INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Since liver cancer is the most fatal kind of cancer, it's critical to catch it early. Due to the lack of symptoms, clinical procedures make early detection hard. Reading a large number of tumour images is a perilous work for radiologists. In contemporary processes, traditional methods are employed to determine if a tumour is malignant or benign. Certain malignancies are difficult to detect visually, which leads to a high percentage of false positives and negatives. Certain tumours have comparable traits, necessitating feature extraction-based classification and identification.
Due to multiple challenges,such as low contrast between the liver and other organs and tumours,and sizes of tumours,and irregular tumour growth, the existing system has not been very good at segmenting the liver and lesions. As a result, a novel technique is required to solve these challenges.
The existing challenges are addressed using a CNN-based multiclass detection approach. Several designs are compared, including GoogLeNet, Inception-v3, ResNet, and VGG-Net, with the VGG architecture being most accurate CNN-based multiclass identification. The RCNN principle is put into practise. The features were retrieved and fed into the RCNN.
The CNN-based detection system has three stages: training, testing, and validation. Several factors such as kernel value, filter size, bias value, learning rate, and momentum can be changed to improve the accuracy of the recommended system. A novel architecture consisting of VGG-16 and ResNet-18 architecture was developed for the classification and detection for liver tumours.
"Classification and Detection of Ultrasound Liver Tumour Using VGG-ResNet", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.7, Issue 8, page no.267-271, August-2022, Available :http://www.ijnrd.org/papers/IJNRD2208030.pdf
Downloads:
000118753
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn