JOIN NOW

AI-Powered Iridology: Transforming the Future of Eye Disease Detection

by | Mar 1, 2025 | Manuscripts | 0 comments

Bharghavy S, M.Optom

Assistant professor Jr., Dr. Agarwal’s Institute of Optometry, Chennai, India.

 

Iridology is a practice in which all the conditions of organs in the human body can be read through the iris. That is because every organ has a complicated nerve connection to the iris. (1) Each eye right and left has 60 parts that represent certain organs. The organs on the right side of the body will be represented on the right iris. Similarly, organs on the left side of the body will also be represented by sectors on the left iris. (2)

Iridology was first introduced in a book called Chromatica Medica published in 1665. Theodore Kriege, the author, does not describe the exact term iridology. Later, Bernard Jensen, introduced this method for detecting abnormalities in the body. Now, he is known as the father of modern iridology. (3)

Iridologist found that the iris has seven topographies that describe the condition of the body’s organs. If the organ is damaged, irregular, or abnormal, the iris representing the organ will show a different sign than the normal iris. (4)

  1. Colour Changes: Alterations in the pigmentation of the iris might be linked to certain eye diseases, such as glaucoma or cataracts.
  2. Structural Changes: Irregularities in the iris structure, such as rings or spots, may be interpreted as indicators of inflammation or other ocular issues.
  3. Reflex Areas: Practitioners often refer to specific areas of the iris that correspond to the eyes, suggesting that issues in these regions could reflect problems in the ocular system.

These observations form the basis of iridology, which posits that the iris can reveal insights about a person’s overall health and specific conditions affecting the eyes.

Application of Artificial Intelligence:

With the advancement of AI technologies, there are several ways in which AI can enhance the practice of iridology (5,6):

Steps involved in detecting an ocular condition using AI

  1. Image Acquisition:
    • Direct Photography: High-resolution cameras, controlled lighting.
    • Indirect Photography: Microscope-based imaging, magnification techniques.
  2. Image Preprocessing:
    • Noise Reduction: Filtering techniques (e.g., Gaussian, median), denoising algorithms.
    • Contrast Enhancement: Histogram equalisation, adaptive contrast enhancement.
    • Image Segmentation: Iris localisation and segmentation, pupil detection.
  3. Feature Extraction:
    • Colour Analysis: Colour space conversion (RGB, HSV), colour histograms.
    • Texture Analysis: Gray-Level Co-occurrence Matrix (GLCM), wavelet transforms.
    • Shape Analysis: Boundary extraction, geometric measurements (e.g., area, perimeter).
  4. Classification and Pattern Recognition:
    • Machine Learning Algorithms: Support Vector Machines (SVM), Artificial Neural Networks (ANN), Decision Trees, ensemble methods.
    • Pattern Matching: Comparing extracted features to known iridology charts and maps. (Note: These charts and maps are based on unproven assumptions)
  5. Interpretation and Analysis:
    • Train the images using deep learning technology and predict for diagnosing the ocular conditions.

Conclusion:

Although iridology is often regarded as an alternative diagnostic method, some studies have reported its potential accuracy in predicting diseases, with success rates ranging from 80% to 97%. These results largely depend on the quality of data collected, the pre-processing techniques applied, and the classification methods employed. The possibility of pre-diagnosing diseases through iris scans presents a fascinating yet challenging avenue for further exploration. However, as artificial intelligence technology is advancing, this is expected to be resolved soon for better disease prediction. (7)

 

References

  1. Holl, R. M. (1999). Iridology: Another Look. Complementary Health Practice Review. https://doi.org/10.1177/153321019900500106
  2. Buchanan, T. J., Sutherland, C. J., Strettle, R. J., Terrell, T. J., & Pewsey, A. (1996). An investigation of the relationship between anatomical features in the iris and systemic disease, with reference to iridology. Complementary Therapies in Medicine, 4(2), 98-102.
  3. Simon, A., Worthen, D. M., & Mitas, J. A. (1979). An Evaluation of Iridology. JAMA. https://doi.org/10.1001/JAMA.1979.03300130029014
  4. Jensen . D., 1980 Iridology Simplified California: Iridologist International.
  5. Erwin, M. F., Passarella, R., & Darmawahyuni, A. (1980). Identifikasi gangguan usus besar (colon) berdasarkan citra iris mata menggunakan metode naïve bayes.
  6. Önal, M. N., Güraksin, G. E., & Duman, R. (2023). Convolutional neural network-based diabetes diagnostic system via iridology technique. Multimedia tools and Applications, 82(1), 173-194.
  7. Avhad, V. V., & Bakal, J. W. (2024). Iridology based human health conditions predictions with computer vision and deep learning. Biomedical Signal Processing and Control, 96, 106656.
  8. Malik, S., Kanwal, N., Asghar, M. N., Sadiq, M. A. A., Karamat, I., & Fleury, M. (2019). Data driven approach for eye disease classification with machine learning. Applied Sciences, 9(14), 2789.
  9. A Review of Image Processing Approaches of the Iridology as A Biomedical. (2022). https://doi.org/10.1109/fortei-icee57243.2022.9972907

Submit a Comment