Performance evaluation of metaheuristics-tuned recurrent neural networks for electroencephalography anomaly detection.

Electroencephalography (EEG) serves as a diagnostic technique for measuring brain waves and brain activity. Despite its precision in capturing brain electrical activity, certain factors like environmental influences during the test can affect the objectivity and accuracy of EEG interpretations. Challenges associated with interpretation, even with advanced techniques to minimize artifact influences, can significantly impact the accurate interpretation of EEG findings. To address this issue, artificial intelligence (AI) has been utilized in this study to analyze anomalies in EEG signals for epilepsy detection. Recurrent neural networks (RNNs) are AI techniques specifically designed to handle sequential data, making them well-suited for precise time-series tasks. While AI methods, including RNNs and artificial neural networks (ANNs), hold great promise, their effectiveness heavily relies on the initial values assigned to hyperparameters, which are crucial for their performance for concrete assignment. To tune RNN performance, the selection of hyperparameters is approached as a typical optimization problem, and metaheuristic algorithms are employed to further enhance the process. The modified hybrid sine cosine algorithm has been developed and used to further improve hyperparameter optimization. To facilitate testing, publicly available real-world EEG data is utilized. A dataset is constructed using captured data from healthy and archived data from patients confirmed to be affected by epilepsy, as well as data captured during an active seizure. Two experiments have been conducted using generated dataset. In the first experiment, models were tasked with the detection of anomalous EEG activity. The second experiment required models to segment normal, anomalous activity as well as detect occurrences of seizures from EEG data. Considering the modest sample size (one second of data, 158 data points) used for classification models demonstrated decent outcomes. Obtained outcomes are compared with those generated by other cutting-edge metaheuristics and rigid statistical validation, as well as results' interpretation is performed.

Marked epithelial to mesenchymal transition in surgical margins of oral cancer-an in vitro study.

Epithelial to mesenchymal transition (EMT) is a feature of several types of human cancer, including oral squamous cell carcinoma (OSCC). In the present study, tumor and margin cell cultures obtained from patients with OSCC were used to determine the expression patterns of certain EMT-associated markers, including vimentin, α-smooth muscle actin, SLUG and SNAIL. In addition, other EMT-associated features, including clonal, proliferative and migratory potential were compared between the two cell types. Cell cultures were generated from tumor and margin tissue samples from 6 patients and cultured up to the fifth passage. EMT marker expression was assessed by reverse transcription-quantitative PCR. Cell proliferation, colony formation and scratch wound healing assays were conducted to characterize the two cell types in terms of proliferation rates, clonality and motility. All of the studied markers were expressed in tumor and margin cells. Although no significant differences were noted with regard to the aforementioned markers, their expression tended to be higher in margin cultures than in tumor cultures. The expressions of the EMT markers were also higher in the fifth passage compared with those noted at the first with a few exceptions. The rates of proliferation and cell migration were decreased during passages, while the number of colonies was increased in both types of cell culture. Tumor and margin cells indicated certain similarities with regard to EMT transition characteristics.

Comparison of four different suture materials in respect to oral wound healing, microbial colonization, tissue reaction and clinical features-randomized clinical study.

OBJECTIVES: Sutures are the most frequently used medical device for wound closure. They support tissue during the early phase of healing until it regains enough tensile strength. The aim of this study was to compare four different suture materials in terms of the influence on wound healing, microbial adherence, tissue reaction, and relevant clinical parameters which determine their clinical value. MATERIALS AND METHODS: Total number of 32 patients undergoing surgical extraction of four impacted third molars were involved in the study. Clinical parameters were estimated intraoperatively and during the control check-ups. Soft tissue healing around sutures were evaluated on the 3rd and 7th day postoperatively. Microbial colonization was assessed by means of qPCR. Also, histological analysis was done to assess inflammatory reaction. RESULTS: Significantly better soft tissue healing was found around monofilament and synthetic sutures compared to multifilament and natural ones respectively. Soft tissue healing was significantly better around all sutures on the 7th day than on the 3rd day postoperatively. CONCLUSIONS: Non-resorbable polypropylene suture showed superior clinical characteristics among all sutures. Moreover, the best healing of soft tissue and the least inflammatory reaction was found around this thread. The poorest soft tissue healing was found around non-resorbable silk suture. This suture elicited strongest inflammatory reaction and showed the greatest microbial adherence affinity compared to alternative sutures. CLINICAL RELEVANCE: Monofilament synthetic suture should be used in order to obtain the best soft tissue healing, reduce the risk of postoperative infection, and alleviate the suturing after oral surgery procedures.

Retrospective study of spontaneous bone regeneration after decompression of large odontogenic cystic lesions in children.

BACKGROUND/AIM: Surgical treatment of odontogenic cysts in childhood could be accompanied by injury of important anatomical structures. Even though enucleation is considered to be preferable treatment of odontogenic cysts, the specificities of pediatric age favor more conservative surgical approach. The aim of this study was to assess the effectiveness of decompression as the uttermost treatment of odontogenic cysts in the pediatric age. METHODS: This retrospective study included 22 patients, 7-16 years old, with a single jaw cystic lesion. The majority of these lesions were dentigerous cyst (14), and the rest belonged to keratocystic odontogenic tumor (KCOT) (8). All lesions were primarily treated with decompression; it was a final treatment (one-stage procedure) in 13 dentigerous cysts, and it was followed by enucleation (two-stage procedure) in one dentigerous cyst and all the KCOT. RESULTS: A total of 13 (59.1%) dentigerous cysts were treated successfully only with decompression as one stage procedure, while the other 9 (40.9%) cysts required enucleation (1 dentigerous and 8 KCOT), after decompression (p ≤ 0.001). CONCLUSION: Related to non-aggressive lesions, more conservative treatment approach, such as decompression as one-stage procedure, should be considered. On the other hand, KCOTs in children require a two-stage procedure for a successful treatment outcome.