Page 138 - TD-4-1

Tumor Discovery Dosiomics

tomography and dose. Similarly, dosiomic-based models dosiomic research. Multicenter and international clinical
have been used to predict distant metastasis by analyzing studies should be designed to evaluate the predictive
the dose delivered to peritumoral regions. These findings accuracy of dosiomics in both toxicity and oncologic
1
suggest that dosiomics may serve as a valuable tool for outcomes. These studies should include diverse patient
tailoring radiotherapy protocols to maximize therapeutic populations and treatment modalities to ensure that the
efficacy while minimizing unnecessary exposure to healthy findings are broadly applicable. Finally, expanding the
tissues. scope of dosiomics beyond radiotherapy to include other

Despite these promising developments, there are still treatment modalities such as concurrent chemotherapy,
challenges in integrating dosiomics into routine clinical immunotherapy, and targeted therapies may provide
practice. First, the lack of standardization in feature a more comprehensive understanding of treatment
extraction and analysis methods limits the reproducibility responses. For example, analyzing the interaction between
of findings across studies. Notwithstanding the existence radiation dose distribution and immune activation may
of commercial software for extracting dosiomic features, open new avenues to optimize combination therapies
much more informative feature extraction methods in lung cancer. In addition, consensus guidelines and
powered by artificial intelligence (AI) are also available. guidelines for predictive models in dosiomics need to be
The creation of prediction models requires the usage established.
of very different algorithms, with certain pilot studies In conclusion, dosiomics is a powerful tool for
diving into the incorporation of big data to enhance achieving personalized treatments in lung cancer patients.
their predictability There is no standardization in the Addressing standardization challenges will be crucial
.1-8
studies yet, but these studies are very valuable and shed for integrating dosiomics into routine clinical practice.
light on the studies that will be created with big data. Dosiomics has the potential to improve both treatment
Different algorithms and software platforms often produce efficacy and quality of life of patients undergoing lung
inconsistent results, making it difficult to establish cancer treatment by leveraging technologies. Further
universal guidelines. Second, most dosiomic studies are research with international collaboration is needed in this
retrospective, relying on a small number of pre-existing exciting area to realize its full potential.
datasets with limited diversity. Prospective, multicenter,
and international studies are needed to validate the clinical Conflict of interest
utility of dosiomics and ensure its generalizability across The author declares that she has no conflict of interest and
different patient populations and treatment settings, has no competing interests.
considering that demographic characteristics also affect
prognosis. Future studies should take a holistic approach References
by integrating dosiomics with other forms of data, such 1. Dudas D, Dilling TJ, Naqa IE. A deep learning-informed
as genomics and immunomics, to capture the complexity interpretation of why and when dose metrics outside the
of treatment responses. To achieve personalized and PTV can affect the risk of distant metastasis in SBRT NSCLC
successful treatments, decisions must be made based on patients. Radiat Oncol. 2024;19(1):127.
more comprehensive data.
doi: 10.1186/s13014-024-02519-1
For clinically adopting dosiomics in the context of 2. Ma Z, Liang B, Wei R, et al. Enhanced prediction of
lung cancer, standardization with heterogeneous big data postoperative radiotherapy-induced esophagitis in non-
is necessary. First, efforts should be made to standardize small cell lung cancer: Dosiomic model development in a
methods for dosiomic feature extraction and identification real-world cohort and validation in the PORT-C randomized
of significant variables, which can be achieved through controlled trial. Thorac Cancer. 2023;14(28):2839-2845.
cross-study comparisons and meta-analyses. Second, doi: 10.1111/1759-7714.15068
AI techniques need to be integrated with dosiomics.
AI-driven models can process high-dimensional dosiomic 3. Zhou L, Wen Y, Zhang G, Wang L, Wu S, Zhang S. machine
data to reveal complex patterns and relationships that learning-based multiomics prediction model for radiation
may be overlooked by traditional statistical methods. pneumonitis. J Oncol. 2023;2023:5328927.
In addition, incorporating AI into dosiomic workflows doi: 10.1155/2023/5328927
can also facilitate clinical decision-making by evaluating 4. Adachi T, Nakamura M, Shintani T, et al. Multi-institutional
large amounts of data and providing real-time prediction. dose-segmented dosiomic analysis for predicting radiation
Third, collaborative efforts among researchers, clinicians, pneumonitis after lung stereotactic body radiation therapy.
and industry stakeholders are essential to advance Med Phys. 2021;48(4):1781-1791.

Volume 4 Issue 1 (2025) 130 doi: 10.36922/td.8465