Small Lesion Segmentation in Brain MRIs with Subpixel Embedding
This work addresses the challenge of accurate small lesion segmentation in medical imaging for stroke diagnosis, which is incremental as it builds upon existing encoder-decoder architectures with novel components.
The paper tackles the problem of segmenting small ischemic stroke lesions in brain MRI scans by proposing a neural network architecture with a spatial expansion embedding network and a learnable downsampler, achieving an 11.7% improvement over the baseline and state-of-the-art results on the ATLAS benchmark dataset.
We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encoder-decoder where predictions are guided by a spatial expansion embedding network. Our embedding network learns features that can resolve detailed structures in the brain without the need for high-resolution training images, which are often unavailable and expensive to acquire. Alternatively, the encoder-decoder learns global structures by means of striding and max pooling. Our embedding network complements the encoder-decoder architecture by guiding the decoder with fine-grained details lost to spatial downsampling during the encoder stage. Unlike previous works, our decoder outputs at 2 times the input resolution, where a single pixel in the input resolution is predicted by four neighboring subpixels in our output. To obtain the output at the original scale, we propose a learnable downsampler (as opposed to hand-crafted ones e.g. bilinear) that combines subpixel predictions. Our approach improves the baseline architecture by approximately 11.7% and achieves the state of the art on the ATLAS public benchmark dataset with a smaller memory footprint and faster runtime than the best competing method. Our source code has been made available at: https://github.com/alexklwong/subpixel-embedding-segmentation.