This study aims to summarize the current state of scientific knowledge on factors that contribute to heat generation during the bone drilling process and how these aspects can be better understood and avoided in the future through new research methodologies. Frictional pressures, mechanical trauma, and surgical methods can cause thermal damage and significant micro-fracturing, which can impede bone recovery. According to current trends in the technical growth of the dental and orthopedic industries’ 4.0 revaluation, enhancing drill bit design is one of the most feasible and cost-effective alternatives. In recent years, research on drilling bones has become important to reduce bone tissue damage, such as osteonecrosis (ON), and other problems that can happen during surgery. Reviewing the influence of feed rate, drill design, drill fatigue, drill speed, and force applied during osteotomies, all of which contribute to heat generation, was a major focus of this article. This comprehensive review can aid medical surgeons and drill bit makers in comprehending the recent improvements through optimization strategies for reducing or limiting thermal damage in bone drilling procedures used in the dental and orthopedic industries.
Surgeons face a significant challenge due to the heat generated during drilling, as excessive temperatures at the bone–tool interface can lead to irreversible damage to the regenerative soft tissue and result in thermal osteonecrosis. While previous studies have explored the use of machine learning to predict the temperature rise during bone drilling, this in vitro study introduces a comprehensive approach by combining the Response Surface Methodology (RSM) with advanced machine learning techniques. The main objective lies in the comprehensive evaluation and comparison of support vector machine (SVM) and random forest (RF) models specifically for the optimization of the bone drilling parameters to prevent thermal bone necrosis. A total of 27 experiments were conducted using a multi-level factorial method, with analysis performed via the Minitab software version 19.1. Performance metrics such as the mean squared error (MSE), mean absolute percentage error (MAPE), and coefficient of determination (R2) were used to assess model accuracy. The RF model emerged as the most effective, with R2 values of 94.2% for testing and 97.3% for training data, significantly outperforming other models in predicting temperature fluctuations. This study demonstrates the superior predictive capabilities of the RF model and offers a robust framework for the optimization of surgical procedures to mitigate the risk of thermal damage.
1 December 2021 in Journal of Physics: Conference Series
Predicting thermal response in orthopedic surgery or dental implantation remains a significant challenge. This study aims to find an effective approach for measuring temperature elevation during a bone drilling experiment by analyzing the existing methods. Traditionally thermocouple has frequently been used to predict the bone temperature in the drilling process. However, several experimental studies demonstrate that the invasive method using thermocouple is impractical in medical conditions and preferred the thermal infrared (IR) camera as a non-invasive method. This work proposes a simplified experimental model that uses the thermocouple to determine temperature rise coupled with the thermal image source approach. Furthermore, our new method provides a significant opportunity to calibrate the thermal IR camera by finding out the undetected heat elevation in a workpiece depth.
Cervical cancer remains a significant cause of female mortality worldwide, primarily due to abnormal cell growth in the cervix. This study proposes an automated classification method to enhance detection accuracy and efficiency, addressing contrast and noise issues in traditional diagnostic approaches. The impact of image enhancement on classification performance is evaluated by comparing transfer learning-based Convolutional Neural Network (CNN) models trained on both original and enhanced images. This study employs transfer learning with pre-trained CNNs to classify preprocessed Pap smear images into three categories. Data augmentation, including rotations, flips, and shifts, enhances variability and prevents overfitting. The OneCycle learning rate schedule dynamically adjusts the learning rate, improving training efficiency. To enhance image quality, the Denoised Pairing Adaptive Gamma with Clipping Histogram Equalization (DPAGCHE) method improves contrast and reduces noise. The evaluation involves five pre-trained CNN models and the publicly available Herlev dataset, implemented in MATLAB Online. The ResNet50 model trained on the DPAGCHE-enhanced dataset achieves the highest classification performance, with 84.15% accuracy, along with improved specificity, recall, precision, and F1-score. ResNet50’s residual connections mitigate vanishing gradient issues and enhance deep feature extraction. Accordingly, the DPAGCHE preprocessing significantly improves classification performance, leading to a 53.65% increase in F1-score and 44.29% in precision. In contrast, the Baseline CNN reaches only 66.67% accuracy, highlighting the advantage of deeper architectures combined with enhanced preprocessing. These findings suggest integrating DPAGCHE-enhanced preprocessing with deep learning improves automated cervical cancer detection. In particular, ResNet50 demonstrates the best performance, reinforcing the effectiveness of contrast enhancement and noise reduction in aiding classification models.
5 May 2024 in Journal of Advanced Research in Applied Mechanics
This study aimed to elucidate the influences of several drilling parameters on bone temperature during drilling, as excessive heat generation can cause thermal bone damage and affect post-surgery recovery. In vitro drilling tests were conducted on bovine femoral shaft cortical bone specimens. The parameters considered included tool rotational speed (s), feed rate (f), tool diameter (d), and drill tip angles of 118° and 135°. Drilling temperatures were studied across a range of 800–2000 rpm rotational speeds, 20–40 mm/min feed rates, and 2–4 mm drill diameters. A predictive statistical model was constructed using the response surface methodology (RSM). Analysis of variance (ANOVA) at a 95% confidence level (α = 0.05) revealed that rotational speed significantly impacted temperature increase, contributing to 59.74% of observed temperature rises. Drill diameter accounted for 16.21% of temperature variations, while feed rate contributed to 10.04% of the temperature rises. The study provides valuable insights into the predominant factors affecting bone temperature during drilling. Understanding these parameters and their interplay is pivotal for optimizing drilling conditions and minimizing potential thermal damage to bones.
Chemi resistive gas sensors based on metal oxide semiconductor (MOX) materials provide a practical and cost-effective solution for detecting hazardous gases in industrial and environmental monitoring applications. However, their sensing performance is strongly influenced by variations in ambient temperature and relative humidity, which can affect sensitivity, selectivity, and long-term stability. This study presents a comprehensive experimental dataset and characterization of MOX gas sensors operating under controlled environmental conditions. Sensors targeting hydrogen sulfide (H 2 S), carbon monoxide (CO), and methane (CH 4 ) were selected due to their relevance in hazardous atmosphere monitoring, particularly in confined-space environments. A custom-designed sensing platform integrating a signal-conditioning circuit, environmental control chamber, and data acquisition unit was developed to enable precise and repeatable measurements across a temperature range of 16 °C–30 °C and relative humidity levels of 45%–75%. The experimental results demonstrate that sensor resistance (Rs) varies systematically with changes in ambient temperature and humidity, confirming the strong environmental cross-sensitivity of MOX sensing materials. In addition to sensor characterization, this work provides a structured and openly accessible time-series dataset containing synchronized measurements of sensor resistance, temperature, and humidity. The dataset offers a valuable resource for the development and benchmarking of environmental compensation algorithms, sensor drift correction techniques, and machine-learning-based gas sensing models.