Electrical Impedance Tomography (EIT) is a medical imaging technique that is primarily used to monitor the respiration of a patient.

Because EIT is based on electrical measurements, it is a safe, non-invasive, and cost-effective imaging technique.

However, the EIT image reconstruction is a severely ill-posed problem that gives low spatial resolution where only large variations in tissue conductivity can be visualized.

Furthermore, widely used time difference EIT relies on a single frequency alternating current measurement which does not allow for discrimination of different tissues for example on their conductivity spectra.

Here we show the application of a new EIT reconstruction algorithm which correlates measurements taken at different frequencies to include the spectral dependency of the tissue properties.

The algorithm is tested on a simulated phantom using tabulated muscle and lung tissue data.

It shows that contrary to a standard EIT image reconstruction, the frequency dependence of the tissues is retained, which can be used to further improve distinguishability in EIT images.

Electrical Impedance Tomography is used to image the cross-sectional conductivity of an object. It is clinically used for high-frame-rate imaging of lung ventilation. Most current systems use very limited current injection waveforms and patterns. We have developed a flexible system for researching alternatives. This paper covers our voltage conditioning module's design and characterisation. The device was shown to work up to the desired 10 MHz. The responses were uniform with minor gain mismatch between all channels after manufacturing variations. The low-frequency (<1 MHz) crosstalk is on the order -55 dB, and the worst cases around 8 MHz are around -35 dB.

Generation of cell painting facilitates high-throughput screening of cellular biology and disease mechanisms, accelerating the discovery of novel therapeutic targets or drugs. This study explores the prediction of cell painted Endoplasmic Reticulum (ER) images from transmitted light brightfield images employing deep learning techniques. A conditional Generative Adversarial Network (cGAN) based framework incorporating Wasserstein loss and Gradient Penalty with a modified UNet++ based generator and a patch discriminator is used to generate cell-painting images from brightfield images captured at varying focal planes. Evaluation of the GAN network reveals promising results with a Mean Absolute Error (MAE) of 0.20, Multi-Scale Structural Similarity Index (MS-SSIM) of 0.80, and Peak Signal-to-Noise Ratio (PSNR) of 56.52. The results showcase the effectiveness of the proposed approach in accurately predicting the ER cell painting channel from transmitted light microscopy. Consequently, the study proposes the ER-WGAN network for predicting cell painting using brightfield images.