Y-DATA#15: ML in Medical Imaging

Y-DATA Meetup #15
ML in Medical Imaging

Online event
https://us02web.zoom.us/j/83261918644
Talks are in English

Intro:
At the upcoming meetup we'll talk about technological application of ML in the health domain and particularly the different ways in which ML is assisting radiologists in their hard work through automation, interpretation and decision support.
The two talks of this meetup complement each other, with one summarizing an industry case (Zebra Medical) and the other focusing on an independent research recently presented at MICCAI 2020 conference.

Agenda:

18:00 - 18:45
From Algorithms to FDA: Improving patients' care with AI-based triaging solutions

Speaker: Eyal Ziv, Senior Machine Learning & Computer Vision Researcher at Zebra Medical Vision

18:45 - 19:30
Nodule2vec: a 3D Deep Learning System for Pulmonary Nodule Retrieval Using Semantic Representation

Speaker: Ilia Kravets, Independent consultant and researcher

-----------
Talk Details:

Talk #1 -
Abstract:
Chest radiography is by far the most commonly performed radiological examination for screening and diagnosis of many cardiac and pulmonary diseases. However, there is an immense world-wide decrease in the number of physicians capable of providing their rapid and accurate interpretation. With 2 billion people joining the middle class worldwide and a growing global shortage of clinical experts, there is a sense of urgency to develop technologies which can help bridge the gap between supply and demand of radiology services.

Here we will review the research and development of Zebra-Medical AI based solutions aimed at providing automated and scalable diagnostic support in interpretation of chest radiographs.
We'll demonstrate the application of our technology on real life clinical examples where such solutions have impacted patients' care by substantially reducing time to treatment and preventing misdiagnosis.

Bio:
Eyal Ziv is a senior ML and computer vision researcher at the R&D team of Zebra Medical Vision. Eyal’s research is focusing on classification and detection of lesions in x-ray images.
Prior to joining Zebra Medical Vision, he worked as a ML researcher in the Aerospace division of Elbit Systems, developing algorithms for autonomous platforms. Eyal Ziv holds his BSc in Aerospace Engineering from the Technion institute. His topics of interest are multimodal learning and meta learning.

Talk #2
Abstract:
Content-based retrieval supports a radiologist decision making process by presenting the doctor the most similar cases from the database containing both historical diagnosis and further disease development history. We present a deep learning system that transforms a 3D image of a pulmonary nodule from a CT scan into a low-dimensional embedding vector. We demonstrate that such a vector representation preserves semantic information about the nodule and offers a viable approach for content-based image retrieval (CBIR). We discuss the theoretical limitations of the available datasets and overcome them by applying transfer learning of the state-of-the-art lung nodule detection model. We evaluate the system using the LIDC-IDRI dataset of thoracic CT scans. We devise a similarity score and show that it can be utilized to measure similarity 1) between annotations of the same nodule by different radiologists and 2) between the query nodule and the top four CBIR results. A comparison between doctors and algorithm scores suggests that the benefit provided by the system to the radiologist end-user is comparable to obtaining a second radiologist's opinion.

Bio:
Ilia Kravets is a freelancer with 20 years of experience combining software, hardware, and algorithms to develop amazing products. He has led the development of multidisciplinary projects, such as imaging radar, algorithmic trading platform, and medical devices. A couple of years ago Ilia discovered machine learning and has been fascinated with the field ever since.