belgrade,Serbia
| | - Marina Zarić
- Department of Molecular Biology and Endocrinology,Vinča Institute of Nuclear Sciences, University of Belgrade,Mike Petrovića Alasa 12-14,11001 Belgrade,Serbia
| | - Nataša Mitrović
- Department of Molecular Biology and Endocrinology,Vinča Institute of Nuclear Sciences, University of Belgrade,Mike Petrovića Alasa 12-14,11001 Belgrade,Serbia
| | - Nadežda Nedeljković
- Department for General Physiology and Biophysics,Faculty of Biology,University of Belgrade,Belgrade,Studentski trg 3,11001 Belgrade,Serbia
| | - Ivana Grković
- Department of Molecular Biology and Endocrinology,Vinča Institute of Nuclear Sciences, University of Belgrade,Mike Petrovića Alasa 12-14,11001 Belgrade,Serbia
| |
Collapse
|
9
|
Park YW, Oh J, You SC, Han K, Ahn SS, Choi YS, Chang JH, Kim SH, Lee SK. Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging. Eur Radiol 2018; 29:4068-4076. [DOI: 10.1007/s00330-018-5830-3] [Citation(s) in RCA: 92] [Impact Index Per Article: 15.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2018] [Revised: 09/19/2018] [Accepted: 10/12/2018] [Indexed: 11/27/2022]
|
10
|
Gray-level co-occurrence matrix analysis of chromatin architecture in periportal and perivenous hepatocytes. Histochem Cell Biol 2018; 151:75-83. [PMID: 30140953 DOI: 10.1007/s00418-018-1714-5] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/21/2018] [Indexed: 02/05/2023]
Abstract
Periportal hepatocytes (PPHs) and perivenous hepatocytes (PVHs) in standard optical microscopy appear to be morphologically identical. However, the functional properties of these two cell populations and their roles in liver lobules are not the same. Despite significant differences in gene expression between these two hepatocyte populations, it is still unclear whether the differences are present at the higher levels of chromatin organization. In this study, we present results, indicating that periportal and perivenous hepatocytes, when stained using toluidine blue histological dye, have different chromatin textural patterns quantified with gray-level co-occurrence matrix (GLCM) method. Hepatic tissue was obtained from ten male, healthy mice. Chromatin structures were analyzed using GLCM. For each structure, we measured the values of angular second moment, inverse difference moment, GLCM Contrast, GLCM Variance, and GLCM Sum Variance. The results indicate that there is a statistically significant difference in all GLCM mathematical parameters except the contrast. In addition, some chromatin GLCM features were in correlation with serum aminotransferase levels in perivenous, but not in periportal hepatocytes. To the best of our knowledge, this is the first study to test the nuclear morphological differences between hepatocytes using GLCM and to investigate the respective relation with serum liver enzymes.
Collapse
|
11
|
Synergies between texture features: an abstract feature based framework for meningioma subtypes classification. Pattern Anal Appl 2017. [DOI: 10.1007/s10044-017-0599-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
12
|
Fatima K, Majeed H, Irshad H. Nuclear spatial and spectral features based evolutionary method for meningioma subtypes classification in histopathology. Microsc Res Tech 2017; 80:851-861. [PMID: 28379628 DOI: 10.1002/jemt.22874] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2017] [Accepted: 03/17/2017] [Indexed: 11/11/2022]
Abstract
Meningioma subtypes classification is a real-world multiclass problem from the realm of neuropathology. The major challenge in solving this problem is the inherent complexity due to high intra-class variability and low inter-class variation in tissue samples. The development of computational methods to assist pathologists in characterization of these tissue samples would have great diagnostic and prognostic value. In this article, we proposed an optimized evolutionary framework for the classification of benign meningioma into four subtypes. This framework investigates the imperative role of RGB color channels for discrimination of tumor subtypes and compute structural, statistical and spectral phenotypes. An evolutionary technique, Genetic Algorithm, in combination with Support Vector Machine is applied to tune classifier parameters and to select the best possible combination of extracted phenotypes that improved the classification accuracy (94.88%) on meningioma histology dataset, provided by the Institute of Neuropathology, Bielefeld. These statistics show that computational framework can robustly discriminate four subtypes of benign meningioma and may aid pathologists in the diagnosis and classification of these lesions.
Collapse
Affiliation(s)
- Kiran Fatima
- Department of Computer Science, National University of Computer and Emerging Sciences, A. K. Brohi Road, H-11/4, Islamabad, Pakistan
| | - Hammad Majeed
- Department of Computer Science, National University of Computer and Emerging Sciences, A. K. Brohi Road, H-11/4, Islamabad, Pakistan
| | - Humayun Irshad
- Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
13
|
|
14
|
Peikari M, Gangeh MJ, Zubovits J, Clarke G, Martel AL. Triaging Diagnostically Relevant Regions from Pathology Whole Slides of Breast Cancer: A Texture Based Approach. IEEE TRANSACTIONS ON MEDICAL IMAGING 2016; 35:307-315. [PMID: 26302511 DOI: 10.1109/tmi.2015.2470529] [Citation(s) in RCA: 34] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
PURPOSE Pathologists often look at whole slide images (WSIs) at low magnification to find potentially important regions and then zoom in to higher magnification to perform more sophisticated analysis of the tissue structures. Many automated methods of WSI analysis attempt to preprocess the down-sampled image in order to select salient regions which are then further analyzed by a more computationally intensive step at full magnification. Although it can greatly reduce processing times, this process may lead to small potentially important regions being overlooked at low magnification. We propose a texture analysis technique to ease the processing of H&E stained WSIs by triaging clinically important regions. METHOD Image patches randomly selected from the whole tissue area were divided into smaller tiles and Gaussian-like texture filters were applied to them. Texture filter responses from each tile were combined together and statistical measures were derived from their histograms of responses. Bag of visual words pipeline was then employed to combine extracted features from tiles to form one histogram of words per every image patch. A support vector machine classifier was trained using the calculated histograms of words to be able to distinguish between clinically relevant and irrelevant patches. RESULT Experimental analysis on 5151 image patches from 10 patient cases (65 tissue slides) indicated that our proposed texture technique out-performed two previously proposed colour and intensity based methods with an area under the ROC curve of 0.87. CONCLUSION Texture features can be employed to triage clinically important areas within large WSIs.
Collapse
|
15
|
Barker J, Hoogi A, Depeursinge A, Rubin DL. Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles. Med Image Anal 2015; 30:60-71. [PMID: 26854941 DOI: 10.1016/j.media.2015.12.002] [Citation(s) in RCA: 65] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2015] [Revised: 12/02/2015] [Accepted: 12/07/2015] [Indexed: 02/07/2023]
Abstract
Computerized analysis of digital pathology images offers the potential of improving clinical care (e.g. automated diagnosis) and catalyzing research (e.g. discovering disease subtypes). There are two key challenges thwarting computerized analysis of digital pathology images: first, whole slide pathology images are massive, making computerized analysis inefficient, and second, diverse tissue regions in whole slide images that are not directly relevant to the disease may mislead computerized diagnosis algorithms. We propose a method to overcome both of these challenges that utilizes a coarse-to-fine analysis of the localized characteristics in pathology images. An initial surveying stage analyzes the diversity of coarse regions in the whole slide image. This includes extraction of spatially localized features of shape, color and texture from tiled regions covering the slide. Dimensionality reduction of the features assesses the image diversity in the tiled regions and clustering creates representative groups. A second stage provides a detailed analysis of a single representative tile from each group. An Elastic Net classifier produces a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level. We evaluated our method by automatically classifying 302 brain cancer cases into two possible diagnoses (glioblastoma multiforme (N = 182) versus lower grade glioma (N = 120)) with an accuracy of 93.1% (p << 0.001). We also evaluated our method in the dataset provided for the 2014 MICCAI Pathology Classification Challenge, in which our method, trained and tested using 5-fold cross validation, produced a classification accuracy of 100% (p << 0.001). Our method showed high stability and robustness to parameter variation, with accuracy varying between 95.5% and 100% when evaluated for a wide range of parameters. Our approach may be useful to automatically differentiate between the two cancer subtypes.
Collapse
Affiliation(s)
- Jocelyn Barker
- Department of Medicine (Stanford Biomedical Informatics Research), Stanford University School of Medicine, CA, USA.
| | - Assaf Hoogi
- Department of Radiology, Stanford University School of Medicine, CA, USA.
| | - Adrien Depeursinge
- Department of Radiology, Stanford University School of Medicine, CA, USA; Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland.
| | - Daniel L Rubin
- Department of Radiology, Stanford University School of Medicine, CA, USA; Department of Medicine (Stanford Biomedical Informatics Research), Stanford University School of Medicine, CA, USA.
| |
Collapse
|
16
|
Schäfer H, Schäfer T, Ackermann J, Dichter N, Döring C, Hartmann S, Hansmann ML, Koch I. CD30 cell graphs of Hodgkin lymphoma are not scale-free--an image analysis approach. Bioinformatics 2015; 32:122-9. [PMID: 26363177 DOI: 10.1093/bioinformatics/btv542] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2015] [Accepted: 09/08/2015] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION Hodgkin lymphoma (HL) is a type of B-cell lymphoma. To diagnose the subtypes, biopsies are taken and immunostained. The slides are scanned to produce high-resolution digital whole slide images (WSI). Pathologists manually inspect the spatial distribution of cells, but little is known on the statistical properties of cell distributions in WSIs. Such properties would give valuable information for the construction of theoretical models that describe the invasion of malignant cells in the lymph node and the intercellular interactions. RESULTS In this work, we define and discuss HL cell graphs. We identify CD30(+) cells in HL WSIs, bringing together the fields of digital imaging and network analysis. We define special graphs based on the positions of the immunostained cells. We present an automatic analysis of complete WSIs to determine significant morphological and immunohistochemical features of HL cells and their spatial distribution in the lymph node tissue under three different medical conditions: lymphadenitis (LA) and two types of HL. We analyze the vertex degree distributions of CD30 cell graphs and compare them to a null model. CD30 cell graphs show higher vertex degrees than expected by a random unit disk graph, suggesting clustering of the cells. We found that a gamma distribution is suitable to model the vertex degree distributions of CD30 cell graphs, meaning that they are not scale-free. Moreover, we compare the graphs for LA and two subtypes of HL. LA and classical HL showed different vertex degree distributions. The vertex degree distributions of the two HL subtypes NScHL and mixed cellularity HL (MXcHL) were similar. AVAILABILITY AND IMPLEMENTATION The CellProfiler pipeline used for cell detection is available at https://sourceforge.net/projects/cellgraphs/. CONTACT ina.koch@bioinformatik.uni-frankfurt.de SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Hendrik Schäfer
- Department of Molecular Bioinformatics, Institute of Computer Science, Cluster of Excellence Macromolecular Complexes, Johann Wolfgang Goethe-University Frankfurt am Main, Robert-Mayer-Str. 11-15, 60325 Frankfurt am Main and
| | - Tim Schäfer
- Department of Molecular Bioinformatics, Institute of Computer Science, Cluster of Excellence Macromolecular Complexes, Johann Wolfgang Goethe-University Frankfurt am Main, Robert-Mayer-Str. 11-15, 60325 Frankfurt am Main and
| | - Jörg Ackermann
- Department of Molecular Bioinformatics, Institute of Computer Science, Cluster of Excellence Macromolecular Complexes, Johann Wolfgang Goethe-University Frankfurt am Main, Robert-Mayer-Str. 11-15, 60325 Frankfurt am Main and
| | - Norbert Dichter
- Department of Molecular Bioinformatics, Institute of Computer Science, Cluster of Excellence Macromolecular Complexes, Johann Wolfgang Goethe-University Frankfurt am Main, Robert-Mayer-Str. 11-15, 60325 Frankfurt am Main and
| | - Claudia Döring
- Dr. Senckenbergisches Institut für Pathologie, Universitätsklinikum Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | - Sylvia Hartmann
- Dr. Senckenbergisches Institut für Pathologie, Universitätsklinikum Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | - Martin-Leo Hansmann
- Dr. Senckenbergisches Institut für Pathologie, Universitätsklinikum Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany
| | - Ina Koch
- Department of Molecular Bioinformatics, Institute of Computer Science, Cluster of Excellence Macromolecular Complexes, Johann Wolfgang Goethe-University Frankfurt am Main, Robert-Mayer-Str. 11-15, 60325 Frankfurt am Main and
| |
Collapse
|