RT info:eu-repo/semantics/conferencePaper
T1 Evaluation of optimizers in pre-trained neural networks : case study on the classification of pathologies in thyroid scans using a reduced and unbalanced dataset
A1 Grossling Vallejos, Benicio
A1 Mello Román, Julio César
A1 Vázquez Noguera, José Luis
A1 Legal Ayala, Horacio Andrés
A1 Rivas Coluchi, Ronald  Alexis
AB This study comparatively evaluates the performance of three pre-trained convolutional neural network architectures (ResNet50, InceptionV3, and DenseNet169) in the multiclass classification of thyroid scintigraphy images, using a reduced and unbalanced dataset. The models were trained in two experimental configurations and three optimizers (SGDM, AdamW, and RMSprop). Evaluation metrics included precision, precision, recall, F1-score and ROC-AUC curves per class. The results indicate that DenseNet169 achieved the best overall performance, with higher F1-scores (with RMSprop) and more balanced ROC curves between classes (with AdamW). InceptionV3 was found to offer intermediate performance, but with greater variability between classes, while ResNet50 showed lower discriminatory power, particularly in the less represented classes. The results highlight the usefulness of the DenseNet169 model for classification tasks with limited data availability and its use as a diagnostic support tool in nuclear medicine.
PB Springer Nature
SN 978-3-032-25651-5 (Print ISBN)
YR 2026
FD 2026-08-02
LK http://hdl.handle.net/20.500.14066/4835
UL http://hdl.handle.net/20.500.14066/4835
LA eng
NO Grossling-Vallejos, B., Mello-Román, J. C., Vázquez Noguera, J. L., Legal-Ayala, H., & Rivas Coluchi, R. (2026, 16-18 de febrero). Evaluation of Optimizers in Pre-trained Neural Networks: Case Study on the Classification of Pathologies in Thyroid Scans Using a Reduced and Unbalanced Dataset [Artículo de la Conferencia]. 2026 International Conference on Information Technology & Systems (ICITS’26), Isla de Roatán, Honduras.https://doi.org/10.1007/978-3-032-25652-2_32
NO Part of the book series: Lecture Notes in Networks and Systems (LNNS, volume 1965).
NO Consejo Nacional de Ciencia y Tecnología
DS MINDS@UW
RD 22-sep-2026