Convolutional Neural Networks (CNNs) have shown a competitive performance in medical imaging applications, such as image segmentation. However, choosing an existing architecture capable of adapting to a specific dataset is challenging and requires design expertise. Neural Architecture Search (NAS) is employed to overcome these limitations. NAS uses techniques to design the Neural Networks architecture. Typically, the models’ weights optimization is carried out using a continuous loss function, unlike model topology optimization, which is highly influenced by the specific problem. Genetic Programming (GP) is an Evolutionary Algorithm (EA) capable of adapting to the topology optimization problem of CNNs by considering the attributes of its representation. A tree representation can express complex connectivity and apply variation operations. This paper presents a tree-based GP algorithm for evolving CNNs based on the well-known U-Net architecture producing compact and flexible models for medical image segmentation across multiple domains. This proposal is called Neural Architecture Search / Genetic Programming / U-Net (NASGP-Net). NASGP-Net uses a cell-based encoding and U-Net architecture as a backbone to construct CNNs based on a hierarchical arrangement of primitive operations. Our experiments indicate that our approach can produce remarkable segmentation results with fewer parameters regarding fixed architectures. Moreover, NASGP-Net presents competitive results against NAS methods. Finally, we observed notable performance improvements based on several evaluation metrics, including Dice similarity coefficient (DSC), Intersection over union (IoU), and Hausdorff Distance (HD).

Within the medical field, computer vision has an important role in different tasks, such as health anomaly detection, diagnosis, treatment, and monitoring medical conditions. Image segmentation is one of the most used techniques for medical support to identify regions of interest in different organs. However, performing accurate segmentation is difficult due to image variations. In this way, this work proposes an automated multiple-feature construction approach for image segmentation, working with magnetic resonance images, computed tomography, and RGB digital images. Genetic programming is used to automatically create and construct pipelines to extract meaningful features for segmentation tasks. Additionally, a co-evolution strategy is proposed within the evolution process to increase diversity without affecting segmentation performance. The segmentation is addressed as a pixel classification task; in this way, a wrapper approach is used, and the classification model’s segmentation performance determines the fitness. To validate the effectiveness of the proposed method, four datasets were used to measure the capability of the proposal to deal with different types of medical images. The results demonstrate that the proposal achieves values of the DICE similarity coefficient of more than 0.6 in MRI and C.T. images. Additionally, the proposal is compared with SOTA GP-based methods and the convolutional neural networks used within the medical field. The method proposed outperforms these methods, achieving improvements greater than $20\%$ in DICE, specificity, and sensitivity. Additionally, the qualitative results demonstrate that the proposal accurately identifies the region of interest.

Genetic programming (GP) and fuzzy logic to automatically segment mammography images. GP allows the evolution of optimized segmentation models, guided by a fuzzy logic-based fitness function that incorporates medical criteria to improve the consistency and accuracy of the segmentation process. Unlike conventional approaches, this function optimizes the segmentation and provides a descriptive representation of the breast tissue, allowing a closer evaluation to that performed by specialists. The proposed method was evaluated in the INbreast and BCDR databases, obtaining a Jaccard index of 0.82 and 0.78, respectively, and a comparative analysis was performed using ROC curves, reaching an AUC of 0.91 in INbreast and 0.89 in BCDR, demonstrating the model’s ability to discriminate between fibroglandular and fat tissue. Its performance was compared with state-of-the-art methods, such as LIBRA, hybrid segmentation with Fuzzy C-Means, and NASGP-Net, showing that integrating fuzzy logic in genetic programming to lead the search allows competitive results with a lower computational burden. These results demonstrate the impact of fuzzy fitness functions in the evolution of segmentation models, highlighting the effectiveness of this approach in improving the segmentation and classification of medical images, in addition to the descriptive capabilities inherent to the fuzzy fitness function.