March 3, 2026Open Access

Left-right relationship-aware 3D volume classification method

Puntos clave

The classification model effectively extracts features from left-right symmetric positions, enhancing accuracy.
Experimental results show that this method outperforms earlier models in classifying 3D volumes related to lung and brain.
Using a multi-shift symmetric feature extraction module addresses small positional gaps, improving feature alignment.
The findings support the model's use in more precise 3D volume analyses, suggesting broad clinical applications.

Resumen

We proposed the LR relationship-aware classification model of 3D volume. The proposed model effectively extracts image features from LR symmetric positions. The multi-shift symmetric feature extraction module was employed to accommodate small positional gaps among LR corresponding positions. The experimental results of 3D volume classification tasks of the lung and brain showed that the proposed method achieved superior performances compared to the previous models. Our code is available at https://github.com/modafone/lr3dvolumeclassification .

Me gusta

Guardar

Ver artículo completo