scholarly journals A deep learning-based model of normal histology

2019 ◽  
Author(s):  
Tobias Sing ◽  
Holger Hoefling ◽  
Imtiaz Hossain ◽  
Julie Boisclair ◽  
Arno Doelemeyer ◽  
...  
Keyword(s):  
Deep Learning ◽  
Rat Tissues ◽  
Learning Models ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Scientific Disciplines ◽  
The Individual ◽  
Rat Tissue ◽  
Human Primate ◽  
Abnormal Tissue

AbstractDeep learning models have been applied on various tissues in order to recognize malignancies. However, these models focus on relatively narrow tissue context or well-defined pathologies. Here, instead of focusing on pathologies, we introduce models characterizing the diversity of normal tissues. We obtained 1,690 slides with rat tissue samples from the control groups of six preclinical toxicology studies, on which tissue regions were outlined and annotated by pathologists into 46 different tissue classes. From these annotated regions, we sampled small patches of 224 × 224 pixels at six different levels of magnification. Using four studies as training set and two studies as test set, we trained VGG-16, ResNet-50, and Inception-v3 networks separately at each of these magnification levels. Among these models, Inception-v3 consistently outperformed the other networks and attained accuracies up to 83.4% (top-3 accuracy: 96.3%). Further analysis showed that most tissue confusions occurred within clusters of histologically similar tissues. Investigation of the embedding layer using the UMAP method revealed not only pronounced clusters corresponding to the individual tissues, but also subclusters corresponding to histologically meaningful structures that had neither been annotated nor trained for. This suggests that the histological representation learned by the normal histology network could also be used to flag abnormal tissue as outliers in the embedding space without a need to explicitly train for specific types of abnormalities. Finally, we found that models trained on rat tissues can be used on non-human primate and minipig tissues with minimal retraining.Author contributionT.S. and H.H. contributed equally to this work.Significance statementLike many other scientific disciplines, histopathology has been profoundly impacted by recent advances in machine learning with deep neural networks. In this field, most deep learning models reported in the literature are trained on pathologies in specific tissues/contexts. Here, we aim to establish a model of normal tissues as a foundation for future models of histopathology. We build models that are specific to histopathology images and we show that their embeddings are better feature vectors for describing the underlying images than those of off-the shelf CNN models. Therefore, our models could be useful for transfer learning to improve the accuracy of other histopathology models.

HistoNet: A Deep Learning-Based Model of Normal Histology

2021 ◽  
pp. 019262332199342
Author(s):  
Holger Hoefling ◽  
Tobias Sing ◽  
Imtiaz Hossain ◽  
Julie Boisclair ◽  
Arno Doelemeyer ◽  
...  
Keyword(s):  
Normal Tissue ◽  
Machine Learning Algorithms ◽  
Rat Tissues ◽  
Training Set ◽  
Tissue Samples ◽  
The Individual ◽  
Rat Tissue ◽  
Different Levels ◽  
Magnification Level ◽  
Human Primate

We introduce HistoNet, a deep neural network trained on normal tissue. On 1690 slides with rat tissue samples from 6 preclinical toxicology studies, tissue regions were outlined and annotated by pathologists into 46 different tissue classes. From these annotated regions, we sampled small 224 × 224 pixels images (patches) at 6 different levels of magnification. Using 4 studies as training set and 2 studies as test set, we trained VGG-16, ResNet-50, and Inception-v3 networks separately at each magnification level. Among these model architectures, Inception-v3 and ResNet-50 outperformed VGG-16. Inception-v3 identified the tissue from query images, with an accuracy up to 83.4%. Most misclassifications occurred between histologically similar tissues. Investigation of the features learned by the model (embedding layer) using Uniform Manifold Approximation and Projection revealed not only coherent clusters associated with the individual tissues but also subclusters corresponding to histologically meaningful structures that had not been annotated or trained for. This suggests that the histological representation learned by HistoNet could be useful as the basis of other machine learning algorithms and data mining. Finally, we found that models trained on rat tissues can be used on non-human primate and minipig tissues with minimal retraining.

scholarly journals Generalization of spatio-temporal deep learning for vision-based force estimation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Finn Behrendt ◽  
Nils Gessert ◽  
Alexander Schlaefer
Keyword(s):  
Deep Learning ◽  
Force Feedback ◽  
Haptic Feedback ◽  
Absolute Error ◽  
Estimation Methods ◽  
Temporal Data ◽  
Learning Models ◽  
Force Estimation ◽  
Tissue Samples ◽  
Spatio Temporal

AbstractRobot-assisted minimally-invasive surgery is increasingly used in clinical practice. Force feedback offers potential to develop haptic feedback for surgery systems. Forces can be estimated in a vision-based way by capturing deformation observed in 2D-image sequences with deep learning models. Variations in tissue appearance and mechanical properties likely influence force estimation methods’ generalization. In this work, we study the generalization capabilities of different spatial and spatio-temporal deep learning methods across different tissue samples. We acquire several data-sets using a clinical laparoscope and use both purely spatial and also spatio-temporal deep learning models. The results of this work show that generalization across different tissues is challenging. Nevertheless, we demonstrate that using spatio-temporal data instead of individual frames is valuable for force estimation. In particular, processing spatial and temporal data separately by a combination of a ResNet and GRU architecture shows promising results with a mean absolute error of 15.450 compared to 19.744 mN of a purely spatial CNN.

Systematic Review on Human Gait Analysis using Deep Learning Models

2021 ◽  
pp. 09-22
Author(s):  
Piyush Kumar Shukla ◽  
◽  
Prashant Kumar Shukla ◽  
Keyword(s):  
Deep Learning ◽  
Gait Analysis ◽  
Gait Recognition ◽  
The Body ◽  
Human Gait ◽  
Learning Models ◽  
Gait Patterns ◽  
Learning Techniques ◽  
The Individual ◽  
Human Gait Analysis

Human Gait is known as a behavioral characteristic of humans, compared with the other biometrics gait is found to be a difficult process to conceal. Human gait analysis is usually done by extracting the features from the body. Analysis of gait involves evaluating the individual by means of kinematic analysis while walking along a surface. The main objective and the purpose of gait recognition is to give the best method where risks are recognized in places where there is a need for high security in any public place and to detect diseases like Parkinson’s. In order to acquire a normal person’s identification and validation performance, various Deep Learning techniques are totally studied and modeled the biometrics of gait which is based on walking data. It is reviewed that among various essential metrics that are used, deep learning convolution neural networks are typically better Machine Learning models. The main objective of the present study was to examine in detail individual gait patterns. Finally, this paper recommends deep learning methods and suggests the directions for future gait analysis and also for its applications.

Tissue metabolic changes for effects of pirfenidone in rats of acute paraquat poisoning by GC-MS

2017 ◽  
Vol 33 (12) ◽  
pp. 887-900 ◽  
Author(s):  
Jianshe Ma ◽  
Fa Sun ◽  
Bingbao Chen ◽  
Xiaoting Tu ◽  
Xiufa Peng ◽  
...  
Keyword(s):  
Treatment Group ◽  
Gas Chromatography Mass Spectrometry ◽  
Control Group ◽  
Rat Tissues ◽  
Tissue Samples ◽  
Metabolic Alterations ◽  
Treatment Groups ◽  
Liver And Kidney ◽  
Rat Tissue ◽  
And Control

We developed a metabolomic method to evaluate the effect of pirfenidone on rats with acute paraquat (PQ) poisoning, through the analysis of various tissues (lung, liver, kidney, and heart), by gas chromatography–mass spectrometry (GC-MS). Thirty-eight rats were randomly divided into a control group, an acute PQ (20 mg kg−1) poisoning group, a pirfenidone (20 mg kg−1) treatment group, and a pirfenidone (40 mg kg−1) treatment group. Partial least squares-discriminate analysis (PLS-DA) revealed metabolic alterations in rat tissue samples from the two pirfenidone treatment groups after acute PQ poisoning. The PLS-DA 3D score chart showed that the rats in the acute PQ poisoning group were clearly distinguished from the rats in the control group. Also, the two pirfenidone treatment groups were distinguished from the acute PQ poisoning group and control group. Additionally, the pirfenidone (40 mg kg−1) treatment group was separated farther than the pirfenidone (20 mg kg−1) treatment group from the acute PQ poisoning group. Evaluation of the pathological changes in the rat tissues revealed that treatment with pirfenidone appeared to decrease pulmonary fibrosis in the acute PQ poisoning rats. The results indicate that pirfenidone induced beneficial metabolic alterations in the tissues of rats with acute PQ poisoning. Rats with acute PQ poisoning exhibited a certain reduction in biochemical indicators after treatment with pirfenidone, indicating that pirfenidone could protect liver and kidney function. Accordingly, the developed metabolomic approach proved to be useful to elucidate the effect of pirfenidone in rats of acute PQ poisoning.

scholarly journals Structural changes of tissue samples exposed to low frequency electromagnetic field: A FT-IR absorbance study

2004 ◽  
Vol 18 (4) ◽  
pp. 513-518 ◽  
Author(s):  
V. Crupi ◽  
S. Interdonato ◽  
D. Majolino ◽  
M. R. Mondello ◽  
S. Pergolizzi ◽  
...  
Keyword(s):  
Morphological Analysis ◽  
Structural Changes ◽  
Low Frequency ◽  
Rat Tissues ◽  
Spectral Features ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Ft Ir ◽  
Wavenumber Region ◽  
Absorbance Spectra

In the present work, we report on a preliminary Fourier Transform Infrared (FT-IR) Absorbance study performed on different kind of rat tissues, such as kidney and heart, exposed to a “non-ionizing” radiation source at low frequency, in the range typical of micro-waves (300 MHz <v< 300 GHz). The data were collected in a wide wavenumber region, from 400 cm−1to 4000 cm−1. The comparison of the absorbance spectra in the case of the normal tissues with the irradiated ones has shown significant differences in the spectral features in accordance with the morphological analysis performed by the optical microscopy.

scholarly journals Selecting precise reference normal tissue samples for cancer research using a deep learning approach

2018 ◽  
Author(s):  
William Zeng ◽  
Benjamin S. Glicksberg ◽  
Yangyan Li ◽  
Bin Chen
Keyword(s):  
Cancer Research ◽  
Deep Learning ◽  
Normal Tissue ◽  
Principal Component ◽  
Tissue Type ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Tissue Of Origin ◽  
Disease Signature ◽  
Disease Signatures

AbstractBackgroundNormal tissue samples are often employed as a control for understanding disease mechanisms, however, collecting matched normal tissues from patients is difficult in many instances. In cancer research, for example, the open cancer resources such as TCGA and TARGET do not provide matched tissue samples for every cancer or cancer subtype. The recent GTEx project has profiled samples from healthy individuals, providing an excellent resource for this field, yet the feasibility of using GTEx samples as the reference remains unanswered.MethodsWe analyze RNA-Seq data processed from the same computational pipeline and systematically evaluate GTEx as a potential reference resource. We use those cancers that have adjacent normal tissues in TCGA as a benchmark for the evaluation. To correlate tumor samples and normal samples, we explore top varying genes, reduced features from principal component analysis, and encoded features from an autoencoder neural network. We first evaluate whether these methods can identify the correct tissue of origin from GTEx for a given cancer and then seek to answer whether disease expression signatures are consistent between those derived from TCGA and from GTEx.ResultsAmong 32 TCGA cancers, 18 cancers have less than 10 matched adjacent normal tissue samples. Among three methods, autoencoder performed the best in predicting tissue of origin, with 12 of 14 cancers correctly predicted. The reason for misclassification of two cancers is that none of normal samples from GTEx correlate well with any tumor samples in these cancers. This suggests that GTEx has matched tissues for the majority cancers, but not all. While using autoencoder to select proper normal samples for disease signature creation, we found that disease signatures derived from normal samples selected via an autoencoder from GTEx are consistent with those derived from adjacent samples from TCGA in many cases. Interestingly, choosing top 50 mostly correlated samples regardless of tissue type performed reasonably well or even better in some cancers.ConclusionsOur findings demonstrate that samples from GTEx can serve as reference normal samples for cancers, especially those do not have available adjacent tissue samples. A deep-learning based approach holds promise to select proper normal samples.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Improving the Accuracy of Protein-Ligand Binding Affinity Prediction by Deep Learning Models: Benchmark and Model

2019 ◽  
Author(s):  
Mohammad Rezaei ◽  
Yanjun Li ◽  
Xiaolin Li ◽  
Chenglong Li
Keyword(s):  
Deep Learning ◽  
Drug Design ◽  
Binding Affinity ◽  
Benchmark Dataset ◽  
Rational Drug Design ◽  
Learning Models ◽  
Structure Based Drug Design ◽  
Binding Affinity Prediction ◽  
Affinity Prediction ◽  
Rational Drug

<b>Introduction:</b> The ability to discriminate among ligands binding to the same protein target in terms of their relative binding affinity lies at the heart of structure-based drug design. Any improvement in the accuracy and reliability of binding affinity prediction methods decreases the discrepancy between experimental and computational results.<br><b>Objectives:</b> The primary objectives were to find the most relevant features affecting binding affinity prediction, least use of manual feature engineering, and improving the reliability of binding affinity prediction using efficient deep learning models by tuning the model hyperparameters.<br><b>Methods:</b> The binding site of target proteins was represented as a grid box around their bound ligand. Both binary and distance-dependent occupancies were examined for how an atom affects its neighbor voxels in this grid. A combination of different features including ANOLEA, ligand elements, and Arpeggio atom types were used to represent the input. An efficient convolutional neural network (CNN) architecture, DeepAtom, was developed, trained and tested on the PDBbind v2016 dataset. Additionally an extended benchmark dataset was compiled to train and evaluate the models.<br><b>Results: </b>The best DeepAtom model showed an improved accuracy in the binding affinity prediction on PDBbind core subset (Pearson’s R=0.83) and is better than the recent state-of-the-art models in this field. In addition when the DeepAtom model was trained on our proposed benchmark dataset, it yields higher correlation compared to the baseline which confirms the value of our model.<br><b>Conclusions:</b> The promising results for the predicted binding affinities is expected to pave the way for embedding deep learning models in virtual screening and rational drug design fields.

Data science in economics: comprehensive review of advanced machine learning and deep learning methods

2020 ◽  
Author(s):  
Saeed Nosratabadi ◽  
Amir Mosavi ◽  
Puhong Duan ◽  
Pedram Ghamisi ◽  
Ferdinand Filip ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Science ◽  
State Of The Art ◽  
Science Methods ◽  
Learning Models ◽  
Diverse Range ◽  
Hybrid Machine ◽  
Economics Research

This paper provides a state-of-the-art investigation of advances in data science in emerging economic applications. The analysis was performed on novel data science methods in four individual classes of deep learning models, hybrid deep learning models, hybrid machine learning, and ensemble models. Application domains include a wide and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency. Prisma method, a systematic literature review methodology, was used to ensure the quality of the survey. The findings reveal that the trends follow the advancement of hybrid models, which, based on the accuracy metric, outperform other learning algorithms. It is further expected that the trends will converge toward the advancements of sophisticated hybrid deep learning models.

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

Sign in / Sign up

Export Citation Format

Share Document