Ashkan Pakzad

Hi! I’m a Medical Imaging i4health PhD Student in the Satsuma Lab, Centre for Medical Image Computing at University College London. I post and share about my work in medical imaging.

About me

Imaging for Cystic Fibrosis Research

Check out this video explaining the motivation behind my imaging research for Cystic Fibrosis.

News

Bloomsbury Festival 2022 with CMIC

Bloomsbury Festival 2022 with CMIC Had a fantastic time at the BREATHE Bloomsbury Festival 2022 along with friends and collages from the centre for medical image computing UCL. It was a great opportunity to speak to those outside the research bubble about what we do.

Oct 20, 2022

ERS 2022 meeting - Oral and poster abstracts presented on AirQuant

It was a pleasure to present our work at #ers2022! Computer derived measures of the airways in CT using #AirQuant can predict mortality in IPF. Thank you to my co-authors Tony Wing Keung Cheung, Nesrin Moğulkoç Bishop, Recep Savas, Daniel Alexander, Yipeng Hu, Professor John Hurst, Joseph Jacob

Sep 10, 2022 conference

ERS 2022 meeting - Oral and poster abstracts presented on AirQuant

MICCAI 2022 meeting - Paper accepted to DGM4MICCAI workshop

New paper on “Evaluation of automated airway morphological quantification for assessing fibrosing lung disease” to be presented at Deep Generative Models workshop @ MICCAI 2022. We present a completely labelless automated airway measurement method that learns to regress to an airway’s diameter.

Aug 30, 2022 conference

See all

Projects

Airway Transfer Network

The problem Chronic lung diseases, like idiopathic pulmonary fibrosis (IPF) are characterised by abnormal dilatation of the airways. Quantification of airway features on computed tomography (CT) can help characterise disease progression.

AirQuant - Quantification of airway tapering, analysis of chest X-ray CT

The goal of this project is to come up with a more objective method to measure the severity of structural lung diseases such as cystic fibrosis and idiopathic pulmonary fibrosis. In these diseases, the airways dilate and worsen with disease progression (bronchiectasis).

Improving X-ray CT images of the Antikythera Mechanism

The Antikythera Mechanism is best described as a 2000 year old ancient greek astronomical computer. Having laid on the sea for the majority of this time its bronze interior has corroded and calcified making it incredibly fragile.

Publications

(2022). Airway measurement by refinement of synthetic images improves mortality prediction in idiopathic pulmonary fibrosis. arXiv.

PDF Cite Code Project

(2022). Radiology of Bronchiectasis. Clinics in Chest Medicine.

PDF Cite

(2021). Evaluation of automated airway morphological quantification for assessing fibrosing lung disease. arXiv.

PDF Cite Code

(2018). Improved X-ray computed tomography reconstruction of the largest fragment of the Antikythera Mechanism, an ancient Greek astronomical calculator. PLOS ONE.

PDF Cite Dataset Project DOI

Posts

Aug 14, 2020 6 min read article

Understanding 3D medical image orientation for programmers

If you’re new to working with medical images, then you’re in for a minefield. You’re going to have to put intuition aside because in alot of this, there isn’t any, or at least there was to start off with.

Apr 5, 2019 4 min read article

Reading & Editing DICOM Metadata w/ Python

When my image viewer wouldn’t load a particular CT dataset, I was struck with errors telling me that I’m ‘missing geometry information’, looking at the metadata associated with DICOM images absolutely overwhelmed me.

Apr 5, 2019 4 min read article

Using GitHub and Google Drive with google collab to manage code and data

Google colab is an incredible resource bringing GPU capabilities to those with just an internet connection (it doesn’t even have to be the best at that!) It’s literally an out of the box, ready set up Jupyter Notebook environment with pretty much every module you’ll want.

Mar 2, 2019 5 min read article

The Antikythera Mechanism and improving the best image we have of its inner workings

The Antikythera Mechanism is an astronomical calculator made by the ancient Greeks in 200 BC that was capable of indicating the timing and characteristics of eclipses, positions of the sun and moon, including the moon’s phase and quite possibly the location of the five visible planets that can be seen with the naked eye.