Semantic segmentation in crystal growth process using fake micrograph machine learning
Ontology highlight
ABSTRACT:
SUBMITTER: Ishiyama T
PROVIDER: S-EPMC11339331 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Purpose/aimThis paper provides a pedagogical example for systematic machine learning optimization in small dataset image segmentation, emphasizing hyperparameter selections. A simple process is presented for medical physicists to examine hyperparameter optimization. This is also applied to a case-study, demonstrating the benefit of the method.Materials and methodsAn unrestricted public Computed Tomography (CT) dataset, with binary organ segmentation, was used to develop a multiclass segmentation model. To start the optimization process, a preliminary manual search of hyperparameters was conducted and from there a grid search identified the most influential result metrics. A total of 658 different models were trained in 2100 h, using 13 160 effective patients. The quantity of results was analyzed using random forest regression, identifying relative hyperparameter impact.ResultsMetric implied segmentation quality (accuracy 96.8%, precision 95.1%) and visual inspection were found to be mismatched. In this work batch normalization was most important, but performance varied with hyperparameters and metrics selected. Targeted grid-search optimization and random forest analysis of relative hyperparameter importance, was an easily implementable sensitivity analysis approach.ConclusionThe proposed optimization method gives a systematic and quantitative approach to something intuitively understood, that hyperparameters change model performance. Even just grid search optimization with random forest analysis presented here can be informative within hardware and data quality/availability limitations, adding confidence to model validity and minimize decision-making risks. By providing a guided methodology, this work helps medical physicists to improve their model optimization, irrespective of specific challenges posed by datasets and model design.
| S-EPMC11633816 | biostudies-literature
Project description:With the rise of social media, the dissemination of forged content and news has been on the rise. Consequently, fake news detection has emerged as an important research problem. Several approaches have been presented to discriminate fake news from real news, however, such approaches lack robustness for multi-domain datasets, especially within the context of Urdu news. In addition, some studies use machine-translated datasets using English to Urdu Google translator and manual verification is not carried out. This limits the wide use of such approaches for real-world applications. This study investigates these issues and proposes fake news classier for Urdu news. The dataset has been collected covering nine different domains and constitutes 4097 news. Experiments are performed using the term frequency-inverse document frequency (TF-IDF) and a bag of words (BoW) with the combination of n-grams. The major contribution of this study is the use of feature stacking, where feature vectors of preprocessed text and verbs extracted from the preprocessed text are combined. Support vector machine, k-nearest neighbor, and ensemble models like random forest (RF) and extra tree (ET) were used for bagging while stacking was applied with ET and RF as base learners with logistic regression as the meta learner. To check the robustness of models, fivefold and independent set testing were employed. Experimental results indicate that stacking achieves 93.39%, 88.96%, 96.33%, 86.2%, and 93.17% scores for accuracy, specificity, sensitivity, MCC, ROC, and F1 score, respectively.
| S-EPMC10280395 | biostudies-literature
Project description:Urban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.
| S-EPMC8319419 | biostudies-literature
Project description:Background/aimsPrevious artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy.MethodsInvestigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values.ResultsFrom the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively.ConclusionThe bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.
| S-EPMC9178134 | biostudies-literature
Project description:Convolutional neural network (CNN)-based deep learning (DL) methods have transformed the analysis of geospatial, Earth observation, and geophysical data due to their ability to model spatial context information at multiple scales. Such methods are especially applicable to pixel-level classification or semantic segmentation tasks. A variety of R packages have been developed for processing and analyzing geospatial data. However, there are currently no packages available for implementing geospatial DL in the R language and data science environment. This paper introduces the geodl R package, which supports pixel-level classification applied to a wide range of geospatial or Earth science data that can be represented as multidimensional arrays where each channel or band holds a predictor variable. geodl is built on the torch package, which supports the implementation of DL using the R and C++ languages without the need for installing a Python/PyTorch environment. This greatly simplifies the software environment needed to implement DL in R. Using geodl, geospatial raster-based data with varying numbers of bands, spatial resolutions, and coordinate reference systems are read and processed using the terra package, which makes use of C++ and allows for processing raster grids that are too large to fit into memory. Training loops are implemented with the luz package. The geodl package provides utility functions for creating raster masks or labels from vector-based geospatial data and image chips and associated masks from larger files and extents. It also defines a torch dataset subclass for geospatial data for use with torch dataloaders. UNet-based models are provided with a variety of optional ancillary modules or modifications. Common assessment metrics (i.e., overall accuracy, class-level recalls or producer's accuracies, class-level precisions or user's accuracies, and class-level F1-scores) are implemented along with a modified version of the unified focal loss framework, which allows for defining a variety of loss metrics using one consistent implementation and set of hyperparameters. Users can assess models using standard geospatial and remote sensing metrics and methods and use trained models to predict to large spatial extents. This paper introduces the geodl workflow, design philosophy, and goals for future development.
| S-EPMC11620637 | biostudies-literature
Project description:Golf swing segmentation with inertial measurement units (IMUs) is an essential process for swing analysis using wearables. However, no attempt has been made to apply machine learning models to estimate and divide golf swing phases. In this study, we proposed and verified two methods using machine learning models to segment the full golf swing into five major phases, including before and after the swing, from every single IMU attached to a body part. Proposed bidirectional long short-term memory-based and convolutional neural network-based methods rely on characteristics that automatically learn time-series features, including sequential body motion during a golf swing. Nine professional and eleven skilled male golfers participated in the experiment to collect swing data for training and verifying the methods. We verified the proposed methods using leave-one-out cross-validation. The results revealed average segmentation errors of 5-92 ms from each IMU attached to the head, wrist, and waist, accurate compared to the heuristic method in this study. In addition, both proposed methods could segment all the swing phases using only the acceleration data, bringing advantage in terms of power consumption. This implies that swing-segmentation methods using machine learning could be applied to various motion-analysis environments by dividing motion phases with less restriction on IMU placement.
| S-EPMC7472298 | biostudies-literature
Project description:Program code has recently become a valuable active data source for training various data science models, from code classification to controlled code synthesis. Annotating code snippets play an essential role in such tasks. This article presents a novel approach that leverages CodeBERT, a powerful transformer-based model, to classify code snippets extracted from Code4ML automatically. Code4ML is a comprehensive machine learning code corpus compiled from Kaggle, a renowned data science competition platform. The corpus includes code snippets and information about the respective kernels and competitions, but it is limited in the quality of the tagged data, which is ~0.2%. Our method addresses the lack of labeled snippets for supervised model training by exploiting the internal ambiguity in particular labeled snippets where multiple class labels are combined. Using a specially designed algorithm, we effectively separate these ambiguous fragments, thereby expanding the pool of training data. This data augmentation approach greatly increases the amount of labeled data and improves the overall quality of the trained models. The experimental results demonstrate the prowess of the proposed code classifier, achieving an impressive F1 test score of ~89%. This achievement not only enhances the practicality of CodeBERT for classifying code snippets but also highlights the importance of enriching large-scale annotated machine learning code datasets such as Code4ML. With a significant increase in accurately annotated code snippets, Code4ML is becoming an even more valuable resource for learning and improving various data processing models.
| S-EPMC10703005 | biostudies-literature
Project description:We present an algorithm for the per-voxel semantic segmentation of a three-dimensional volume. At the core of our algorithm is a novel "pyramid context" feature, a descriptive representation designed such that exact per-voxel linear classification can be made extremely efficient. This feature not only allows for efficient semantic segmentation but enables other aspects of our algorithm, such as novel learned features and a stacked architecture that can reason about self-consistency. We demonstrate our technique on 3D fluorescence microscopy data of Drosophila embryos for which we are able to produce extremely accurate semantic segmentations in a matter of minutes, and for which other algorithms fail due to the size and high-dimensionality of the data, or due to the difficulty of the task.
| S-EPMC4445881 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:The process of crystallization is often understood in terms of the fundamental microstructural elements of the crystallite being formed, such as surface orientation or the presence of defects. Considerably less is known about the role of the liquid structure on the kinetics of crystal growth. Here atomistic simulations and machine learning methods are employed together to demonstrate that the liquid adjacent to solid-liquid interfaces presents significant structural ordering, which effectively reduces the mobility of atoms and slows down the crystallization kinetics. Through detailed studies of silicon and copper we discover that the extent to which liquid mobility is affected by interface-induced ordering (IIO) varies greatly with the degree of ordering and nature of the adjacent interface. Physical mechanisms behind the IIO anisotropy are explained and it is demonstrated that incorporation of this effect on a physically-motivated crystal growth model enables the quantitative prediction of the growth rate temperature dependence.
| S-EPMC7319977 | biostudies-literature