In the new study that was published in the journal Cancers (October, 2024), the researchers said that they have improved ArMOR and tested its ability to detect retinoblastoma in a multiracial patient group or cohort.

Hyderabad: For the first time in India, Hyderabad-based researchers have developed an Artificial Intelligence (AI) based model to detect eye cancers, also known as Retinoblastoma (RB).

Eye researches from Hyderabad-based L V Prasad Eye Institute (LVPEI), Dr. Vijitha S. Vempuluru, Dr Swathi Kaliki, ocular specialist from US-based Wills Eye Hospital, Dr Carol L. Shields, IIIT-Hyderabad, and TechSophy Inc collaborated to develop the first AI model dubbed as Artificial Intelligence and Machine Learning in Ocular Oncology, Retinoblastoma (ArMOR), to diagnose eye cancers for peoples of all ethnicities with pinpoint accuracy.

In the new study that was published in the journal Cancers (October, 2024), the researchers said that they have improved ArMOR and tested its ability to detect retinoblastoma in a multiracial patient group or cohort.

The ArMOR technology was refined with the help of researchers from International Institute of Information Technology (IIIT-Hyderabad), and Bourntec Solutions Pvt Ltd. The researchers used deep learning and geometric calculations to extract various features of retinal tumors, such as tumor seeds, blood vessels, hemorrhage, etc., that an AI can identify.

“The AI model displayed an accuracy of 97 percent for detecting retinoblastoma, and 98 percent, 93 percent, more than 99 percent, 94 percent and 93 percent for grouping tumors into the International Classification of Retinoblastoma groups A to E, respectively,” the researchers in the study published in Cancers said.

Since AI/ML have been increasingly explored in the field of intraocular tumors and early detection of retinoblastoma (RB) is crucial for optimizing treatment outcomes. “Hence, we aimed to employ AI/ML to develop a potential screening tool for RB and established the feasibility of training an AI model to detect and classify RB from fundus images in an Asian Indian cohort previously. Taking this work ahead, we explored the model’s ability to detect and classify RB in a multiracial cohort. Despite unequal frequency distribution between the races, we identified the scope for improvement and retrained the AI model to detect and classify RB,” the researchers said.

“We began this journey by developing an AI model for diagnosis of retinoblastoma which was validated of in the Asian Indian population. However, we realized that the same AI model cannot be used for all races. Through this study, we refined our existing AI model so that it can be used in all races irrespective of the color of the fundus,” says Dr Swathi Kaliki, Head, OEU Institute for Eye Cancer, LVPEI and the corresponding author of this paper.