Aruna Devi R, B. Optom Student,
IIVM College of Optometry, Coimbatore, India
Radiomics is a well-known image analysis technique that allows the extraction of quantitative descriptors from a digital radiological image that describe the morphology, texture, and intensity of a region or volume of interest. Classification models that automatically classify the presence or absence of diseases (a “positive” vs. “negative” task) have demonstrated that these traits correspond with the pathophysiology of numerous diseases. (1)
Radiomics Applications in Ophthalmology
Radiomics-based texture analysis utilises standard image analysis techniques to extract texture features from images. These techniques have had wide application in the fields of radiology and pathology and in recent years have seen increasing application in Ophthalmology to a variety of imaging modalities including OCT-Angiography (OCT-A), Optical Coherence Tomography (OCT) and ultra-wide field fluorescein angiography and to a variety of pathologies including Diabetic Macular Oedema, Myopic Maculopathy and Age-Related Macular Degeneration. (2)
Radiomics is a procedure that turns medical images into objective, mineable data by extracting a huge number of quantitative variables. (3) Radiomic analysis is made possible in Ophthalmology by high-resolution imaging modalities such as orbital MRI, fundus photography, ultrasound bio microscopy, OCT-A, and OCT. Early diagnosis, disease classification, and therapy result prediction are made possible by these applications. (4)
Workflow of Ophthalmic Radiomics
Radiomics starts with acquiring standardised, high-quality images to ensure consistency. Clinically significant Volumes of Interests (VOIs) are identified and segmented using computer-assisted methods. Quantitative features such as intensity, texture, and shape are then extracted from these regions and stored in a structured database. Finally, machine learning and data mining techniques analyse these features to develop predictive or prognostic classifier models.
Clinical Value of Radiomics in Eye Diseases
Radiomics plays a significant role in improving diagnostic accuracy and it has other specifications which are described in Table 1.
| Specifications | Clinical Value |
| Enhanced diagnostic accuracy | Better detection and differentiation of ocular diseases |
| Objective biomarkers | Reduces subjective bias and improves repeatability |
| Early/sub-clinical detection | Timely interventions before disease progression |
| Improved differential diagnosis | Accurate distinction between similar conditions |
| Prognosis/therapy prediction | Tailored treatment selection and monitoring |
| AI integration | Automated and intelligent clinical decision support |
| Non-invasive “virtual biopsy” | Safer alternative to invasive diagnostics |
Table 1: This table shows the advantages of radiomics.
Radiomics-Based Assessment of OCT-A For Doctor Diagnosis
A key demonstrated that radiomic features extracted from OCT and OCT-A images can accurately differentiate Diabetic Retinopathy stages. Their model showed that texture-based and vascular density related features improved classification performance compared with conventional metrics alone. (3)
Radiomics applied to OCT-A enables quantitative assessment of Capillary non-perfusion areas, Microaneurysms, Vessel tortuosity, Foveal Avascular Zone (FAZ) irregularity, Fractal dimension and vascular density. These radiomic descriptors provide early indicators of microvascular damage even before clinically visible retinopathy develops. (6)
Radiomics In Ocular Tumours (Orbital MRI)
Radiomics applied to orbital MRI enables Tumour differentiation (benign vs malignant), Prediction of histopathology, Assessment of treatment response, Quantitative MRI features have shown potential in differentiating orbital lymphoma, meningioma, and other masses. (5)
Conclusion
In conclusion, radiomics has the potential to transform modern healthcare by providing precise, data-driven insights into disease detection and characterisation. By integrating quantitative imaging features with clinical, demographic, and genomic information, radiomics models can accurately predict disease presence, progression, and treatment response. Its ability to detect subtle changes within specific areas of interest enhances diagnostic accuracy and supports earlier intervention. Ultimately, radiomics can significantly influence clinical decision-making and disease management, paving the way for more personalised and effective patient care.
References
- Interlenghi, M., Sborgia, G., Venturi, A., Sardone, R., Pastore, V., Boscia, G., … & Castiglioni, I. (2023). A Radiomic-based machine learning system to diagnose age-related macular degeneration from ultra-Widefield fundus Retinography. Diagnostics, 13(18), 2965.
- Williamson, R. C., Vupparaboina, K. K., Bollepalli, S. C., Ibrahim, M. N., Valsecchi, N., Zarnegar, A., … & Chhablani, J. (2025). Radiomics-Based OCT Analysis of Choroid Reveals Biomarkers of Central Serous Chorioretinopathy. Translational Vision Science & Technology, 14(4), 23-23.
- Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., Van Stiphout, R. G., Granton, P., … & Aerts, H. J. (2012). Radiomics: extracting more information from medical images using advanced feature analysis. European journal of cancer, 48(4), 441-446.
- Carrera-Escalé, L., Benali, A., Rathert, A. C., Martín-Pinardel, R., Bernal-Morales, C., Alé-Chilet, A., … & Zarranz-Ventura, J. (2023). Radiomics-based assessment of OCT angiography images for diabetic retinopathy diagnosis. Ophthalmology Science, 3(2), 100259.
- Gillies, R. J., Kinahan, P. E., & Hricak, H. (2016). Radiomics: images are more than pictures, they are data. Radiology, 278(2), 563-577.
- Zhang, H., Zhang, H., Jiang, M., Li, J., Li, J., Zhou, H., … & Fan, X. (2025). Radiomics in ophthalmology: a systematic review. European Radiology, 35(1), 542-557.
- Wong, P. K., Chan, I. N., Yan, H. M., Gao, S., Wong, C. H., Yan, T., Yao, L., Hu, Y., Wang, Z. R., & Yu, H. H. (2022). Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview. World journal of gastroenterology, 28(45), 6363–6379.
About the Author
Aruna Devi R
Optom Student,
Recent Comments