ANT-UNet: Accurate and Noise-Tolerant Segmentation for Pathology Image Processing

2022 ◽  
Vol 18 (2) ◽  
pp. 1-17
Author(s):  
Yufei Chen ◽  
Tingtao Li ◽  
Qinming Zhang ◽  
Wei Mao ◽  
Nan Guan ◽  
...  
Keyword(s):  
Image Processing ◽  
Network Architecture ◽  
Data Augmentation ◽  
Complex Nature ◽  
Effective Option ◽  
Segmentation Approach ◽  
Speed Up ◽  
Detection And Diagnosis ◽  
Noise Tolerant ◽  
Pathology Image

Pathology image segmentation is an essential step in early detection and diagnosis for various diseases. Due to its complex nature, precise segmentation is not a trivial task. Recently, deep learning has been proved as an effective option for pathology image processing. However, its efficiency is highly restricted by inconsistent annotation quality. In this article, we propose an accurate and noise-tolerant segmentation approach to overcome the aforementioned issues. This approach consists of two main parts: a preprocessing module for data augmentation and a new neural network architecture, ANT-UNet. Experimental results demonstrate that, even on a noisy dataset, the proposed approach can achieve more accurate segmentation with 6% to 35% accuracy improvement versus other commonly used segmentation methods. In addition, the proposed architecture is hardware friendly, which can reduce the amount of parameters to one-tenth of the original and achieve 1.7× speed-up.

Detection of Leukemia Using Image Processing

2018 ◽  
Vol 8 (4) ◽  
pp. 61
Author(s):  
A. Sivasangari ◽  
G. Sasikumar
Keyword(s):  
Image Processing ◽  
Statistical Analysis ◽  
Early Detection ◽  
Visual Inspection ◽  
Causes Of Death ◽  
Cure Rate ◽  
Blood Disorders ◽  
Detection And Diagnosis ◽  
The Moment ◽  
Early Detection And Diagnosis

Leukemia   disease   is one   of    the   leading   causes   of death   among   human. Its  cure  rate and  prognosis   depends   mainly   on  the  early  detection   and  diagnosis  of   the  disease. At  the  moment, identification  of  blood  disorders  is  through   visual  inspection  of  microscopic  images  by  examining  changes  like  texture, geometry, colour  and   statistical  analysis  of  images . This  project  aims  to  preliminary  of  developing  a  detection  of  leukemia  types  using   microscopic  blood  sample using MATLAB. Images  are  used  as  they  are  cheap  and  do  not  expensive  for testing  and  lab  equipment.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals X-ray image based pneumonia classification using convolutional neural networks

2020 ◽  
Vol 6 (20) ◽  
pp. 54-67
Author(s):  
Sarah Badr AlSumairi ◽  
Mohamed Maher Ben Ismail
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Critical Factor ◽  
Classification Problem ◽  
X Rays ◽  
X Ray ◽  
Erroneous Decision ◽  
Short Period

Pneumonia is an infectious disease of the lungs. About one third to one half of pneumonia cases are caused by bacteria. Early diagnosis is a critical factor for a successful treatment process. Typically, the disease can be diagnosed by a radiologist using chest X-ray images. In fact, chest X-rays are currently the best available method for diagnosing pneumonia. However, the recognition of pneumonia symptoms is a challenging task that relies on the availability of expert radiologists. Such “human” diagnosis can be inaccurate and subjective due to lack of clarity and erroneous decision. Moreover, the error can increase more if the physician is requested to analyze tens of X-rays within a short period of time. Therefore, Computer-Aided Diagnosis (CAD) systems were introduced to support and assist physicians and make their efforts more productive. In this paper, we investigate, design, implement and assess customized Convolutional Neural Networks to overcome the image-based Pneumonia classification problem. Namely, ResNet-50 and DenseNet-161 models were inherited to design customized deep network architecture and improve the overall pneumonia classification accuracy. Moreover, data augmentation was deployed and associated with standard datasets to assess the proposed models. Besides, standard performance measures were used to validate and evaluate the proposed system.

scholarly journals 5G Wireless/Wired Convergence of UFMC Based Modulation for Intensity Modulation Direct Detection

2021 ◽  
Author(s):  
Keerthivasan K ◽  
Shibu S
Keyword(s):  
Network Architecture ◽  
Direct Detection ◽  
Low Cost ◽  
Cost Effective ◽  
Theoretical Work ◽  
Base Stations ◽  
Complex Nature ◽  
Implementation Model ◽  
Effective Manner ◽  
Media Applications

Faster data speeds, shorter end-to-end latencies, improved end-user service efficiency, and a wider range of multi-media applications are expected with the new 5G wireless services. The dramatic increase in the number of base stations required to meet these criteria, which undermines the low-cost constraints imposed by operators, demonstrates the need for a paradigm shift in modern network architecture. Alternative formats will be required for next-generation architectures, where simplicity is the primary goal. The number of connections is expected to increase rapidly, breaking the inherent complexity of traditional coherent solutions and lowering the resulting cost percentage. A novel implementation model is used to migrate complex-nature modulation structures in a highly efficient and cost-effective manner. Theoretical work to analyses modulations’ behavior over a wired/fiber setup and wireless mode is also provided. The state-of-the-art computational complexity, simplicity, and ease of execution while maintaining efficiency throughput and bit error rate.

scholarly journals CLIJ: GPU-accelerated image processing for everyone

2019 ◽  
Author(s):  
Robert Haase ◽  
Loic A. Royer ◽  
Peter Steinbach ◽  
Deborah Schmidt ◽  
Alexandr Dibrov ◽  
...  
Keyword(s):  
Image Processing ◽  
Graphics Processing Units ◽  
End Users ◽  
Entry Level ◽  
Speed Up ◽  
Mobile Computers ◽  
Graphics Processing

AbstractGraphics processing units (GPU) allow image processing at unprecedented speed. We present CLIJ, a Fiji plugin enabling end-users with entry level experience in programming to benefit from GPU-accelerated image processing. Freely programmable workflows can speed up image processing in Fiji by factor 10 and more using high-end GPU hardware and on affordable mobile computers with built-in GPUs.

scholarly journals Spinal cord segmentation and classification of degenerative disease

2019 ◽  
Vol 10 (3) ◽  
pp. 2426-2432 ◽  
Author(s):  
Arjun ◽  
Kanchana V
Keyword(s):  
Image Processing ◽  
Spinal Cord ◽  
Human Life ◽  
Semantic Segmentation ◽  
Processing Technique ◽  
Degenerative Disease ◽  
Image Processing Technique ◽  
Segmentation Approach ◽  
Work First ◽  
Mri Image

spinal cord plays an important role in human life. In our work, we are using digital image processing technique, the interior part of the human body can be analyzed using MRI, CT and X-RAY etc. Medical image processing technique is extensively used in medical field. In here we are using MRI image to perform our work In our proposed work, we are finding degenerative disease from spinal cord image. In our work first, we are preprocessing the MRI image and locate the degenerative part of the spinal cord, finding the degenerative part using various segmentation approach after that classifying degenerative disease or normal spinal cord using various classification algorithm. For segmentation, we are using an efficient semantic segmentation approach

scholarly journals CNN-based visual analysis to study local boiling characteristics

2021 ◽  
Vol 2119 (1) ◽  
pp. 012068
Author(s):  
A N Chernyavskiy ◽  
I P Malakhov
Keyword(s):  
Network Architecture ◽  
High Speed ◽  
Visual Analysis ◽  
Nucleation Site ◽  
High Speed Video ◽  
Site Density ◽  
Segmentation Approach ◽  
Nucleation Site Density ◽  
Instance Segmentation

Abstract Visual analysis allows an estimate of different local boiling characteristics including bubble growth rate, departure diameters and frequencies of nucleation, nucleation site density and evolution of bubbles and dry spots in time. At the same time, visual determination of the presented characteristics in case of big amounts of data requires the development of the appropriate software which will allow not only determination of bubble location, but also an estimate of their sizes based on high-speed video. The presented problem can be solved by using the instance segmentation approach based on a convolutional neural network. In the presented work Mask R-CNN network architecture was used for estimation of the local boiling characteristics.

Image Processing-based Lung Region Detection and Diagnosis Support System

2011 ◽  
Author(s):  
Suk-Tae Seo ◽  
Hee-Joon Park ◽  
Min Soo Kim ◽  
Chang-Sik Son ◽  
Hyoung-Seob Park ◽  
...  
Keyword(s):  
Image Processing ◽  
Support System ◽  
Lung Region ◽  
Region Detection ◽  
Detection And Diagnosis

scholarly journals Robotic grasp detection based on image processing and random forest

2019 ◽  
Vol 79 (3-4) ◽  
pp. 2427-2446 ◽  
Author(s):  
Jiahao Zhang ◽  
Miao Li ◽  
Ying Feng ◽  
Chenguang Yang
Keyword(s):  
Image Processing ◽  
Random Forest ◽  
Main Idea ◽  
Morphological Image Processing ◽  
Segmentation Approach ◽  
Novel Objects ◽  
Set Up ◽  
The One ◽  
Objects Detection ◽  
Morphological Image

AbstractReal-time grasp detection plays a key role in manipulation, and it is also a complex task, especially for detecting how to grasp novel objects. This paper proposes a very quick and accurate approach to detect robotic grasps. The main idea is to perform grasping of novel objects in a typical RGB-D scene view. Our goal is not to find the best grasp for every object but to obtain the local optimal grasps in candidate grasp rectangles. There are three main contributions to our detection work. Firstly, an improved graph segmentation approach is used to do objects detection and it can separate objects from the background directly and fast. Secondly, we develop a morphological image processing method to generate candidate grasp rectangles set which avoids us to search grasp rectangles globally. Finally, we train a random forest model to predict grasps and achieve an accuracy of 94.26%. The model is mainly used to score every element in our candidate grasps set and the one gets the highest score will be converted to the final grasp configuration for robots. For real-world experiments, we set up our system on a tabletop scene with multiple objects and when implementing robotic grasps, we control Baxter robot with a different inverse kinematics strategy rather than the built-in one.

Sign in / Sign up

Export Citation Format

Share Document