scholarly journals Effectiveness of Learning Systems from Common Image File Types to Detect Osteosarcoma Based on Convolutional Neural Networks (CNNs) Models

2021 ◽  
Vol 8 (1) ◽  
pp. 2
Author(s):  
Chanunya Loraksa ◽  
Sirima Mongkolsomlit ◽  
Nitikarn Nimsuk ◽  
Meenut Uscharapong ◽  
Piya Kiatisevi

Osteosarcoma is a rare bone cancer which is more common in children than in adults and has a high chance of metastasizing to the patient’s lungs. Due to initiated cases, it is difficult to diagnose and hard to detect the nodule in a lung at the early state. Convolutional Neural Networks (CNNs) are effectively applied for early state detection by considering CT-scanned images. Transferring patients from small hospitals to the cancer specialized hospital, Lerdsin Hospital, poses difficulties in information sharing because of the privacy and safety regulations. CD-ROM media was allowed for transferring patients’ data to Lerdsin Hospital. Digital Imaging and Communications in Medicine (DICOM) files cannot be stored on a CD-ROM. DICOM must be converted into other common image formats, such as BMP, JPG and PNG formats. Quality of images can affect the accuracy of the CNN models. In this research, the effect of different image formats is studied and experimented. Three popular medical CNN models, VGG-16, ResNet-50 and MobileNet-V2, are considered and used for osteosarcoma detection. The positive and negative class images are corrected from Lerdsin Hospital, and 80% of all images are used as a training dataset, while the rest are used to validate the trained models. Limited training images are simulated by reducing images in the training dataset. Each model is trained and validated by three different image formats, resulting in 54 testing cases. F1-Score and accuracy are calculated and compared for the models’ performance. VGG-16 is the most robust of all the formats. PNG format is the most preferred image format, followed by BMP and JPG formats, respectively.

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Gustaf Halvardsson ◽  
Johanna Peterson ◽  
César Soto-Valero ◽  
Benoit Baudry

AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.


The vehicle classification and detecting its license plate are important tasks in intelligent security and transportation systems. However, theexisting methods of vehicle classification and detection are highly complex which provides coarse-grained outcomesbecause of underfitting or overfitting of the model. Due toadvanced accomplishmentsof the Deep Learning, it was efficiently implemented to image classification and detection of objects. This proposed paper come up with a new approach which makes use of convolutional neural networks concept in Deep Learning.It consists of two steps: i) vehicle classification ii) vehicle license plate recognition. Numerous classicmodules of neural networks hadbeen implemented in training and testing the vehicle classification and detection of license plate model, such as CNN (convolutional neural networks), TensorFlow, and Tesseract-OCR. The suggestedtechnique candetermine the vehicle type, number plate and other alternative dataeffectively. This model provides security and log details regarding vehicles by using AI Surveillance. It guides the surveillance operators and assists human resources. With the help of the original dataset (training) and enriched dataset (testing), this customized model(algorithm) can achieve best outcomewith a standard accuracy of around 97.32% inclassification and detection of vehicles. By enlarging the quantity of the training dataset, the loss function and mislearning rate declines progressively. Therefore, this proposedmodelwhich uses DeepLearning hadbetterperformance and flexibility. When compared to outstandingtechniques in the strategicImage datasets, this deep learning modelscan gethigher competitor outcomes. Eventually, the proposed system suggests modern methods for advancementof the customized model and forecasts the progressivegrowth of deep learningperformance in the explorationof artificial intelligence (AI) &machine learning (ML) techniques.


2019 ◽  
Vol 11 (21) ◽  
pp. 2585 ◽  
Author(s):  
Michael Fromm ◽  
Matthias Schubert ◽  
Guillermo Castilla ◽  
Julia Linke ◽  
Greg McDermid

Monitoring tree regeneration in forest areas disturbed by resource extraction is a requirement for sustainably managing the boreal forest of Alberta, Canada. Small remotely piloted aircraft systems (sRPAS, a.k.a. drones) have the potential to decrease the cost of field surveys drastically, but produce large quantities of data that will require specialized processing techniques. In this study, we explored the possibility of using convolutional neural networks (CNNs) on this data for automatically detecting conifer seedlings along recovering seismic lines: a common legacy footprint from oil and gas exploration. We assessed three different CNN architectures, of which faster region-CNN (R-CNN) performed best (mean average precision 81%). Furthermore, we evaluated the effects of training-set size, season, seedling size, and spatial resolution on the detection performance. Our results indicate that drone imagery analyzed by artificial intelligence can be used to detect conifer seedling in regenerating sites with high accuracy, which increases with the size in pixels of the seedlings. By using a pre-trained network, the size of the training dataset can be reduced to a couple hundred seedlings without any significant loss of accuracy. Furthermore, we show that combining data from different seasons yields the best results. The proposed method is a first step towards automated monitoring of forest restoration/regeneration.


2019 ◽  
Vol 10 (1) ◽  
pp. 41
Author(s):  
Yuchen Xin ◽  
Hon-Cheng Wong ◽  
Sio-Long Lo ◽  
Junliang Li

Anime-style comics are popular world-wide and an important industry in Asia. However, the output quantity and quality control of art workers have become the biggest obstacle to industrialization, and it is time consuming to produce new manga without the help of an intelligence assisted tool. As deep learning techniques have achieved great successes in different areas, it is worth exploring them to develop algorithms and systems for computational manga. Extracting line drawings from finished illustrations is one of the main tasks in drawing a manuscript and also a crucial task in the common painting process. However, traditional filters such as Sobel, Laplace, and Canny cannot output good results and require manual adjustments of the parameters. In order to address these problems, in this paper, we propose progressive full data convolutional neural networks for extracting lines from anime-style illustrations. Experimental results show that our progressive full data convolutional neural networks not only can learn as much as processing methods for the detailed regions, but also can accomplish the target extraction work with only a small training dataset.


In the proposed paper we introduce a new Pashtu numerals dataset having handwritten scanned images. We make the dataset publically available for scientific and research use. Pashtu language is used by more than fifty million people both for oral and written communication, but still no efforts are devoted to the Optical Character Recognition (OCR) system for Pashtu language. We introduce a new method for handwritten numerals recognition of Pashtu language through the deep learning based models. We use convolutional neural networks (CNNs) both for features extraction and classification tasks. We assess the performance of the proposed CNNs based model and obtained recognition accuracy of 91.45%.


Author(s):  
Glen Williams ◽  
Nicholas A. Meisel ◽  
Timothy W. Simpson ◽  
Christopher McComb

Abstract The widespread growth of additive manufacturing, a field with a complex informatic “digital thread”, has helped fuel the creation of design repositories, where multiple users can upload distribute, and download a variety of candidate designs for a variety of situations. Additionally, advancements in additive manufacturing process development, design frameworks, and simulation are increasing what is possible to fabricate with AM, further growing the richness of such repositories. Machine learning offers new opportunities to combine these design repository components’ rich geometric data with their associated process and performance data to train predictive models capable of automatically assessing build metrics related to AM part manufacturability. Although design repositories that can be used to train these machine learning constructs are expanding, our understanding of what makes a particular design repository useful as a machine learning training dataset is minimal. In this study we use a metamodel to predict the extent to which individual design repositories can train accurate convolutional neural networks. To facilitate the creation and refinement of this metamodel, we constructed a large artificial design repository, and subsequently split it into sub-repositories. We then analyzed metadata regarding the size, complexity, and diversity of the sub-repositories for use as independent variables predicting accuracy and the required training computational effort for training convolutional neural networks. The networks each predict one of three additive manufacturing build metrics: (1) part mass, (2) support material mass, and (3) build time. Our results suggest that metamodels predicting the convolutional neural network coefficient of determination, as opposed to computational effort, were most accurate. Moreover, the size of a design repository, the average complexity of its constituent designs, and the average and spread of design spatial diversity were the best predictors of convolutional neural network accuracy.


2019 ◽  
Vol 24 (3-4) ◽  
pp. 107-113
Author(s):  
Kondratiuk S.S. ◽  

The technology, which is implemented with cross platform tools, is proposed for modeling of gesture units of sign language, animation between states of gesture units with a combination of gestures (words). Implemented technology simulates sequence of gestures using virtual spatial hand model and performs recognition of dactyl items from camera input using trained on collected training dataset set convolutional neural network. With the cross platform means technology achieves the ability to run on multiple platforms without re-implementing for each platform


2019 ◽  
Vol 24 (1-2) ◽  
pp. 94-100
Author(s):  
Kondratiuk S.S. ◽  

The technology, which is implemented with cross platform tools, is proposed for modeling of gesture units of sign language, animation between states of gesture units with a combination of gestures (words). Implemented technology simulates sequence of gestures using virtual spatial hand model and performs recognition of dactyl items from camera input using trained on collected training dataset set convolutional neural network, based on the MobileNetv3 architecture, and with the optimal configuration of layers and network parameters. On the collected test dataset accuracy of over 98% is achieved.


PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0242013
Author(s):  
Hongyu Wang ◽  
Hong Gu ◽  
Pan Qin ◽  
Jia Wang

Background Pneumothorax can lead to a life-threatening emergency. The experienced radiologists can offer precise diagnosis according to the chest radiographs. The localization of the pneumothorax lesions will help to quickly diagnose, which will be benefit for the patients in the underdevelopment areas lack of the experienced radiologists. In recent years, with the development of large neural network architectures and medical imaging datasets, deep learning methods have become a methodology of choice for analyzing medical images. The objective of this study was to the construct convolutional neural networks to localize the pneumothorax lesions in chest radiographs. Methods and findings We developed a convolutional neural network, called CheXLocNet, for the segmentation of pneumothorax lesions. The SIIM-ACR Pneumothorax Segmentation dataset was used to train and validate CheXLocNets. The training dataset contained 2079 radiographs with the annotated lesion areas. We trained six CheXLocNets with various hyperparameters. Another 300 annotated radiographs were used to select parameters of these CheXLocNets as the validation set. We determined the optimal parameters by the AP50 (average precision at the intersection over union (IoU) equal to 0.50), a segmentation evaluation metric used by several well-known competitions. Then CheXLocNets were evaluated by a test set (1082 normal radiographs and 290 disease radiographs), based on the classification metrics: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV); segmentation metrics: IoU and Dice score. For the classification, CheXLocNet with best sensitivity produced an AUC of 0.87, sensitivity of 0.78 (95% CI 0.73-0.83), and specificity of 0.78 (95% CI 0.76-0.81). CheXLocNet with best specificity produced an AUC of 0.79, sensitivity of 0.46 (95% CI 0.40-0.52), and specificity of 0.92 (95% CI 0.90-0.94). For the segmentation, CheXLocNet with best sensitivity produced an IoU of 0.69 and Dice score of 0.72. CheXLocNet with best specificity produced an IoU of 0.77 and Dice score of 0.79. We combined them to form an ensemble CheXLocNet. The ensemble CheXLocNet produced an IoU of 0.81 and Dice score of 0.82. Our CheXLocNet succeeded in automatically detecting pneumothorax lesions, without any human guidance. Conclusions In this study, we proposed a deep learning network, called, CheXLocNet, for the automatic segmentation of chest radiographs to detect pneumothorax. Our CheXLocNets generated accurate classification results and high-quality segmentation masks for the pneumothorax at the same time. This technology has the potential to improve healthcare delivery and increase access to chest radiograph expertise for the detection of diseases. Furthermore, the segmentation results can offer comprehensive geometric information of lesions, which can benefit monitoring the sequential development of lesions with high accuracy. Thus, CheXLocNets can be further extended to be a reliable clinical decision support tool. Although we used transfer learning in training CheXLocNet, the parameters of CheXLocNet was still large for the radiograph dataset. Further work is necessary to prune CheXLocNet suitable for the radiograph dataset.


Author(s):  
Monika Stipsitz ◽  
Hèlios Sanchis-Alepuz

Thermal simulations are an important part in the design of electronic systems, especially as systems with high power density become common. In simulation-based design approaches, a considerable amount of time is spent by repeated simulations. In this work, we present a proof-of-concept study of the application of convolutional neural networks to accelerate those thermal simulations. The goal is not to replace standard simulation tools but to provide a method to quickly select promising samples for more detailed investigations. Based on a training set of randomly generated circuits with corresponding Finite Element solutions, the full 3D steady-state temperature field is estimated using a fully convolutional neural network. A custom network architecture is proposed which captures the long-range correlations present in heat conduction problems. We test the network on a separate dataset and find that the mean relative error is around 2 % and the typical evaluation time is 35 ms per sample ( 2 ms for evaluation, 33 ms for data transfer). The benefit of this neural-network-based approach is that, once training is completed, the network can be applied to any system within the design space spanned by the randomised training dataset (which includes different components, material properties, different positioning of components on a PCB, etc.).


Sign in / Sign up

Export Citation Format

Share Document