KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks

Aleksei Tiulpin, Iaroslav Melekhov, Simo Saarakkala

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

This paper addresses the challenge of localization of anatomical landmarks in knee X-ray images at different stages of osteoarthritis (OA). Landmark localization can be viewed as regression problem, where the landmark position is directly predicted by using the region of interest or even full-size images leading to large memory footprint, especially in case of high resolution medical images. In this work, we propose an efficient deep neural networks framework with an hourglass architecture utilizing a soft-argmax layer to directly predict normalized coordinates of the landmark points. We provide an extensive evaluation of different regularization techniques and various loss functions to understand their influence on the localization performance. Furthermore, we introduce the concept of transfer learning from low-budget annotations, and experimentally demonstrate that such approach is improving the accuracy of landmark localization. Compared to the prior methods, we validate our model on two datasets that are independent from the train data and assess the performance of the method for different stages of OA severity. The proposed approach demonstrates better generalization performance compared to the current state-of-the-art.
Original languageEnglish
Title of host publicationThe IEEE International Conference on Computer Vision (ICCV) Workshops
PublisherIEEE
ISBN (Electronic)978-1-7281-5023-9
DOIs
Publication statusAccepted/In press - 2019
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Computer Vision Workshop - Seoul, Korea, Republic of
Duration: 27 Oct 201928 Oct 2019

Conference

ConferenceIEEE International Conference on Computer Vision Workshop
Abbreviated titleICCvW
CountryKorea, Republic of
CitySeoul
Period27/10/201928/10/2019

Fingerprint Dive into the research topics of 'KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks'. Together they form a unique fingerprint.

  • Cite this

    Tiulpin, A., Melekhov, I., & Saarakkala, S. (Accepted/In press). KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks. In The IEEE International Conference on Computer Vision (ICCV) Workshops IEEE. https://doi.org/10.1109/ICCVW.2019.00046