Towards clinically applicable automated mandibular canal segmentation on CBCT.

OBJECTIVES: To develop a deep learning-based system for precise, robust, and fully automated segmentation of the mandibular canal on cone beam computed tomography (CBCT) images. METHODS: The system was developed on 536 CBCT scans (training set: 376, validation set: 80, testing set: 80) from one center and validated on an external dataset of 89 CBCT scans from 3 centers. Each scan was annotated using a multi-stage annotation method and refined by oral and maxillofacial radiologists. We proposed a three-step strategy for the mandibular canal segmentation: extraction of the region of interest based on 2D U-Net, global segmentation of the mandibular canal, and segmentation refinement based on 3D U-Net. RESULTS: The system consistently achieved accurate mandibular canal segmentation in the internal set (Dice similarity coefficient [DSC], 0.952; intersection over union [IoU], 0.912; average symmetric surface distance [ASSD], 0.046 mm; 95% Hausdorff distance [HD95], 0.325 mm) and the external set (DSC, 0.960; IoU, 0.924; ASSD, 0.040 mm; HD95, 0.288 mm). CONCLUSIONS: These results demonstrated the potential clinical application of this AI system in facilitating clinical workflows related to mandibular canal localization. CLINICAL SIGNIFICANCE: Accurate delineation of the mandibular canal on CBCT images is critical for implant placement, mandibular third molar extraction, and orthognathic surgery. This AI system enables accurate segmentation across different models, which could contribute to more efficient and precise dental automation systems.

Deep learning-based evaluation of the relationship between mandibular third molar and mandibular canal on CBCT.

OBJECTIVES: The objective of our study was to develop and validate a deep learning approach based on convolutional neural networks (CNNs) for automatic detection of the mandibular third molar (M3) and the mandibular canal (MC) and evaluation of the relationship between them on CBCT. MATERIALS AND METHODS: A dataset of 254 CBCT scans with annotations by radiologists was used for the training, the validation, and the test. The proposed approach consisted of two modules: (1) detection and pixel-wise segmentation of M3 and MC based on U-Nets; (2) M3-MC relation classification based on ResNet-34. The performances were evaluated with the test set. The classification performance of our approach was compared with two residents in oral and maxillofacial radiology. RESULTS: For segmentation performance, the M3 had a mean Dice similarity coefficient (mDSC) of 0.9730 and a mean intersection over union (mIoU) of 0.9606; the MC had a mDSC of 0.9248 and a mIoU of 0.9003. The classification models achieved a mean sensitivity of 90.2%, a mean specificity of 95.0%, and a mean accuracy of 93.3%, which was on par with the residents. CONCLUSIONS: Our approach based on CNNs demonstrated an encouraging performance for the automatic detection and evaluation of the M3 and MC on CBCT. Clinical relevance An automated approach based on CNNs for detection and evaluation of M3 and MC on CBCT has been established, which can be utilized to improve diagnostic efficiency and facilitate the precision diagnosis and treatment of M3.

Theoretical prediction of the impact sensitivities of energetic C-nitro compounds.

In order to design high-energetic and insensitive explosives, the frontier orbital energy gaps, surface electrostatic potentials, nitro group charges, bond dissociation energies (BDEs) of the C-NO2 trigger bonds, and intermolecular interactions obtained by the M06-2X/6-311++G(2d,p) method were quantitatively correlated with the experimental drop hammer potential energies of 10 typical C-nitro explosives. The changes of several information-theoretic quantities (ITQs) in the density functional reactivity theory were discussed upon the formation of complexes. The BDEs in the explosives with six-membered ring are larger than those with five-membered ring. The frontier orbital energy gaps of the compounds with benzene ring are larger than those with N-heterocycle. The models involving the intermolecular interaction energies and the energy gaps could be used to predict the impact sensitivity of the C-nitro explosives, while those involving ΔSS, ΔIF, and ΔSGBP are invalid. With the more and more ITQs, the further studies are needed to seek for a good correlation between impact sensitivity measurements and ITQs for the energetic C-nitro compounds. The origin of sensitivity was revealed by the reduced density gradient method.

Five-year long-term outcomes of laparoscopic surgery for colon cancer.

AIM: To perform a meta-analysis to answer whether long-term recurrence rates after laparoscopic-assisted surgery are comparable to those reported after open surgery. METHODS: A comprehensive literature search of the MEDLINE database, EMBASE database, and the Cochrane Central Register of Controlled Trials for the years 1991-2010 was performed. Prospective randomized clinical trials (RCTs) were eligible if they included patients with colon cancer treated by laparoscopic surgery vs open surgery and followed for more than five years. RESULTS: Three studies involving 2147 patients reported long-term outcomes based on five-year data and were included in the analysis. The overall mortality was similar in the two groups (24.9%, 268/1075 in the laparoscopic group and 26.4%, 283/1072 in open group). No significant differences between laparoscopic and open surgery were found in overall mortality during the follow-up period of these studies [OR (fixed) 0.92, 95% confidence intervals (95% CI): 0.76-1.12, P = 0.41]. No significant difference in the development of overall recurrence was found in colon cancer patients, when comparing laparoscopic and open surgery [2147 pts, 19.3% vs 20.0%; OR (fixed) 0.96, 95% CI: 0.78-1.19, P = 0.71]. CONCLUSION: This meta-analysis suggests that laparoscopic surgery was as efficacious and safe as open surgery for colon cancer, based on the five-year data of these included RCTs.

Aspirin use and the risk of gastric cancer: a meta-analysis.

PURPOSE: Studies investigating the association between aspirin use and gastric cancer risk have reported conflicting results. The objective of this study was to quantitatively summarize the evidence for such a relationship. RESULTS: Two investigators independently searched the Medline, PubMed, Embase, and Academic Search Premier (EBSCO) databases. Fourteen studies with a total number of 5,640 gastric cancer cases were identified. Most of the study populations were Caucasian. The combined results based on all studies showed there was no statistically significant difference between aspirin use and gastric cancer risk (odds ratio (OR) = 0.80, 95% confidence intervals (CI) = 0.54-1.19). When stratifying by study designs and gender, results were similar except for cohort and randomized controlled trial (RCT) studies (OR = 0.72, 95% CI = 0.62-0.84). When stratifying by location and Helicobacter pylori (H. pylori) infection, we observed there were lower risks in noncardia gastric cancer (OR = 0.62, 95% CI = 0.55-0.69) and H. pylori-infected individuals (OR = 0.62, 95% CI = 0.42-0.90) for aspirin users. Among Caucasians, there were lower risks for noncardia gastric cancer (OR = 0.73, 95% CI = 0.62-0.87) and H. pylori-infected individuals (OR = 0.62, 95% CI = 0.42-0.90) also. CONCLUSIONS: This meta-analysis indicated that regular use of aspirin may be associated with reduced risk of noncardia gastric cancer, especially among Caucasians; for H. pylori-infected subjects the result was similar.

Overweight, obesity and gastric cancer risk: results from a meta-analysis of cohort studies.

The relationship between excess body weight and gastric cancer risk has not been well studied to date. We therefore carried out a systematic review and meta-analysis of published cohort studies to evaluate the association between excess body weight and gastric cancer risk. An electronic search of the MEDLINE, PubMed, EMBASE and Academic Search Premier (EBSCO) databases, which contain articles published from 1950 onwards, was conducted in order to select studies for this meta-analysis. Ten studies with a total number of 9492 gastric cancer cases and a studied population of 3,097,794 were identified. Overall, excess body weight [body mass index (BMI)25] was associated with an increased risk of gastric cancer [odds ratio (OR)=1.22; 95% confidence intervals (CIs)=1.06-1.41]. Specifically, a stratified analysis showed that excess body weight was associated with an increased risk of cardia gastric cancer [overweight and obese (BMI 25), OR=1.55, 95% CIs=1.31-1.84] and gastric cancer among non-Asians (overweight and obese, OR=1.24, 95% CIs=1.14-1.36); however, the stratified analysis also showed that there was no statistically significant link between excess body weight and gastric cancer in the following subgroups: males (overweight and obese, OR=1.22, 95% CIs=0.96-1.55), females (overweight and obese, OR=1.13, 95% CIs=0.65-1.94), non-cardia gastric cancer (overweight and obese, OR=1.18, 95% CIs=0.96-1.45) and Asians (overweight and obese, OR=1.17, 95% CIs=0.88-1.56). The combined results of this meta-analysis, however, do indicate that overweight and obesity are associated with an increased risk of gastric cancer. The strength of the association also increases with increasing BMI.