Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910824503705600 |
|---|---|
| author | Syed, Tahir Khan, Ariba Hanif, Sawera |
| author_facet | Syed, Tahir Khan, Ariba Hanif, Sawera |
| contents | Medical images are often high-resolution and lose important detail if downsampled, making pixel-level methods such as semantic segmentation much less efficient if performed on a low-dimensional image. We propose a low-rank Matryoshka projection and a hybrid segmenting architecture that preserves important information while retaining sufficient pixel geometry for pixel-level tasks. We design the Matryoshka Autoencoder (MatAE-U-Net) which combines the hierarchical encoding of the Matryoshka Autoencoder with the spatial reconstruction capabilities of a U-Net decoder, leveraging multi-scale feature extraction and skip connections to enhance accuracy and generalisation. We apply it to the problem of segmenting the left ventricle (LV) in echocardiographic images using the Stanford EchoNet-D dataset, including 1,000 standardised video-mask pairs of cardiac ultrasound videos resized to 112x112 pixels. The MatAE-UNet model achieves a Mean IoU of 77.68\%, Mean Pixel Accuracy of 97.46\%, and Dice Coefficient of 86.91\%, outperforming the baseline U-Net, which attains a Mean IoU of 74.70\%, Mean Pixel Accuracy of 97.31\%, and Dice Coefficient of 85.20\%. The results highlight the potential of using the U-Net in the recursive Matroshka latent space for imaging problems with low-contrast such as echocardiographic analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08988 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes Syed, Tahir Khan, Ariba Hanif, Sawera Computer Vision and Pattern Recognition G3 Medical images are often high-resolution and lose important detail if downsampled, making pixel-level methods such as semantic segmentation much less efficient if performed on a low-dimensional image. We propose a low-rank Matryoshka projection and a hybrid segmenting architecture that preserves important information while retaining sufficient pixel geometry for pixel-level tasks. We design the Matryoshka Autoencoder (MatAE-U-Net) which combines the hierarchical encoding of the Matryoshka Autoencoder with the spatial reconstruction capabilities of a U-Net decoder, leveraging multi-scale feature extraction and skip connections to enhance accuracy and generalisation. We apply it to the problem of segmenting the left ventricle (LV) in echocardiographic images using the Stanford EchoNet-D dataset, including 1,000 standardised video-mask pairs of cardiac ultrasound videos resized to 112x112 pixels. The MatAE-UNet model achieves a Mean IoU of 77.68\%, Mean Pixel Accuracy of 97.46\%, and Dice Coefficient of 86.91\%, outperforming the baseline U-Net, which attains a Mean IoU of 74.70\%, Mean Pixel Accuracy of 97.31\%, and Dice Coefficient of 85.20\%. The results highlight the potential of using the U-Net in the recursive Matroshka latent space for imaging problems with low-contrast such as echocardiographic analysis. |
| title | Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes |
| topic | Computer Vision and Pattern Recognition G3 |
| url | https://arxiv.org/abs/2502.08988 |