Cancer is one of the most common causes of death in the world, with 9.6 million deaths recorded globally for the year 2018 alone. Cancer can occur in any part of the human body and is characterized by an uncontrolled cell division caused by the activation of carcinogen genes, leading to disorders in the growth of the tissue. Oral cancer (OC) is one of the prominent cancer types, especially in India, with a record of 11.54% new cases and 10.16% deaths. Till date, there is no promising treatment to cure cancer. Early detection of cancer can increase the chances of survival and quality of life after the treatment. Nowadays, various imaging and non-imaging diagnosis techniques are available. Imaging techniques have received popularity due to their non-invasiveness, painless procedures, and repetitiveness. X-ray, ultrasound, magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), and fluorescent imaging are some of those techniques. Fluorescent imaging uses fluorescence contrast agents, whereas all other techniques use ionizing radiation, which is harmful when repetitive imaging is required. However, all these techniques have their pros and cons. Recently, the research community has been working on thermal imaging, photoacoustic imaging, and hyperspectral imaging (HSI) to overcome these limitations. HSI is a promising technique for in vivo diagnosis, due to its multiband capturing capability. It can capture the same location tissue with a higher spatial and spectral resolution, for a wide range of wavelengths from visible to near infra-red (NIR). It provides ionization-free diagnosis, has less dependence on skilled pathologists, produces quick results, and is safe even to undergo diagnosis many times. HSI can also be used for the effective identification of resection margin while operating to remove OC tumors. It normally generates a huge three-dimensional data cube, where effective processing of these data can produce good results. Currently, the research community is working on the OC HSI data using deep learning techniques such as convolutional neural network (CNN), 3DCNN, R-CNN, mask R-CNN, and customized CNN. In this chapter, we present state-of-the-art works employing HSI with deep learning techniques for early detection of OC and propose future research directions to the OC research community.