Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Content based COVID-19 image retrieval system using local histogram equalization and deep convolutional neural network

International Journal of Electrical and Computer Engineering (IJECE) · Vol. 14 No. 4 (2024)

DOI
10.11591/ijece.v14i4.pp3942-3950
ISSN
2722-2578, 2088-8708
Terbit
2024-08-01
Penerbit
Institute of Advanced Engineering and Science
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Doctors play a critical role in interpreting medical images as part of their core responsibilities. They need to find comparable examples that can assist in making informed decisions, especially when encountering ambiguous visuals. Traditionally, Systems such as content-based medical image retrieval (CBMIR) have been used for this. The proposed method employs a novel technique, local histogram equalization (LHE) for preprocessing, transfer learning-based convolutional neural network to extract the representative features with Manhattan and Euclidean distance metrics to assess how similar the query image and database image are to one another. This model is trained on a standard dataset namely Chest X-Ray images. Top-k, Precision and Recall measure is employed to assess system performance. From the results, the suggested enhanced convolutional neural network (CNN) model demonstrates significantly superior performance in the top 10 retrieval rates of 97.13% for coronavirus disease 2019 (COVID-19), 96.84% for normal, 82.63% for pneumonia-bacterial, and 81.72% for pneumonia-viral and precision@recall10 of 93.14% for COVID-19, 91.88% for normal, 77.84% for pneumonia-bacterial and 74.71% for pneumonia-viral.

Jaringan kolaborasi para penulis

4 penulis · 6 tautan kepenulisan bersama · 4 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Kasturba Medical College, Manipal
  • Shri Dharmasthala Manjunatheshwara University
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Data ini berasal dari Crossref (yang disetorkan penerbit), karena endpoint OAI-PMH milik jurnal tidak dapat di-harvest.

Sumber metadata: Crossref API (cadangan, berdasarkan ISSN) https://api.crossref.org/journals/2088-8708/works, pertama di-harvest 27 Okt 2026, terakhir terlihat 15 Nov 2026.
Metadata sebagai oai_dc, dikonversi dari Crossref
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title>Content based COVID-19 image retrieval system using local histogram equalization and deep convolutional neural network</dc:title><dc:creator>Shetty, Rani</dc:creator><dc:creator>S. Bhat, Vandana</dc:creator><dc:creator>Pujari, Jagadeesh</dc:creator><dc:creator>Shetty, Rashmi</dc:creator><dc:description>&lt;jats:p&gt;Doctors play a critical role in interpreting medical images as part of their core responsibilities. They need to find comparable examples that can assist in making informed decisions, especially when encountering ambiguous visuals. Traditionally, Systems such as content-based medical image retrieval (CBMIR) have been used for this. The proposed method employs a novel technique, local histogram equalization (LHE) for preprocessing, transfer learning-based convolutional neural network to extract the representative features with Manhattan and Euclidean distance metrics to assess how similar the query image and database image are to one another. This model is trained on a standard dataset namely Chest X-Ray images. Top-k, Precision and Recall measure is employed to assess system performance. From the results, the suggested enhanced convolutional neural network (CNN) model demonstrates significantly superior performance in the top 10 retrieval rates of 97.13% for coronavirus disease 2019 (COVID-19), 96.84% for normal, 82.63% for pneumonia-bacterial, and 81.72% for pneumonia-viral and precision@recall10 of 93.14% for COVID-19, 91.88% for normal, 77.84% for pneumonia-bacterial and 74.71% for pneumonia-viral.&lt;/jats:p&gt;</dc:description><dc:publisher>Institute of Advanced Engineering and Science</dc:publisher><dc:date>2024-08-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/ijece.v14i4.pp3942-3950</dc:identifier><dc:identifier>10.11591/ijece.v14i4.pp3942-3950</dc:identifier><dc:source>International Journal of Electrical and Computer Engineering (IJECE); Vol 14 No 4 (2024); 3942</dc:source><dc:source>2722-2578</dc:source><dc:source>2088-8708</dc:source><dc:relation>https://ijece.iaescore.com/index.php/IJECE/article/viewFile/34684/17512</dc:relation><dc:rights>http://creativecommons.org/licenses/by-sa/4.0</dc:rights></oai_dc:dc>