# Segmentation of Lung Tumor from CT Images using Deep Supervision

arXiv: https://arxiv.org/abs/2111.09262 · HTML: https://mlsanity.com/paper/2111.09262/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 17 Nov 2021.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://mlsanity.com/paper/1902.04049/) (2019)
- [Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge](https://mlsanity.com/paper/1705.09435/) (2017)
- [Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet](https://mlsanity.com/paper/1812.01951/) (2018)
- [Semantic Segmentation of Pathological Lung Tissue with Dilated Fully Convolutional Networks](https://mlsanity.com/paper/1803.06167/) (2018)

## Built on by (most cited first, 2 of 2)

- [Optimizing Lung Cancer Detection in CT Imaging: A Wavelet Multi-Layer Perceptron (WMLP) Approach Enhanced by Dragonfly Algorithm (DA)](https://mlsanity.com/paper/2408.15355/) (2024)
- [Subgraph Clustering and Atom Learning for Improved Image Classification](https://mlsanity.com/paper/2407.14772/) (2024)

## Abstract (arXiv)

Lung cancer is a leading cause of death in most countries of the world. Since prompt diagnosis of tumors can allow oncologists to discern their nature, type and the mode of treatment, tumor detection and segmentation from CT Scan images is a crucial field of study worldwide. This paper approaches lung tumor segmentation by applying two-dimensional discrete wavelet transform (DWT) on the LOTUS dataset for more meticulous texture analysis whilst integrating information from neighboring CT slices before feeding them to a Deeply Supervised MultiResUNet model. Variations in learning rates, decay and optimization algorithms while training the network have led to different dice co-efficients, the detailed statistics of which have been included in this paper. We also discuss the challenges in this dataset and how we opted to overcome them. In essence, this study aims to maximize the success rate of predicting tumor regions from two dimensional CT Scan slices by experimenting with a number of adequate networks, resulting in a dice co-efficient of 0.8472.