Enhancing Interstitial Lung Disease Diagnosis Through Deep Learning Frameworks DOI
Biswajit Jena, Ishan Ayus, Shantilata Palei

et al.

Published: Nov. 17, 2023

The study involves an in-depth analysis of Interstitial Lung Disease (ILD) diagnosis using deep learning frameworks with substantial datasets encompassing diverse medical images. Specifically, Convolutional Neural Network (CNN) architectures, including Inception V3, DenseNet-121, and VGG-16, are implemented to facilitate early accurate identification a range lung diseases. dataset employed in this research comprises extensive collection 5866 high-resolution computed tomography (HRCT) scans, enhancing the robustness generalizability models. This contributes ongoing efforts improve ILD through rigorous experimentation evaluation 95% precision on 97% ultimately offering potential benefits for clinical practice patient care.

Language: Английский

Prediction of O-6-methylguanine-DNA methyltransferase and overall survival of the patients suffering from glioblastoma using MRI-based hybrid radiomics signatures in machine and deep learning framework DOI
Sanjay Saxena,

Aaditya Agrawal,

Pankaj Kumar

et al.

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 35(18), P. 13647 - 13663

Published: March 17, 2023

Language: Английский

Citations

18
Lightweight Evolving U-Net for Next-Generation Biomedical Imaging DOI Creative Commons
Furkat Safarov,

Ugiloy Khojamuratova,

Misirov Komoliddin

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(9), P. 1120 - 1120

Published: April 28, 2025

Background/Objectives: Accurate and efficient segmentation of cell nuclei in biomedical images is critical for a wide range clinical research applications, including cancer diagnostics, histopathological analysis, therapeutic monitoring. Although U-Net its variants have achieved notable success medical image segmentation, challenges persist balancing accuracy with computational efficiency, especially when dealing large-scale datasets resource-limited settings. This study aims to develop lightweight scalable U-Net-based architecture that enhances performance while substantially reducing overhead. Methods: We propose novel evolving integrates multi-scale feature extraction, depthwise separable convolutions, residual connections, attention mechanisms improve robustness across diverse imaging conditions. Additionally, we incorporate channel reduction expansion strategies inspired by ShuffleNet minimize model parameters without sacrificing precision. The was extensively validated using the 2018 Data Science Bowl dataset. Results: Experimental evaluation demonstrates proposed achieves Dice Similarity Coefficient (DSC) 0.95 an 0.94, surpassing state-of-the-art benchmarks. effectively delineates complex overlapping structures high fidelity, maintaining efficiency suitable real-time applications. Conclusions: variant offers adaptable solution tasks. Its strong both highlights potential deployment diagnostics biological research, paving way resource-conscious solutions.

Language: Английский

Citations

0
WU-Net++: A novel enhanced Weighted U-Net++ model for brain tumor detection and segmentation from multi-parametric magnetic resonance scans DOI
Suchismita Das, Rajni Dubey, Biswajit Jena

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(28), P. 71885 - 71908

Published: Feb. 8, 2024

Language: Английский

Citations

3
An Approach to Segment Nuclei and Cytoplasm in Lung Cancer Brightfield Images Using Hybrid Swin-Unet Transformer DOI

Sreelekshmi Palliyil Sreekumar,

Rohini Palanisamy, Ramakrishnan Swaminathan

et al.

Journal of Medical and Biological Engineering, Journal Year: 2024, Volume and Issue: 44(3), P. 448 - 459

Published: May 29, 2024

Language: Английский

Citations

2
光学显微图像定量评价方法及应用研究进展（特邀） DOI Open Access

王瑾 Wang Jin,

张祖鑫 Zhang Zuxin,

Xieyu Chen

et al.

Laser & Optoelectronics Progress, Journal Year: 2024, Volume and Issue: 61(6), P. 0618013 - 0618013

Published: Jan. 1, 2024

作为工业数字图像质量评价在应用领域的重要延伸,光学显微图像定量评价主要通过对图像特征和属性进行分析计算,针对性地量化评估图像的质量。近年来,随着各类光学显微成像技术的蓬勃发展,图像定量化评价的重要性日益凸显,在总体图像处理中具有指导性作用。对现有的光学显微图像定量评价指标及相关算法进行总结,对各个算法的模型结构和性能表现进行讨论说明,阐述显微图像定量评价的应用和发展趋势,并对该领域目前所存在的问题和难点进行分析和展望。

Citations

1
Fundamentals pipelines of radiomics and radiogenomics (R-n-R) DOI
Ishan Ayus, Biswajit Jena, Sanjay Saxena

et al.

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 3 - 21

Published: Jan. 1, 2024

Language: Английский

Citations

0
Clinical applications implementation in neuro-oncology using machine learning approaches DOI
Biswajit Jena, Ishan Ayus, Sanjay Saxena

et al.

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 251 - 265

Published: Jan. 1, 2024

Language: Английский

Citations

0
Synthesis of Glioblastoma Segmentation Data Using Generative Adversarial Network DOI
Mullapudi Venkata Sai Samartha,

Gorantla Maheswar,

Shantilata Palei

et al.

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 301 - 312

Published: Jan. 1, 2024

Language: Английский

Citations

0
Development of U-net Neural Network for Biomedical Images with Big Data DOI
Yameng Zhang, Min Wan, Hua Tian

et al.

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 27 - 39

Published: Jan. 1, 2024

Language: Английский

Citations

0
Exploring the impact of network depth on 3D U-Net-based dose prediction for cervical cancer radiotherapy DOI Creative Commons
Mingqing Wang,

Yuxi Pan,

Xile Zhang

et al.

Frontiers in Oncology, Journal Year: 2024, Volume and Issue: 14

Published: Sept. 16, 2024

Purpose The 3D U-Net deep neural network structure is widely employed for dose prediction in radiotherapy. However, the attention to depth and its impact on accuracy robustness of remains inadequate. Methods 92 cervical cancer patients who underwent Volumetric Modulated Arc Therapy (VMAT) are geometrically augmented investigate effects by training testing three different structures with depths 3, 4, 5. Results For planning target volume (PTV), differences between predicted true values D 98 , 99 Homogeneity were statistically 1.00 ± 0.23, 0.32 0.72, -0.02 0.02 model a 5, respectively. Compared other two models, these parameters also better. most organs at risk, mean maximum 5 better than models. Conclusions results reveal that exhibits superior performance, albeit expense longest time computational memory A small server NVIDIA GeForce RTX 3090 GPUs 24 G was this training. more cannot be supported due insufficient memory, commonly used optimal choice servers.

Language: Английский

Citations

0