In 2007, International Agency for Cancer Research presented compelling evidence that linked smokeless tobacco use to the development of human oral cancer. While these findings imply vigorous local carcinogen metabolism, little is known regarding levels and distribution of Phase I, II and drug egress enzymes in human oral mucosa. In the study presented here, we integrated clinical data, imaging and histopathologic analyses of an oral squamous cell carcinoma that arose at the site of smokeless tobacco quid placement in a patient. Immunoblot and immunohistochemical (IHC) analyses were employed to identify tumor and normal human oral mucosal smokeless tobacco-associated metabolic activation and detoxification enzymes. Human oral epithelium contains every known Phase I enzyme associated with nitrosamine oxidative bioactivation with ~2 fold inter-donor differences in protein levels. Previous studies have confirmed ~3.5 fold inter-donor variations in intraepithelial Phase II enzymes. Unlike the superficially located enzymes in non-replicating esophageal surface epithelium, IHC studies confirmed oral mucosal nitrosamine metabolizing enzymes reside in the basilar and suprabasilar region which notably is the site of ongoing keratinocyte DNA replication. Clearly, variations in product composition, nitrosamine metabolism and exposure duration will modulate clinical outcomes. The data presented here form a coherent picture consistent with the abundant experimental data that links tobacco-specific nitrosamines to human oral cancer.
Unavailability of large training datasets is a bottleneck that needs to be overcome to realize the true potential of deep learning in histopathology applications. Although slide digitization via whole slide imaging scanners has increased the speed of data acquisition, labeling of virtual slides requires a substantial time investment from pathologists. Eye gaze annotations have the potential to speed up the slide labeling process. This work explores the viability and timing comparisons of eye gaze labeling compared to conventional manual labeling for training object detectors. Challenges associated with gaze based labeling and methods to refine the coarse data annotations for subsequent object detection are also discussed. Results demonstrate that gaze tracking based labeling can save valuable pathologist time and delivers good performance when employed for training a deep object detector. Using the task of localization of Keratin Pearls in cases of oral squamous cell carcinoma as a test case, we compare the performance gap between deep object detectors trained using hand-labelled and gaze-labelled data. On average, compared to 'Bounding-box' based hand-labeling, gaze-labeling required 57.6% less time per label and compared to 'Freehand' labeling, gazelabeling required on average 85% less time per label.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.