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

Mid-infrared spectroscopic imaging (MIRSI) is an emerging class of label-free techniques being leveraged for digital histopathology. Modern histopathologic identification of ovarian cancer involves tissue staining followed by morphological pattern recognition. This process is time-consuming and subjective and requires extensive expertise. This paper presents the first label-free, quantitative, and automated histological recognition of ovarian tissue subtypes using a new MIRSI technique. This optical photothermal infrared (O-PTIR) imaging technique provides a 10× enhancement in spatial resolution relative to prior instruments. It enables sub-cellular spectroscopic investigation of tissue at biochemically important fingerprint wavelengths. We demonstrate that the enhanced resolution of sub-cellular features, combined with spectroscopic information, enables reliable classification of ovarian cell subtypes achieving a classification accuracy of 0.98. Moreover, we present a statistically robust analysis from 78 patient samples with over 60 million data points. We show that sub-cellular resolution from five wavenumbers is sufficient to outperform state-of-the-art diffraction-limited techniques with up to 235 wavenumbers. We also propose two quantitative biomarkers based on the relative quantities of epithelia and stroma that exhibit efficacy in early cancer diagnosis. This paper demonstrates that combining deep learning with intrinsic biochemical MIRSI measurements enables quantitative evaluation of cancerous tissue, improving the rigor and reproducibility of histopathology.

Irrupting prey populations in the absence of a mammalian apex predator drive shifts in prey selection by eagles.

Removal of apex predators can have far-reaching effects on the organization and structure of ecosystems. This occurs because apex predators can exert strong suppressive effects on their prey and competitors and perturbation of these interactions can shift the balance of interactions between dyads of species at lower trophic levels and trigger trophic cascades. Dingoes (Canis dingo) are Australia's largest mammalian carnivore. Because they are a pest to livestock producers, dingo populations are suppressed in many regions. Suppression of dingo populations has been linked to a suite of ecosystem changes due to ensuing population irruptions of their prey and competitors. Here, we investigate the impact that the suppression of dingoes has on the diet of wedge-tailed eagles (Aquila audax) in Australia's Strzelecki Desert. Wedge-tailed eagles are generalist predators that readily shift their diet in relation to prey availability. We assessed the abundance of species frequently preyed on by eagles and quantified prey remains at eagle nests located on either side of a dingo-proof fence where dingoes were common and rare, respectively. Wedge-tailed eagles consumed more species where dingoes were rare compared to where dingoes were common. Kangaroos (Macropodidae) and western bearded dragons (Pogona vitticeps) were more abundant and were consumed more frequently by eagles where dingoes were rare. Introduced European rabbits (Oryctolagus cuniculus) were the prey item most frequently identified at eagle nests. However, rabbits were more abundant and their remains were found at a higher proportion of nests where dingoes were common. Our results provide evidence that shifts in the composition of vertebrate assemblages associated with the presence/absence of dingoes, particularly the irruption of kangaroos, influence the diet of wedge-tailed eagles. More generally, by showing that the presence/absence of dingoes can influence the diet of wedge-tailed eagles, our study highlights how pervasive apex predators' effects on ecosystems can be.