Prior Guided 3D Medical Image Landmark Localization

Yijie Pang, Pujin Cheng, Junyan Lyu, Fan Lin, Xiaoying Tang
Medical Imaging with Deep Learning, PMLR 227:1163-1175, 2024.

Abstract

Accurate detection of 3D landmarks is critical for evaluating and characterizing anatomical features and performing preoperative diagnostic screening. However, detecting 3D landmarks can be challenging due to the local structural homogeneity of medical images. To address this issue, physicians often annotate multiple landmarks in a single slice, particularly when estimating 3D distance or volume. In this study, we present a prior guided coarse-to-fine framework for efficient and accurate 3D medical landmark detection; we make use of the prior information that in specific settings physicians annotate multiple landmarks on a same slice. The coarse stage uses coordinate regression on downsampled 3D images to maintain the structural relationships across different landmarks. The fine stage categorizes landmarks as correlated and independent landmarks based on their annotation prior. For independent landmarks, we train multiple models to capture local features and ensure reliable local predictions. For correlated landmarks, we mimic the manual annotation process and propose a correlated landmark detection model that merges information from various patches to query key slices and identify correlated landmarks. Our method is extensively evaluated on two datasets, exhibiting superior performance with an average detection error of respective 3.29 mm and 2.13 mm.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-pang24a, title = {Prior Guided 3D Medical Image Landmark Localization}, author = {Pang, Yijie and Cheng, Pujin and Lyu, Junyan and Lin, Fan and Tang, Xiaoying}, booktitle = {Medical Imaging with Deep Learning}, pages = {1163--1175}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/pang24a/pang24a.pdf}, url = {https://proceedings.mlr.press/v227/pang24a.html}, abstract = {Accurate detection of 3D landmarks is critical for evaluating and characterizing anatomical features and performing preoperative diagnostic screening. However, detecting 3D landmarks can be challenging due to the local structural homogeneity of medical images. To address this issue, physicians often annotate multiple landmarks in a single slice, particularly when estimating 3D distance or volume. In this study, we present a prior guided coarse-to-fine framework for efficient and accurate 3D medical landmark detection; we make use of the prior information that in specific settings physicians annotate multiple landmarks on a same slice. The coarse stage uses coordinate regression on downsampled 3D images to maintain the structural relationships across different landmarks. The fine stage categorizes landmarks as correlated and independent landmarks based on their annotation prior. For independent landmarks, we train multiple models to capture local features and ensure reliable local predictions. For correlated landmarks, we mimic the manual annotation process and propose a correlated landmark detection model that merges information from various patches to query key slices and identify correlated landmarks. Our method is extensively evaluated on two datasets, exhibiting superior performance with an average detection error of respective 3.29 mm and 2.13 mm.} }
Endnote
%0 Conference Paper %T Prior Guided 3D Medical Image Landmark Localization %A Yijie Pang %A Pujin Cheng %A Junyan Lyu %A Fan Lin %A Xiaoying Tang %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-pang24a %I PMLR %P 1163--1175 %U https://proceedings.mlr.press/v227/pang24a.html %V 227 %X Accurate detection of 3D landmarks is critical for evaluating and characterizing anatomical features and performing preoperative diagnostic screening. However, detecting 3D landmarks can be challenging due to the local structural homogeneity of medical images. To address this issue, physicians often annotate multiple landmarks in a single slice, particularly when estimating 3D distance or volume. In this study, we present a prior guided coarse-to-fine framework for efficient and accurate 3D medical landmark detection; we make use of the prior information that in specific settings physicians annotate multiple landmarks on a same slice. The coarse stage uses coordinate regression on downsampled 3D images to maintain the structural relationships across different landmarks. The fine stage categorizes landmarks as correlated and independent landmarks based on their annotation prior. For independent landmarks, we train multiple models to capture local features and ensure reliable local predictions. For correlated landmarks, we mimic the manual annotation process and propose a correlated landmark detection model that merges information from various patches to query key slices and identify correlated landmarks. Our method is extensively evaluated on two datasets, exhibiting superior performance with an average detection error of respective 3.29 mm and 2.13 mm.
APA
Pang, Y., Cheng, P., Lyu, J., Lin, F. & Tang, X.. (2024). Prior Guided 3D Medical Image Landmark Localization. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:1163-1175 Available from https://proceedings.mlr.press/v227/pang24a.html.

Related Material