DEAU-Net: Attention networks based on dual encoder for Medical Image Segmentation

Article Computer Science, Interdisciplinary Applications

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

Jeya Maria Jose Valanarasu et al.

Summary: Most medical image segmentation methods use U-Net or its variants, but they often struggle with detecting smaller structures and accurately segmenting boundary regions. To address this issue, we propose KiU-Net, a convolutional architecture that combines overcomplete projection and U-Net to capture both high-level features and fine details. We demonstrate through experiments on multiple datasets that KiU-Net achieves good performance with fewer parameters and faster convergence.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2022)

Add to Collection

Article Engineering, Biomedical

Anterior chamber angle classification in anterior segment optical coherence tomography images using hybrid attention based pyramidal convolutional network

Quan Zhou et al.

Summary: This study proposes a deep learning algorithm for accurate classification of ACA in AS-OCT images. The method uses pyramid convolution to learn distinguishable representations from training images, with skip connections and a hybrid attention module to increase classification accuracy.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Engineering, Biomedical

Deep learning architecture based on segmented fundus image features for classification of diabetic retinopathy

Sraddha Das et al.

Summary: Diabetic retinopathy is a vision issue caused by blood vessel blockages, lesions, or bleeding in the retina, with assessment of retinal vasculature being crucial for diagnosis. The algorithm utilizes the maximal principal curvature technique for vessel extraction and achieves improved diagnostic results through histogram equalization and morphological processing. By training a classifier with CNN, the proposed method demonstrates high classification accuracy on the DIARETDB1 dataset.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Engineering, Biomedical