A survey on deep learning in medical image analysis

TL;DR: The accuracy of semi-automatic segmentation is competitive with the top specialized brain tumor segmentation methods evaluated in the BRATS challenge, with most results obtained in ITK-SNAP being more accurate, relative to the BRats reference manual segmentation, than the second-best performer in theBRATS challenge.

TL;DR: In this paper, a new method for detecting COVID-19 and pneumonia using chest X-ray images was proposed, which can be described as a three-step process and achieved the highest testing classification accuracy of 96.6% using the VGG-19 model associated with the binary robust invariant scalable key-points (BRISK) algorithm.

TL;DR: This review introduces and defines key concepts from the field of artificial intelligence and discusses how the techniques from this field can be applied to nuclear medicine imaging applications with a particular focus on radio(geno)mics.

TL;DR: This investigation focuses on the following critical challenges: understanding radiology text/image structures and datasets, applying DL algorithms (mainly CNN and RNN), generating Radiology text, and improving existing DL based models and evaluation metrics.

TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.

TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.