Finding a Suitable Class Distribution for Building Histological Images Datasets Used in Deep Model Training—The Case of Cancer Detection

Abstract

The class distribution of a training data set is an important factor which influences the performance of a deep learning-based system. Understanding the optimal class distribution is therefore crucial when building a new training set which may be costly to annotate. This is the case for histological images used in cancer diagnosis where image annotation requires domain experts. In this paper we tackle the problem of finding the optimal class distribution of a training set to be able to train an optimal model that detects cancer in histological images. We formulate several hypotheses which are then tested in scores of experiments with hundreds of trials. The experiments have been designed to account for both segmentation and clas-

Prediction of Subclinical and Clinical Multiple Organ Failure Dysfunction in Breast Cancer Patients—A Review Using AI Tools

“…Understanding these dynamics is crucial for preventing the chain decompensation of subsequent affected organs. We note that AI has already been employed in cancer detection [ 98 ], providing assistance to physicians around the world. Once sufficient data about the subclinical syndrome of organ insufficiency are gathered, AI-based techniques can be employed in future work to learn patterns from these data, which could lead to the discovery of automatic tools for diagnosing this syndrome.…”