• 대한두개안면성형외과학회지
• /
• 제12권2호
• /
• pp.116-120
• /
• 2011

Purpose: Scalp avulsion is a life-threatening injury that may cause trauma to the forehead, eyebrows, and periauricular tissue. It is difficult to treat scalp avulsion as it may lead to severe bleeding. Therefore, emergency scalp replantation surgery is necessary, and we must consider the function, aesthetics, and psychology of the patients. A case of scalp avulsion leading to massive bleeding was encountered by these authors, which led to a failure to achieve the proper operation conditions in an adequate time period. Methods: A 49-year-old female was hospitalized due to having had her head caught in a rotatory machine, causing complete scalp avulsion which included the dorsum of the nose, both eyebrows, and ears. Emergent microsurgical replantation was performed, where a superficial temporal artery and a vein were anastomosed, but the patient's vital signs were too unstable for further operation due to excessive blood loss. Three days after the microanastomosis, venous congestion developed at the replanted scalp, and a medicinal leech was used. Leech therapy resolved the venous congestion. A demarcation then developed between the vitalized scalp tissue and the necrotized area. Debridement was performed 2 times on the necrotized scalp area. Finally, split-thickness skin graft with a dermal acellular matrix ($Matriderm^{(R)}$) was performed on the defective areas, which included the left temporal area, the occipital area, and both eyebrows. Results: The forehead, vertex, right temporal area, and half of the occipital area were successfully replanted, and the hair at the replanted scalp was preserved. As stated above, two-thirds of the scalp survived; the patient could cover the skin graft area with her hair, and could wear a wig. Conclusion: Complete scalp avulsion needs emergent replantation with microsurgical revascularization, but it often leads to serious vital conditions. We report a case with acceptable results, although the microanastomosed vessel was minimal due to the patient's unstable vital signs.

• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.27-35
• /
• 2023

본 논문에서는 복합소재 생산 분야에서 수요가 높은 프리프레그 섬유 제조 공정에 딥러닝 기반의 결함 검출 및 분류 시스템을 적용하여 생산성을 높이는 과정을 제안한다. 다양한 조건별 다량의 불량 발생으로 해결방안이 필요한 토우 프리프레그 제조 장비에 적용하기 위해 우선 결함 감지와 분류 모델 제작에 필요한 카메라 및 조명을 선정하여 최적의 환경을 구축하였다. 그리고 다중 분류 모델 제작에 필요한 데이터를 수집하고 정상 및 불량 조건에 따라 라벨링을 진행하였다. 다중 분류 모델은 CNN 기반으로 제작하였으며 VGGNet과 MobileNet, ResNet 등의 사전 학습모델을 적용하여 성능을 비교하고 정확도 및 손실 그래프로 개선 방향을 파악한다. 주요 문제로 과적합 문제를 확인하여 개선하기 위해 데이터 증강 및 Dropout 기법을 적용하여 보완하였다. 모델에 대한 성능 평가를 위해 혼돈행렬을 성능지표로 한 성능 평가를 진행하였으며 99% 이상의 성능을 확인하였다. 또한, 실제 공정에 적용하여 실시간 획득된 이미지에 대한 분류 결과를 확인해보며 판별 값이 정확히 도출되는지 확인한다.