\n \n \n
\n
\n\n \n \n \n \n \n Spatio-Temporal Deep Learning-Based Segmentation of Left Ventricular Wall in Murine Model Echocardiography.\n \n \n \n\n\n \n Carcedo-Rodríguez, Gabriel; Vazquez, B.; Perez-Gonzalez, J.; and Hevia-Montiel, N.\n\n\n \n\n\n\n In Zuñiga-Aguilar, E.; Benítez-Mata, Balam; Reyes-Lagos, J. J.; Hernandez Acosta, H. Y.; Botello Arredondo, A. I.; Bayareh Mancilla, R.; Vázquez de la Rosa, J. F.; and Gutiérrez Valenzuela, C. A., editor(s),
XLVIII Mexican Conference on Biomedical Engineering, pages 108–117, Cham, 2026. Springer Nature Switzerland\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@InProceedings{10.1007/978-3-032-13729-6_12,\n\tauthor="Carcedo-Rodr{\\'i}guez, Gabriel\n\tand Vazquez, Blanca\n\tand Perez-Gonzalez, Jorge\n\tand Hevia-Montiel, Nidiyare",\n\teditor="Zu{\\~{n}}iga-Aguilar, Esmeralda\n\tand Ben{\\'i}tez-Mata, Balam\n\tand Reyes-Lagos, Jose Javier\n\tand Hernandez Acosta, Humiko Yahaira\n\tand Botello Arredondo, Adeodato Israel\n\tand Bayareh Mancilla, Rafael\n\tand V{\\'a}zquez de la Rosa, Jaime Fabian\n\tand Guti{\\'e}rrez Valenzuela, Cindy Alejandra",\n\ttitle="Spatio-Temporal Deep Learning-Based Segmentation of Left Ventricular Wall in Murine Model Echocardiography",\n\tbooktitle="XLVIII Mexican Conference on Biomedical Engineering",\n\tyear="2026",\n\tpublisher="Springer Nature Switzerland",\n\taddress="Cham",\n\tpages="108--117",\n\tabstract="Accurate segmentation of the left ventricular wall in echocardiography of murine models is crucial for cardiac functional assessment, but it presents a challenge due to anatomical variability, low resolution and the effort required in manual annotation. This work proposes a modular automatic segmentation architecture composed of two modules: the Res-SE-U-Net, which is based on U-Net architecture and incorporates a ResNet18 encoder and Squeeze-and-Excitation attentional blocks to extract spatial features, followed by a ConvLSTM module to refine the segmentations by incorporating temporal information. The model was trained and evaluated on a dataset of 452 long-axis echocardiography frames, with data augmentation applied during training, achieving competitive performance metrics, with an Intersection over Union score of 0.803 and a Dice coefficient of 0.889, which proved to be an efficient, reproducible and effective approach.",\n\tisbn="978-3-032-13729-6"\n}\n\n\n \n
\n\n\n
\n Accurate segmentation of the left ventricular wall in echocardiography of murine models is crucial for cardiac functional assessment, but it presents a challenge due to anatomical variability, low resolution and the effort required in manual annotation. This work proposes a modular automatic segmentation architecture composed of two modules: the Res-SE-U-Net, which is based on U-Net architecture and incorporates a ResNet18 encoder and Squeeze-and-Excitation attentional blocks to extract spatial features, followed by a ConvLSTM module to refine the segmentations by incorporating temporal information. The model was trained and evaluated on a dataset of 452 long-axis echocardiography frames, with data augmentation applied during training, achieving competitive performance metrics, with an Intersection over Union score of 0.803 and a Dice coefficient of 0.889, which proved to be an efficient, reproducible and effective approach.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n Deep Learning Applied to Segmentation of Ischemic Brain Infarct Lesions in Magnetic Resonance Images.\n \n \n \n\n\n \n May-Balam, V.; Carcedo-Rodríguez, G.; Perez-Gonzalez, J. L.; and Hevia-Montiel, N.\n\n\n \n\n\n\n In Zuñiga-Aguilar, E.; Benítez-Mata, Balam; Reyes-Lagos, J. J.; Hernandez Acosta, H. Y.; Botello Arredondo, A. I.; Bayareh Mancilla, R.; Vázquez de la Rosa, J. F.; and Gutiérrez Valenzuela, C. A., editor(s),
XLVIII Mexican Conference on Biomedical Engineering, pages 315–324, Cham, 2026. Springer Nature Switzerland\n
\n\n
\n\n
\n\n
\n\n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@InProceedings{10.1007/978-3-032-13729-6_34,\n\tauthor="May-Balam, V.\n\tand Carcedo-Rodr{\\'i}guez, G.\n\tand Perez-Gonzalez, J. Luis\n\tand Hevia-Montiel, N.",\n\teditor="Zu{\\~{n}}iga-Aguilar, Esmeralda\n\tand Ben{\\'i}tez-Mata, Balam\n\tand Reyes-Lagos, Jose Javier\n\tand Hernandez Acosta, Humiko Yahaira\n\tand Botello Arredondo, Adeodato Israel\n\tand Bayareh Mancilla, Rafael\n\tand V{\\'a}zquez de la Rosa, Jaime Fabian\n\tand Guti{\\'e}rrez Valenzuela, Cindy Alejandra",\n\ttitle="Deep Learning Applied to Segmentation of Ischemic Brain Infarct Lesions in Magnetic Resonance Images",\n\tbooktitle="XLVIII Mexican Conference on Biomedical Engineering",\n\tyear="2026",\n\tpublisher="Springer Nature Switzerland",\n\taddress="Cham",\n\tpages="315--324",\n\tabstract="Early and accurate diagnosis of ischemic stroke is essential to improve patient treatment and prognosis. In this context, automatic lesion segmentation in DWI images constitutes a valuable tool to assist specialists in identifying and quantifying affected areas. In this work, we propose an approach based on deep learning using an Attention U-Net model, designed to enhance lesion localization by utilizing attention mechanisms. This approach achieves a DICE Similarity Coefficient (DSC) of 0.78 in acute phase images (<6 h post-infarction) and demonstrates generalization in follow-up images (48 h post-infarction). The model was trained and validated with data from 55 patients, employing data augmentation and cross-validation to address the limited dataset size. The results showed high sensitivity (0.85) and an F1 score of 0.89 with an optimal threshold of 0.90, indicating that this approach may be useful in supporting the diagnosis of cerebral infarction.",\n\tisbn="978-3-032-13729-6"\n}\n\n\n
\n\n\n
\n Early and accurate diagnosis of ischemic stroke is essential to improve patient treatment and prognosis. In this context, automatic lesion segmentation in DWI images constitutes a valuable tool to assist specialists in identifying and quantifying affected areas. In this work, we propose an approach based on deep learning using an Attention U-Net model, designed to enhance lesion localization by utilizing attention mechanisms. This approach achieves a DICE Similarity Coefficient (DSC) of 0.78 in acute phase images (<6 h post-infarction) and demonstrates generalization in follow-up images (48 h post-infarction). The model was trained and validated with data from 55 patients, employing data augmentation and cross-validation to address the limited dataset size. The results showed high sensitivity (0.85) and an F1 score of 0.89 with an optimal threshold of 0.90, indicating that this approach may be useful in supporting the diagnosis of cerebral infarction.\n
\n\n\n
\n\n\n\n\n\n