Auto-MeDiSine: an auto-tunable medical decision support engine using an automated class outlier detection method and AutoMLP

MedGAN: An adaptive GAN approach for medical image generation

Generative adversarial networks (GANs) and their variants as an effective method for generating visually appealing images have shown great potential in different medical imaging applications during past decades. However, some issues remain insufficiently investigated: many models still suffer from model collapse, vanishing gradients, and convergence failure. Considering the fact that medical images differ from typical RGB images in terms of complexity and dimensionality, we propose an adaptive generative adversarial network, namely MedGAN, to mitigate these issues. Specifically, we first use Wasserstein loss as a convergence metric to measure the convergence degree of the generator and the discriminator. Then, we adaptively train MedGAN based on this metric. Finally, we generate medical images based on MedGAN and use them to build few-shot medical data learning models for disease classification and lesion localization. On demodicosis, blister, molluscum, and parakeratosis datasets, our experimental results verify the advantages of MedGAN in model convergence, training speed, and visual quality of generated samples. We believe this approach can be generalized to other medical applications and contribute to radiologists' efforts for disease diagnosis. The source code can be downloaded at https://github.com/geyao-c/MedGAN.

A novel ensemble model of automatic multilayer perceptron, random forest, and ZeroR for groundwater potential mapping

Declining levels of the water table in India have become a major concern, especially with climate change and burgeoning population compounding the problem and causing a perpetual state of water crisis. A better insight into the state of these precious resources is essential for their planned exploration and usage. This study introduces a novel machine learning ensemble model (ARZ ensemble), through an implementation of majority voting-based technique over its standalone classifier constituents, namely, Automatic Multilayer Perceptron (AutoMLP), random forest (RF), and ZeroR for undertaking the groundwater potential mapping for the Jabalpur district, Madhya Pradesh. Ten groundwater influencing factors (i.e., slope, rainfall, aspect, elevation, topographic wetness index, land use, lithology, distance from rivers, plan and profile curvature) and groundwater well locations from the study area were used to construct the spatial database. In order to validate the applicability of the proposed model, its performance was compared against a conventionally employed statistical method of Shannon's entropy (SE) model. The results revealed that the ARZ ensemble model (AUC: 0.8542) outperformed SE (AUC: 0.7639). The groundwater potential map revealed that approximately 4.18% of the region has very high groundwater potential, while 47.66% belongs to a low potential zone. Such information can hold solutions for a lot of the ailments afflicting these resources and can genuinely aid in the attempts to restore them to their natural state.