High-Quality, Low-Quantity: A Data-Centric Approach to Deep Learning Performance Optimization in Digital X-Ray Radiography DOI
Bata Hena, Ziang Wei,

Clemente Ibarra-Castanedo

et al.

Published: Jan. 1, 2024

Language: Английский

Modified Residual Variable Correlation Kernel Convolutional Neural Network for Classifying Spices DOI

Reny Jose,

K. Ponmozhi

Analytical Letters, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: Feb. 1, 2025

Language: Английский

Citations

0
High-Quality, Low-Quantity: A Data-Centric Approach to Deep Learning Performance Optimization in Digital X-Ray Radiography DOI Creative Commons
Bata Hena, Ziang Wei, Clemente Ibarra‐Castanedo

et al.

NDT & E International, Journal Year: 2025, Volume and Issue: unknown, P. 103327 - 103327

Published: Jan. 1, 2025

Language: Английский

Citations

0
Advancements in Healthcare Medical Imaging through SHO optimized CNN DOI Open Access
Umang Kumar Agrawal, Nibedan Panda, Prithviraj Mohanty

et al.

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 4128 - 4135

Published: Jan. 1, 2025

Language: Английский

Citations

0
An Explainable Contrastive-based Dilated Convolutional Network with Transformer for pediatric pneumonia detection DOI
Chandravardhan Singh Raghaw, Parth Shirish Bhore,

Mohammad Zia Ur Rehman

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 167, P. 112258 - 112258

Published: Sept. 19, 2024

Language: Английский

Citations

3
Spatial attention-based CSR-Unet framework for subdural and epidural hemorrhage segmentation and classification using CT images DOI Creative Commons

Nikita Konstantina S.,

P. Prakasam

BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)

Published: Oct. 22, 2024

Abstract Background Automatic diagnosis and brain hemorrhage segmentation in Computed Tomography (CT) may be helpful assisting the neurosurgeon developing treatment plans that improve patient’s chances of survival. Because medical images is important performing operations manually challenging, many automated algorithms have been developed for this purpose, primarily focusing on certain image modalities. Whenever a blood vessel bursts, dangerous condition known as intracranial (ICH) occurs. For best results, quick action required. That being said, identifying subdural (SDH) epidural haemorrhages (EDH) difficult task field calls new, more precise detection method. Methods This work uses head CT scan to detect cerebral bleeding distinguish between two types dural hemorrhages using deep learning techniques. paper proposes rich approach segment both SDH EDH by enhancing efficiency with better feature extraction procedure. method incorporates Spatial attention- based CSR (convolution-SE-residual) Unet, extraction. Results According study’s findings, network performs than other models, exhibiting impressive metrics all assessed parameters mean dice coefficient 0.970 IoU 0.718, while scores are 0.983 0.969 respectively. Conclusions The experiment results show it can perform well regarding coefficient. Furthermore, Unet effectively model complicated segmentations representation compared alternative techniques, illness treatment, enhance meticulousness predicting fatality.

Language: Английский

Citations

1
Detecting DDoS Attacks Through Decision Tree Analysis: An EDA Approach with the CIC DDoS 2019 Dataset DOI
Ahmad Turmudi Zy,

Amali,

Anggi Muhammad Rifa’i

et al.

Published: Aug. 29, 2024

Language: Английский

Citations

1
DSCIMABNet: A novel multi-head attention depthwise separable CNN model for skin cancer detection DOI
Hatice Çatal Reis, Veysel Turk

Pattern Recognition, Journal Year: 2024, Volume and Issue: 159, P. 111182 - 111182

Published: Nov. 7, 2024

Language: Английский

Citations

1
TransMVAN: Multi-view Aggregation Network with Transformer for Pneumonia Diagnosis DOI
Xiaohong Wang, Zhongkang Lu,

Su Huang

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: unknown

Published: July 8, 2024

Automated and accurate classification of pneumonia plays a crucial role in improving the performance computer-aided diagnosis systems for chest X-ray images. Nevertheless, it is challenging task due to difficulty learning complex structure information lung abnormality from In this paper, we propose multi-view aggregation network with Transformer (TransMVAN) Specifically, incorporate knowledge glance focus views enrich feature representation abnormality. Moreover, capture relationships among different regions, bi-directional multi-scale vision (biMSVT), which informative messages between regions are propagated through two directions. addition, also gated (GMVA) adaptively select further enhancement diagnosis. Our proposed method achieves AUCs 0.9645 0.9550 on image datasets. an AUC 0.9761 evaluating positive negative polymerase chain reaction (PCR). Furthermore, our attains 0.9741 classifying non-COVID-19 pneumonia, COVID-19 normal cases. Experimental results demonstrate effectiveness over other methods used comparison

Language: Английский

Citations

0
Leveraging Data Augmentation and Dropout Layer in MobileNetV3 for Accurate Skin Cancer Detection ISIC Dataset DOI
Anggi Muhammad Rifa’i, Ahmad Turmudi Zy,

Wahyu Hadikristanto

et al.

Published: Aug. 29, 2024

Language: Английский

Citations

0
ARM-UNet: attention residual path modified UNet model to segment the fungal pathogen diseases in potato leaves DOI
D. N. Kiran Pandiri,

R. Murugan,

Tripti Goel

et al.

Signal Image and Video Processing, Journal Year: 2024, Volume and Issue: 19(1)

Published: Dec. 6, 2024

Language: Английский

Citations

0