scholarly journals A Generic Neural Network Approach to Infer Segmenting Classifiers for Disease-Associated Regions in Medical Images

2020 ◽  
Author(s):  
David Schuhmacher ◽  
Klaus Gerwert ◽  
Axel Mosig
Keyword(s):  
Neural Network ◽  
Medical Images ◽  
Digital Pathology ◽  
Training Data ◽  
Learning Approaches ◽  
Label Free ◽  
Network Approach ◽  
Neural Network Approach ◽  
Data Set ◽  
Microscopic Images

AbstractIn many settings in digital pathology or radiology, it is of predominant importance to train classifiers that can segment disease-associated regions in medical images. While numerous deep learning approaches, most notably U-Nets, exist to learn segmentations, these approaches typically require reference segmentations as training data. As a consequence, obtaining pixel level annotations of histopathological samples has become a major bottleneck to establish segmentation learning approaches. Our contribution introduces a neural network approach to avoid the annotation bottleneck in the first place: our approach requires two-class labels such as cancer vs. healthy at the sample level only. Using these sample-labels, a meta-network is trained that infers a segmenting neural network which will segment the disease-associated region (e.g. tumor) that is present in the cancer samples, but not in the healthy samples. This process results in a network, e.g. a U-Net, that can segment tumor regions in arbitrary further samples of the same type.We establish and validate our approach in the context of digital label-free pathology, where hyperspectral infrared microscopy is used to segment and characterize the disease status of histopathological samples. Trained on a data set comprising infrared microscopic images of 100 tissue microarray spots labelled as either cancerous or cancer-free, the approach yields a U-Net that reliably identifies tumor regions or the absence of tumor in an independent test set involving 40 samples.While our present work is focused on training a U-Net for infrared microscopic images, the approach is generic in the sense that it can be adapted to other image modalities and essentially arbitrary segmenting network topologies.

THE STAG OIL FIELD FORMATION EVALUATION: A NEURAL NETWORK APPROACH

1999 ◽  
Vol 39 (1) ◽  
pp. 451 ◽  
Author(s):  
H. Crocker ◽  
C.C. Fung ◽  
K.W. Wong
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Oil Field ◽  
Training Data ◽  
Ann Model ◽  
Neural Network Approach ◽  
Data Set ◽  
Formation Evaluation ◽  
Core Data

The producing M. australis Sandstone of the Stag Oil Field is a bioturbated glauconitic sandstone that is difficult to evaluate using conventional methods. Well log and core data are available for the Stag Field and for the nearby Centaur–1 well. Eight wells have log data; six also have core data.In the past few years artificial intelligence has been applied to formation evaluation. In particular, artificial neural networks (ANN) used to match log and core data have been studied. The ANN approach has been used to analyse the producing Stag Field sands. In this paper, new ways of applying the ANN are reported. Results from simple ANN approach are unsatisfactory. An integrated ANN approach comprising the unsupervised Self-Organising Map (SOM) and the Supervised Back Propagation Neural Network (BPNN) appears to give a more reasonable analysis.In this case study the mineralogical and petrophysical characteristics of a cored well are predicted from the 'training' data set of the other cored wells in the field. The prediction from the ANN model is then used for comparison with the known core data. In this manner, the accuracy of the prediction is determined and a prediction qualifier computed.This new approach to formation evaluation should provide a match between log and core data that may be used to predict the characteristics of a similar uncored interval. Although the results for the Stag Field are satisfactory, further study applying the method to other fields is required.

scholarly journals AN INTELLIGENT DENGUE HEMORRHAGIC FEVER SEVERITY LEVEL DETECTION BASED ON DEEP NEURAL NETWORK APPROACH

2019 ◽  
Vol 12 (2) ◽  
pp. 57
Author(s):  
Dian Pratiwi ◽  
Gatot Budi Santoso ◽  
Leni Muslimah ◽  
Raden Davin Rizki
Keyword(s):  
Neural Network ◽  
Dengue Hemorrhagic Fever ◽  
Deep Neural Network ◽  
Hemorrhagic Fever ◽  
Training Data ◽  
Network Approach ◽  
Neural Network Approach ◽  
Severity Level ◽  
Fully Connected ◽  
Learning Data

Dengue hemorrhagic fever is one of the most dangerous diseases which often leads to death for the sufferer due to delays or improper handling of the severity that has occurred. In determining that severity level, a specialist analyzes it from the symptoms and blood testing results. This research was developed to produce a system by applying Deep Neural Network approach that is able to give the same analytical ability as a doctor, so that it can give fast and precise decision of dengue handling. The research stages consisted of normalizing data to 0 – 1 intervals by Min-Max method, training data into multilayer networks with fully connected and partially connected schemes to produce the best weights, validating data and final testing. From the use of network parameters as much as 10 input units, 1 bias, 2 hidden layers, 2 output units, learning rate of 0.3, epoch 1000, tolerance rate 0.02, threshold 0.5, the system succeeded in generating a maximum accuracy of 95% in data learning (60 data), 87.5% on data learning and non-learning (40 data), 85% on non-learning data (20 data).

Automatic detection of volcanic eruptions in Doppler radar observations using a neural network approach

2020 ◽  
Author(s):  
Matthias Hort ◽  
Daniel Uhle ◽  
Fabio Venegas ◽  
Lea Scharff ◽  
Jan Walda ◽  
...  
Keyword(s):  
Neural Network ◽  
Doppler Radar ◽  
Volcanic Eruptions ◽  
Radar Data ◽  
Visual Observation ◽  
Data Sets ◽  
Network Approach ◽  
Neural Network Approach ◽  
Data Set ◽  
The Impact

<p>Immediate detection of volcanic eruptions is essential when trying to mitigate the impact on the health of people living in the vicinity of a volcano or the impact on infrastructure and aviation. Eruption detection is most often done by either visual observation or the analysis of acoustic data. While visual observation is often difficult due to environmental conditions, infrasound data usually provide the onset of an event. Doppler radar data, admittedly not available for a lot of volcanoes, however, provide information on the dynamics of the eruption and the amount of material released. Eruptions can be easily detected in the data by visual analysis and here we present a neural network approach for the automatic detection of eruptions in Doppler radar data. We use data recorded at Colima volcano in Mexico in 2014/2015 and a data set recorded at Turrialba volcano between 2017 and 2019. In a first step we picked eruptions, rain and typical noise in both data sets, which were the used for training two networks (training data set) and testing the performance of the network using a separate test data set. The accuracy for classifying the different type of signals was between 95 and 98% for both data sets, which we consider quite successful. In case of the Turriabla data set eruptions were picked based on observations of OVSICORI data. When classifying the complete data set we have from Turriabla using the trained network, an additional 40 eruptions were found, which were not in the OVSICORI catalogue.</p><p>In most cases data from the instruments are transmitted to an observatory by radio, so the amount of data available is an issue. We therefore tested by what amount the data could be reduced to still be able to successfully detect an eruption. We also kept the network as small as possible to ideally run it on a small computer (e.g. a Rasberry Pi architecture) for eruption detection on site, so only the information that an eruption is detected needs to be transmitted.</p>

Extraction of features from medical images using a modular neural network approach that relies on learning by sample

2000 ◽  
Author(s):  
Djamel Brahmi ◽  
Camille Serruys ◽  
Nathalie Cassoux ◽  
Alain Giron ◽  
Raoul Triller ◽  
...  
Keyword(s):  
Neural Network ◽  
Medical Images ◽  
Network Approach ◽  
Neural Network Approach ◽  
Modular Neural Network

scholarly journals Biodiversity Image Quality Metadata Augments Convolutional Neural Network Classification of Fish Species

2021 ◽  
Author(s):  
Jeremy Leipzig ◽  
Yasin Bakis ◽  
Xiaojun Wang ◽  
Mohannad Elhamod ◽  
Kelly Diamond ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Quality ◽  
Convolutional Neural Network ◽  
Training Data ◽  
Biological Research ◽  
Small Subset ◽  
Learning Approaches ◽  
Species Classification ◽  
Neural Network Approach

AbstractBiodiversity image repositories are crucial sources of training data for machine learning approaches to biological research. Metadata, specifically metadata about object quality, is putatively an important prerequisite to selecting sample subsets for these experiments. This study demonstrates the importance of image quality metadata to a species classification experiment involving a corpus of 1935 fish specimen images which were annotated with 22 metadata quality properties. A small subset of high quality images produced an F1 accuracy of 0.41 compared to 0.35 for a taxonomically matched subset of low quality images when used by a convolutional neural network approach to species identification. Using the full corpus of images revealed that image quality differed between correctly classified and misclassified images. We found the visibility of all anatomical features was the most important quality feature for classification accuracy. We suggest biodiversity image repositories consider adopting a minimal set of image quality metadata to support future machine learning projects.

A Neural Network Approach to the Prediction of Pure Tone Thresholds with Distortion Product Emissions

1994 ◽  
Vol 73 (11) ◽  
pp. 812-823 ◽  
Author(s):  
Barry P. Kimberley ◽  
Brent M. Kimberley Leah Roth
Keyword(s):  
Neural Network ◽  
Hearing Impairment ◽  
Prediction Accuracy ◽  
Pure Tone ◽  
Correct Classification ◽  
Network Approach ◽  
Neural Network Approach ◽  
Data Set ◽  
Distortion Product

Distortion Product Emission (DPE) growth functions, demographic data, and pure tone thresholds were recorded in 229 normal-hearing and hearing-impaired ears. Half of the data set (115 ears) was used to train a set of neural networks to map DPE and demographic features to pure tone thresholds at six frequencies in the audiometric range. The six networks developed from this training process were then used to predict pure tone thresholds in the remaining 114-ear data set. When normal pure tone threshold was defined as a threshold less than 20 dB HL, frequency-specific prediction accuracy varied from 57% (correct classification of hearing impairment at 1025 Hz) to 100% (correct classification of hearing impairment at 2050 Hz). Overall prediction accuracy was 90% for impaired pure tone thresholds and 80% for normal pure tone thresholds. This neural network approach was found to be more accurate than discriminant analysis in the prediction of pure tone thresholds. It is concluded that a general strategy exists whereby DPE measures can accurately categorize pure tone thresholds as normal or impaired in large populations of ears with purely cochlear hearing dysfunction.

Sign in / Sign up

Export Citation Format

Share Document