Publication:

Recent advances in computed tomography and magnetic resonance imaging techniques for cancer detection with artificial intelligence and machine learning integration

Cancer is one of the leading causes of death all over the world. The International Agency for Research on Cancer (IARC) estimated 20 million new cancer cases in 2022. However, detecting cancer is difficult because it shows symptoms in the final stage. Diagnostic imaging plays a vital role in the early detection of cancer. Advanced imaging technology includes X-ray mammography, ultra-low-dose computed tomography (ULDCT), and dual-source CT, which uses two X-ray sources and improves the resolution of images. Radiomics is another advanced approach that converts medical images into quantitative data and deep learning methods (DL) using Artificial intelligence (AI), which tremendously increases the accuracy of tumor detection. Several automated and semi-automated methods are proposed to detect pulmonary nodules using DL methods such as Conventional neural network (CNNs), which include ResNet-50, VGG16, and InceptionV3. In addition to techniques that involves ionizing radiation, this review also explains the magnetic resonance imaging (MRI) techniques for cancer detection. MRI uses radio-frequency (RF) pulses to form images with high spatial resolution. Diffusion-weighted imaging (DWI), functional magnetic resonance imaging (fMRI), and MR spectroscopy (MRS) are the MRI sequences generally used for cancer detection. The aim of this paper is to provide an overview of modern CT and MR imaging techniques integrating with AI and machine learning for cancer detection.