TY - GEN
T1 - Lung Pathology Using Artificial Intelligence Analysis of Ultrasound Images
T2 - 2024 International Conference on Sustainable Technology and Engineering, i-COSTE 2024
AU - Alwadi, Ali
AU - Chetty, Girija
AU - Alwadi, Mohammad
AU - Alnaimi, Jawad
AU - Gawanmeh, Amjad
AU - Mahmoud, Khaled Zuhair Said
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - This paper first studies and analyses the Artificial Intelligence algorithms that can potentially be used to identify various diseases from medical images and scans. Then researches the related work in this area to find a suitable Machine Learning model that can be used to identify Interstitial Syndrome in Lung Ultra Sound images. By researching similar applications of the latest Machine Learning algorithms, this team of researchers are adopting a Vision Transformer system developed on a Convolutional Neural Network-based algorithm. The later has proven to be efficient in the area of UltraSound image processing in general and more flexible to configure and parameterize in the training process. The Vision Transformer system is a segmentation-based model that divides the input image to smaller subset of images of the same size. By merging the adjacent small patches into bigger layers, bigger windows to perform self-attention on, the system extracts the points of interest out of these frames.
AB - This paper first studies and analyses the Artificial Intelligence algorithms that can potentially be used to identify various diseases from medical images and scans. Then researches the related work in this area to find a suitable Machine Learning model that can be used to identify Interstitial Syndrome in Lung Ultra Sound images. By researching similar applications of the latest Machine Learning algorithms, this team of researchers are adopting a Vision Transformer system developed on a Convolutional Neural Network-based algorithm. The later has proven to be efficient in the area of UltraSound image processing in general and more flexible to configure and parameterize in the training process. The Vision Transformer system is a segmentation-based model that divides the input image to smaller subset of images of the same size. By merging the adjacent small patches into bigger layers, bigger windows to perform self-attention on, the system extracts the points of interest out of these frames.
KW - Deep learning
KW - Image processing
KW - Machine learning
KW - Neural networks
KW - Segmentation based model transformer
UR - http://www.scopus.com/inward/record.url?scp=105009072984&partnerID=8YFLogxK
UR - http://ieeexplore.ieee.org/xpl/conhome/11024274/proceeding
UR - https://i-coste.org/2024/
UR - https://i-coste.org/2024/committee.html
U2 - 10.1109/i-COSTE63786.2024.11024656
DO - 10.1109/i-COSTE63786.2024.11024656
M3 - Conference contribution
AN - SCOPUS:105009072984
T3 - 2024 International Conference on Sustainable Technology and Engineering, i-COSTE 2024
SP - 1
EP - 8
BT - 2024 International Conference on Sustainable Technology and Engineering, i-COSTE 2024
A2 - Shafiullah, GM
A2 - Rajapakse, Athula
A2 - Padmanaban, Sanjeevikumar
A2 - Urmee, Tania
A2 - Hossain, Mofazzal
A2 - Hettiwatte, Sujeewa
A2 - Kumar, Jashnil
PB - IEEE, Institute of Electrical and Electronics Engineers
Y2 - 18 December 2024 through 20 December 2024
ER -