EUVIMEDDescubrir EUVIMED
Open access

Deep learning for automatic organ and tumor segmentation in nanomedicine pharmacokinetics

Alex Dhaliwal, Jun Ma, Mark Zheng, Qing Lyu, Maneesha A Rajora, Shihao Ma, Laura Oliva, Anthony Ku, Michael Valic, Bo Wang, Gang Zheng

Theranostics · 2024 · 14 (3) · 973-987

DOI: 10.7150/thno.90246 ↗

At a glance

Journal article in Theranostics, 2024. Written by Alex Dhaliwal and 10 co-authors. Institution: Princess Margaret Cancer Centre, University Health Network, 101 College Street, Toronto, M5G 1L7, Ontario, Canada. Major MEDLINE topics: Deep Learning, Neoplasms. Cited 24 times so far (Crossref). The full text is freely available in PubMed Central.

ResumenSubjectsDatos bibliográficosCiteRelated studies

Abstract (original language)

Rationale

Multimodal imaging provides important pharmacokinetic and dosimetry information during nanomedicine development and optimization. However, accurate quantitation is time-consuming, resource intensive, and requires anatomical expertise.

Methods

We present NanoMASK: a 3D U-Net adapted deep learning tool capable of rapid, automatic organ segmentation of multimodal imaging data that can output key clinical dosimetry metrics without manual intervention. This model was trained on 355 manually-contoured PET/CT data volumes of mice injected with a variety of nanomaterials and imaged over 48 hours.

Results

NanoMASK produced 3-dimensional contours of the heart, lungs, liver, spleen, kidneys, and tumor with high volumetric accuracy (pan-organ average %DSC of 92.5). Pharmacokinetic metrics including %ID/cc, %ID, and SUVmax achieved correlation coefficients exceeding R = 0.987 and relative mean errors below 0.2%. NanoMASK was applied to novel datasets of lipid nanoparticles and antibody-drug conjugates with a minimal drop in accuracy, illustrating its generalizability to different classes of nanomedicines. Furthermore, 20 additional auto-segmentation models were developed using training data subsets based on image modality, experimental imaging timepoint, and tumor status. These were used to explore the fundamental biases and dependencies of auto-segmentation models built on a 3D U-Net architecture, revealing significant differential impacts on organ segmentation accuracy.

Conclusions

NanoMASK is an easy-to-use, adaptable tool for improving accuracy and throughput in imaging-based pharmacokinetic studies of nanomedicine. It has been made publicly available to all readers for automatic segmentation and pharmacokinetic analysis across a diverse array of nanoparticles, expediting agent development.

Subjects

MeSH terms (MEDLINE)

Deep LearningNeoplasmsAnimalsMiceNanomedicinePositron Emission Tomography Computed TomographyHeart

Author keywords

Auto-SegmentationCTContouringDeep LearningFunctional ImagingMultimodalMultiparameterNanomedicinePETPharmacokineticsRadioimaging

Authors and institutions

  • Princess Margaret Cancer Centre, University Health Network, 101 College Street, Toronto, M5G 1L7, Ontario, Canada.
  • Department of Medical Biophysics, University of Toronto, 101 College Street, Toronto, M5G 1L7, Ontario, Canada.
  • Department of Laboratory Medicine and Pathobiology, University of Toronto, 1 King's College Circle, Toronto, M5S 1A8, Ontario, Canada.
  • Peter Munk Cardiac Centre, University Health Network, 190 Elizabeth St, Toronto, M5G 2C4, Ontario, Canada.
  • Vector Institute for Artificial Intelligence, 661 University Avenue, Toronto, M4G 1M1, Ontario, Canada.
  • Department of Computer Science, University of Toronto, 101 College Street, Toronto, M5G 1L7, Ontario, Canada.

Cite

APA

Dhaliwal, A., Ma, J., Zheng, M., Lyu, Q., Rajora, M. A., Ma, S., Oliva, L., Ku, A., Valic, M., Wang, B., & Zheng, G. (2024). Deep learning for automatic organ and tumor segmentation in nanomedicine pharmacokinetics. Theranostics, 14(3), 973-987. https://doi.org/10.7150/thno.90246

Vancouver

Dhaliwal A, Ma J, Zheng M, Lyu Q, Rajora MA, Ma S, et al. Deep learning for automatic organ and tumor segmentation in nanomedicine pharmacokinetics. Theranostics. 2024;14(3):973-987. doi:10.7150/thno.90246

BibTeX
@article{Dhaliwal2024,
  author = {Dhaliwal, Alex and Ma, Jun and Zheng, Mark and Lyu, Qing and Rajora, Maneesha A and Ma, Shihao and Oliva, Laura and Ku, Anthony and Valic, Michael and Wang, Bo and Zheng, Gang},
  title = {Deep learning for automatic organ and tumor segmentation in nanomedicine pharmacokinetics},
  journal = {Theranostics},
  year = {2024},
  volume = {14},
  number = {3},
  pages = {973--987},
  doi = {10.7150/thno.90246}
}
Start for free →