The Histograms of Oriented Gradients (HOG) descriptor represents shape information by storing the local gradients in an image. The Haar wavelet transform is a simple yet powerful technique that can separately enhance the horizontal and vertical local features in an image. In this paper, we enhance the HOG descriptor by subjecting the image to the Haar wavelet transform and then computing HOG from the result in a manner that enriches the shape information encoded in the descriptor. First, we define the novel HaarHOG descriptor for grayscale images and extend this idea for color images. Second, we compare the image recognition performance of the HaarHOG descriptor with the traditional HOG descriptor in four different color spaces and grayscale. Finally, we compare the image classification performance of the HaarHOG descriptor with some popular descriptors used by other researchers on four grand challenge datasets.
Tumour cellularity (TC) is an important metric used in the cancer treatment journey, from monitoring the therapeutic response to guiding subsequent treatment decisions. It can be defined as the area occupied by malignant cells in a Region of Interest. Although deep learning (DL)-based automated systems have gained considerable momentum in medical image analysis, there are still challenges associated with efficient TC computation. The scope of performance improvement by comprehensively addressing issues of aleatoric uncertainty in TC labels and epistemic uncertainty in model parameters due to limited data remains unexplored. In this research, a novel regression-based framework is developed to address these two types of uncertainties for efficient computation of TC. While a loss function is introduced to handle aleatoric uncertainty, the epistemic uncertainty is handled by training the DL model in two stages by skilfully utilizing limited data. First, a novel task-specific pre-training is done in a semi-supervised framework to capture fine-grained cell-level features. Then, it is fine-tuned for effective TC computation. The experimental results show effective performance with different encoders, demonstrating robustness. Quantitative and qualitative results demonstrate the potential of the framework to serve as a robust tool for clinical decision support in cancer. Achieving a PK score of 0.95 and an R2 score of 0.88, it outperforms state-of-the-art histopathology-specific foundation models and other related methods w.r.t. both metrics and parameters. Thus, our framework offers a reliable and scalable solution for improved automated tumour cellularity estimation and for reducing the workload of pathologists.
5 March 2018 in IOP Conference Series: Earth and Environmental Science
Driven by a desire to control climate change and reduce the dependence on fossil fuels, governments around the world are increasing the adoption of renewable energy sources. However, among the US states, we observe a wide disparity in renewable penetration. In this study, we have identified and cleaned over a dozen datasets representing solar energy penetration in each US state, and the potentially relevant socioeconomic and other factors that may be driving the growth in solar. We have applied a number of predictive modeling approaches - including machine learning and regression - on these datasets over a 17-year period and evaluated the relative performance of the models. Our goals were: (1) identify the most important factors that are driving the growth in solar, (2) choose the most effective predictive modeling technique for solar growth, and (3) develop a model for predicting next year's solar growth using this year's data. We obtained very promising results with random forests (about 90% efficacy) and varying degrees of success with support vector machines and regression techniques (linear, polynomial, ridge). We also identified states with solar growth slower than expected and representing a potential for stronger growth in future.