Radiology | DAISYlabs

StructSeg 2019 - Task 4

Tue, 01 Oct 2019 00:01:00 +0000

Aim

The goal of this task was the segmentation of the gross target volume of lung cancer in chest CT scans:

Background

Radiation therapy is one type of important cancer treatment for killing cancer cells with external beam radiation. Treatment planning is vital for the treatment, which sets up the radiation dose distribution for tumor and ordinary organs. The goal of planning is to ensure the cancer cells receiving enough radiation and to prevent normal cells in organs-at-risk (OAR) from being damaged too much. Organs-at-risk are usually the organs that are sensitive to radiation. For instance, optical nerves and chiasma in the head cannot receive too much radiation otherwise the patient risks losing his/her vision. Gross Target Volume (GTV) is the position and extent of gross tumor imaged by CT scans, i.e. what can be seen.

One important step in radiotherapy treatment planning is therefore to delineate the boundaries of tens of OARs and GTV in every slice of a patient’s CT scans, which is tedious and occupies much of oncologists’ time. Automatic OAR and GTV delineation would substantially reduce the treatment planning time and therefore reduce the overall cost for radiotherapy.

Results

Challenge

https://structseg2019.grand-challenge.org

MR Brain Segmentation 2018 - MRBrainS18

Sun, 16 Sep 2018 00:00:00 +0000

Aim

The purpose of this challenge is to directly compare methods for segmentation of gray matter, white matter, cerebrospinal fluid, and other structures on 3T MRI scans of the brain, and to assess the effect of (large) pathologies on segmentation and volumetry.

Background

Many algorithms for segmenting brain structures in MRI scans have been proposed over the years. Especially in such a well-established research area, there is a tremendous need for fair comparison of these methods with respect to accuracy and robustness. Although there is an increasing awareness of the importance of comparing different algorithms on the same data, many methods are still compared to previous versions of the same type of algorithm on privately held data. This complicates the choice for a certain brain segmentation method among a wide variety of available methods.

This challenge aims to directly compare automated brain segmentation methods. The output will be a ranking of techniques that robustly and accurately segment brain structure on MR brain images, both with and without pathology. We welcome both multi- and single-sequence (i.e. T1-weighted only) approaches.

Results

Challenge

https://mrbrains18.isi.uu.nl

StructSeg 2019 - Task 3

Tue, 01 Oct 2019 00:00:00 +0000

Aim

The goal of this task was the segmentation of six organ-at-risk in chest CT scans:

left lung
right lung
spinal cord
esophagus
heart
trachea

Background

Results

Challenge

https://structseg2019.grand-challenge.org

SIIM-ACR Pneumothorax Segmentation

Mon, 26 Aug 2019 00:00:00 +0000

Aim

Th goal of this competition is to develop a model to classify (and if present, segment) pneumothorax from a set of chest radiographic images.

Background

Imagine suddenly gasping for air, helplessly breathless for no apparent reason. Could it be a collapsed lung? In the future, your entry in this competition could predict the answer.

Pneumothorax can be caused by a blunt chest injury, damage from underlying lung disease, or most horrifying—it may occur for no obvious reason at all. On some occasions, a collapsed lung can be a life-threatening event.

Pneumothorax is usually diagnosed by a radiologist on a chest x-ray, and can sometimes be very difficult to confirm. An accurate AI algorithm to detect pneumothorax would be useful in a lot of clinical scenarios. AI could be used to triage chest radiographs for priority interpretation, or to provide a more confident diagnosis for non-radiologists.

Challenge

https://www.kaggle.com/c/siim-acr-pneumothorax-segmentation/