Abstract
Semantic segmentation consists of classifying each pixel according to a set of classes. Conventional models spend as much effort classifying easy-to-segment pixels as they do classifying hard-to-segment pixels. This is inefficient, especially when deploying to situations with computational constraints. In this work, we propose a framework wherein the model first produces a rough segmentation of the image, and then patches of the image estimated as hard to segment are refined. The framework is evaluated in four datasets (autonomous driving and biomedical), across four state-of-the-art architectures. Our method accelerates inference time by four, with additional gains for training time, at the cost of some output quality.

Abstract

Abstract
In many real-world prediction tasks, the class labels contain information about the relative order between the labels that are not captured by commonly used loss functions such as multicategory cross-entropy. In ordinal regression, many works have incorporated ordinality into models and loss functions by promoting unimodality of the probability output. However, current approaches are based on heuristics, particularly non-parametric ones, which are still insufficiently explored in the literature. We analyze the set of unimodal distributions in the probability simplex, establishing fundamental properties and giving new perspectives to understand the ordinal regression problem. Two contributions are then proposed to incorporate the preference for unimodal distributions into the predictive model: 1) UnimodalNet, a new architecture that by construction ensures the output is a unimodal distribution, and 2) Wasserstein Regularization, a new loss term that relies on the notion of projection in a set to promote unimodality. Experiments show that the new architecture achieves top performance, while the proposed new loss term is very competitive while maintaining high unimodality.

Abstract

Abstract
Training machine learning models for artificial intelligence (AI) applications in pathology often requires extensive annotation by human experts, but there is little guidance on the subject. In this work, we aimed to describe our experience and provide a simple, useful, and practical guide addressing annotation strategies for AI development in computational pathology. Annotation methodology will vary significantly depending on the specific study's objectives, but common difficulties will be present across different settings. We summarize key aspects and issue guiding principles regarding team interaction, ground-truth quality assessment, different annotation types, and available software and hardware options and address common difficulties while annotating. This guide was specifically designed for pathology annotation, intending to help pathologists, other researchers, and AI developers with this process.(c) 2022 THE AUTHORS. Published by Elsevier Inc. on behalf of the United States & Canadian Academy of Pathology. This is an open access article under the CC BY-NC-ND license (http://creativecommons. org/licenses/by-nc-nd/4.0/).

Abstract
The original version of this Article contained an error in the Acknowledgements section. “This work was partially funded by the Project TAMI—Transparent Artificial Medical Intelligence (NORTE- 01-0247-FEDER-045905) financed by ERDF—European Regional Fund through the North Portugal Regional Operational Program—NORTE 2020 and by the Portuguese Foundation for Science and Technology—FCT under the CMU—Portugal International Partnership, and also by the Portuguese Foundation for Science and Technology—FCT within PhD grants SFRH/BD/139468/2018 and 2020.06434.BD. The authors thank the Swiss National Science Foundation grant number 198388, as well as the Lindenhof foundation for their grant support.” now reads: “This work was supported by National Funds through the Portuguese Funding Agency, FCT–Foundation for Science and Technology Portugal, under Project LA/P/0063/2020, and also by the Portuguese Foundation for Science and Technology - FCT within PhD grants SFRH/BD/139468/2018 and 2020.06434.BD. The authors thank the Swiss National Science Foundation grant number 198388, as well as the Lindenhof foundation for their grant support.” The original Article has been corrected. © The Author(s) 2023.