Extraction and Classification of Liver Abnormality Based on Neutrosophic and SVM Classifier

Muthuswamy, Jayanthi

doi:10.1007/978-981-13-1708-8_25

Cited by 13 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suggested solution is an improvement of our previous hybrid approach to the problem of liver diagnostics [16]. We emphasized the significance of hybrid methods for extracting liver shape.…”

Section: Introductionmentioning

confidence: 97%

Reinforcing optimization enabled interactive approach for liver tumor extraction in computed tomography images

Muthuswamy

Reddy²,

Narayanaswamy³

2023

IJECE

View full text Add to dashboard Cite

<p>Detecting liver abnormalities is a difficult task in radiation planning and treatment. The modern development integrates medical imaging into computer techniques. This advancement has monumental effect on how medical images are interpreted and analyzed. In many circumstances, manual segmentation of liver from computerized tomography (CT) imaging is imperative, and cannot provide satisfactory results. However, there are some difficulties in segmenting the liver due to its uneven shape, fuzzy boundary and complicated structure. This leads to necessity of enabling optimization in interactive segmentation approach. The main objective of reinforcing optimization is to search the optimal threshold and reduce the chance of falling into local optimum with survival of the fittest (SOF) technique. The proposed methodology makes use of pre-processing stage and reinforcing meta heuristics optimization based fuzzy c-means (FCM) for obtaining detailed information about the image. This information gives the optimal threshold value that is used for segmenting the region of interest with minimum user input. Suspicious areas are recognized from the segmented output. Both public and simulated dataset have been taken for experimental purposes. To validate the effectiveness of the proposed strategy, performance criteria such as dice coefficient, mode and user interaction level are taken and compared with state-of-the-art algorithms.</p>

show abstract

Section: Introductionmentioning

confidence: 97%