# Prostate segmentation using Z-net

## TL;DR

This paper introduces Z-net, a novel CNN architecture inspired by U-net, designed for prostate segmentation in MRI images, demonstrating superior performance over classical CNNs through extensive evaluation.

## Contribution

The paper presents Z-net, a new CNN architecture with multi-level feature capturing, and compares three sample size normalization methods, establishing 2D resize as most effective.

## Key findings

- Z-net outperforms classical CNNs in prostate segmentation.
- 2D resize is the most suitable sample normalization method.
- Z-net effectively captures multi-level features for improved segmentation.

## Abstract

In this paper, we proposed a novel architecture of convolutional neural network (CNN), namely Z-net, for segmenting prostate from magnetic resonance images (MRIs). In the proposed Z-net, 5 pairs of Z-block and decoder Z-block with different sizes and numbers of feature maps were assembled in a way similar to that of U-net. The proposed architecture can capture more multi-level features by using concatenation and dense connection. A total of 45 training images were used to train the proposed Z-net and the evaluations were conducted qualitatively on 5 validation images and quantitatively on 30 testing images. In addition, three approaches including pad and cut, 2D resize, and 3D resize for uniforming the size of samples were evaluated and compared. The experimental results demonstrated that the 2D resize is the most suitable approach for the proposed Z-net. Compared to the other two classical CNN architectures, the proposed method was observed with superior performance for segmenting prostate.