scholarly journals An Explainable Convolutional Neural Networks for Automatic Segmentation of the Left Ventricle in Cardiac MRI

2021 ◽  
Author(s):  
Jun Liu ◽  
Feng Deng ◽  
Geng Yuan ◽  
Xue Lin ◽  
Houbing Song ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Left Ventricle ◽  
Convolutional Neural Networks ◽  
Cardiac Mri ◽  
Large Scale ◽  
Data Science ◽  
Training System ◽  
Data Sets

Recently, the study on model interpretability has become a hot topic in deep learning research area. Especially in the field of medical imaging, the requirements for safety are extremely high; Moreover, it is very important for the model to be able to explain. However, the existing solutions for left ventricular segmentation by convolutional neural networks are black boxes; explainable CNNs remains a challenge; explainable deep learning models has always been a task often overlooked in the entire data science lifecycle by data scientists or deep learning engineers. Because of very limited medical imaging data, most solutions currently use transfer learning methods to transfer the model which used on large-scale benchmark data sets (such as ImageNet) to fine tune medical imaging models. Consequently, a large amount of useless parameters are generated, resulting in further barrier for the model to provide a convincing explanation. This paper presents a novel method to automatically segment the Left Ventricle in Cardiac MRI by explainable convolutional neural networks with optimized size and parameters by our enhanced Deep Learning GPU Training System. It is very suitable for deployment on mobile devices. We simplify deep learning tasks on DIGITS systems, monitoring performance, and displaying the heat map of each layer of the network with advanced visualizations in real time. Our experiment results demonstrated that the proposed method is feasible and efficient.

scholarly journals MS2CNN: predicting MS/MS spectrum based on protein sequence using deep convolutional neural networks

BMC Genomics ◽  
2019 ◽  
Vol 20 (S9) ◽  
Author(s):  
Yang-Ming Lin ◽  
Ching-Tai Chen ◽  
Jia-Ming Chang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Learning Algorithm ◽  
Pearson Correlation ◽  
Tandem Mass ◽  
Spectral Library ◽  
Deep Convolutional Neural Networks ◽  
Library Search

Abstract Background Tandem mass spectrometry allows biologists to identify and quantify protein samples in the form of digested peptide sequences. When performing peptide identification, spectral library search is more sensitive than traditional database search but is limited to peptides that have been previously identified. An accurate tandem mass spectrum prediction tool is thus crucial in expanding the peptide space and increasing the coverage of spectral library search. Results We propose MS2CNN, a non-linear regression model based on deep convolutional neural networks, a deep learning algorithm. The features for our model are amino acid composition, predicted secondary structure, and physical-chemical features such as isoelectric point, aromaticity, helicity, hydrophobicity, and basicity. MS2CNN was trained with five-fold cross validation on a three-way data split on the large-scale human HCD MS2 dataset of Orbitrap LC-MS/MS downloaded from the National Institute of Standards and Technology. It was then evaluated on a publicly available independent test dataset of human HeLa cell lysate from LC-MS experiments. On average, our model shows better cosine similarity and Pearson correlation coefficient (0.690 and 0.632) than MS2PIP (0.647 and 0.601) and is comparable with pDeep (0.692 and 0.642). Notably, for the more complex MS2 spectra of 3+ peptides, MS2PIP is significantly better than both MS2PIP and pDeep. Conclusions We showed that MS2CNN outperforms MS2PIP for 2+ and 3+ peptides and pDeep for 3+ peptides. This implies that MS2CNN, the proposed convolutional neural network model, generates highly accurate MS2 spectra for LC-MS/MS experiments using Orbitrap machines, which can be of great help in protein and peptide identifications. The results suggest that incorporating more data for deep learning model may improve performance.

Left ventricle segmentation in cardiac MRI images using fully convolutional neural networks

2017 ◽  
Author(s):  
Liset Vázquez Romaguera ◽  
Marly Guimarães Fernandes Costa ◽  
Francisco Perdigón Romero ◽  
Cicero Ferreira Fernandes Costa Filho
Keyword(s):  
Neural Networks ◽  
Left Ventricle ◽  
Convolutional Neural Networks ◽  
Cardiac Mri ◽  
Fully Convolutional Neural Networks ◽  
Ventricle Segmentation

scholarly journals Application of Artificial Intelligence in Medical Imaging Diagnosis

2020 ◽  
Vol 9 (1) ◽  
pp. 5
Author(s):  
Linyi Zhang
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Image Segmentation ◽  
Deep Learning ◽  
Medical Imaging ◽  
Accurate Diagnosis ◽  
Data Sets ◽  
Special Role ◽  
Imaging Diagnosis ◽  
Learning Data

Both the treatment of cancer and other serious diseases often depends on the diagnosis of artificial complexity and heavy experience. The introduction of artificial intelligence in medical imaging has injected vitality into the diagnosis of images. Artificial intelligence uses deep learning, image segmentation, neural networks and other algorithms flexibly in image recognition through learning data sets to extract features for accurate diagnosis of clinical diseases. At the same time, it also plays a special role in controlling the spread of infectious diseases such as new coronary pneumonia.

scholarly journals Convolutional Neural Networks(CNN) based Eye-Gaze Tracking System using Machine Learning Algorithm

2021 ◽  
Vol 5 (2) ◽  
pp. 36-40
Author(s):  
Prakash Kanade ◽  
Fortune David ◽  
Sunay Kanade
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
User Interfaces ◽  
Data Science ◽  
Learning Algorithm ◽  
Tracking System ◽  
Eye Gaze ◽  
Classification Systems ◽  
Gaze Tracking

To avoid the rising number of car crash deaths, which are mostly caused by drivers' inattentiveness, a paradigm shift is expected. The knowledge of a driver's look area may provide useful details about his or her point of attention. Cars with accurate and low-cost gaze classification systems can increase driver safety. When drivers shift their eyes without turning their heads to look at objects, the margin of error in gaze detection increases. For new consumer electronic applications such as driver tracking systems and novel user interfaces, accurate and effective eye gaze prediction is critical. Such systems must be able to run efficiently in difficult, unconstrained conditions while using reduced power and expense. A deep learning-based gaze estimation technique has been considered to solve this issue, with an emphasis on WSN based Convolutional Neural Networks (CNN) based system. The proposed study proposes the following architecture, which is focused on data science: The first is a novel neural network model that is programmed to manipulate any possible visual feature, such as the states of both eyes and head location, as well as many augmentations; the second is a data fusion approach that incorporates several gaze datasets. However, due to different factors such as environment light shifts, reflections on glasses surface, and motion and optical blurring of the captured eye signal, the accuracy of detecting and classifying the pupil centre and corneal reflection centre depends on a car environment. This work also includes pre-trained models, network structures, and datasets for designing and developing CNN-based deep learning models for Eye-Gaze Tracking and Classification.

scholarly journals Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6936
Author(s):  
Remis Balaniuk ◽  
Olga Isupova ◽  
Steven Reece
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Satellite Imagery ◽  
Large Scale ◽  
Data Science ◽  
Social Impact ◽  
New Technologies ◽  
Google Earth ◽  
Illegal Mining ◽  
Tailings Dams

This work explores the combination of free cloud computing, free open-source software, and deep learning methods to analyze a real, large-scale problem: the automatic country-wide identification and classification of surface mines and mining tailings dams in Brazil. Locations of officially registered mines and dams were obtained from the Brazilian government open data resource. Multispectral Sentinel-2 satellite imagery, obtained and processed at the Google Earth Engine platform, was used to train and test deep neural networks using the TensorFlow 2 application programming interface (API) and Google Colaboratory (Colab) platform. Fully convolutional neural networks were used in an innovative way to search for unregistered ore mines and tailing dams in large areas of the Brazilian territory. The efficacy of the approach is demonstrated by the discovery of 263 mines that do not have an official mining concession. This exploratory work highlights the potential of a set of new technologies, freely available, for the construction of low cost data science tools that have high social impact. At the same time, it discusses and seeks to suggest practical solutions for the complex and serious problem of illegal mining and the proliferation of tailings dams, which pose high risks to the population and the environment, especially in developing countries.

scholarly journals GeoBoost: An Incremental Deep Learning Approach toward Global Mapping of Buildings from VHR Remote Sensing Images

2020 ◽  
Vol 12 (11) ◽  
pp. 1794
Author(s):  
Naisen Yang ◽  
Hong Tang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Data Sets ◽  
Data Set ◽  
Large Scale Data ◽  
Learning Tasks ◽  
Global Mapping ◽  
Scale Data

Modern convolutional neural networks (CNNs) are often trained on pre-set data sets with a fixed size. As for the large-scale applications of satellite images, for example, global or regional mappings, these images are collected incrementally by multiple stages in general. In other words, the sizes of training datasets might be increased for the tasks of mapping rather than be fixed beforehand. In this paper, we present a novel algorithm, called GeoBoost, for the incremental-learning tasks of semantic segmentation via convolutional neural networks. Specifically, the GeoBoost algorithm is trained in an end-to-end manner on the newly available data, and it does not decrease the performance of previously trained models. The effectiveness of the GeoBoost algorithm is verified on the large-scale data set of DREAM-B. This method avoids the need for training on the enlarged data set from scratch and would become more effective along with more available data.

scholarly journals Deep Learning Using Isotroping, Laplacing, Eigenvalues Interpolative Binding, and Convolved Determinants with Normed Mapping for Large-Scale Image Retrieval

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1139
Author(s):  
Khadija Kanwal ◽  
Khawaja Tehseen Ahmad ◽  
Rashid Khan ◽  
Naji Alhusaini ◽  
Li Jing
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Image Retrieval ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Spatial Dependencies ◽  
Hidden Patterns ◽  
Large Scale Image Retrieval ◽  
High Level ◽  
Object Features

Convolutional neural networks (CNN) are relational with grid-structures and spatial dependencies for two-dimensional images to exploit location adjacencies, color values, and hidden patterns. Convolutional neural networks use sparse connections at high-level sensitivity with layered connection complying indiscriminative disciplines with local spatial mapping footprints. This fact varies with architectural dependencies, insight inputs, number and types of layers and its fusion with derived signatures. This research focuses this gap by incorporating GoogLeNet, VGG-19, and ResNet-50 architectures with maximum response based Eigenvalues textured and convolutional Laplacian scaled object features with mapped colored channels to obtain the highest image retrieval rates over millions of images from versatile semantic groups and benchmarks. Time and computation efficient formulation of the presented model is a step forward in deep learning fusion and smart signature capsulation for innovative descriptor creation. Remarkable results on challenging benchmarks are presented with a thorough contextualization to provide insight CNN effects with anchor bindings. The presented method is tested on well-known datasets including ALOT (250), Corel-1000, Cifar-10, Corel-10000, Cifar-100, Oxford Buildings, FTVL Tropical Fruits, 17-Flowers, Fashion (15), Caltech-256, and reported outstanding performance. The presented work is compared with state-of-the-art methods and experimented over tiny, large, complex, overlay, texture, color, object, shape, mimicked, plain and occupied background, multiple objected foreground images, and marked significant accuracies.

scholarly journals Image Classification With Convolutional Neural Networks In MapReduce

2021 ◽  
Author(s):  
Min Chen
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Large Scale ◽  
Data Science ◽  
Fault Tolerant ◽  
Computational Cost ◽  
Data Intensive ◽  
Computationally Intensive

Abstract Deep learning (DL) techniques, more specifically Convolutional Neural Networks (CNNs), have become increasingly popular in advancing the field of data science and have had great successes in a wide array of applications including computer vision, speech, natural language processing and etc. However, the training process of CNNs is computationally intensive and high computational cost, especially when the dataset is huge. To overcome these obstacles, this paper takes advantage of distributed frameworks and cloud computing to develop a parallel CNN algorithm. MapReduce is a scalable and fault-tolerant data processing tool that was developed to provide significant improvements in large-scale data-intensive applications in clusters. A MapReduce-based CNN (MCNN) is developed in this work to tackle the task of image classification. In addition, the proposed MCNN adopted the idea of adding dropout layers in the networks to tackle the overfitting problem. Close examination of the implementation of MCNN as well as how the proposed algorithm accelerates learning are discussed and demonstrated through experiments. Results reveal high classification accuracy and significant improvements in speedup, scaleup and sizeup compared to the standard algorithms.

scholarly journals A Strategic Analytics Using Convolutional Neural Networks for Weed Identification in Sugar Beet Fields

2021 ◽  
Vol 13 (1) ◽  
pp. 49-57
Author(s):  
Brahim Jabir ◽  
Noureddine Falih ◽  
Asmaa Sarih ◽  
Adil Tannouche
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Sugar Beet ◽  
Convolutional Neural Networks ◽  
Precision Agriculture ◽  
Large Scale ◽  
Aerial Images ◽  
Data Set ◽  
High Level ◽  
And Control

Researchers in precision agriculture regularly use deep learning that will help growers and farmers control and monitor crops during the growing season; these tools help to extract meaningful information from large-scale aerial images received from the field using several techniques in order to create a strategic analytics for making a decision. The information result of the operation could be exploited for many reasons, such as sub-plot specific weed control. Our focus in this paper is on weed identification and control in sugar beet fields, particularly the creation and optimization of a Convolutional Neural Networks model and train it according to our data set to predict and identify the most popular weed strains in the region of Beni Mellal, Morocco. All that could help select herbicides that work on the identified weeds, we explore the way of transfer learning approach to design the networks, and the famous library Tensorflow for deep learning models, and Keras which is a high-level API built on Tensorflow.

Sign in / Sign up

Export Citation Format

Share Document