27 July 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
The susceptibility of super paramagnetic iron oxide (SPIO) particles makes them a useful contrast agent for different purposes in MRI. These particles are typically quantified with relaxometry or by measuring the inhomogeneities they produced. These methods rely on the phase, which is unreliable for high concentrations. We present in this study a novel Deep Learning method to quantify the SPIO concentration distribution. We acquired the data with a new sequence called View Line in which the field map information is encoded in the geometry of the image. The novelty of our network is that it uses residual blocks as the bottleneck and multiple decoders to improve the gradient flow in the network. Each decoder predicts a different part of the wavelet decomposition of the concentration map. This decomposition improves the estimation of the concentration, and also it accelerates the convergence of the model. We tested our SPIO concentration reconstruction technique with simulated images and data from actual scans from phantoms. The simulations were done using images from the IXI dataset, and the phantoms consisted of plastic cylinders containing agar with SPIO particles at different concentrations. In both experiments, the model was able to quantify the distribution accurately.
2 June 2025 in Small Methods
It is shown that regularizing the signal gradient statistics during training of deep‐learning models of super‐resolution fluorescence microscopy improves the generated images. Specifically, regularizing the images in the training data set is proposed to have gradient and Laplacian statistics closer to those expected for natural‐scene images. The BioSR data set of matched pairs of diffraction‐limited and super‐resolution images is used to evaluate the proposed regularization in a state‐of‐the‐art generative deep‐learning model of super‐resolution microscopy, the Conditional Variational Diffusion Model (CVDM). Since the proposed regularization is applied as a preprocessing step to the training data, it can be used in conjunction with any supervised machine‐learning model. However, its utility is limited to images for which the prior is appropriate, which in the BioSR data set are the images of filamentous structures. The quality and generalization power of CVDM trained with and without the proposed regularization are compared, showing that the new prior yields images with clearer visual detail and better small‐scale structure.
1 September 2024 in bioRxiv
Detecting virus-infected cells in light microscopy requires a reporter signal commonly achieved by immunohistochemistry or genetic engineering. While classification-based machine learning approaches to the detection of virus-infected cells have been proposed, their results lack the nuance of a continuous signal. Such a signal can be achieved by virtual staining. Yet, while this technique has been rapidly growing in importance, the virtual staining of virus-infected cells remains largely uncharted. In this work, we propose a benchmark and datasets to address this. We collate microscopy datasets, containing a panel of viruses of diverse biology and reporters obtained with a variety of magnifications and imaging modalities. Next, we explore the virus infection reporter virtual staining (VIRVS) task employing U-Net and pix2pix architectures as prototypical regressive and generative models. Together our work provides a comprehensive benchmark for VIRVS, as well as defines a new challenge at the interface of Data Science and Virology.