In this research, we introduce a classification procedure based on rule induction and fuzzy reasoning. The classifier generalizes attribute information to handle uncertainty, which often occurs in real data. To induce fuzzy rules, we define the corresponding fuzzy information system. A transformation of the derived rules into interval type-2 fuzzy rules is provided as well. The fuzzification applied is optimized with respect to the footprint of uncertainty of the corresponding type-2 fuzzy sets. The classification process is related to a Mamdani type fuzzy inference. The method proposed was evaluated by the F-score measure on benchmark data.

Multiple studies presented satisfactory performances for the treatment of various ocular diseases. To date, there has been no study that describes a multiclass model, medically accurate, and trained on large diverse dataset. No study has addressed a class imbalance problem in one giant dataset originating from multiple large diverse eye fundus image collections. To ensure a real-life clinical environment and mitigate the problem of biased medical image data, 22 publicly available datasets were merged. To secure medical validity only Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD) and Glaucoma (GL) were included. The state-of-the-art models ConvNext, RegNet and ResNet were utilized. In the resulting dataset, there were 86,415 normal, 3787 GL, 632 AMD and 34,379 DR fundus images. ConvNextTiny achieved the best results in terms of recognizing most of the examined eye diseases with the most metrics. The overall accuracy was 80.46 ± 1.48. Specific accuracy values were: 80.01 ± 1.10 for normal eye fundus, 97.20 ± 0.66 for GL, 98.14 ± 0.31 for AMD, 80.66 ± 1.27 for DR. A suitable screening model for the most prevalent retinal diseases in ageing societies was designed. The model was developed on a diverse, combined large dataset which made the obtained results less biased and more generalizable.

This article proposes a novel concept for a two-step Ki-67/lymphocytes classification cell detection pipeline on Ki-67 stained histopathological slides utilizing commonly available and undedicated, in terms of the medical problem considered, deep learning models. Models used vary in implementation, complexity, and applications, allowing for the use of a dedicated architecture depending on the physician’s needs. Moreover, generic models’ performance was compared with the problem-dedicated one. Experiments highlight that with relatively small training datasets, commonly used architectures for instance segmentation and object detection are competitive with a dedicated model. To ensure generalization and minimize biased sampling, experiments were performed on data derived from two unrelated histopathology laboratories.

The main purpose of this research was to introduce a classification method, which combines a rule induction procedure with the Takagi–Sugeno inference model. This proposal is a continuation of our previous research, in which a classification process based on interval type-2 fuzzy rule induction was introduced. The research goal was to verify if the Mamdani fuzzy inference used in our previous research could be replaced with the first-order Takagi–Sugeno inference system. In the both cases to induce fuzzy rules, a new concept of a fuzzy information system was defined in order to deal with interval type-2 fuzzy sets. Additionally, the introduced rule induction assumes an optimization procedure concerning the footprint of uncertainty of the considered type-2 fuzzy sets. A key point in the concept proposed is the generalization of the fuzzy information systems’ attribute information to handle uncertainty, which occurs in real data. For experimental purposes, the classification method was tested on different classification benchmark data and very promising results were achieved. For the data sets: Breast Cancer Data, Breast Cancer Wisconsin, Data Banknote Authentication, HTRU 2 and Ionosphere, the following F-scores were achieved, respectively: 97.6%, 96%, 100%, 87.8%, and 89.4%. The results proved the possibility of applying the Takagi–Sugeno model in the classification concept. The model parameters were optimized using an evolutionary strategy.