Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: This study explores the potential of artificial intelligence (AI) in optimizing radiotherapy protocols for personalized cancer treatment. Specifically, it investigates the role of AI-based segmentation tools in improving accuracy and efficiency across various anatomical regions. Methods: A dataset of 500 anonymized patient computed tomography scans from Chungbuk National University Hospital was used to develop and validate AI models for segmenting organs-atrisk. The models were tailored for five anatomical regions: head and neck, chest, abdomen, breast, and pelvis. Performance was evaluated using Dice Similarity Coefficient (DSC), Mean Surface Distance, and the 95th Percentile Hausdorff Distance (HD95). Results: The AI models achieved high segmentation accuracy for large, well-defined structures such as the brain, lungs, and liver, with DSC values exceeding 0.95 in many cases. However, challenges were observed for smaller or complex structures, including the optic chiasm and rectum, with instances of segmentation failure and infinity values for HD95. These findings highlight the variability in performance depending on anatomical complexity and structure size. Conclusions AI-based segmentation tools demonstrate significant potential to streamline radiotherapy workflows, reduce inter-observer variability, and enhance treatment accuracy. Despite challenges with smaller structures, the integration of AI enables dynamic, patient-specific adaptations to anatomical changes, contributing to more precise and effective cancer treatments.Future work should focus on refining models for anatomically complex structures and validating these methods in diverse clinical settings.

Purpose: To predict the presence of tractional retinal detachment (TRD) in eyes with dense vitreous hemorrhage (VH) and proliferative diabetic retinopathy (PDR) by evaluating the status of posterior vitreous detachment (PVD) in fellow eyes using optical coherence tomography (OCT). Methods: A total of 44 eyes from 22 patients who underwent vitrectomy due to dense VH with PDR were enrolled. Using OCT, the PVD status in the fellow eye was divided into two groups (incomplete and complete PVD). The incomplete PVD group included eyes without PVD and eyes with partial PVD. B-scan ultrasonography was performed on eyes with dense VH to evaluate the presence of TRD. Both OCT and B-scan images were reviewed by four ophthalmologists (two novices and two experienced), and the interobserver agreement was evaluated. Results: There was a difference in the interobserver agreement regarding the presence of TRD in eyes with dense VH evaluated by B scan between novice and experienced ophthalmologists (novice, κ = 0.421 vs. experienced, κ = 0.814), although there was no difference between novice and experienced ophthalmologists in the interobserver agreement regarding the status of PVD in the fellow eye evaluated by OCT (novice, κ = 1.000 vs. experienced, κ = 1.000). All observed TRD during vitrectomy occurred in eyes with incomplete PVD in the fellow eye. Logistic regression analysis revealed a statistically significant relation between TRD and the age of the patient (odds ratio [OR], 0.874; p = 0.047), and between TRD and incomplete PVD in the fellow eye evaluated by OCT (OR, 13.904; p = 0.042). Conclusions Evaluation of the PVD status in the fellow eye using OCT may be a useful predictor for detecting the presence of TRD in eyes with dense VH and PDR.

Background and Objectives: Recently, the improvement of music perception abilities for emotional stability and high quality of life has become important for the hearing loss group. This study aimed to examine and compare the music perception abilities of the normal hearing (NH) and hearing amplification system (HAS) groups to find the needs and methods of music rehabilitation. Subjects and Methods: The data were collected from 15 NH adults (33.1±11.4 years) and 15 HAS adults (38.7±13.4 years), of whom eight wore cochlear implant [CI] systems and seven wore CI and hearing aid systems depending on pitch, melody, rhythm, timbre, emotional reaction, and harmony perception tests. A mismatch negativity test was also conducted, and attitudes toward and satisfaction with listening to music were measured. Results: The correction percentages for the NH and HAS groups were 94.0%±6.1% and 75.3%±23.2% in the pitch test; 94.0%±7.1% and 30.3%±25.9% in the melody test; 99.3%±1.8% and 94.0%± 7.6% in the rhythm test; 78.9%±41.8% and 64.4%±48.9% in the timbre test; 96.7%±10.4% and 81.7%±16.3% in the emotional reaction test; and 85.7%±14.1% and 58.4%±13.9% in the harmony test, respectively, showing statistical significance (p<0.05). For the mismatch negativity test, the area of the waveform was smaller in the HAS groups than in the NH groups, with 70 dB of stimulation showing no statistical significance. The response rates for satisfaction with listening to music were 80% and 93.3% for the NH and HAS groups, showing no statistical significance. Conclusions Although the HAS group showed lower music perception ability than the NH group overall, they showed a strong desire for music listening. Also, the HAS group revealed a higher degree of satisfaction even when listening to unfamiliar music played with unusual instruments. It is suggested that systematic and constant musical rehabilitation based on musical elements and different listening experiences will improve music perception qualities and abilities for HAS users.

Neurocritical patients who can self-report pain use the 0-10 numerical rating scale (NRS, verbal or visual form). However, critically ill patients whose nervous systems cannot express pain use the behavioral pain scale (BPS) and the critical care pain observation tool (CPOT) behavioral pain assessment tools. These tools reveal pain-related changes in movement, facial expression, posture, and physiological indicators such as heart rate, blood pressure, and respiratory rate. In pain control, it is first essential to reduce unnecessary painkillers through non-drug therapy and maximize the effect of the administered analgesics. For nonneuropathic pain, narcotic analgesics such as fentanyl, hydromorphone, morphine, and remifentanil are administered intravenously. Gabapentin, pregabalin, and carbamazepine are recommended along with narcotic analgesics for neuropathic pain control. In addition, nonnarcotic analgesics for multi-modal analgesia are used to reduce the use of narcotic analgesics or the side effects of narcotic analgesics. In the intensive care unit (ICU), the sedation-agitation scale (SAS) and the Richmond agitation-sedation scale (RASS) are used to determine the depth of sedation to be maintained during shallow or deep sedation, considering the condition of the critically ill patient. When selecting sedatives for critically ill patients, preferentially consider nonbenzodiazepines such as propofol or dexmedetomidine rather than benzodiazepines such as midazolam or lorazepam. In addition, patients use painkillers or sedatives for over a week, and neurological changes or physiological dependence may occur. Therefore, clinicians should evaluate the critically ill patient’s condition, and sedatives and painkillers should be reduced or discontinued.

Background and Objectives: Natural and synthetic speech signals effectively stimulate cortical auditory evoked potential (CAEP). This study aimed to select the speech materials for CAEP and identify CAEP waveforms according to gender of speaker (GS) and gender of listener (GL). Subjects and Methods: Two experiments including a comparison of natural and synthetic stimuli and CAEP measurement were performed of 21 young announcers and 40 young adults. Plosive /g/ and /b/ and aspirated plosive /k/ and /p/ were combined to /a/. Six bisyllables–/ga/-/ka/, /ga/-/ba/, /ga/-/pa/, /ka/-/ba/, /ka/-/pa/, and /ba/-/pa/–were formulated as tentative forwarding and backwarding orders. In the natural and synthetic stimulation mode (SM) according to GS, /ka/ and /pa/ were selected through the first experiment used for CAEP measurement. Results: The correction rate differences were largest (74%) at /ka/-/ pa/ and /pa/-/ka/; thus, they were selected as stimulation materals for CAEP measurement. The SM showed shorter latency with P2 and N1-P2 with natural stimulation and N2 with synthetic stimulation. The P2 amplitude was larger with natural stimulation. The SD showed significantly larger amplitude for P2 and N1-P2 with /pa/. The GS showed shorter latency for P2, N2, and N1-P2 and larger amplitude for N2 with female speakers. The GL showed shorter latency for N2 and N1-P2 and larger amplitude for N2 with female listeners. Conclusions Although several variables showed significance for N2, P2, and N1-P2, P1 and N1 did not show any significance for any variables. N2 and P2 of CAEP seemed affected by endogenous factors.