UniToChest: A Lung Image Dataset for Segmentation of Cancerous Nodules on CT Scans

Abstract

Lung cancer has emerged as a major causes of death and early detection of lung nodules is the key towards early cancer diagnosis and treatment effectiveness assessment. Deep neural networks achieve outstanding results in tasks such as lung nodules detection, segmentation and classification, however their performance depends on the quality of the training images and on the training procedure. This paper introduces UniToChest , a dataset consisting Computed Tomography (CT) scans of 623 patients and 10071 lesions labelled for segmentation with nodules spanning different diameters ranges. Then, we propose a lung nodules segmentation scheme relying on a convolutional neural architecture that we also re-purpose for a nodule detection task. The experimental results show accurate segmentation of lung nodules across a wide diameter range and better detection accuracy over a traditional detection approach. The datasets and the code used in this paper are publicly made available as a baseline reference.

Lung Nodules Segmentation with DeepHealth Toolkit

“…Moreover, it includes images acquired using 10 different devices. The demographic details of patients and insights of the data collection process can be found in the original dataset paper (accepted to ICIAP 2022) [4]. For all the CT scan slices in UniToChest, the radiologist has manually segmented the present lung nodules to provide a segmentation mask.…”