1 January 2021 in Journal of Pathology Informatics
Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research.
8 September 2017 in Biomedical Optics Express
Deterioration in mitochondrial function leads to hepatic ischemia and reperfusion injury (IRI) in liver surgery and transplantation. 3D optical cryoimaging was used to measure the levels of mitochondrial coenzymes NADH and FAD, and their redox ratio (NADH/FAD) gave a quantitative marker for hepatocyte oxidative stress during IRI. Using a rat model, five groups were compared: control, ischemia for 60 or 90 minutes (Isc60, Isc90), ischemia for 60 or 90 minutes followed by reperfusion of 24 hours (IRI60, IRI90). Ischemia alone did not cause a significant increase in the redox ratio; however, the redox ratio in both IRI60 and IRI90 groups was significantly decreased by 29% and 71%, respectively. A significant correlation was observed between the redox ratio and other markers of injury such as serum aminotransferase levels and the tissue ATP level. The mitochondrial redox state can be successfully measured using optical cryoimaging as a quantitative marker of hepatic IR injury.
16 August 2021 in IEEE Journal of Translational Engineering in Health and Medicine
Background: Mitochondrial $\beta $ -oxidation of fatty acids is the primary energy source for the heart and carried out by Hydroxy Acyl-CoA Dehydrogenase (HADH) encoded trifunctional protein. Mutations in the genes encoding mitochondrial proteins result in functionally defective protein complexes that contribute to energy deficiencies, excessive reactive oxygen species (ROS) production, and accumulation of damaged mitochondria. We hypothesize that a dramatic alternation in redox state and associated mitochondrial dysfunction is the underlying cause of Fatty Acid Oxidation (FAO) deficiency mutant, resulting in heart failure. Mitochondrial co-enzymes, NADH and FAD, are autofluorescent metabolic indices of cells when imaged, yield a quantitative assessment of the cells’ redox status and, in turn, that of the tissue and organ. Method: We utilized an optical cryo-imager to quantitively evaluate the three-dimensional distribution of mitochondrial redox state in newborn rats’ hearts and kidneys. Redox ratio (RR) assessment shows that mitochondrial dysfunction is extreme and could contribute to severe heart problems and eventual heart failure in the mutants. Results: Three-dimensional redox ratio (NADH/FAD) rendering, and the volumetric mean value calculations confirmed significantly decreased cardiac RR in mutants by 31.90% and 12.32%, in renal mitochondrial RR compared to wild-type control. Further, histological assessment of newborn heart myocardial tissue indicated no significant difference in myocardial tissue architecture in both control and severe (HADHA e4−/− ) conditions. Conclusion: These results demonstrate that optical imaging can accurately estimate the redox state changes in newborn rat organs. It is also apparent that the FAO mutant’s heart tissue with a low redox ratio is probably more vulnerable to cumulative damages than kidneys and fails prematurely, contributing to sudden death.
18 October 2019 in IEEE Journal of Translational Engineering in Health and Medicine
Background: Diabetes is known to cause delayed wound healing, and chronic non-healing lower extremity ulcers may end with lower limb amputations and mortalities. Given the increasing prevalence of diabetes mellitus worldwide, it is critical to focus on underlying mechanisms of these debilitating wounds to find novel therapeutic strategies and thereby improve patient outcome. Methods: This study aims to design a label-free optical fluorescence imager that captures metabolic indices (NADH and FAD autofluorescence) and monitors the in vivo wound healing progress noninvasively. Furthermore, 3D optical cryo-imaging of the mitochondrial redox state was utilized to assess the volumetric redox state of the wound tissue. Results: The results from our in vivo fluorescence imager and the 3D cryo-imager quantify the differences between the redox state of wounds on diabetic mice in comparison with the control mice. These metabolic changes are associated with mitochondrial dysfunction and higher oxidative stress in diabetic wounds. A significant correlation was observed between the redox state and the area of the wounds. Conclusion: The results suggest that our developed novel optical imaging system can successfully be used as an optical indicator of the complex wound healing process noninvasively.
24 August 2022 in Toxicologic Pathology
In nonclinical toxicity studies, stage-aware evaluation is often expected to assess drug-induced testicular toxicity. Although stage-aware evaluation does not require identification of specific stages, it is important to understand microscopic features of spermatogenic staging. Staging of the spermatogenic cycle in dogs is a challenging and time-consuming process. In this study, we first defined morphologic features for the eight spermatogenic stages in standard histology sections (H&E slides) of dog testes. For image analysis, we defined the key morphologic features of five stages/pooled stage groups (I-II, III-IV, V, VI-VII, and VIII). These criteria were used to develop a deep learning (DL) algorithm for staging of the spermatogenic cycle of control dog testes using whole slide images. In addition, a DL-based nucleus segmentation model was trained to detect and quantify the number of different germ cells, including spermatogonia, spermatocytes, and spermatids. Identification of spermatogenic stages and quantification of germ cell populations were successfully automated by the DL models. Combining these two algorithms provided color-coding visual spermatogenic staging and quantitative information on germ cell populations at specific stages that would facilitate the stage-aware evaluation and detection of changes in germ cell populations in nonclinical toxicity studies.
8 July 2021 in Journal of Biomedical Optics
Damaged vasculature and the resulting impaired blood circulation in organs can cause pathological injuries, such as organ failure and stroke.1 Therefore, vascular imaging plays a pivotal role in diagnosis, follow-up of disease progression, and assessment of treatment efficacy.2 Assessment of vascular structure in rodent models is key to quantitate organ vasculature.3,4 This quantitation could be beneficial in analyzing pathological conditions, such as hypertension,5 diabetes,6 and retinopathy7 as well as changes induced by environmental or chemical agents such as radiation8 or drugs.9 Vascular imaging is also important to study therapeutic angiogenesis.10