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, gaze-labeling required on average 85% less time per label.
Background: Toll like receptors (TLR) 2 and 4 present on innate immune cells of the dental pulp detect cariogenic bacteria. Along with bacteria, C. albicans may also be present in dental caries. The presence of C. albicans can be detected by Dectin-1 a C type Lectin receptor. Expression of Dectin-1 in human pulpits has not been reported. Similarly, cytokines are released as a consequence of dental pulp inflammation caused by cariogenic bacteria. The T helper (Th) 1 inflammatory response leads to exacerbation of inflammation and its relationship with Osteopontin (OPN) is not known in pulp inflammation. Objective: The aim of this study was to observe the expression of Dectin-1, TLR-2, OPN and pro-inflammatory cytokines in irreversibly inflamed human dental pulp and to observe relationship between Dectin-1/TLR-2 and OPN/Pro-inflammatory cytokines in the presence of appropriate controls. Methods: A total of 28 subjects diagnosed with irreversible pulpitis were included in this ex-vivo study. Fifteen samples were subjected to standard hematoxylin and Eosin (H&E) and immunohistochemistry staining. Whereas, gene expression analysis was performed on 13 samples to observe mRNA expression of pro-inflammatory cytokines; tumor necrosis factor-alpha (TNF-α), interleukin (IL)-1 beta (ß), IL-6 Dectin-1, OPN, TLR-2 and TLR-4. SPSS version 21 was used for statistical analysis. One way analysis of variance (ANOVA), Pearson correlation and Chi-square test were used at p ≤ 0.05. Results: Gene expressions of Dectin-1, TLR-2 and TLR-4 were observed in all samples. Dectin-1 and TLR-2 expressions were significantly correlated (r = 0.5587, p = 0.0002). Similarly, OPN and TNF-α expression showed a significant correlation (r = 0.5860, p = 0001). The agreement between histologic and clinical diagnosis was 69.2% in the cases of irreversible pulpitis. Conclusion: Dectin-1 was expressed by inflamed human dental pulp. Dectin-1 and TLR-2 expression pattern was suggestive of a collaborative receptor response in inflamed pulp environment. OPN and TNF-α expressions showed a positive correlation indicating a possible relationship.
29 August 2019 in Journal of Dermatological Treatment
This study documented the response of erosive oral lichen planus (OLP) to exclusive treatment with 0.1% topical tacrolimus over a 12-month period or until the patient became unresponsive to therapy...