Table 2 Summary of key studies in medical imaging utilizing deep learning techniques
From: Skin lesion segmentation using deep learning algorithm with ant colony optimization
Ref | Focus area | Methodology | Key outcomes | Specific contributions |
|---|---|---|---|---|
Rana and Bhushan [19] | General Medical Imaging | Survey/Review | Overview of deep learning applications | Comprehensive survey of deep learning applications across various imaging modalities. |
Iqbal [20] | Dermatological Imaging | Deep Neural Networks | High accuracy in skin cancer classification | Achieved dermatologist-level accuracy in classifying skin cancer using deep learning. |
Jones, et al. [21] | General Medical Imaging | Deep Learning Review | Discussed deep learning in medical analysis | Highlighted the role of deep learning in improving medical image analysis and its challenges. |
Du, et al. [22] | MRI Imaging | Deep Learning Algorithms | Improved speed and efficiency | Significantly reduced MRI scan times without compromising image quality. |
De Matos, et al. [23] | Histopathological Imaging | Deep Learning Models | Enhanced histopathological image analysis | Provided detailed methods for applying machine learning to histopathology. |
Strzelecki, et al. [24] | Radiology | AI in Radiology Review | Assessed AI applications in radiology | Discussed AI's impact, potential, and limitations in enhancing radiological diagnostics. |
Abunadi and Senan [30] | Automated skin lesion classification | Deep learning (ResNet, CNNs) | ISIC 2018, PH2 | Demonstrated high accuracy in classifying melanoma using deep learning models, with ResNet achieving 90% accuracy. |