Two-Stage Segmentation Framework Based on Distance Transformation

With the rise of deep learning, using deep learning to segment lesions and assist in diagnosis has become an effective means to promote clinical medical analysis. However, the partial volume effect of organ tissues leads to unclear and blurred edges of ROI in medical images, making it challenging to achieve high-accuracy segmentation of lesions or organs. In this paper, we assume that the distance map obtained by performing distance transformation on the ROI edge can be used as a weight map to make the network pay more attention to the learning of the ROI edge region. To this end, we design a novel framework to flexibly embed the distance map into the two-stage network to improve left atrium MRI segmentation performance. Furthermore, a series of distance map generation methods are proposed and studied to reasonably explore how to express the weight of assisting network learning. We conduct thorough experiments to verify the effectiveness of the proposed segmentation framework, and experimental results demonstrate that our hypothesis is feasible.

Download Full-text

Two-stage pyramidal convolutional neural networks for image colorization

APSIPA Transactions on Signal and Information Processing ◽

10.1017/atsip.2021.13 ◽

2021 ◽

Vol 10 ◽

Author(s):

Yu-Jen Wei ◽

Tsu-Tsai Wei ◽

Tien-Ying Kuo ◽

Po-Chyi Su

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Computational Complexity ◽

Color Space ◽

Research Trend ◽

Two Stage ◽

Map Generation ◽

Generation Network ◽

Chroma Components

The development of colorization algorithms through deep learning has become the current research trend. These algorithms colorize grayscale images automatically and quickly, but the colors produced are usually subdued and have low saturation. This research addresses this issue of existing algorithms by presenting a two-stage convolutional neural network (CNN) structure with the first and second stages being a chroma map generation network and a refinement network, respectively. To begin, we convert the color space of an image from RGB to HSV to predict its low-resolution chroma components and therefore reduce the computational complexity. Following that, the first-stage output is zoomed in and its detail is enhanced with a pyramidal CNN, resulting in a colorized image. Experiments show that, while using fewer parameters, our methodology produces results with more realistic color and higher saturation than existing methods.

Download Full-text

Deep Learning-Based Approaches to Optimize the Electricity Contract Capacity Problem for Commercial Customers

Energies ◽

10.3390/en14082181 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2181

Author(s):

Rafik Nafkha ◽

Tomasz Ząbkowski ◽

Krzysztof Gajowniczek

Keyword(s):

Deep Learning ◽

Power Grid ◽

Hybrid Approach ◽

Electricity Consumption ◽

Maximum Power ◽

Learning Approaches ◽

Two Stage ◽

Load Optimization ◽

Optimal Capacity ◽

Maximal Load

The electricity tariffs available to customers in Poland depend on the connection voltage level and contracted capacity, which reflect the customer demand profile. Therefore, before connecting to the power grid, each consumer declares the demand for maximum power. This amount, referred to as the contracted capacity, is used by the electricity provider to assign the proper connection type to the power grid, including the size of the security breaker. Maximum power is also the basis for calculating fixed charges for electricity consumption, which is controlled and metered through peak meters. If the peak demand exceeds the contracted capacity, a penalty charge is applied to the exceeded amount, which is up to ten times the basic rate. In this article, we present several solutions for entrepreneurs based on the implementation of two-stage and deep learning approaches to predict maximal load values and the moments of exceeding the contracted capacity in the short term, i.e., up to one month ahead. The forecast is further used to optimize the capacity volume to be contracted in the following month to minimize network charge for exceeding the contracted level. As confirmed experimentally with two datasets, the application of a multiple output forecast artificial neural network model and a genetic algorithm (two-stage approach) for load optimization delivers significant benefits to customers. As an alternative, the same benefit is delivered with a deep learning architecture (hybrid approach) to predict the maximal capacity demands and, simultaneously, to determine the optimal capacity contract.

Download Full-text

A Two-Stage Deep Learning Scheme to Estimate Depth of Anesthesia from EEG Signals

2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME) ◽

10.1109/icbme51989.2020.9319416 ◽

2020 ◽

Author(s):

Sara Afshar ◽

Reza Boostani

Keyword(s):

Deep Learning ◽

Depth Of Anesthesia ◽

Eeg Signals ◽

Two Stage ◽

Learning Scheme

Download Full-text

On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data

Remote Sensing ◽

10.3390/rs13010089 ◽

2020 ◽

Vol 13 (1) ◽

pp. 89

Author(s):

Manuel Carranza-García ◽

Jesús Torres-Mateo ◽

Pedro Lara-Benítez ◽

Jorge García-Gutiérrez

Keyword(s):

Deep Learning ◽

Real Time ◽

Autonomous Vehicles ◽

Remote Sensing Data ◽

Autonomous Driving ◽

Two Stage ◽

Detection Systems ◽

One Stage ◽

Time Requirements ◽

Speed Accuracy

Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.

Download Full-text

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

Algorithms ◽

10.3390/a14070212 ◽

2021 ◽

Vol 14 (7) ◽

pp. 212

Author(s):

Youssef Skandarani ◽

Pierre-Marc Jodoin ◽

Alain Lalande

Keyword(s):

Deep Learning ◽

Cardiac Mri ◽

Expert Knowledge ◽

Medical Image Analysis ◽

Ground Truth ◽

Cine Mri ◽

Data Sets ◽

Mri Segmentation ◽

Segmentation Evaluation ◽

Ground Truth Data

Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires a large number of annotated data so that a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated data sets on which machine learning can successfully be trained. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with different loss functions on expert and non-expert ground truth for cardiac cine–MRI segmentation. Evaluation was done with classic segmentation metrics (Dice index and Hausdorff distance) as well as clinical measurements, such as the ventricular ejection fractions and the myocardial mass. The results reveal that generalization performances of a segmentation neural network trained on non-expert ground truth data is, to all practical purposes, as good as that trained on expert ground truth data, particularly when the non-expert receives a decent level of training, highlighting an opportunity for the efficient and cost-effective creation of annotations for cardiac data sets.

Download Full-text

Scanner Independent Deep Learning-Based Segmentation Framework Applied to Mouse Embryos

2020 IEEE International Ultrasonics Symposium (IUS) ◽

10.1109/ius46767.2020.9251626 ◽

2020 ◽

Author(s):

Orlando Aristizabal ◽

Daniel H. Turnbull ◽

Jeffrey A. Ketterling ◽

Yao Wang ◽

Ziming Qiu ◽

...

Keyword(s):

Deep Learning ◽

Mouse Embryos ◽

Segmentation Framework

Download Full-text

Patch-Based Change Detection Method for SAR Images with Label Updating Strategy

Remote Sensing ◽

10.3390/rs13071236 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1236

Author(s):

Yuanjun Shu ◽

Wei Li ◽

Menglong Yang ◽

Peng Cheng ◽

Songchen Han

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Change Detection ◽

Detection Method ◽

Training Data ◽

Synthetic Aperture ◽

Learning Method ◽

Sar Images ◽

Two Stage ◽

Second Stage

Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.

Download Full-text

A novel two-stage method of plant seedlings classification based on deep learning

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-211507 ◽

2021 ◽

pp. 1-11

Author(s):

Tianhong Dai ◽

Shijie Cong ◽

Jianping Huang ◽

Yanwen Zhang ◽

Xinwang Huang ◽

...

Keyword(s):

Deep Learning ◽

Learning Technology ◽

Two Stage ◽

Second Stage ◽

Stage Classification ◽

Different Types ◽

Two Stages ◽

Plant Seedlings

In agricultural production, weed removal is an important part of crop cultivation, but inevitably, other plants compete with crops for nutrients. Only by identifying and removing weeds can the quality of the harvest be guaranteed. Therefore, the distinction between weeds and crops is particularly important. Recently, deep learning technology has also been applied to the field of botany, and achieved good results. Convolutional neural networks are widely used in deep learning because of their excellent classification effects. The purpose of this article is to find a new method of plant seedling classification. This method includes two stages: image segmentation and image classification. The first stage is to use the improved U-Net to segment the dataset, and the second stage is to use six classification networks to classify the seedlings of the segmented dataset. The dataset used for the experiment contained 12 different types of plants, namely, 3 crops and 9 weeds. The model was evaluated by the multi-class statistical analysis of accuracy, recall, precision, and F1-score. The results show that the two-stage classification method combining the improved U-Net segmentation network and the classification network was more conducive to the classification of plant seedlings, and the classification accuracy reaches 97.7%.

Download Full-text