DeepMed: A unified, modular pipeline for end-to-end deep learning in computational pathology

The interpretation of digitized histopathology images has been transformed thanks to artificial intelligence (AI). End-to-end AI algorithms can infer high-level features directly from raw image data, extending the capabilities of human experts. In particular, AI can predict tumor subtypes, genetic mutations and gene expression directly from hematoxylin and eosin (H&E) stained pathology slides. However, existing end-to-end AI workflows are poorly standardized and not easily adaptable to new tasks. Here, we introduce DeepMed, a Python library for predicting any high-level attribute directly from histopathological whole slide images alone, or from images coupled with additional meta-data (https://github.com/KatherLab/deepmed). Unlike earlier computational pipelines, DeepMed is highly developer-friendly: its structure is modular and separates preprocessing, training, deployment, statistics, and visualization in such a way that any one of these processes can be altered without affecting the others. Also, DeepMed scales easily from local use on laptop computers to multi-GPU clusters in cloud computing services and therefore can be used for teaching, prototyping and for large-scale applications. Finally, DeepMed is user-friendly and allows researchers to easily test multiple hypotheses in a single dataset (via cross-validation) or in multiple datasets (via external validation). Here, we demonstrate and document DeepMed's abilities to predict molecular alterations, histopathological subtypes and molecular features from routine histopathology images, using a large benchmark dataset which we release publicly. In summary, DeepMed is a fully integrated and broadly applicable end-to-end AI pipeline for the biomedical research community.

Download Full-text

Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis

Cancers ◽

10.3390/cancers13112606 ◽

2021 ◽

Vol 13 (11) ◽

pp. 2606

Author(s):

Evi J. van Kempen ◽

Max Post ◽

Manoj Mannil ◽

Benno Kusters ◽

Mark ter Laan ◽

...

Keyword(s):

Machine Learning ◽

Large Scale ◽

Meta Analysis ◽

Learning Algorithms ◽

External Validation ◽

Machine Learning Algorithms ◽

Molecular Characteristics ◽

Aggregated Data ◽

Molecular Features

Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.

Download Full-text

Federated Learning and Differential Privacy for Medical Image Analysis

10.21203/rs.3.rs-1005694/v1 ◽

2021 ◽

Author(s):

Mohammed Adnan ◽

Shivam Kalra ◽

Jesse C. Cresswell ◽

Graham W. Taylor ◽

Hamid Tizhoosh

Keyword(s):

Machine Learning ◽

Image Analysis ◽

Medical Image ◽

Large Scale ◽

Differential Privacy ◽

Medical Image Analysis ◽

External Validation ◽

The Cancer Genome Atlas ◽

Distributed Training ◽

Histopathology Images

Abstract The artificial intelligence revolution has been spurred forward by the availability of large-scale datasets. In contrast, the paucity of large-scale medical datasets hinders the application of machine learning in healthcare. The lack of publicly available multi-centric and diverse datasets mainly stems from confidentiality and privacy concerns around sharing medical data. To demonstrate a feasible path forward in medical image imaging, we conduct a case study of applying a differentially private federated learning framework for analysis of histopathology images, the largest and perhaps most complex medical images. We study the effects of IID and non-IID distributions along with the number of healthcare providers, i.e., hospitals and clinics, and the individual dataset sizes, using The Cancer Genome Atlas (TCGA) dataset, a public repository, to simulate a distributed environment. We empirically compare the performance of private, distributed training to conventional training and demonstrate that distributed training can achieve similar performance with strong privacy guarantees. We also study the effect of different source domains for histopathology images by evaluating the performance using external validation. Our work indicates that differentially private federated learning is a viable and reliable framework for the collaborative development of machine learning models in medical image analysis.

Download Full-text

Social inequality in the evolution of human societies

Sociology: Theory, Methods, Marketing ◽

10.15407/sociology2019.02.098 ◽

2019 ◽

pp. 98-120

Author(s):

Georgi Derluguian

Keyword(s):

Social Inequality ◽

Large Scale ◽

Human Beings ◽

Mass Violence ◽

Public And Private ◽

Tangible Assets ◽

Transition To Agriculture ◽

New Institutions ◽

High Level ◽

Political Economic

The author develops ideas about the origin of social inequality during the evolution of human societies and reflects on the possibilities of its overcoming. What makes human beings different from other primates is a high level of egalitarianism and altruism, which contributed to more successful adaptability of human collectives at early stages of the development of society. The transition to agriculture, coupled with substantially increasing population density, was marked by the emergence and institutionalisation of social inequality based on the inequality of tangible assets and symbolic wealth. Then, new institutions of warfare came into existence, and they were aimed at conquering and enslaving the neighbours engaged in productive labour. While exercising control over nature, people also established and strengthened their power over other people. Chiefdom as a new type of polity came into being. Elementary forms of power (political, economic and ideological) served as a basis for the formation of early states. The societies in those states were characterised by social inequality and cruelties, including slavery, mass violence and numerous victims. Nowadays, the old elementary forms of power that are inherent in personalistic chiefdom are still functioning along with modern institutions of public and private bureaucracy. This constitutes the key contradiction of our time, which is the juxtaposition of individual despotic power and public infrastructural one. However, society is evolving towards an ever more efficient combination of social initiatives with the sustainability and viability of large-scale organisations.

Download Full-text

Phoneme-to-Grapheme Conversion Based Large-Scale Pre-Training for End-to-End Automatic Speech Recognition

10.21437/interspeech.2020-1930 ◽

2020 ◽

Author(s):

Ryo Masumura ◽

Naoki Makishima ◽

Mana Ihori ◽

Akihiko Takashima ◽

Tomohiro Tanaka ◽

...

Keyword(s):

Speech Recognition ◽

Automatic Speech Recognition ◽

Large Scale ◽

End To End

Download Full-text

Large-Scale Road Network Congestion Pattern Analysis and Prediction Using Deep Convolutional Autoencoder

Sustainability ◽

10.3390/su13095108 ◽

2021 ◽

Vol 13 (9) ◽

pp. 5108

Author(s):

Navin Ranjan ◽

Sovit Bhandari ◽

Pervez Khan ◽

Youn-Sik Hong ◽

Hoon Kim

Keyword(s):

Traffic Congestion ◽

Network Architecture ◽

Road Network ◽

Large Scale ◽

Pattern Analysis ◽

Image Data ◽

Urban Life ◽

Prediction Algorithm ◽

Rapid Urbanization ◽

Convolutional Autoencoder

The transportation system, especially the road network, is the backbone of any modern economy. However, with rapid urbanization, the congestion level has surged drastically, causing a direct effect on the quality of urban life, the environment, and the economy. In this paper, we propose (i) an inexpensive and efficient Traffic Congestion Pattern Analysis algorithm based on Image Processing, which identifies the group of roads in a network that suffers from reoccurring congestion; (ii) deep neural network architecture, formed from Convolutional Autoencoder, which learns both spatial and temporal relationships from the sequence of image data to predict the city-wide grid congestion index. Our experiment shows that both algorithms are efficient because the pattern analysis is based on the basic operations of arithmetic, whereas the prediction algorithm outperforms two other deep neural networks (Convolutional Recurrent Autoencoder and ConvLSTM) in terms of large-scale traffic network prediction performance. A case study was conducted on the dataset from Seoul city.

Download Full-text

NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

Applied Sciences ◽

10.3390/app11104426 ◽

2021 ◽

Vol 11 (10) ◽

pp. 4426

Author(s):

Chunyan Ma ◽

Ji Fan ◽

Jinghao Yao ◽

Tao Zhang

Keyword(s):

Action Recognition ◽

Large Scale ◽

Short Term Memory ◽

Evaluation Criteria ◽

Image Data ◽

Basketball Player ◽

Basketball Players ◽

Convolutional Network ◽

Atomic Actions ◽

New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

Download Full-text

Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

Applied Sciences ◽

10.3390/app11156975 ◽

2021 ◽

Vol 11 (15) ◽

pp. 6975

Author(s):

Tao Zhang ◽

Lun He ◽

Xudong Li ◽

Guoqing Feng

Keyword(s):

Performance Improvement ◽

State Of The Art ◽

Error Rates ◽

Convolutional Network ◽

Convolutional Networks ◽

Sentence Level ◽

End To End ◽

High Level ◽

Improved Accuracy ◽

Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

Download Full-text

Symmetry perception with spiking neural networks

Scientific Reports ◽

10.1038/s41598-021-85232-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Jonathan K. George ◽

Cesare Soci ◽

Mario Miscuglio ◽

Volker J. Sorger

Keyword(s):

Neural Networks ◽

Mirror Symmetry ◽

Satellite Image ◽

Image Data ◽

Coincidence Detection ◽

Spiking Neural Networks ◽

Feed Forward Neural Network ◽

Neuromorphic Computing ◽

Symmetry Perception ◽

High Level

AbstractMirror symmetry is an abundant feature in both nature and technology. Its successful detection is critical for perception procedures based on visual stimuli and requires organizational processes. Neuromorphic computing, utilizing brain-mimicked networks, could be a technology-solution providing such perceptual organization functionality, and furthermore has made tremendous advances in computing efficiency by applying a spiking model of information. Spiking models inherently maximize efficiency in noisy environments by placing the energy of the signal in a minimal time. However, many neuromorphic computing models ignore time delay between nodes, choosing instead to approximate connections between neurons as instantaneous weighting. With this assumption, many complex time interactions of spiking neurons are lost. Here, we show that the coincidence detection property of a spiking-based feed-forward neural network enables mirror symmetry. Testing this algorithm exemplary on geospatial satellite image data sets reveals how symmetry density enables automated recognition of man-made structures over vegetation. We further demonstrate that the addition of noise improves feature detectability of an image through coincidence point generation. The ability to obtain mirror symmetry from spiking neural networks can be a powerful tool for applications in image-based rendering, computer graphics, robotics, photo interpretation, image retrieval, video analysis and annotation, multi-media and may help accelerating the brain-machine interconnection. More importantly it enables a technology pathway in bridging the gap between the low-level incoming sensor stimuli and high-level interpretation of these inputs as recognized objects and scenes in the world.

Download Full-text

Arabidopsis Genes Essential for Seedling Viability: Isolation of Insertional Mutants and Molecular Cloning

Genetics ◽

10.1093/genetics/159.4.1765 ◽

2001 ◽

Vol 159 (4) ◽

pp. 1765-1778

Author(s):

Gregory J Budziszewski ◽

Sharon Potter Lewis ◽

Lyn Wegrich Glover ◽

Jennifer Reineke ◽

Gary Jones ◽

...

Keyword(s):

Large Scale ◽

Protein Translocation ◽

Gene Families ◽

Mutant Phenotype ◽

Lethal Mutant ◽

A Genome ◽

Genes Encoding ◽

High Level ◽

Mutant Lines ◽

Genome Scale

Abstract We have undertaken a large-scale genetic screen to identify genes with a seedling-lethal mutant phenotype. From screening ~38,000 insertional mutant lines, we identified >500 seedling-lethal mutants, completed cosegregation analysis of the insertion and the lethal phenotype for >200 mutants, molecularly characterized 54 mutants, and provided a detailed description for 22 of them. Most of the seedling-lethal mutants seem to affect chloroplast function because they display altered pigmentation and affect genes encoding proteins predicted to have chloroplast localization. Although a high level of functional redundancy in Arabidopsis might be expected because 65% of genes are members of gene families, we found that 41% of the essential genes found in this study are members of Arabidopsis gene families. In addition, we isolated several interesting classes of mutants and genes. We found three mutants in the recently discovered nonmevalonate isoprenoid biosynthetic pathway and mutants disrupting genes similar to Tic40 and tatC, which are likely to be involved in chloroplast protein translocation. Finally, we directly compared T-DNA and Ac/Ds transposon mutagenesis methods in Arabidopsis on a genome scale. In each population, we found only about one-third of the insertion mutations cosegregated with a mutant phenotype.

Download Full-text

New Harvesting and Curing Techniques in the Production of Breeder's Seed Peanuts1

Peanut Science ◽

10.3146/i0095-3679-6-2-1 ◽

1979 ◽

Vol 6 (2) ◽

pp. 70-72

Author(s):

T. A. Coffelt ◽

F. S. Wright ◽

J. L. Steele

Keyword(s):

Large Scale ◽

Combine Method ◽

Frost Damage ◽

New Method ◽

Experimental Equipment ◽

Harvesting Method ◽

Curing Methods ◽

Labor Requirements ◽

High Level ◽

Varietal Purity

Abstract A new method of harvesting and curing breeder's seed peanuts in Virginia was initiated that would 1) reduce the labor requirements, 2) maintain a high level of germination, 3) maintain varietal purity at 100%, and 4) reduce the risk of frost damage. Three possible harvesting and curing methods were studied. The traditional stack-pole method satisfied the latter 3 objectives, but not the first. The windrow-combine method satisfied the first 2 objectives, but not the last 2. The direct harvesting method satisfied all four objectives. The experimental equipment and curing procedures for direct harvesting had been developed but not tested on a large scale for seed harvesting. This method has been used in Virginia to produce breeder's seed of 3 peanut varieties (Florigiant, VA 72R and VA 61R) during five years. Compared to the stackpole method, labor requirements have been reduced, satisfactory levels of germination and varietal purity have been obtained, and the risk of frost damage has been minimized.

Download Full-text