Dipak Kumar Patra
Dipak Kumar Patra has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Prakash Mukherjee
Department of Mathematics, Hijli College, Midnapore, India
4 shared publications - Sukumar Mondal
Department of Mathematics, Raja N. L. Khan Women’s College (Autonomous), Midnapore 721102, India
4 shared publications - Tapas Si
Department of Computer Science & Engineering, University of Engineering & Management, Jaipur, India
2 shared publications - Tapas Si
AI Innovation Lab, Department of Computer Science & Engineering, University of Engineering & Management, Jaipur, India
2 shared publications Prakash Mukherjee
Hijli College
1 shared publicationSukumar Mondal
Department of Mathematics, Raja Narendralal Khan Women’s College (Autonomous)
1 shared publication
Latest Publications
- 27 February 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (20) , 30599-30641
Breast lesion detection from MRI images using quasi-oppositional slime mould algorithm
- 27 February 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (20) , 30599-30641
Breast lesion detection from MRI images using quasi-oppositional slime mould algorithm
- 10 August 2022
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 26 (1) , 201-216
Segmentation of breast lesion in DCE-MRI by multi-level thresholding using sine cosine algorithm with quasi opposition-based learning
- 10 August 2022
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 26 (1) , 201-216
Segmentation of breast lesion in DCE-MRI by multi-level thresholding using sine cosine algorithm with quasi opposition-based learning
- 13 May 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 204
Breast DCE-MRI segmentation for lesion detection using Chimp Optimization Algorithm
- 13 May 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 204
Breast DCE-MRI segmentation for lesion detection using Chimp Optimization Algorithm
- 24 April 2022
- Published by Springer Nature
- p. 327-340
Breast DCE-MRI Segmentation for Lesion Detection by Multilevel Thresholding Using Arithmetic Optimization Algorithm
- 24 April 2022
- Published by Springer Nature
- p. 327-340
Breast DCE-MRI Segmentation for Lesion Detection by Multilevel Thresholding Using Arithmetic Optimization Algorithm
- 18 March 2022
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 32 (1) , 174-186
Magnetic Resonance Image of Breast Segmentation by Multi-Level Thresholding Using Moth-Flame Optimization and Whale Optimization Algorithms
In this paper, we propose two breast lesion segmentation methods in dynamic contrast enhanced magnetic resonance image (DCE-MRI) using moth-flame optimizer (MFO) and whale optimization algorithm (WOA). In the first method, at the outset, MR images are denoised using the median filter in the preprocessing step. After that, a multi-level thresholding technique using MFO is used to search the suitable thresholds through entropy maximization to segment the lesions in MR images. In the second method, WOA is used in place of MFO in the framework of the first method. Segment the breast DCE-MRI lesion detection using MFO and WOA. The proposed methods are applied to 50 Sagittal T2-weighted DCE-MRI slices of 10 patients. The proposed methods are compared with algorithms such as particle swarm optimizer (PSO), improved Markov random field (IMRF), hidden Markov random field (HMRF), and conventional Markov random field (CMRF) methods. The high accuracy level of 99.88% and sensitivity 95.51% are achieved using the proposed MFO segmentation method. The high accuracy and sensitivity level of another proposed method WOA are achieved, 99.78 and 93.09%, respectively. The experimental results demonstrate that the proposed methods perform better than other methods in breast lesion segmentation in DCE-MRI.
- 18 March 2022
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 32 (1) , 174-186
Magnetic Resonance Image of Breast Segmentation by Multi-Level Thresholding Using Moth-Flame Optimization and Whale Optimization Algorithms
In this paper, we propose two breast lesion segmentation methods in dynamic contrast enhanced magnetic resonance image (DCE-MRI) using moth-flame optimizer (MFO) and whale optimization algorithm (WOA). In the first method, at the outset, MR images are denoised using the median filter in the preprocessing step. After that, a multi-level thresholding technique using MFO is used to search the suitable thresholds through entropy maximization to segment the lesions in MR images. In the second method, WOA is used in place of MFO in the framework of the first method. Segment the breast DCE-MRI lesion detection using MFO and WOA. The proposed methods are applied to 50 Sagittal T2-weighted DCE-MRI slices of 10 patients. The proposed methods are compared with algorithms such as particle swarm optimizer (PSO), improved Markov random field (IMRF), hidden Markov random field (HMRF), and conventional Markov random field (CMRF) methods. The high accuracy level of 99.88% and sensitivity 95.51% are achieved using the proposed MFO segmentation method. The high accuracy and sensitivity level of another proposed method WOA are achieved, 99.78 and 93.09%, respectively. The experimental results demonstrate that the proposed methods perform better than other methods in breast lesion segmentation in DCE-MRI.