Finally! Our newest paper is now published online | Springer Nature
I am thrilled to share that our groundbreaking study, “Machine Learning Applications in Detection and Diagnosis of Urology Cancer Diagnosis: A Systematic Literature Review,” has been published in the prestigious journal Neural Computing and Applications, known for its exceptional impact on the scientific community.
Journal Info
This publication in Neural Computing and Applications holds particular significance due to the journal’s outstanding impact factor, which stands at an impressive 6.0 for 2022. The 5-year impact factor further underscores the journal’s sustained influence, with a remarkable score of 5.6 in the same year. These figures attest to the journal’s high regard and visibility within the academic and research community.
Study Brief
Our research addresses a critical gap in the existing literature by systematically reviewing and evaluating AI models employed in urology cancer diagnosis. Integrating deep learning techniques in cancer diagnosis has demonstrated remarkable advancements in accuracy and speed, significantly impacting clinical decision-making and ultimately improving health outcomes.
The systematic review, conducted through thorough searches in Scopus, Microsoft Academic, and PubMed/MEDLINE databases, identifies and analyzes 48 relevant articles published within the last 20 years. Our evaluation focuses on quantitative and qualitative aspects, encompassing diverse urology subspecialties. Notably, 25 studies propose innovative approaches for prostate cancers, 15 for bladder cancers, and 8 studies delve into renal cell carcinoma and kidney cancer.
The findings reveal that AI models designed for urology cancer detection consistently achieve high accuracy rates ranging from 77% to 95%. Notably, deep learning approaches, particularly those utilizing convolutional neural networks, exhibit the highest accuracy among various techniques. This emphasizes the potential of AI models in transforming the landscape of urology cancer diagnosis.
Our study acknowledges the ongoing progress in developing AI models for urology cancer applications and underscores their promising trajectory. However, it also highlights the need for additional research, emphasizing the importance of further employing extensive, high-quality, and recent datasets to validate these AI models’ clinical performance.
We invite you to access our article through the following link: [DOI: 10.1007/s00521–023–09375–2](https://link.springer.com/article/10.1007/s00521-023-09375-2).
Your continued interest and feedback are highly valued as we strive to make impactful contributions to the scientific community.
Thank you for your ongoing support.
Learn More
If you like the article and would like to support me, make sure to:
👏 Clap for the story (100 Claps) and follow me 👉🏻 Mohammed Lubbad
📑 View more content on my Medium Profile
🔔 Follow Me: LinkedIn | Medium | GitHub | Twitter | Telegram
🚀 Help me reach a wider audience by sharing my content with your friends and colleagues.
🌐 Reference
https://link.springer.com/article/10.1007/s00521-023-09375-2