Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

No abstract

Accurately estimating the size of tumours and reproducing their boundaries from lung CT images provides crucial information for early diagnosis, staging and evaluating patients response to cancer therapy. This paper presents an advanced solution to segment lung nodules from CT images by employing a deep residual network structure with Atrous convolution. The Atrous convolution increases the field of view of the filters and helps to improve classification accuracy. Moreover, in order to address the significant class imbalance issue between the nodule pixels and background non-nodule pixels, a weighted loss function is proposed. We evaluate our proposed solution on the widely adopted benchmark dataset LIDC. A promising result of an average DCS of 81.24% is achieved, outperforming the state of the arts. This demonstrates the effectiveness and importance of applying the Atrous convolution and weighted loss for such problems.

No abstract

Connecting distributed generation (DG) units to the distribute networks impose several impacts on it which have not been considered in conventional fault location algorithms. This paper presents an accurate fault location technique for unbalanced radial distribution networks based on evaluating measured values of short Circuit Current (S/C.C) at the source bus with a designed Multi-Layer Feed Forwarded Neural Network (ML-FFNN). The estimated locations of different fault types are compared with the actual distances and Average Difference Percentage (ADP) is calculated for each fault type. The designed neural network is able to work with small scale datasets. Hence the proposed method can be implemented in the real distribution networks.