• Title/Summary/Keyword: Sensory image

Search Result 160, Processing Time 0.026 seconds

Diagnosis and Visualization of Intracranial Hemorrhage on Computed Tomography Images Using EfficientNet-based Model (전산화 단층 촬영(Computed tomography, CT) 이미지에 대한 EfficientNet 기반 두개내출혈 진단 및 가시화 모델 개발)

  • Youn, Yebin;Kim, Mingeon;Kim, Jiho;Kang, Bongkeun;Kim, Ghootae
    • Journal of Biomedical Engineering Research
    • /
    • v.42 no.4
    • /
    • pp.150-158
    • /
    • 2021
  • Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

Analysis of browning degree on fresh-cut lotus root (Nelumbo nucifera G.) using image analysis (이미지 분석을 이용한 신선편이 연근의 갈변도 분석)

  • Cho, Jeong-Seok;Kim, Dae-Hyun;Park, Jung-Hoon;Moon, Kwang-Deog
    • Food Science and Preservation
    • /
    • v.20 no.6
    • /
    • pp.760-765
    • /
    • 2013
  • The image analysis as a tool for evaluation of browning degree on fresh-cut lotus root was studied. The fresh-cut lotus root treated as 4 groups (Cont-without any treatment, DB-blanching at $50^{\circ}C$ for 5 min in distilled water, AB-blanching at $45^{\circ}C$ for 5 min in 1% ascorbic acid, CB-blanching at $45^{\circ}C$ for 5 min in 1% citric acid). The samples treated with each methods were packaged with 0.04 mm polyethylene bag ($25cm{\times}30cm$) and stored at $4^{\circ}C$ for 9 days. On the RGB color space, the AB and CB group showed high R, G, B value. On the HSV and CIE $L^*a^*b^*$ color space, the AB and CB group showed low browning area, $a^*$, $b^*$ value and high $L^*$ value. Polyphenol oxidase activity was low in the AB and CB groups in all storage period. This result means that the AB and CB groups were inhibited the development of tissue browning. The result of sensory evaluation also supported this opinion. And the correlation coefficient between sensory evaluation with all color values was over 0.84. Especially, the $L^*$ value showed the highest correlation coefficient (0.93). In conclusion, the image analysis is suitable for analysis of browning degree on fresh-cut lotus root by analyzing diverse color value.

Pattern Making Method for Crescent-Shaped Sleeve Used in Power Shoulder Jacket (파워 숄더 재킷에 적용된 Crescent Shaped Sleeve의 패턴제도법)

  • Lee, Jung-Soon
    • Journal of the Korea Fashion and Costume Design Association
    • /
    • v.13 no.1
    • /
    • pp.59-71
    • /
    • 2011
  • As an exaggerated-shoulder becomes a growing trend women's clothing, the crescent shaped sleeve with parallel style lines in the arm hole is a highly used women's sleeve pattern. This study develops and provides an applicable method for making the crescent shaped power shoulder sleeve. An efficient basic method for making the 2 piece crescent shaped sleeve was developed and the sensory appearance test was carried out with experimental clothes. There are two principles for making the crescent shaped sleeve: having a style line in the sleeve and pasting part of the cut arm hole of the bodice to the sleeve. The latter would be more convenient for a 2 piece sleeve, mostly used for jackets. The crescent shaped sleeve used in power shoulder jackets should set the shoulder angle as you wish to extend and raise the shoulder point of the bodice and sleeve to the same height. For a stronger power shoulder image, a 3 piece sleeve has a better appearance. Also, the height of the shoulder has to be enhanced with a shoulder pad for a more stable sleeve.

  • PDF

Relationship characteristics of intermedia and fashion show in the Chanel collection (샤넬 컬렉션에 나타난 인터미디어와 패션쇼의 관계적 특성)

  • Lee, Seulah;Lee, Younhee
    • The Research Journal of the Costume Culture
    • /
    • v.24 no.3
    • /
    • pp.367-384
    • /
    • 2016
  • The aim of this paper is to examine relationship characteristics and the relevance there of in the context of the Chanel collection, between the contemporary fashion show viewed from the artistic side and intermedia on interaction. This study analyzed the relationship characteristics between intermedia and fashion shows by focusing on Chanel fashion shows from 2010 S/S to 2016 F/W as actual case. The results are as follow: First, participational accessibility indicates the experience of a designer and audience in active participation changing into passive participation. Second, audience immersion is represented by the perception of being involved by the audience in the place and acting. Third, conceptual symbolism is sending of messages through the designer's concept manifesting in the specific features of the design. Finally, expandability of media explains trans-boundaries in experimental attempts. It concludes that fashion show is a space where the audience can have visual as well as new knowledge and experience through multi-sensory channels. The Chanel collection which is considered a huge art project at the fashion show, showed a relationship between philosophy and the direction through season concepts and brands. The Chanel collection has brought a new experience through the convergence of communications and cultural media, such as music and art according to traditional brand image.

Estimation of the Light Intensity by Using Bright-Chip LED Sensory System (고휘도 발광 Chip 소자를 이용한 빛의 명암도 분석)

  • Choi, Ju-Hyeon;Kim, Ji-Sun;Jung, Gu-In;Lee, Tae-Hee;Kim, A-Hee;Oh, Han-Byeol;Park, Hee-Jung;Kim, Kyung-Seop;Jun, Jae-Hoon
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.62 no.9
    • /
    • pp.1290-1296
    • /
    • 2013
  • The light intensity which represents the relative amount of brightness and darkness is very important feature to discern the color hue and its relevant information. With this aim, we devise a new optical system and method to analyze the light intensity. Our suggested system including a phototransistor and white-high-brightness chip light-emitting diode intend estimate the contrast value utilizing Image Research Institute(I.R.I.) Hue & Tone samples which includes 120 color sheets arranged by the color hue and tone. As a result, we confirmed that the brightness of the color checker can be accurately estimated by a high-brightness light-emitting-diode optical system.

Estimation of Lifetime Data Storage Capacity for Human Senses (인간 감각 정보를 위한 평생 기억용량 평가)

  • You, Young-Gap;Song, Young-Jun;Kim, Dong-Woo
    • The Journal of the Korea Contents Association
    • /
    • v.9 no.1
    • /
    • pp.23-29
    • /
    • 2009
  • This paper presents a capacity estimation of a storage system accumulating all data sensed during the lifetime of an individual human being. The calculation assumes modern data compression and data collection schemes based on wearable or implanted devices under ubiquitous environment. More than 76% of the storage area is found to be used for video data storage of common TV image quality. The remaining storage area is for data from other sensing organs including audio, taste, olfactory and tactual systems in addition to indexing information. Total storage area of around 600 tera bytes is needed to cover 100 years of human life including his fetal period.

Congenital Cleft of Anterior Arch and Partial Aplasia of the Posterior Arch of the C1

  • Choi, Ji-Won;Jeong, Je-Hoon;Moon, Seung-Myung;Hwang, Hyung-Sik
    • Journal of Korean Neurosurgical Society
    • /
    • v.49 no.3
    • /
    • pp.178-181
    • /
    • 2011
  • Congenital anomalies in arches of the atlas are rare, and are usually discovered incidentally. However, a very rare subgroup of patients with unique radiographic features is predisposed to transient quadriparesis after minor cervical or head trauma, A 46-year-old male presented with a 2-month history of tremor and hyperesthesia of the lower extremities after experiencing a minor head trauma. He said that he had been quadriplegic for about 2 weeks after that trauma. Radiographs of his cervical spine revealed bilateral bony defects of the lateral aspects of the posterior arch of C1 and a midline cleft within the anterior arch of the atlas. A magnetic resonance imaging revealed an increased cord signal at the C2 level on the T2-weighted sagittal image. A posterior, suboccipital midline approach for excision of the remnant posterior tubercle was performed. The patient showed significant improvement of his motor and sensory functions. Since major neurologic deficits can be produced by a minor trauma, it is crucial to recognize this anomaly.

The types and expressions of new media fashion film

  • Kim, Sejin
    • The Research Journal of the Costume Culture
    • /
    • v.28 no.1
    • /
    • pp.96-113
    • /
    • 2020
  • A new form of media is changing the expression and content of fashion. In this paper, fashion films that have appeared since 2010 - when digital fashion communication was increasing - will be discussed and explored to consider how technological transitions in fashion media are changing the appearance and role of fashion. A literature review was conducted to derive characteristics, types, and expressive elements of new media fashion films, which were defined for this study as fashion films produced and distributed since 2010 using digital media. Films were categorized into three types: promotional, editorial, and independent fashion films. Furthermore, elements of the films were identified as fashion mise-en-scene, auditory structure, and content structure. Types and expressions of digital fashion images in 40 fashion films were analyzed according to these elements. The results showed that promotional fashion films maximize various narrative and sensory effects on fashion products, whilst editorial fashion films strengthen the role of entertainment. Independent fashion films expand the area of fashion and promote the diversification of fashion systems. Moreover, the results show that fashion films are not a secondary form of media that just expresses fashion; they provide a tool for the creation of new fashion content. New media fashion films promote the expansion of expressive spectra and boundaries, offering various multisensory experiences of fashion, and enhancing creativity and the aesthetic values of fashion.

Retained large glass fragments for over 40 years in the maxillofacial region

  • Na, Woong Gyu;Lim, Hyoseob;Koh, Sung Hoon;Jung, Sung Won
    • Archives of Craniofacial Surgery
    • /
    • v.19 no.1
    • /
    • pp.60-63
    • /
    • 2018
  • Foreign body (FB) impaction in the maxillofacial area could be caused by knives, glass fragments, and vegetative materials. We present the rare case of a 62-year-old man with a large glass FB in the left cheek retained for over 40 years. He had traffic accident over 40 years ago and glass fragments impacted on his left cheek. Glass fragments were retained around the zygomatic arch with dimpled scar and unclear serous discharge, but other facial motor or sensory dysfunction was not observed. We confirmed three glass fragments with radiologic examination including plain radiograph and computed tomographic image. Under general anesthesia, impacted glass fragments were removed through the direct incision on the dimpled scar and the additional incision on the left lateral canthal area. Remnant FBs were not seen on an intraoperative C-arm radiograph. After 2 days of irrigation for inflammation control, the dimpled wound was sutured. The wound was healed without major complication and the original dimpled scar was much improved.

Implementation of Oriental Medicine Baby Ocular Inspection Technique Using Face Image Analysis (얼굴 영상 분석을 이용한 한방 소아 망진 기법의 구현)

  • Cho Dong-Uk;Kim Bong-Hyun;Lee Se-Hwan
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2005.11a
    • /
    • pp.257-263
    • /
    • 2005
  • If baby disease not treats at early, case that cause problem in health hereafter much exists. Specially, because baby expresses own inexpedience by crying, parents or practitioner's is not apt to grasp. Therefore, In this paper, I wish to develop system for analyze if disease is in some region to analyze face and baby cry that organism signal appears intensive for baby disease diagnosis. In this paper, I wish to propose methodology that analyze organism signal that appear in face of whole baby organism signal analysis system. For this, I necessary region binary input baby face picture and to draw necessary five sensory organ and Myungdang region in baby disease diagnosis. Finally, the usefulness of this paper is verified by several experiments.

  • PDF