scholarly journals A deep learning-based iterative digital pathology annotation tool

2021 ◽  
Author(s):  
Mustafa I. Jaber ◽  
Bing Song ◽  
Liudmila Beziaeva ◽  
Christopher W. Szeto ◽  
Patricia Spilman ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Gold Standard ◽  
Image Annotation ◽  
Digital Pathology ◽  
Tumor Stroma ◽  
Automation System ◽  
Annotation Tool ◽  
Comparable Performance ◽  
Pathology Image

ABSTRACTWell-annotated exemplars are an important prerequisite for supervised deep learning schemes. Unfortunately, generating these annotations is a cumbersome and laborious process, due to the large amount of time and effort needed. Here we present a deep-learning-based iterative digital pathology annotation tool that is both easy to use by pathologists and easy to integrate into machine vision systems. Our pathology image annotation tool greatly reduces annotation time from hours to a few minutes, while maintaining high fidelity with human-expert manual annotations. Here we demonstrate that our active learning tool can be used for a variety of pathology annotation tasks including masking tumor, stroma, and lymphocyte-rich regions, among others. This annotation automation system was validated on 90 unseen digital pathology images with tumor content from the CAMELYON16 database and it was found that pathologists’ gold standard masks were re-produced successfully using our tool. That is, an average of 2.7 positive selections (mouse clicks) and 8.0 negative selections (mouse clicks) were sufficient to generate tumor masks similar to pathologists’ gold standard in CAMELYON16 test WSIs. Furthermore, the developed image annotation tool has been used to build gold standard masks for hundreds of TCGA digital pathology images. This set was used to train a convolutional neural network for identification of tumor epithelium. The developed pan-cancer deep neural network was then tested on TCGA and internal data with comparable performance. The validated pathology image annotation tool described herein has the potential to be of great value in facilitating accurate, rapid pathological analysis of tumor biopsies.

scholarly journals Learning from crowds in digital pathology using scalable variational Gaussian processes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Miguel López-Pérez ◽  
Mohamed Amgad ◽  
Pablo Morales-Álvarez ◽  
Pablo Ruiz ◽  
Lee A. D. Cooper ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Gaussian Processes ◽  
Gold Standard ◽  
Digital Pathology ◽  
Machine Learning Algorithms ◽  
Medical Applications ◽  
Comparable Performance ◽  
Primary Determinant ◽  
Scale Data

AbstractThe volume of labeled data is often the primary determinant of success in developing machine learning algorithms. This has increased interest in methods for leveraging crowds to scale data labeling efforts, and methods to learn from noisy crowd-sourced labels. The need to scale labeling is acute but particularly challenging in medical applications like pathology, due to the expertise required to generate quality labels and the limited availability of qualified experts. In this paper we investigate the application of Scalable Variational Gaussian Processes for Crowdsourcing (SVGPCR) in digital pathology. We compare SVGPCR with other crowdsourcing methods using a large multi-rater dataset where pathologists, pathology residents, and medical students annotated tissue regions breast cancer. Our study shows that SVGPCR is competitive with equivalent methods trained using gold-standard pathologist generated labels, and that SVGPCR meets or exceeds the performance of other crowdsourcing methods based on deep learning. We also show how SVGPCR can effectively learn the class-conditional reliabilities of individual annotators and demonstrate that Gaussian-process classifiers have comparable performance to similar deep learning methods. These results suggest that SVGPCR can meaningfully engage non-experts in pathology labeling tasks, and that the class-conditional reliabilities estimated by SVGPCR may assist in matching annotators to tasks where they perform well.

Postal Automation System in Gurmukhi Script using Deep Learning

2021 ◽  
Author(s):  
Sandhya Sharma ◽  
Sheifali Gupta ◽  
Neeraj Kumar ◽  
Tanvi Arora
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Holistic Approach ◽  
North India ◽  
Automation System ◽  
Official Language ◽  
Major Research ◽  
Research Areas ◽  
Postal Automation ◽  
Gurmukhi Script

Nowadays in the era of automation, the postal automation system is one of the major research areas. Developing a postal automation system for a nation like India is much troublesome than other nations because of India’s multi-script and multi-lingual behavior. This proposed work will be helpful in the postal automation of district names of Punjab (state) written in Gurmukhi script, which is the official language of the state in North India. For this, a holistic approach i.e. a segmentation-free technique has been used with the help of Convolutional Neural Network (CNN) and Deep learning (DL). For the purpose of recognition, a database of 22[Formula: see text]000 images (samples) which are handwritten in Gurmukhi script for all the 22 districts of Punjab is prepared. Each sample is written two times by 500 different writers generating 1000 samples for each district name. Two CNN models are proposed which are named as ConvNetGuru and ConvNetGuruMod for the purpose of recognition. Maximum validation accuracy achieved by ConvNetGuru is 90% and ConvNetGuruMod is 98%.

scholarly journals 833 A scalable deep learning framework for rapid automated annotation of histologic and morphologic features from large unlabeled pan-cancer H&E datasets

2021 ◽  
Vol 9 (Suppl 3) ◽  
pp. A874-A874
Author(s):  
David Soong ◽  
David Soong ◽  
David Soong ◽  
Anantharaman Muthuswamy ◽  
Clifton Drew ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Solid Tumor ◽  
Blood Cells ◽  
White Blood Cells ◽  
Digital Pathology ◽  
Area Under The Curve ◽  
Morphological Characteristics ◽  
Learning Framework ◽  
Tumor Types

BackgroundRecent advances in machine learning and digital pathology have enabled a variety of applications including predicting tumor grade and genetic subtypes, quantifying the tumor microenvironment (TME), and identifying prognostic morphological features from H&E whole slide images (WSI). These supervised deep learning models require large quantities of images manually annotated with cellular- and tissue-level details by pathologists, which limits scale and generalizability across cancer types and imaging platforms. Here we propose a semi-supervised deep learning framework that automatically annotates biologically relevant image content from hundreds of solid tumor WSI with minimal pathologist intervention, thus improving quality and speed of analytical workflows aimed at deriving clinically relevant features.MethodsThe dataset consisted of >200 H&E images across >10 solid tumor types (e.g. breast, lung, colorectal, cervical, and urothelial cancers) from advanced disease patients. WSI were first partitioned into small tiles of 128μm for feature extraction using a 50-layer convolutional neural network pre-trained on the ImageNet database. Dimensionality reduction and unsupervised clustering were applied to the resultant embeddings and image clusters were identified with enriched histological and morphological characteristics. A random subset of representative tiles (<0.5% of whole slide tissue areas) from these distinct image clusters was manually reviewed by pathologists and assigned to eight histological and morphological categories: tumor, stroma/connective tissue, necrotic cells, lymphocytes, red blood cells, white blood cells, normal tissue and glass/background. This dataset allowed the development of a multi-label deep neural network to segment morphologically distinct regions and detect/quantify histopathological features in WSI.ResultsAs representative image tiles within each image cluster were morphologically similar, expert pathologists were able to assign annotations to multiple images in parallel, effectively at 150 images/hour. Five-fold cross-validation showed average prediction accuracy of 0.93 [0.8–1.0] and area under the curve of 0.90 [0.8–1.0] over the eight image categories. As an extension of this classifier framework, all whole slide H&E images were segmented and composite lymphocyte, stromal, and necrotic content per patient tumor was derived and correlated with estimates by pathologists (p<0.05).ConclusionsA novel and scalable deep learning framework for annotating and learning H&E features from a large unlabeled WSI dataset across tumor types was developed. This automated approach accurately identified distinct histomorphological features, with significantly reduced labeling time and effort required for pathologists. Further, this classifier framework was extended to annotate regions enriched in lymphocytes, stromal, and necrotic cells – important TME contexture with clinical relevance for patient prognosis and treatment decisions.

scholarly journals A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology

2019 ◽  
Vol 144 (3) ◽  
pp. 370-378 ◽  
Author(s):  
David R. Martin ◽  
Joshua A. Hanson ◽  
Rama R. Gullapalli ◽  
Fred A. Schultz ◽  
Aisha Sethi ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Gold Standard ◽  
Phase 1 ◽  
Phase 2 ◽  
Gastric Biopsies ◽  
H Pylori ◽  
Sensitivity Specificity ◽  
Receiver Operating

Context.— Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched. Objective.— To investigate the use of DL for nonneoplastic gastric biopsies. Design.— Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100 Helicobacter pylori, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion. Results.— For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and H pylori (AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%), H pylori (100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for H pylori, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%), H pylori (95.7%, 100%), reactive gastropathy (100%, 62.5%). Conclusions.— A convolutional neural network can serve as an effective screening tool/diagnostic aid for H pylori gastritis.

scholarly journals Devanagari Handwritten Character Recognition Using Deep Learning

2022 ◽  
Vol 10 (1) ◽  
pp. 102-105
Author(s):  
Kannuru Padmaja
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Character Recognition ◽  
Automation System ◽  
Handwritten Character Recognition ◽  
Image Processing Techniques ◽  
Handwritten Character ◽  
Processing Techniques ◽  
Deep Learning Model

Abstract: In this paper, we present the implementation of Devanagari handwritten character recognition using deep learning. Hand written character recognition gaining more importance due to its major contribution in automation system. Devanagari script is one of various languages script in India. It consists of 12 vowels and 36 consonants. Here we implemented the deep learning model to recognize the characters. The character recognition mainly five steps: pre-processing, segmentation, feature extraction, prediction, post-processing. The model will use convolutional neural network to train the model and image processing techniques to use the character recognition and predict the accuracy of rcognition. Keywords: convolutional neural network, character recognition, Devanagari script, deep learning.

scholarly journals Ovarian Toxicity Assessment in Histopathological Images Using Deep Learning

2019 ◽  
Vol 48 (2) ◽  
pp. 350-361 ◽  
Author(s):  
Fangyao Hu ◽  
Leah Schutt ◽  
Cleopatra Kozlowski ◽  
Karen Regan ◽  
Noel Dybdal ◽  
...  
Keyword(s):  
Deep Learning ◽  
Gold Standard ◽  
Safety Concern ◽  
Digital Pathology ◽  
Cancer Therapeutics ◽  
Corpora Lutea ◽  
Ovarian Toxicity ◽  
Toxicity Studies ◽  
Automated Method ◽  
Microscopic Evaluation

As ovarian toxicity is often a safety concern for cancer therapeutics, identification of ovarian pathology is important in early stages of preclinical drug development, particularly when the intended patient population include women of child-bearing potential. Microscopic evaluation by pathologists of hematoxylin and eosin (H&E)–stained tissues is the current gold standard for the assessment of organs in toxicity studies. However, digital pathology and advanced image analysis are being explored with greater frequency and broader applicability to tissue evaluations in toxicologic pathology. Our objective in this work was to develop an automated method that rapidly enumerates rat ovarian corpora lutea on standard H&E-stained slides with comparable accuracy to the gold standard assessment by a pathologist. Herein, we describe an algorithm generated by a deep learning network and tested on 5 rat toxicity studies, which included studies that both had and had not previously been diagnosed with effects on number of ovarian corpora lutea. Our algorithm could not only enumerate corpora lutea accurately in all studies but also revealed distinct trends for studies with and without reproductive toxicity. Our method could be a widely applied tool to aid analysis in general toxicity studies.

scholarly journals A Deep Learning Approach for Segmentation of Red Blood Cell Images and Malaria Detection

Entropy ◽  
2020 ◽  
Vol 22 (6) ◽  
pp. 657 ◽  
Author(s):  
Maria Delgado-Ortet ◽  
Angel Molina ◽  
Santiago Alférez ◽  
José Rodellar ◽  
Anna Merino
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Graphic Processing Unit ◽  
Healthcare Providers ◽  
Digital Pathology ◽  
Processing Unit ◽  
Protozoan Parasites ◽  
Genus Plasmodium ◽  
Global Accuracy ◽  
Species Specific

Malaria is an endemic life-threating disease caused by the unicellular protozoan parasites of the genus Plasmodium. Confirming the presence of parasites early in all malaria cases ensures species-specific antimalarial treatment, reducing the mortality rate, and points to other illnesses in negative cases. However, the gold standard remains the light microscopy of May-Grünwald–Giemsa (MGG)-stained thin and thick peripheral blood (PB) films. This is a time-consuming procedure, dependent on a pathologist’s skills, meaning that healthcare providers may encounter difficulty in diagnosing malaria in places where it is not endemic. This work presents a novel three-stage pipeline to (1) segment erythrocytes, (2) crop and mask them, and (3) classify them into malaria infected or not. The first and third steps involved the design, training, validation and testing of a Segmentation Neural Network and a Convolutional Neural Network from scratch using a Graphic Processing Unit. Segmentation achieved a global accuracy of 93.72% over the test set and the specificity for malaria detection in red blood cells (RBCs) was 87.04%. This work shows the potential that deep learning has in the digital pathology field and opens the way for future improvements, as well as for broadening the use of the created networks.

scholarly journals Quantitative Assessment of the Effects of Compression on Deep Learning in Digital Pathology Image Analysis

2020 ◽  
pp. 221-233
Author(s):  
Yijiang Chen ◽  
Andrew Janowczyk ◽  
Anant Madabhushi
Keyword(s):  
Deep Learning ◽  
Image Compression ◽  
Operating Characteristic ◽  
Performance Metrics ◽  
Signal To Noise Ratio ◽  
Characteristic Curve ◽  
Digital Pathology ◽  
Jpeg2000 Compression ◽  
Classifier Performance ◽  
Pathology Image

PURPOSE Deep learning (DL), a class of approaches involving self-learned discriminative features, is increasingly being applied to digital pathology (DP) images for tasks such as disease identification and segmentation of tissue primitives (eg, nuclei, glands, lymphocytes). One application of DP is in telepathology, which involves digitally transmitting DP slides over the Internet for secondary diagnosis by an expert at a remote location. Unfortunately, the places benefiting most from telepathology often have poor Internet quality, resulting in prohibitive transmission times of DP images. Image compression may help, but the degree to which image compression affects performance of DL algorithms has been largely unexplored. METHODS We investigated the effects of image compression on the performance of DL strategies in the context of 3 representative use cases involving segmentation of nuclei (n = 137), segmentation of lymph node metastasis (n = 380), and lymphocyte detection (n = 100). For each use case, test images at various levels of compression (JPEG compression quality score ranging from 1-100 and JPEG2000 compression peak signal-to-noise ratio ranging from 18-100 dB) were evaluated by a DL classifier. Performance metrics including F1 score and area under the receiver operating characteristic curve were computed at the various compression levels. RESULTS Our results suggest that DP images can be compressed by 85% while still maintaining the performance of the DL algorithms at 95% of what is achievable without any compression. Interestingly, the maximum compression level sustainable by DL algorithms is similar to where pathologists also reported difficulties in providing accurate interpretations. CONCLUSION Our findings seem to suggest that in low-resource settings, DP images can be significantly compressed before transmission for DL-based telepathology applications.

Deep Multi-Instance Multi-Label Learning for Image Annotation

2017 ◽  
Vol 32 (03) ◽  
pp. 1859005 ◽  
Author(s):  
Hai-Feng Guo ◽  
Lixin Han ◽  
Shoubao Su ◽  
Zhou-Bao Sun
Keyword(s):  
Neural Network ◽  
Social Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Real World ◽  
Supervised Classification ◽  
Image Annotation ◽  
Learning Framework ◽  
Recent Advancement ◽  
Real World Datasets

Multi-Instance Multi-Label learning (MIML) is a popular framework for supervised classification where an example is described by multiple instances and associated with multiple labels. Previous MIML approaches have focused on predicting labels for instances. The idea of tackling the problem is to identify its equivalence in the traditional supervised learning framework. Motivated by the recent advancement in deep learning, in this paper, we still consider the problem of predicting labels and attempt to model deep learning in MIML learning framework. The proposed approach enables us to train deep convolutional neural network with images from social networks where images are well labeled, even labeled with several labels or uncorrelated labels. Experiments on real-world datasets demonstrate the effectiveness of our proposed approach.

Sign in / Sign up

Export Citation Format

Share Document