‘Publishing this research has been an immensely rewarding experience’

Liannaka Dadi is a young researcher from Apeejay Stya University (ASU) whose work bridges artificial intelligence and healthcare innovation. Her research on CNN-based models for early breast cancer detection has been presented at prestigious international conferences, including IEEE DELCON 2025, highlighting her focus on impactful, ethical, and technology-driven medical solutions. Read edited excerpts of her interview in which she explains about her recent research work: 

How do you feel about publishing this research work?

Publishing this research has been an immensely rewarding experience. Having the paper accepted and presented at IEEE DELCON 2025 marks a significant academic milestone. It reflects the depth of research, technical refinement, and the relevance of the study in the field of AI-driven healthcare. The research journey began at an international conference (ICFWT 2025), where valuable feedback helped refine the work, leading to its advancement and acceptance at IEEE DELCON 2025.

What inspired you to explore the role of Artificial Intelligence, particularly CNN models, in the early detection of breast cancer?

The inspiration came from the urgent need for early and accurate breast cancer diagnosis. Convolutional Neural Networks (CNNs) have demonstrated strong performance in medical image analysis by identifying complex patterns that may not be easily visible to the human eye. Exploring this area allowed the integration of advanced AI techniques with impactful healthcare solutions.

How does your CNN-based model improve breast cancer detection compared to traditional diagnostic methods?

Traditional diagnostic methods rely heavily on manual interpretation, which can be time-consuming and subject to variability. CNN-based models automate feature extraction, enhance consistency, and reduce analysis time. The research positions AI as a clinical decision-support system that assists medical professionals in improving diagnostic efficiency.

How did the faculty at Apeejay Stya University support you during this research journey?

Faculty mentorship and guidance were instrumental throughout the research journey. Special acknowledgement goes to Dr. (Prof.) Moin Uddin sir and Dr. Divya Khapra for their encouragement and academic support.

How did you prepare for this research, and what process did you follow?

The research followed a structured approach that included an extensive literature review, identification of research gaps, analysis of CNN architectures, refinement of findings, and alignment with IEEE publication standards. Each stage involved critical evaluation and continuous improvement to ensure academic rigor.

Your research discusses the ‘black box’ challenge of AI. What does this mean in medical diagnosis?

The ‘black box’ challenge refers to the limited interpretability of deep learning models, where the reasoning behind predictions is not easily understandable. In medical diagnosis, this lack of transparency can affect trust, accountability, and clinical adoption. Addressing this challenge is essential for responsible and ethical AI implementation in healthcare.

What future improvements do you suggest to make AI-based cancer detection more reliable and transparent?

Future improvements include integrating Explainable AI (XAI) techniques, using larger and more diverse datasets, collaborating closely with medical professionals, and ensuring continuous real-world validation. Ethical alignment and regulatory compliance are also essential to make AI-based systems reliable for clinical use.