Researchers of a new study proposed a multi-scale segmentation network using a cascading pyramid convolution module (CPCM) and a double-input channel attention module (DCAM) for accurately segmenting prostate cancer (PCa) lesions using multiparametric magnetic resonance imaging (mpMRI). The results appeared in the journal Medical Physics.
To construct the datasets, the investigators first extracted the region of interest (ROI) data by enlarging target region to reduce the background noise. Subsequently, they designed four CPCMs with large convolution to enhance the feature extraction. They simultaneously used convolution decomposition to attenuate any computational complexity before adopting the DCAM.
According to the results, this proposed model achieved a robust Dice similarity coefficient (DSC) of 79.31% and an average boundary distance (ABD) of 4.15 mm. The researchers noted that the the Prostate Multi-parametric MRI (PROMM) dataset, the method “greatly improved” the DSC to 82.11% and obtained an ABD of 3.64 mm.
“The experimental results on two different mpMRI prostate datasets demonstrate that our model is more accurate and reliable on small targets. In addition, it outperforms other state-of-the-art methods. This article is protected by copyright. All rights reserved,” the researchers concluded.