Application of Artificial Intelligence in Digital Histopathology: Evaluating the Effectiveness of Deep Learning for Cancer Diagnosis
Novitasari* & Anak Agung Ayu Ngurah Susraini
Abstract
Background: Digital histopathology has become a cornerstone in cancer diagnosis, enabling detailed analysis of tissue slides to identify pathological features. Traditional methods often face challenges such as inter-observer variability and prolonged processing time, highlighting the need for faster and more accurate diagnostic approaches. Artificial Intelligence (AI), particularly deep learning algorithms, has transformed this field by enabling automated analysis of high-resolution medical images. Methods: This study employed a systematic review approach to evaluate the effectiveness of deep learning methods in cancer diagnosis based on digital imaging. Literature searches were conducted across four major electronic databases, applying stringent inclusion criteria to ensure the relevance and quality of the selected studies. Results: From a total of 1,423 identified articles, 14 met the inclusion criteria. The findings indicate that the application of deep learning in cancer diagnosis yields high diagnostic accuracy, with most studies reporting accuracy rates above 85%. In several contexts, AI-based models demonstrated performance that matched or exceeded that of clinical practitioners. Conclusion: The application of AI in digital histopathology offers significant potential to enhance the accuracy, efficiency, and accessibility of cancer diagnosis. With the ability to accelerate diagnostic workflows and support clinical decision-making, the integration of this technology could improve clinical outcomes for cancer patients globally.
Keywords
digital histopathology; cancer; artificial intelligence; deep learning; cancer diagnosis.
Cite This Article
Novitasari, Susraini, A. A. A. N. (2025). Application of Artificial Intelligence in Digital Histopathology: Evaluating the Effectiveness of Deep Learning for Cancer Diagnosis. International Journal of Scientific Advances (IJSCIA), Volume 6| Issue 5: Sep – Oct 2025, Pages 872-882 URL: https://www.ijscia.com/wp-content/uploads/2025/09/Volume6-Issue5-Sep-Oct-No.942-872-882.pdf
Volume 6 | Issue 5: Sep – Oct 2025
