Deep learning is a type of machine learning in which a model learns to perform classification tasks directly from images, text or sound. Image-based deep learning models (DLMs) have been used in other disciplines, but this method has yet to be used to predict surgical outcomes. With this background, researchers carried out a study to examine whether deep learning models (DLMs) using routine preoperative imaging can predict surgical complexity and outcomes in abdominal wall reconstruction. They applied image-based deep learning to predict complexity, defined as need for component separation, and pulmonary and wound complications after abdominal wall reconstruction (AWR). This quality improvement study was performed at an 874-bed hospital and tertiary hernia referral center from September 2019 to January 2020.

Automated analysis of CT scan images using AI solutions to diagnose abnormalities will help in overcoming the costly, time consuming and prone to error from manual analysis. Deep Learning has proved to be quite efficient to mimic human cognitive abilities (and even exceed that in many cases), especially with unstructured data. DL algorithms can detect, localize and quantify a growing list of brain pathologies including intra-cerebral bleeds and their subtypes, infarcts, mass effect, midline shift, and cranial fractures. So, with advanced DL algorithms, analysis of radiographic data can be easily achieved and this can accelerate early detection of certain critical medical conditions, powered by AI. As mentioned, Deep Learning algorithms for computer vision use cases has been extremely successful for classification and localization related problems.

With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data demanding and since, medical data is not easily accessible, they suffer from data insufficiency. To deal with this limitation, different data augmentation techniques are used. Here, we propose a novel unsupervised data-driven approach for data augmentation that can generate 2D Computed Tomography (CT) images using a simple GAN. The generated CT images have good global and local features of a real CT image and can be used to augment the training datasets for effective learning. In this proof-of-concept study, we show that our proposed solution using GANs is able to capture some of the global and local CT variabilities. Our network is able to generate visually realistic CT images and we aim to further enhance its output by scaling it to a higher resolution and potentially from 2D to 3D.