Search

Camera images are ubiquitous in machine learning research. They also play a central role in the delivery of important services spanning medicine and environmental surveying. However, the application of machine learning models in these domains has been limited because of robustness concerns. A primary failure mode are performance drops due to differences between the training and deployment data. While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of the primary object of interest: the data. This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner. In this study, we demonstrate how to overcome this limitation by pairing traditional machine learning with physical optics to obtain explicit and differentiable data models. We demonstrate how such data models can be constructed for image data and used to control downstream machine learning model performance related to dataset drift. The findings are distilled into three applications. First, drift synthesis enables the controlled generation of physically faithful drift test cases to power model selection and targeted generalization. Second, the gradient connection between machine learning task model and data model allows advanced, precise tolerancing of task model sensitivity to changes in the data generation. These drift forensics can be used to precisely specify the acceptable data environments in which a task model may be run. Third, drift optimization opens up the possibility to create drifts that can help the task model learn better faster, effectively optimizing the data generating process itself. A guide to access the open code and datasets is available at https://github.com/aiaudit-org/raw2logit., Comment: Published as a journal paper in the Transactions on Machine Learning Research 2023 (TMLR) available at https://openreview.net/forum?id=I4IkGmgFJz

Optical Projection Tomography (OPT) is a powerful tool for 3D imaging of mesoscopic samples, thus of great importance to image whole organs for the study of various disease models in life sciences. OPT is able to achieve resolution at a few tens of microns over a large sample volume of several cubic centimeters. However, the reconstructed OPT images often suffer from artifacts caused by different kinds of physical miscalibration. This work focuses on the refractive index (RI) mismatch between the rotating object and the surrounding medium. We derive a 3D cone beam forward model to approximate the effect of RI mismatch and implement a fast and efficient reconstruction method to correct the induced seagull-shaped artifacts on experimental images of fluorescent beads.

The impressive growth of data throughput in optical microscopy has triggered a widespread use of supervised learning (SL) models running on compressed image datasets for efficient automated analysis. However, since lossy image compression risks to produce unpredictable artifacts, quantifying the effect of data compression on SL applications is of pivotal importance to assess their reliability, especially for clinical use. We propose an experimental method to evaluate the tolerability of image compression distortions in 2D and 3D cell segmentation SL tasks: predictions on compressed data are compared to the raw predictive uncertainty, which is numerically estimated from the raw noise statistics measured through sensor calibration. We show that predictions on object- and image-specific segmentation parameters can be altered by up to 15% and more than 10 standard deviations after 16-to-8 bits downsampling or JPEG compression. In contrast, a recently developed lossless compression algorithm provides a prediction spread which is statistically equivalent to that stemming from raw noise, while providing a compression ratio of up to 10:1. By setting a lower bound to the SL predictive uncertainty, our technique can be generalized to validate a variety of data analysis pipelines in SL-assisted fields., Comment: 26 pages, 8 figures

We present a novel extended-focus optical coherence microscope (OCM) attaining 0.7 {\mu}m axial and 0.4 {\mu}m lateral resolution maintained over a depth of 40 {\mu}m, while preserving the advantages of Fourier domain OCM. Our method uses an ultra-broad spectrum from a super- continuum laser source. As the spectrum spans from near-infrared to visible wavelengths (240 nm in bandwidth), we call the method visOCM. The combination of such a broad spectrum with a high-NA objective creates an almost isotropic 3D submicron resolution. We analyze the imaging performance of visOCM on microbead samples and demonstrate its image quality on cell cultures and ex-vivo mouse brain tissue., Comment: 15 pages, 7 figures

We present a numerical analysis to simulate the response of a spherical resonant gravitational wave detector and to compute its sensitivity. Under the assump- tion of optimal filtering, we work out the sensitivity curve for a sphere first taking into account only a single transducer, and then using a coherent analysis of the whole set of transducers., Comment: 24 pages, 11 figures, published version