Machine Learning Based Classification from Whole-Slide Histopathological Images Enables Reliable and Interpretable Diagnosis of Inverted Urothelial Papilloma

2021 ◽  
Author(s):  
Wei Shao ◽  
Michael Cheng ◽  
Zhi Huang ◽  
Zhi Han ◽  
Tongxin Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Histopathological Images

scholarly journals PyHIST: A Histological Image Segmentation Tool

2020 ◽  
Vol 16 (10) ◽  
pp. e1008349
Author(s):  
Manuel Muñoz-Aguirre ◽  
Vasilis F. Ntasis ◽  
Santiago Rojas ◽  
Roderic Guigó
Keyword(s):  
Machine Learning ◽  
Input Image ◽  
Biological Knowledge ◽  
Imaging Data ◽  
Tissue Segmentation ◽  
Histological Image ◽  
Command Line Tool ◽  
Machine Learning Applications ◽  
Histopathological Images ◽  
High Resolution Images

The development of increasingly sophisticated methods to acquire high-resolution images has led to the generation of large collections of biomedical imaging data, including images of tissues and organs. Many of the current machine learning methods that aim to extract biological knowledge from histopathological images require several data preprocessing stages, creating an overhead before the proper analysis. Here we present PyHIST (https://github.com/manuel-munoz-aguirre/PyHIST), an easy-to-use, open source whole slide histological image tissue segmentation and preprocessing command-line tool aimed at tile generation for machine learning applications. From a given input image, the PyHIST pipeline i) optionally rescales the image to a different resolution, ii) produces a mask for the input image which separates the background from the tissue, and iii) generates individual image tiles with tissue content.

scholarly journals Automated Detection and Classification of Ki-67 Stained Nuclear Section Using Machine Learning Based on Texture of Nucleus to Measure Proliferation Score for Prognostic Evaluation of Breast Carcinoma

2020 ◽  
Author(s):  
Anil Kumar ◽  
Manish Prateek
Keyword(s):  
Machine Learning ◽  
Breast Carcinoma ◽  
Automatic Segmentation ◽  
Blue Color ◽  
Ki 67 ◽  
Data Set ◽  
Unsupervised Machine Learning ◽  
Histopathological Images ◽  
Hematoxylin And Eosin

Abstract Background: This study aimed significance of Ki-67 labels and calculated the proliferation score based on the counting of immunopositive and immunonegative nuclear sections with the help of machine learning to predict the intensity of breast carcinoma.Methods: BreCaHAD (Breast Cancer Histopathological Annotation and Diagnosis) dataset includes various malignant cases of different patients in their routine diagnosis. It contains H&E stained microscopic histopathological images at 40x magnification and stored in .tiff format using RGB band. In this study, the method start with preprocessing that focuses on resizing, smoothing and enhancement. After preprocessing, it is decomposed RGB sample into HSI values. BreCaHAD data set is hematoxylin and eosin (H&E) stained, where brown and blue color level have a major role to differentiate the immunopositive and immunonegative nuclear sections. Blue color in RGB and Hue in HSI are the intrinsic characteristic of H&E Ki-67. The shape parameters are calculated after segmentation preceded by Otsu thresholding and unsupervised machine learning. Morphological operators help to solve the problem of overlapping of nucleus section in sample images so that the counting will be correct and increase the accuracy of automatic segmentation.Result: With the help of nine morphological features and supported by unsupervised machine learning technique on BreCaHAD dataset, it is predicted the label of breast carcinoma. The performance measures like precision: 95.7%, recall: 93.8%, f-score: 94.74%, accuracy: 0.9088, specificity: 0.6803, BCR: 0.7975 and MCC: 0.5855 are obtained in proposed methodology which is better than existing techniques. Conclusion: This study developed an efficient automated nuclear section segmentation model implemented on BreCaHAD dataset contains H&E stained microscopic biopsy images. Potentially, this model will assist the pathologist for fast, effective, efficient and accurate computation of Ki-67 proliferation score on breast IHC carcinoma images.

scholarly journals ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

2019 ◽  
Author(s):  
Łukasz Rączkowski ◽  
Marcin Możejko ◽  
Joanna Zambonelli ◽  
Ewa Szczurek
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Machine Learning Algorithms ◽  
Diagnostic Process ◽  
Entropy Measure ◽  
Classification Framework ◽  
Uncertainty Measurement ◽  
Histopathological Images ◽  
Histopathological Image Classification ◽  
Measure Of Uncertainty

ABSTRACTMachine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

scholarly journals Classification of Neuroblastoma Histopathological Images Using Machine Learning

2020 ◽  
pp. 3-14
Author(s):  
Adhish Panta ◽  
Matloob Khushi ◽  
Usman Naseem ◽  
Paul Kennedy ◽  
Daniel Catchpoole
Keyword(s):  
Machine Learning ◽  
Histopathological Images

scholarly journals ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Łukasz Rączkowski ◽  
Marcin Możejko ◽  
Joanna Zambonelli ◽  
Ewa Szczurek
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Machine Learning Algorithms ◽  
Diagnostic Process ◽  
Entropy Measure ◽  
Classification Framework ◽  
Uncertainty Measurement ◽  
Histopathological Images ◽  
Histopathological Image Classification ◽  
Measure Of Uncertainty

Abstract Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

Classification of Invasive Ductal Carcinoma from histopathology breast cancer images using Stacked Generalized Ensemble

2020 ◽  
pp. 1-16
Author(s):  
Deepika Kumar ◽  
Usha Batra
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Deep Learning ◽  
Invasive Ductal Carcinoma ◽  
Cancer Detection ◽  
Ductal Carcinoma ◽  
Machine Learning Algorithms ◽  
Diagnostic Methods ◽  
Learner Model ◽  
Histopathological Images

Breast cancer positions as the most well-known threat and the main source of malignant growth-related morbidity and mortality throughout the world. It is apical of all new cancer incidences analyzed among females. However, Machine learning algorithms have given rise to progress across different domains. There are various diagnostic methods available for cancer detection. However, cancer detection through histopathological images is considered to be more accurate. In this research, we have proposed the Stacked Generalized Ensemble (SGE) approach for breast cancer classification into Invasive Ductal Carcinoma+ and Invasive Ductal Carcinoma-. SGE is inspired by the stacking model which utilizes output predictions. Here, SGE uses six deep learning models as level-0 learner models or sub-models and Logistic regression is used as Level – 1 learner or meta – learner model. Invasive Ductal Carcinoma dataset for histopathology images is used for experimentation. The results of the proposed methodology have been compared and analyzed with existing machine learning and deep learning methods. The results demonstrate that the proposed methodology performed exponentially good in image classification in terms of accuracy, precision, recall, and F1 measure.

scholarly journals Histopathological Images and Multi-Omics Integration Predict Molecular Characteristics and Survival in Lung Adenocarcinoma

2021 ◽  
Vol 9 ◽  
Author(s):  
Linyan Chen ◽  
Hao Zeng ◽  
Yu Xiang ◽  
Yeqian Huang ◽  
Yuling Luo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Adenocarcinoma ◽  
Image Features ◽  
Molecular Characteristics ◽  
Learning Models ◽  
Training Set ◽  
Test Set ◽  
Genetic Aberrations ◽  
Histopathological Images ◽  
Machine Learning Models

Histopathological images and omics profiles play important roles in prognosis of cancer patients. Here, we extracted quantitative features from histopathological images to predict molecular characteristics and prognosis, and integrated image features with mutations, transcriptomics, and proteomics data for prognosis prediction in lung adenocarcinoma (LUAD). Patients obtained from The Cancer Genome Atlas (TCGA) were divided into training set (n = 235) and test set (n = 235). We developed machine learning models in training set and estimated their predictive performance in test set. In test set, the machine learning models could predict genetic aberrations: ALK (AUC = 0.879), BRAF (AUC = 0.847), EGFR (AUC = 0.855), ROS1 (AUC = 0.848), and transcriptional subtypes: proximal-inflammatory (AUC = 0.897), proximal-proliferative (AUC = 0.861), and terminal respiratory unit (AUC = 0.894) from histopathological images. Moreover, we obtained tissue microarrays from 316 LUAD patients, including four external validation sets. The prognostic model using image features was predictive of overall survival in test and four validation sets, with 5-year AUCs from 0.717 to 0.825. High-risk and low-risk groups stratified by the model showed different survival in test set (HR = 4.94, p < 0.0001) and three validation sets (HR = 1.64–2.20, p < 0.05). The combination of image features and single omics had greater prognostic power in test set, such as histopathology + transcriptomics model (5-year AUC = 0.840; HR = 7.34, p < 0.0001). Finally, the model integrating image features with multi-omics achieved the best performance (5-year AUC = 0.908; HR = 19.98, p < 0.0001). Our results indicated that the machine learning models based on histopathological image features could predict genetic aberrations, transcriptional subtypes, and survival outcomes of LUAD patients. The integration of histopathological images and multi-omics may provide better survival prediction for LUAD.

scholarly journals PyHIST: A Histological Image Segmentation Tool

2020 ◽  
Author(s):  
Manuel Muñoz-Aguirre ◽  
Vasilis F. Ntasis ◽  
Roderic Guigó
Keyword(s):  
Machine Learning ◽  
Biological Knowledge ◽  
Data Preparation ◽  
Imaging Data ◽  
Tissue Segmentation ◽  
Histological Image ◽  
Machine Learning Applications ◽  
Histopathological Images ◽  
High Resolution Images ◽  
Proper Analysis

AbstractThe development of increasingly sophisticated methods to acquire high resolution images has led to the generation of large collections of biomedical imaging data, including images of tissues and organs. Many of the current machine learning methods that aim to extract biological knowledge from histopathological images require several data preprocessing stages, creating an overhead before the proper analysis. Here we present PyHIST (https://github.com/manuel-munoz-aguirre/PyHIST), an easy-to-use, open source whole slide histological image tissue segmentation and preprocessing tool aimed at data preparation for machine learning applications.

Sign in / Sign up

Export Citation Format

Share Document