An application of explainable artificial intelligence on medical data is presented. There is an increasing demand in machine learning literature for such explainable models in health-related applications. This work aims to generate explanations on how a Convolutional Neural Network (CNN) detects tumor tissue in patches extracted from histology whole slide images. This is achieved using the “locally-interpretable model-agnostic explanations” methodology. Two publicly-available convolutional neural networks trained on the Patch Camelyon Benchmark are analyzed. Three common segmentation algorithms are compared for superpixel generation, and a fourth simpler parameter-free segmentation algorithm is proposed. The main characteristics of the explanations are discussed, as well as the key patterns identified in true positive predictions. The results are compared to medical annotations and literature and suggest that the CNN predictions follow at least some aspects of human expert knowledge.

Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Aim: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. Methodology: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). Main results: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias.

A learning algorithm is proposed for the task of Arabic Handwritten Character and Digit recognition. The architecture consists on an ensemble of different Convolutional Neural Networks. The proposed training algorithm uses a combination of adaptive gradient descent on the first epochs and regular stochastic gradient descent in the last epochs, to facilitate convergence. Different validation strategies are tested, namely Monte Carlo Cross-Validation and K-fold Cross Validation. Hyper-parameter tuning was done by using the MADbase digits dataset. State of the art validation and testing classification accuracies were achieved, with average values of 99.74% and 99.47% respectively. The same algorithm was then trained and tested with the AHCD character dataset, also yielding state of the art validation and testing classification accuracies: 98.60% and 98.42% respectively.

The results of a computer simulation examining the compliance of a given transcranial magnetic stimulation device to the 2010 International Commission on Non-Ionizing Radiation Protection (ICNIRP) guidelines are presented. The objective was to update the safe distance estimates with the most current safety guidelines, as well as comparing these to values reported in previous publications. The 3D data generated was compared against results available in the literature, regarding the MCB-70 coil by Medtronic. Regarding occupational exposure, safe distances of 1.46 m and 0.96 m are derived from the simulation according to the 2003 and 2010 ICNIRP guidelines, respectively. These values are then compared to safe distances previously reported in other studies.