Adaptive Compressive Sampling for Mid-Infrared Spectroscopic Imaging

Abstract

Mid-infrared spectroscopic imaging (MIRSI) is an emerging class of label-free, biochemically quantitative technologies targeting digital histopathology. Conventional histopathology relies on chemical stains that alter tissue color. This approach is qualitative, often making histopathologic examination subjective and difficult to quantify. MIRSI addresses these challenges through quantitative and repeatable imaging that leverages native molecular contrast. Fourier transform infrared (FTIR) imaging, the best-known MIRSI technology, has two challenges that have hindered its widespread adoption: data collection speed and spatial resolution. Recent technological breakthroughs, such as photothermal MIRSI, provide an order of magnitude improvement in spatial resolution. However, this comes at the cost of acquisition speed, which is impractical for clinical tissue samples. This paper introduces an adaptive compressive sampling technique to reduce hyperspectral data acquisition time by an order of magnitude by leveraging spectral and spatial sparsity. This method identifies the most informative spatial and spectral features, integrates a fast tensor completion algorithm to reconstruct megapixel-scale images, and demonstrates speed advantages over FTIR imaging while providing spatial resolutions comparable to new photothermal approaches.

Cervical Cancer Tissue Analysis Using Photothermal Midinfrared Spectroscopic Imaging

“…Both sets included multiple cancer grades. The structures of the RF and CNN classifiers are derived from our published work. − The last TMA row, which contained normal tissue, was used exclusively for testing, while for all other rows, the first five cores were used for training and the remaining cores for testing. This protocol ensures the independence of training and testing data sets, which is a limitation in previously published work …”

Leveraging mid-infrared spectroscopic imaging and deep learning for tissue subtype classification in ovarian cancer

“…Since the O-PTIR signal was detected using a point detector, the time taken to collect an image of a single core varies between 90 and 100 minutes per wavenumber. 59 Collecting a hyperspectral data cube of a core at all wavenumbers (900–1900 cm −1 at 2 cm −1 spacing) would take approximately 35 days. We therefore collected fewer bands, focusing on acquiring important biochemical information.…”