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)
Histopathological tissues are not only critical to cancer diagnosis, but they also provide useful tumor microen- vironment information for cancer research. Current CNN classi- fication has already shown strong feature representation ability and promising outcomes for histopathology tissue classification. In this paper, we propose a method using optimized convolutional neural networks (OPCNN) and Bidirectional Encoder Repre- sentations from Transformers (BERT). The convolutional Auto encoder’s aim is to learn an input function to reconstruct the input to an output of fewer dimensions. Tissue Classification is compelled to learn numerical changes that carry the most useful details about the structure of data in order for the deciphering part to operate well in the rebuilding task. The BERT model’s remarkable performance could possibly be attributable to the fact that it is bidirectionally trained. This implies that BERT, which is built on the Transformer model architecture, uses its self- attention mechanism during training to learn information from both the left and right sides, resulting in a deep understanding of the context. On two downstream tasks, picture classification, and semantic segmentation, we fine-tune the pre-trained BERT and self-supervised learning. The output of the BERT layer is routed into OPCNN, which then passes the output to a completely linked bulky layer, which produces a single posture as its final output. On the Lung Colon Cancer Histopathological Image Dataset, we subjected the proposed approach to the test. The findings from the study indicate that the proposed technique can improve tissue-level accuracy for classification by up to 96.91% over time. It significantly shortens the processing time.
"Enhancing Histopathological Tissue Accuracy Using: OPCNN And BERT", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 7, page no.a622-a627, July-2023, Available :http://www.ijnrd.org/papers/IJNRD2307078.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