Dipak Kumar Patra

Dipak Kumar Patra

Auto-generated profile, based on publicly available information

Dipak Kumar Patra

Department of Computer Science, Raja Narendra Lal Khan Women’s College (Autonomous), Midnapore, India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 May 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
TSTapas Si
Tapas Si
DPDipak Kumar Patra
Dipak Kumar Patra
SMSukumar Mondal
Sukumar Mondal
PMPrakash Mukherjee
Prakash Mukherjee

10 August 2022 in Pattern Analysis and Applications
Verified
Journal Article
Closed access
PDF file
TSTapas Si
Tapas Si
DPDipak Kumar Patra
Dipak Kumar Patra
SMSukumar Mondal
Sukumar Mondal
PMPrakash Mukherjee
Prakash Mukherjee

27 February 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
DPDipak Kumar Patra
Dipak Kumar Patra
TSTapas Si
Tapas Si
SMSukumar Mondal
Sukumar Mondal
PMPrakash Mukherjee
Prakash Mukherjee

18 March 2022 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
DPDipak Kumar Patra
Dipak Kumar Patra
TSTapas Si
Tapas Si
SMSukumar Mondal
Sukumar Mondal
PMPrakash Mukherjee
Prakash Mukherjee
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.

24 April 2022
Verified
Book Chapter
Closed access
PDF file
DPDipak Kumar Patra
Dipak Kumar Patra
TSTapas Si
Tapas Si
SMSukumar Mondal
Sukumar Mondal
PMPrakash Mukherjee
Prakash Mukherjee