Enhanced tissue slide imaging in the complex domain via cross-explainable GAN for Fourier ptychographic microscopy.

Achieving microscopy with large space-bandwidth products plays a key role in diagnostic imaging and is widely significant in the overall field of clinical practice. Among quantitative microscopy techniques, Fourier Ptychography (FP) provides a wide field of view and high-resolution images, suitable to the histopathological field, but onerous in computational terms. Artificial intelligence can be a solution in this sense. In particular, this research delves into the application of Generative Adversarial Networks (GAN) for the dual-channel complex FP image enhancement of human kidney samples. The study underscores the GANs' efficacy in promoting biological architectures in FP domain, thereby still guaranteeing high resolution and visibility of detailed microscopic structures. We demonstrate successful GAN-based enhanced reconstruction through two strategies: cross-explainability and expert survey. The cross-explainability is evaluated through the comparison of explanation maps for both real and imaginary components underlining its robustness. This comparison further shows that their interplay is pivotal for accurate reconstruction without hallucinations. Secondly, the enhanced reconstruction accuracy and effectiveness in a clinical workflow are confirmed through a two-step survey conducted with nephrologists.

Label-free cell classification in holographic flow cytometry through an unbiased learning strategy.

Nowadays, label-free imaging flow cytometry at the single-cell level is considered the stepforward lab-on-a-chip technology to address challenges in clinical diagnostics, biology, life sciences and healthcare. In this framework, digital holography in microscopy promises to be a powerful imaging modality thanks to its multi-refocusing and label-free quantitative phase imaging capabilities, along with the encoding of the highest information content within the imaged samples. Moreover, the recent achievements of new data analysis tools for cell classification based on deep/machine learning, combined with holographic imaging, are urging these systems toward the effective implementation of point of care devices. However, the generalization capabilities of learning-based models may be limited from biases caused by data obtained from other holographic imaging settings and/or different processing approaches. In this paper, we propose a combination of a Mask R-CNN to detect the cells, a convolutional auto-encoder, used to the image feature extraction and operating on unlabelled data, thus overcoming the bias due to data coming from different experimental settings, and a feedforward neural network for single cell classification, that operates on the above extracted features. We demonstrate the proposed approach in the challenging classification task related to the identification of drug-resistant endometrial cancer cells.