Occupational percutaneous injuries and exposures in a dental teaching environment: A 10-year report.

PURPOSE: Percutaneous injuries (PIs) are woefully underreported and the risk at dental academic institutions is higher due to lack of knowledge and experience of students. The aims of this study are to (1) present data on the prevalence of PIs and exposures over a 10-year period in a dental teaching institution; (2) provide information on areas with increased risk as it relates to personnel and instruments; and (3) improve the awareness of the risk of occupational PIs and exposures in dentistry. METHODS: Data presented were collected as a part of an infection control program. A description of the incident reporting and collecting methodology is provided. Distribution tables and confidence intervals for injuries by year were calculated. Overall associations were produced using either Fisher's exact or Chi-square test. RESULTS: Between 2009 and 2019, a total of 342 PIs (338) and mucosal exposures (4) were reported. A significant number of injuries occurred while reaching for an instrument (15.2%), injecting local anesthetic (13.2%), and cleaning an instrument (11.7%). About 31% of the injuries were caused by needlesticks followed by burs (22.8%). There was a statistically significant association between work practice controls and activity type (p < 0.001) and position (p = 0.01). PIs and compliance issues were higher among the third-year dental students. CONCLUSIONS: There was a declining trend in incidents over the years, which could be attributed to the extra-protective measures that were implemented. Uncovered dental burs and needlesticks continue to be the predominant cause of PIs in academia. We found that collection of data on such occupation-related injuries to be useful in observing any trends and implementation of corrective actions.

Three-Class Mammogram Classification Based on Descriptive CNN Features.

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.