Bengaluru-based Researcher Develops AI Model to Support Early Cancer Risk Detection
Advertisement
The AI model named CMT-CNN is designed to combine which integrates sequential colposcopy images with clinical data.
A Bengaluru-based researcher has developed a series of AI-based models aimed at identifying women at elevated risk of cervical cancer by analysing precancerous changes.
The research was led by Lalasa Mukku, a researcher from the Department of Artificial Intelligence and Data Science Engineering, Christ (Deemed-to-be-University).
The initiative focuses on detecting Cervical Intraepithelial Neoplasia (CIN), precancerous abnormalities that can develop into cervical cancer if left untreated.
Mukku also holds patents related to an AI model designed to predict cervical cancer risk up to five years before tumour formation.
Cervical cancer remains among the leading cancers affecting women worldwide, with the burden falling disproportionately on low- and middle-income countries, where access to specialists and screening remains limited. Early diagnosis is known to improve outcomes substantially
The research approach combines images captured during colposcopy examinations with patient clinical information. During these tests, doctors examine the cervix after applying saline, acetic acid, and iodine solutions. Each stage highlights tissue differently, producing clues that can reveal precancerous changes.
In a 2024 study published in the International Journal of Advances in Intelligent Informatics, Mukku developed an AI model named CMT-CNN, designed to combine which integrates sequential colposcopy images with clinical data.
According to the study, the system reported a classification accuracy of 92.3% in identifying CIN.
The researchers stated the model was intended to support clinicians and improve screening while enhancing early risk detection.
The research also addressed challenges associated with medical image analysis. Bright reflections caused by moisture on the cervix often resemble the white lesions doctors look for, potentially confusing computer systems.
To address this, Mukku developed a separate technique, detailed in a paper published in Multimedia Tools and Applications, that removes these reflections and accurately isolates the cervical region before analysis, which is expected to improve diagnosis.
More recently, in a paper presented at a conference, she proposed a quantum convolutional neural network architecture for analysing medical images. The model reported an overall accuracy of about 98.6% when evaluated on publicly available cervical cancer screening datasets.
The researchers further noted that the technology remains at the research stage and would require extensive clinical validation before being used in hospitals. If successfully validated, the AI-based approach could support earlier risk assessment, assist clinicians in decision-making, and strengthen cervical cancer screening programmes.
Stay tuned for more such updates on Digital Health News
