EUVIMEDEUVIMED entdecken
Crossref

A comprehensive review of medical imaging data using deep learning techniques for cancer detection

M. P. Kumbhare, P. Parlewar, G. K. Bharti

Nigerian Journal of Technology · 08.06.2026 · 45 · 43-63

DOI: 10.4314/njt.v45i.4s ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nigerian Journal of Technology, online erschienen am 08.06.2026. Verfasst von M. P. Kumbhare und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cancer remains a significant public health issue due to the uncontrolled growth of abnormal cells that can harm normal tissues. Early detection is vital for improving treatment outcomes and survival rates, yet over the past decade, more than 0.4 million new cancer cases were diagnosed, with over 0.17 million fatalities. Current diagnostic methods, such as CT, MRI, PET, ultrasound, and biopsies, often struggle to identify subtle signs of early-stage cancer and do not fully leverage the available data from medical imaging and histopathology. This research aims to summarize studies that use deep learning algorithms on medical imaging data for early-stage cancer diagnosis. By integrating diverse data types, including imaging and histopathology, we seek to empower clinicians with enhanced diagnostic tools that reduce false positives and negatives. Ultimately, the goal is to improve patient treatment options and survival rates. Addressing the challenges of early cancer detection and treatment remains crucial in modern medicine. The development of innovative diagnostic technologies has the potential to improve the effectiveness of cancer treatments, thereby reducing mortality rates associated with the disease. Traditional clinical diagnostic methods have had limited success in detecting early-stage cancers because of the early subtle nature of their manifestations. Using Deep Learning to analyze large volumes of medical images that are taken from patients diagnosed with many different forms of cancer to develop a system that will allow clinicians to take advantage of medical images to make an early diagnosis of cancer, thereby enhancing the quality of care for patients. This is a literature review of medical imaging modalities commonly used in clinics, including X-ray, CT, PET, and MRI, which are commonly insufficient to detect early-stage cancer using Machine Learning, and there has been limited research on analyzing Optical Coherence Tomography medical images in conjunction with a Hybrid Convolutional-Recurrent Neural Network.

Zitieren

APA

Kumbhare, M. P., Parlewar, P., & Bharti, G. K. (2026). A comprehensive review of medical imaging data using deep learning techniques for cancer detection. Nigerian Journal of Technology, 45, 43-63. https://doi.org/10.4314/njt.v45i.4s

Vancouver

Kumbhare MP, Parlewar P, Bharti GK. A comprehensive review of medical imaging data using deep learning techniques for cancer detection. Nigerian Journal of Technology. 2026;45:43-63. doi:10.4314/njt.v45i.4s

BibTeX
@article{Kumbhare2026,
  author = {Kumbhare, M. P. and Parlewar, P. and Bharti, G. K.},
  title = {A comprehensive review of medical imaging data using deep learning techniques for cancer detection},
  journal = {Nigerian Journal of Technology},
  year = {2026},
  volume = {45},
  pages = {43--63},
  doi = {10.4314/njt.v45i.4s}
}
Kostenlos starten →