Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer Journal Article
| Authors: | Jiang, J.; Choi, C. M. S.; Thor, M.; Deasy, J. O.; Veeraraghavan, H. |
| Article Title: | Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer |
| Abstract: | Background: Voxel-based analysis (VBA) for population level radiotherapy (RT) outcomes modeling requires topology preserving inter-patient deformable image registration (DIR) that preserves tumors on moving images while avoiding unrealistic deformations due to tumors occurring on fixed images. Purpose: We developed a tumor-aware recurrent registration (TRACER) deep learning (DL) method and evaluated its suitability for VBA. Methods: TRACER consists of encoder layers implemented with stacked 3D convolutional long short term memory network (3D-CLSTM) followed by decoder and spatial transform layers to compute dense deformation vector field (DVF). Multiple CLSTM steps are used to compute a progressive sequence of deformations. Input conditioning was applied by including tumor segmentations with 3D image pairs as input channels. Bidirectional tumor rigidity, image similarity, and deformation smoothness losses were used to optimize the network in an unsupervised manner. TRACER and multiple DL methods were trained with 204 3D computed tomography (CT) image pairs from patients with lung cancers (LC) and evaluated using (a) Dataset I (N = 308 pairs) with DL segmented LCs, (b) Dataset II (N = 765 pairs) with manually delineated LCs, and (c) Dataset III with 42 LC patients treated with RT. Results: TRACER accurately aligned normal tissues. It best preserved tumors, indicated by the smallest tumor volume difference of 0.24%, 0.40%, and 0.13 % and mean square error in CT intensities of 0.005, 0.005, 0.004, computed between original and resampled moving image tumors, for Datasets I, II, and III, respectively. It resulted in the smallest planned RT tumor dose difference computed between original and resampled moving images of 0.01 and 0.013 Gy when using a female and a male reference. Conclusions: TRACER is a suitable method for inter-patient registration involving LC occurring in both fixed and moving images and applicable to voxel-based analysis methods. © 2024 American Association of Physicists in Medicine. |
| Keywords: | cancer recurrence; radiation dose; computer assisted tomography; tumor volume; lung neoplasms; radiotherapy; lung cancer; tomography, x-ray computed; diagnostic imaging; information processing; lung tumor; computerized tomography; imaging, three-dimensional; image processing, computer-assisted; image processing; computed tomography; image registration; image segmentation; lung cancers; procedures; image pairs; image coding; deformable image registration; three-dimensional imaging; humans; human; article; learning methods; x-ray computed tomography; deep learning; convolutional neural network; voxel-based analysis; long short-term memory; deformable registration algorithm; photointerpretation; inter-patient registration; tumor conditioning; linear transformations; moving image; patient registration; convolutional long short term memory network |
| Journal Title: | Medical Physics |
| Volume: | 52 |
| Issue: | 2 |
| ISSN: | 0094-2405 |
| Publisher: | American Association of Physicists in Medicine |
| Date Published: | 2025-02-01 |
| Start Page: | 938 |
| End Page: | 950 |
| Language: | English |
| DOI: | 10.1002/mp.17536 |
| PUBMED: | 39589333 |
| PROVIDER: | scopus |
| PMCID: | PMC12153972 |
| DOI/URL: | |
| Notes: | The MSK Cancer Center Support Grant (P30 CA008748) is acknowledged in the PubMed record and PDF. Corresponding MSK authors are Jue Jiang and Harini Veeraraghavan -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
-
527Deasy -
159Veeraraghavan -
150Thor -
79Jiang -
3Choi
Related MSK Work