Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 1 (2026) · hlm. 327–337

DOI
10.11591/eei.v15i1.10447
ISSN
2089-3191, 2302-9285
Terbit
2026-02-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Ultrasonography is frequently used to identify thyroid nodules. Because of their internal features, variable appearances, and ill-defined borders, it might be difficult for a hospitalist to distinguish amongst benign and malignant forms of the nodule based solely on visual inspection. Although deep learning, a subset of artificial intelligence, has significantly advanced medical image recognition, challenges remain in achieving accurate and efficient diagnosis of thyroid nodules. To identify and classify thyroid nodules, this study uses an innovative hybrid DL-assisted multi-classification technique. A median blur eliminates salt-and-pepper noise, and this is followed by segmentation using a method based on enhanced pooling integrated U-Net (EPIU-Net). To produce a single histogram series, features are recovered from the segmented image, including multi-texton, and local ternary pattern (LTP) based patterns. Following feature extraction, the data is expanded and input into a fusion classification model utilizing Deep Maxout and convolutional neural network (CNN) to categorize nodules. This work uses 2 types of datasets and for both datasets, we achieved great results with our hybrid technique across all performance criteria. 0.976, 0.008, 0.992, and 0.017 are the corresponding values for accuracy, false discovery rate (FDR), sensitivity, false negative rate (FNR). Moreover proposed work is verified by k-fold method.

Kata kunci

Jaringan kolaborasi para penulis

27 penulis · 120 tautan kepenulisan bersama · 31 lintas organisasi

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

  • MIT Art, Design and Technology University
  • Vishwakarma Institute of Technology
  • CSMSS Chh. Shahu College of Engineering
  • G H Raisoni University
  • Indian Institute of Information Technology, Nagpur
  • VIT-AP University
  • Afiliasi tidak diketahui
  • 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
Mangesh D. SalunkeAfiliasi tidak diketahui4
Babeetta BbhagatMIT Art, Design and Technology University4
Saleha I. SaudagarMIT Art, Design and Technology University4
Madhura Eknath SanapVishwakarma Institute of Technology4
Gitanjali R. ShindeVishwakarma Institute of Technology1
Vaishali M. JoshiAfiliasi tidak diketahui1
Prajkta P. DandavateVishwakarma Institute of Technology1
R. RashmiAfiliasi tidak diketahui1
Riddhi MirajkarAfiliasi tidak diketahui1
Girish Shrikrushnarao BhavekarCSMSS Chh. Shahu College of Engineering1
Pratiksha V. ChafleG H Raisoni University1
Agam Das GoswamiVIT-AP University1
Ganesh Kumar MarathulaAfiliasi tidak diketahui1
Suraj Rajesh KarpeCSMSS Chh. Shahu College of Engineering1
Nitin Sonaji MagarAfiliasi tidak diketahui1
Amarsinh Baburao FarakteAfiliasi tidak diketahui1
Nileshchandra Kalbarao PikleIndian Institute of Information Technology, Nagpur1
Snehal Bankatrao ShindeIndian Institute of Information Technology, Nagpur1
Amit Kamalakar GaikwadG H Raisoni University1

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.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<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 xml:lang="en">Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules</dc:title><dc:creator>Mayuresh Gulame</dc:creator><dc:creator>Deepthi D. Kulkarni</dc:creator><dc:creator>Priya Khune</dc:creator><dc:creator>Nilesh N. Thorat</dc:creator><dc:creator>Ashwini Shahapurkar</dc:creator><dc:creator>Vijaya S. Patil</dc:creator><dc:creator>Sumit Arun Hirve</dc:creator><dc:creator>Aarti Paresh Pimpalkar</dc:creator><dc:subject>thyroid nodules</dc:subject><dc:subject>ultrasound image classification</dc:subject><dc:subject>benign versus malignant differentiation</dc:subject><dc:subject>multi-class classification</dc:subject><dc:subject>image segmentation</dc:subject><dc:subject>salt and pepper noise removal</dc:subject><dc:subject>local ternary pattern</dc:subject><dc:subject>convolutional neural networks</dc:subject><dc:subject>feature fusion</dc:subject><dc:subject>hybrid deep learning model</dc:subject><dc:description xml:lang="en">Ultrasonography is frequently used to identify thyroid nodules. Because of their internal features, variable appearances, and ill-defined borders, it might be difficult for a hospitalist to distinguish amongst benign and malignant forms of the nodule based solely on visual inspection. Although deep learning, a subset of artificial intelligence, has significantly advanced medical image recognition, challenges remain in achieving accurate and efficient diagnosis of thyroid nodules. To identify and classify thyroid nodules, this study uses an innovative hybrid DL-assisted multi-classification technique. A median blur eliminates salt-and-pepper noise, and this is followed by segmentation using a method based on enhanced pooling integrated U-Net (EPIU-Net). To produce a single histogram series, features are recovered from the segmented image, including multi-texton, and local ternary pattern (LTP) based patterns. Following feature extraction, the data is expanded and input into a fusion classification model utilizing Deep Maxout and convolutional neural network (CNN) to categorize nodules. This work uses 2 types of datasets and for both datasets, we achieved great results with our hybrid technique across all performance criteria. 0.976, 0.008, 0.992, and 0.017 are the corresponding values for accuracy, false discovery rate (FDR), sensitivity, false negative rate (FNR). Moreover proposed work is verified by k-fold method.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-02-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i1.10447</dc:identifier><dc:identifier>10.11591/eei.v15i1.10447</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 1 (2026); 327-337</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/10447/4558</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>