Artificial intelligence (AI) has the potential to revolutionize disease diagnosis and management by performing classification difficult for human experts and by rapidly reviewing immense amounts of images. Despite its potential, clinical interpretability and feasible preparation of AI remains challenging.
OCT has profoundly disrupted conventional diagnostic and therapeutic strategies in clinical management and has led to paradigm shifts in the understanding of macular disease. Although OCT has continuously undergone hardware improvements since its inception,1x1Huang, D., Swanson, E.A., Lin, C.P. et al. The number of patients with macular disease requiring efficient disease management based on OCT in clinical practice continues to increase, similarly to the amount of image data produced by advanced OCT technology such as swept source. Therefore, the feasibility of manual OCT assessment in clinical practice has become largely unrealistic. Likewise, poor reproducibility between OCT assessors, even in a research setting, also has been reported.2x2Toth, Specifically, there is a clear need to advance automated analysis beyond a purely anatomic presence/absence detection to an accurate measurement of markers for disease activity.
Deep learning, a recently described AI machine learning technique, when applied to image analysis, allows the algorithm to analyze data using multiple processing layers to extract different image features,1x1LeCun, Y., Bengio, Y., and Hinton, G. Deep learning. In ophthalmology, many groups have reported exceptional diagnostic performance using deep learning algorithms to detect various ocular conditions based on anterior segment topography (e.g., keratoconus),5x5Hwang, E.S., Perez-Straziota, C.E., Kim, S.W. et al. Distinguishing highly asymmetric keratoconus eyes using combined Scheimpflug and spectral-domain OCT analysis. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning.
Skin cancer is the most common malignancy in fair-skinned populations, and melanoma accounts for the majority of skin cancer–related deaths worldwide [1xSchadendorf, D., van Akkooi, A.C., Berking, C., Griewank, K.G., Gutzmer, R., Hauschild, A. et al. Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology. The CNN deconstructed digital images of skin lesions and generated its own diagnostic criteria for melanoma detection during training. Several follow-up publications by other authors have demonstrated dermatologist-level skin cancer classification by using deep neural networks (CNN) [4xMarchetti, M.A., Codella, N.C., Dusza, S.W., Gutman, D.A., Helba, B., Kalloo, A. et al. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task.
Artificial Intelligence (AI) has emerged as one of the most important topics in radiology today. The Association of University Radiologists (AUR9) in its role of organizing and representing the interests of academic radiologists and those of radiology at large, convened a roundtable to help radiologists and industry leaders share their points of view and their goals in order to foster a shared understanding about the impact and benefits of AI applications in the field of radiology. There is a clear mutual interdependence between the radiology community and industry partners, which, in the case of AI, should foster collaboration between the two groups. In order to advance radiological sciences and to bridge the gap between clinicians and engineers, members of both groups need to work together so as to ensure the development of common goals, shared understanding, and mutually productive efforts. This type of collaboration occurs most frequently at the local level between a single radiology academic department and a single manufacturer.