Development of a Machine learning image segmentation-based algorithm for the determination of the adequacy of Gram-stained sputum smear images

AbstractMachine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.

Download Full-text

Efficiency of Machine Learning Algorithms for the Determination of Macrovesicular Steatosis in Frozen Sections Stained with Sudan to Evaluate the Quality of the Graft in Liver Transplantation

Sensors ◽

10.3390/s21061993 ◽

2021 ◽

Vol 21 (6) ◽

pp. 1993

Author(s):

Fernando Pérez-Sanz ◽

Miriam Riquelme-Pérez ◽

Enrique Martínez-Barba ◽

Jesús de la Peña-Moral ◽

Alejandro Salazar Nicolás ◽

...

Keyword(s):

Machine Learning ◽

Liver Transplantation ◽

Learning Algorithms ◽

Selection Procedure ◽

Machine Learning Algorithms ◽

Liver Biopsies ◽

Convenient Technique ◽

End Stage ◽

Macrovesicular Steatosis

Liver transplantation is the only curative treatment option in patients diagnosed with end-stage liver disease. The low availability of organs demands an accurate selection procedure based on histological analysis, in order to evaluate the allograft. This assessment, traditionally carried out by a pathologist, is not exempt from subjectivity. In this sense, new tools based on machine learning and artificial vision are continuously being developed for the analysis of medical images of different typologies. Accordingly, in this work, we develop a computer vision-based application for the fast and automatic objective quantification of macrovesicular steatosis in histopathological liver section slides stained with Sudan stain. For this purpose, digital microscopy images were used to obtain thousands of feature vectors based on the RGB and CIE L*a*b* pixel values. These vectors, under a supervised process, were labelled as fat vacuole or non-fat vacuole, and a set of classifiers based on different algorithms were trained, accordingly. The results obtained showed an overall high accuracy for all classifiers (>0.99) with a sensitivity between 0.844 and 1, together with a specificity >0.99. In relation to their speed when classifying images, KNN and Naïve Bayes were substantially faster than other classification algorithms. Sudan stain is a convenient technique for evaluating ME in pre-transplant liver biopsies, providing reliable contrast and facilitating fast and accurate quantification through the machine learning algorithms tested.

Download Full-text

Using machine learning to automate image segmentation for analysis of in vitro osteoclast formation and bone resorption

Bone Reports ◽

10.1016/j.bonr.2021.100865 ◽

2021 ◽

Vol 14 ◽

pp. 100865

Author(s):

B.K. Davies ◽

Andrew Hibbert ◽

Mark Hopkinson ◽

Gill Holdsworth ◽

Isabel Orriss

Keyword(s):

Machine Learning ◽

Image Segmentation ◽

Bone Resorption ◽

Osteoclast Formation

Download Full-text

Determination of Body Parts in Holstein Friesian Cows Comparing Neural Networks and k Nearest Neighbour Classification

Animals ◽

10.3390/ani11010050 ◽

2020 ◽

Vol 11 (1) ◽

pp. 50

Author(s):

Jennifer Salau ◽

Jan Henning Haas ◽

Wolfgang Junge ◽

Georg Thaller

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Body Parts ◽

Nearest Neighbour ◽

Data Set ◽

3D Data ◽

Holstein Friesian ◽

Knn Classification ◽

Friesian Cows

Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is still a widely studied topic and especially challenging when it comes to the partition of objects into predefined segments. In this study, two machine learning approaches were utilized for the recognition of body parts of dairy cows from 3D point clouds, i.e., sets of data points in space. The low cost off-the-shelf depth sensor Microsoft Kinect V1 has been used in various studies related to dairy cows. The 3D data were gathered from a multi-Kinect recording unit which was designed to record Holstein Friesian cows from both sides in free walking from three different camera positions. For the determination of the body parts head, rump, back, legs and udder, five properties of the pixels in the depth maps (row index, column index, depth value, variance, mean curvature) were used as features in the training data set. For each camera positions, a k nearest neighbour classifier and a neural network were trained and compared afterwards. Both methods showed small Hamming losses (between 0.007 and 0.027 for k nearest neighbour (kNN) classification and between 0.045 and 0.079 for neural networks) and could be considered successful regarding the classification of pixel to body parts. However, the kNN classifier was superior, reaching overall accuracies 0.888 to 0.976 varying with the camera position. Precision and recall values associated with individual body parts ranged from 0.84 to 1 and from 0.83 to 1, respectively. Once trained, kNN classification is at runtime prone to higher costs in terms of computational time and memory compared to the neural networks. The cost vs. accuracy ratio for each methodology needs to be taken into account in the decision of which method should be implemented in the application.

Download Full-text

Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations

Energies ◽

10.3390/en14040930 ◽

2021 ◽

Vol 14 (4) ◽

pp. 930

Author(s):

Fahimeh Hadavimoghaddam ◽

Mehdi Ostadhassan ◽

Ehsan Heidaryan ◽

Mohammad Ali Sadri ◽

Inna Chapanova ◽

...

Keyword(s):

Machine Learning ◽

Viscosity Data ◽

Oil Viscosity ◽

Pvt Data ◽

Proposed Model ◽

Wide Range ◽

Engineering Problems ◽

Functional Forms ◽

Insight Into

Dead oil viscosity is a critical parameter to solve numerous reservoir engineering problems and one of the most unreliable properties to predict with classical black oil correlations. Determination of dead oil viscosity by experiments is expensive and time-consuming, which means developing an accurate and quick prediction model is required. This paper implements six machine learning models: random forest (RF), lightgbm, XGBoost, multilayer perceptron (MLP) neural network, stochastic real-valued (SRV) and SuperLearner to predict dead oil viscosity. More than 2000 pressure–volume–temperature (PVT) data were used for developing and testing these models. A huge range of viscosity data were used, from light intermediate to heavy oil. In this study, we give insight into the performance of different functional forms that have been used in the literature to formulate dead oil viscosity. The results show that the functional form f(γAPI,T), has the best performance, and additional correlating parameters might be unnecessary. Furthermore, SuperLearner outperformed other machine learning (ML) algorithms as well as common correlations that are based on the metric analysis. The SuperLearner model can potentially replace the empirical models for viscosity predictions on a wide range of viscosities (any oil type). Ultimately, the proposed model is capable of simulating the true physical trend of the dead oil viscosity with variations of oil API gravity, temperature and shear rate.

Download Full-text

Determination of thermodynamic state variables of liquids from its microscopic structure using an artificial neural network

Soft Matter ◽

10.1039/d0sm02127j ◽

2020 ◽

Author(s):

Ulices Que-Salinas ◽

Pedro Ezequiel Ramirez-Gonzalez ◽

Alexis Torres-Carbajal

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Distribution Function ◽

Microscopic Structure ◽

Machine Learning Method ◽

Learning Method ◽

State Variables ◽

Thermodynamic State

In this work we implement a machine learning method to predict the thermodynamic state of a liquid using only its microscopic structure provided by the radial distribution function (RDF). The...

Download Full-text

A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia

Sensors ◽

10.3390/s19224893 ◽

2019 ◽

Vol 19 (22) ◽

pp. 4893 ◽

Cited By ~ 22

Author(s):

Hejar Shahabi ◽

Ben Jarihani ◽

Sepideh Tavakkoli Piralilou ◽

David Chittleborough ◽

Mohammadtaghi Avand ◽

...

Keyword(s):

Machine Learning ◽

Image Segmentation ◽

Vegetation Index ◽

Scale Parameter ◽

Slope Aspect ◽

Support Vector ◽

Topographic Wetness Index ◽

Slope Length ◽

Optimal Scale ◽

Object Based

Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks.

Download Full-text