Building a DenseNet-Based Neural Network with Transformer and MBConv Blocks for Penile Cancer Classification DOI Creative Commons
Marcos Gabriel Mendes Lauande, Geraldo Bráz, João Dallyson Sousa de Almeida

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10536 - 10536

Опубликована: Ноя. 15, 2024

Histopathological analysis is an essential exam for detecting various types of cancer. The process traditionally time-consuming and laborious. Taking advantage deep learning models, assisting the pathologist in diagnosis possible. In this work, a study was carried out based on DenseNet neural network. It consisted changing its architecture through combinations Transformer MBConv blocks to investigate impact classifying histopathological images penile Due limited number samples dataset, pre-training performed another larger lung colon cancer image dataset. Various these architectural components were systematically evaluated compare their performance. results indicate significant improvements feature representation, demonstrating effectiveness combined elements resulting F1-Score up 95.78%. Its diagnostic performance confirms importance techniques men’s health.

Язык: Английский

Enhancing lung cancer diagnostic accuracy and reliability with LCDViT: an expressly developed vision transformer model featuring explainable AI DOI
Amol Satsangi, K. Srinivas, A. Charan Kumari

и другие.

Multimedia Tools and Applications, Год журнала: 2025, Номер unknown

Опубликована: Янв. 29, 2025

Язык: Английский

Процитировано

0
Automatic lung cancer detection from CT image using optimized Robust Deformed Convolutional Neural Network with TriHorn-Net DOI

Chakradhar Reddy,

M. V. D. Prasad

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127124 - 127124

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Optimizing lung cancer classification using transformer and Gooseneck Barnacle Optimization DOI

Arockia Jesuraj Yagappan,

Hemalatha Karuppiah,

Mohanapriya Muthusamy

и другие.

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127413 - 127413

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
A Wavelet-Based Two-Stage Vision Transformer Model for Histological Subtypes Classification of Lung Cancers on CT Images DOI Open Access
Eri Matsuyama,

Haruyuki Watanabe,

Noriyuki Takahashi

и другие.

Open Journal of Medical Imaging, Год журнала: 2025, Номер 15(02), С. 57 - 72

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A Combined Approach of Vision Transformer and Transfer Learning Based Model for Accurate Lung Cancer Classification DOI
Arvind Kumar,

Muhammad Rashid Ansari,

Koushlendra Kumar Singh

и другие.

SN Computer Science, Год журнала: 2025, Номер 6(5)

Опубликована: Май 30, 2025

Язык: Английский

Процитировано

0
GSC-DVIT: A vision transformer based deep learning model for lung cancer classification in CT images DOI

Durgaprasad Mannepalli,

K. T. Tan, Sivaneasan Bala Krishnan

и другие.

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 103, С. 107371 - 107371

Опубликована: Дек. 30, 2024

Язык: Английский

Процитировано

1
Building a DenseNet-Based Neural Network with Transformer and MBConv Blocks for Penile Cancer Classification DOI Creative Commons
Marcos Gabriel Mendes Lauande, Geraldo Bráz, João Dallyson Sousa de Almeida

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10536 - 10536

Опубликована: Ноя. 15, 2024

Histopathological analysis is an essential exam for detecting various types of cancer. The process traditionally time-consuming and laborious. Taking advantage deep learning models, assisting the pathologist in diagnosis possible. In this work, a study was carried out based on DenseNet neural network. It consisted changing its architecture through combinations Transformer MBConv blocks to investigate impact classifying histopathological images penile Due limited number samples dataset, pre-training performed another larger lung colon cancer image dataset. Various these architectural components were systematically evaluated compare their performance. results indicate significant improvements feature representation, demonstrating effectiveness combined elements resulting F1-Score up 95.78%. Its diagnostic performance confirms importance techniques men’s health.

Язык: Английский

Процитировано

0