banner

Journal of Autonomous Intelligence

Submit Papers
Apply for special issue

Image Processing Technologies: Applications and Innovations

Submission deadline: 2023-05-20
Special Issue Editors

Special Issue Information

Dear Colleagues,

Images are ubiquitous nowadays as they are present in many daily situations, ranging from consumer and health applications to industrial process monitoring and surveillance. Image processing algorithms developments allow to model and process images using a series of frameworks and paradigms, such as vector manifolds, Fourier analysis, cosine and wavelet transforms, time–frequency analysis, differential equations, statistical models, fuzzy logic, and machine learning, among others. In this special issue we cover both the development of new procedures and methodologies for image processing as well as novel application domains of known algorithms.

This Special Issue is devoted to the publication of new, scientifically sound, image processing methods and applications of them. Contributions from both theoretical advances and applications are welcome.


Dr. Samuel Morillas

Guest Editors

Keywords

Health-related Applications; Image Processing; Biomedical Image Processing; Machine Learning based Methods for Signals and Images; Perceptual Imaging; Vision Science; Computer Vision; New Applications of Color Imaging; Image Quality Measures; Imaging Psychophysics;Image Compression and Transmission Methods; New Image Synthesis Methods; Artificial Intelligence Applications on Images; Image Retrieval; Video Surveillance; Other New Signal and Image Processing Methods and Applications

Published Paper

Leukocyte classification for acute lymphoblastic leukemia timely diagnosis by interpretable artificial neural network

Agnese Sbrollini;Selene Tomassini;Ruba Sharaan;Micaela Morettini;Aldo Franco Dragoni;Laura Burattini;
Leukemia is a blood cancer characterized by leukocyte overproduction. Clinically, the reference for acute lymphoblastic leukemia diagnosis is a blood biopsy that allows obtain microscopic images of leukocytes, whose early-stage classification into leukemic (LEU) and healthy (HEA) may be disease predictor. Thus, the aim of this study is to propose an interpretable artificial neural network (ANN) for leukocyte classification to timely diagnose acute lymphoblastic leukemia. The “ALL_IDB2” dataset was used. It contains 260 microscopic images showing leukocytes acquired from 130 LEU and 130 HEA subjects. Each microscopic image shows a single leukocyte that was characterized by 8 morphological and 4 statistical features. An ANN was developed to distinguish microscopic images acquired from LEU and HEA subjects, considering 12 features as inputs and the local-interpretable model-agnostic explanatory (LIME) algorithm as an interpretable post-processing algorithm. The ANN was evaluated by the leave-one-out cross-validation procedure. The performance of our ANN is promising, presenting a testing area under the curve of the receiver operating characteristic equal to 87%. Being implemented using standard features and having LIME as a post-processing algorithm, it is clinically interpretable. Therefore, our ANN seems to be a reliable instrument for leukocyte classification to timely diagnose acute lymphoblastic leukemia, guaranteeing a high clinical interpretability level.

Localization of image fragments with high frequency intensity oscillation

Andrey Trubitsyn;Maksim Shadrin;Andrey Serezhin;
The problem of detecting image fragments characterized by high-frequency fluctuations in spatial intensity in the general case has not been previously considered in the literature.The article researches a sequence of known and new algorithms that allows detection and localization of such fragments.The geometric localization of the fragments is basedon the Hough transform of the pixel array of the external contours of the connected components.The components connecting becomes possible due to the use of the oscillation function proposed by the authors. The oscillation function turns out to be an effective tool for highlighting intensity fluctuations zones in an image and is superior in reliability to alternative methods for detecting such zones, based, for example, on gradient methods. The article demonstrates examples of localization of the image fragments with different levels of background complexity

Characterization of ink-based phantoms with deep networks and photoacoustic method

Hui Ling Chua;Audrey Huong;Xavier Ngu;
This study aims to explore the feasibility of using an in-house developed photoacoustic (PA) system for predicting blood phantom concentrations using a pretrained Alexnet and a Long Short-Term Memory (LSTM) network. In two separate experiments, we investigate the performance of our strategy using a point laser source and a color-tunable LightEmitting Diode (LED) as the illumination source. A single-point transducer is employed to measure signal change by adding ten different black ink concentrations into a tube. These PA signals are used for training and testing the employed deep networks. We found that the LED system with light wavelength of 450 nm gives the best characterization performance. The classification accuracy of the Alexnet and LSTM models tested on this dataset shows an average value of 94% and 96%, respectively, making this a preferred light wavelength for future operation. Our system may be used for the noninvasive assessment of microcirculatory changes in humans.

The core business of Frontier Scientific Publishing focuses on publishing academic journals and organizing international academic conferences. At the same time, FSP provides educational training, consultations on scientific and technological information, translation services, and publications of e-books.

21 Serangoon North Avenue 5, #03-03 Ban Teck Han Building, Singapore (554864)
Tel: +65 9821 9348
E-mail: contact@front-sci.com

Front-sci

Valueble Links

Frontier Scientific Publishing © 2022 All Right Reserved