Domingos Alves Dias Júnior
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Domingos Alves Dias Júnior has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- João Otávio Bandeira Diniz
Federal Institute of Maranhão (IFMA)
4 shared publications - Luana Batista da Cruz
Federal University of Cariri (UFCA)
4 shared publications - Anselmo Cardoso de Paiva
Universidade Federal do Maranhão (UFMA)
3 shared publications - Aristófanes Corrêa Silva
Federal University of Maranhão (UFMA)
3 shared publications - Giovanni Lucca França da Silva
Federal University of Maranhão (UFMA)
2 shared publications - Daniel Lima Gomes Junior
Universidade Federal do Maranhão - UFMA
1 shared publication
Latest Publications
- 30 January 2025
- Published by Springer Nature
- p. 95-109
AnisotropicBreast-ViT: Breast Cancer Classification in Ultrasound Images Using Anisotropic Filtering and Vision Transformer
- 30 January 2025
- Published by Springer Nature
- p. 95-109
AnisotropicBreast-ViT: Breast Cancer Classification in Ultrasound Images Using Anisotropic Filtering and Vision Transformer
- 30 January 2025
- Published by Springer Nature
- p. 110-124
Anomalies Diagnostic in Endoscopic Images Using Deep Learning Ensemble Models
- 30 January 2025
- Published by Springer Nature
- p. 110-124
Anomalies Diagnostic in Endoscopic Images Using Deep Learning Ensemble Models
- 1 April 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 192
Kidney tumor segmentation from computed tomography images using DeepLabv3+ 2.5D model
- 1 April 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 192
Kidney tumor segmentation from computed tomography images using DeepLabv3+ 2.5D model
- 3 March 2022
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 11 (3) , 317-325
Heart segmentation in planning CT using 2.5D U-Net++ with attention gate
Organs at risk (OARs) are healthy tissues around cancers that must be preserved in radiotherapy (RT). Heart is one of the fundamental organs for the full functioning of the human body, protecting this organ in the RT is of paramount importance. For this, the planning process must be careful. Planning begins with manual segmentation by specialists in computed tomography (CT). We propose a deep learning method for heart segmentation from planning CT. The method consists of four steps: (1) material acquisition from a public database; (2) volume standardisation using registration and histogram matching; (3) Volume of Interest (VOI) segmentation using atlas; and (4) a U-Net variation with 2.5D input layer for final segmentation. We tested in 36 CTs and achieved 93.82% of the Dice similarity coefficient, 88.42% of the Jaccard. With the innovation of the proposed method and the promising results, we show that our method effectively uses heart segmentation.
- 3 March 2022
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 11 (3) , 317-325
Heart segmentation in planning CT using 2.5D U-Net++ with attention gate
Organs at risk (OARs) are healthy tissues around cancers that must be preserved in radiotherapy (RT). Heart is one of the fundamental organs for the full functioning of the human body, protecting this organ in the RT is of paramount importance. For this, the planning process must be careful. Planning begins with manual segmentation by specialists in computed tomography (CT). We propose a deep learning method for heart segmentation from planning CT. The method consists of four steps: (1) material acquisition from a public database; (2) volume standardisation using registration and histogram matching; (3) Volume of Interest (VOI) segmentation using atlas; and (4) a U-Net variation with 2.5D input layer for final segmentation. We tested in 36 CTs and achieved 93.82% of the Dice similarity coefficient, 88.42% of the Jaccard. With the innovation of the proposed method and the promising results, we show that our method effectively uses heart segmentation.