EUVIMEDPoznaj EUVIMED
Open access

Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers

Yao Zhao, Xin Wang, Jack Phan, Xinru Chen, Anna Lee, Cenji Yu, Kai Huang, Laurence E Court, Tinsu Pan, He Wang, Kareem Abdul Wahid, Abdalah S R Mohamed and 3 more

Medical Physics · 2024-10 · 51 (10) · 7295-7307

DOI: 10.1002/mp.17260 ↗

At a glance

Journal article in Medical Physics, published online on 2024-06-19. Written by Yao Zhao and 14 co-authors. Institution: Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA. Major MEDLINE topics: Head and Neck Neoplasms, Image Processing, Computer-Assisted, Positron Emission Tomography Computed Tomography, Tumor Burden. Cited 6 times so far (Crossref); 44 references. The full text is freely available in PubMed Central. Funded by: NCI NIH HHS, MD Anderson Cancer Center, Image Guided Cancer Therapy.

AbstraktSubjectsDane bibliograficzneCiteRelated studies

Abstract (original language)

Background

Head and neck (HN) gross tumor volume (GTV) auto‐segmentation is challenging due to the morphological complexity and low image contrast of targets. Multi‐modality images, including computed tomography (CT) and positron emission tomography (PET), are used in the routine clinic to assist radiation oncologists for accurate GTV delineation. However, the availability of PET imaging may not always be guaranteed.

Purpose

To develop a deep learning segmentation framework for automated GTV delineation of HN cancers using a combination of PET/CT images, while addressing the challenge of missing PET data.

Methods

Two datasets were included for this study: Dataset I: 524 (training) and 359 (testing) oropharyngeal cancer patients from different institutions with their PET/CT pairs provided by the HECKTOR Challenge; Dataset II: 90 HN patients(testing) from a local institution with their planning CT, PET/CT pairs. To handle potentially missing PET images, a model training strategy named the “Blank Channel” method was implemented. To simulate the absence of a PET image, a blank array with the same dimensions as the CT image was generated to meet the dual‐channel input requirement of the deep learning model. During the model training process, the model was randomly presented with either a real PET/CT pair or a blank/CT pair. This allowed the model to learn the relationship between the CT image and the corresponding GTV delineation based on available modalities. As a result, our model had the ability to handle flexible inputs during prediction, making it suitable for cases where PET images are missing. To evaluate the performance of our proposed model, we trained it using training patients from Dataset I and tested it with Dataset II. We compared our model (Model 1) with two other models which were trained for specific modality segmentations: Model 2 trained with only CT images, and Model 3 trained with real PET/CT pairs. The performance of the models was evaluated using quantitative metrics, including Dice similarity coefficient (DSC), mean surface distance (MSD), and 95% Hausdorff Distance (HD95). In addition, we evaluated our Model 1 and Model 3 using the 359 test cases in Dataset I.

Results

Our proposed model(Model 1) achieved promising results for GTV auto‐segmentation using PET/CT images, with the flexibility of missing PET images. Specifically, when assessed with only CT images in Dataset II, Model 1 achieved DSC of 0.56 ± 0.16, MSD of 3.4 ± 2.1 mm, and HD95 of 13.9 ± 7.6 mm. When the PET images were included, the performance of our model was improved to DSC of 0.62 ± 0.14, MSD of 2.8 ± 1.7 mm, and HD95 of 10.5 ± 6.5 mm. These results are comparable to those achieved by Model 2 and Model 3, illustrating Model 1′s effectiveness in utilizing flexible input modalities. Further analysis using the test dataset from Dataset I showed that Model 1 achieved an average DSC of 0.77, surpassing the overall average DSC of 0.72 among all participants in the HECKTOR Challenge.

Conclusions

We successfully refined a multi‐modal segmentation tool for accurate GTV delineation for HN cancer. Our method addressed the issue of missing PET images by allowing flexible data input, thereby providing a practical solution for clinical settings where access to PET imaging may be limited.

Subjects

MeSH terms (MEDLINE)

Head and Neck NeoplasmsImage Processing, Computer-AssistedPositron Emission Tomography Computed TomographyTumor BurdenDeep LearningHumansAutomation

Author keywords

PET/CTauto‐segmentationgross tumor volumehead and neck cancermulti‐modality

Authors and institutions

  • Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • UTHealth Houston Graduate School of Biomedical Sciences, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.
  • Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.

Funding

  • NCI NIH HHS
  • MD Anderson Cancer Center
  • Image Guided Cancer Therapy
  • National Institutes of Health through Cancer
  • T32 Training Program Fellowship
  • University of Texas MD Anderson Cancer Center

Cite

APA

Zhao, Y., Wang, X., Phan, J., Chen, X., Lee, A., Yu, C., Huang, K., Court, L. E., Pan, T., Wang, H., Wahid, K. A., Mohamed, A. S. R., Naser, M., Fuller, C. D., & Yang, J. (2024). Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers. Medical Physics, 51(10), 7295-7307. https://doi.org/10.1002/mp.17260

Vancouver

Zhao Y, Wang X, Phan J, Chen X, Lee A, Yu C, et al. Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers. Medical Physics. 2024;51(10):7295-7307. doi:10.1002/mp.17260

BibTeX
@article{Zhao2024,
  author = {Zhao, Yao and Wang, Xin and Phan, Jack and Chen, Xinru and Lee, Anna and Yu, Cenji and Huang, Kai and Court, Laurence E and Pan, Tinsu and Wang, He and Wahid, Kareem Abdul and Mohamed, Abdalah S R and Naser, Mohamed and Fuller, Clifton D and Yang, Jinzhong},
  title = {Multi‐modal segmentation with missing image data for automatic delineation of gross tumor volumes in head and neck cancers},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {10},
  pages = {7295--7307},
  doi = {10.1002/mp.17260}
}
Start for free →