• Journal of the Korean Society of Radiology
• /
• v.83 no.5
• /
• pp.1090-1103
• /
• 2022

Purpose To evaluate the diagnostic performance of digital breast tomosynthesis (DBT) with the two-dimensional synthesized mammogram (2DSM), compared to full-field digital mammography (FFDM), for suspicious microcalcifications in the breast ahead of stereotactic biopsy and to assess the diagnostic image visibility of the images. Materials and Methods This retrospective study involved 189 patients with microcalcifications, which were histopathologically verified by stereotactic breast biopsy, who underwent DBT with 2DSM and FFDM between January 8, 2015, and January 20, 2020. Two radiologists assessed all cases of microcalcifications based on Breast Imaging Reporting and Data System (BI-RADS) independently. They were blinded to the histopathologic outcome and additionally evaluated lesion visibility using a fivepoint scoring scale. Results Overall, the inter-observer agreement was excellent (0.9559). Under the setting of category 4A as negative due to the low possibility of malignancy and to avoid the dilution of malignancy criteria in our study, McNemar tests confirmed no significant difference between the performances of the two modalities in detecting microcalcifications with a high potential for malignancy (4B, 4C, or 5; p = 0.1573); however, the tests showed a significant difference between their performances in detecting microcalcifications with a high potential for benignancy (4A; p = 0.0009). DBT with 2DSM demonstrated superior visibility and diagnostic performance than FFDM in dense breasts. Conclusion DBT with 2DSM is superior to FFDM in terms of total diagnostic accuracy and lesion visibility for benign microcalcifications in dense breasts. This study suggests a promising role for DBT with 2DSM as an accommodating tool for stereotactic biopsy in female with dense breasts and suspicious breast microcalcifications.

• Journal of the Korean Society of Radiology
• /
• v.82 no.4
• /
• pp.889-902
• /
• 2021

Purpose To assess the diagnostic performance of contrast-enhanced ultrasound (CEUS) for additional MR-detected enhancing lesions and to determine whether or not kinetic pattern results comparable to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast can be obtained using the quantitative analysis of CEUS. Materials and Methods In this single-center prospective study, a total of 71 additional MR-detected breast lesions were included. CEUS examination was performed, and lesions were categorized according to the Breast Imaging-Reporting and Data System (BI-RADS). The sensitivity, specificity, and diagnostic accuracy of CEUS were calculated by comparing the BI-RADS category to the final pathology results. The degree of agreement between CEUS and DCE-MRI kinetic patterns was evaluated using weighted kappa. Results On CEUS, 46 lesions were assigned as BI-RADS category 4B, 4C, or 5, while 25 lesions category 3 or 4A. The diagnostic performance of CEUS for enhancing lesions on DCE-MRI was excellent, with 84.9% sensitivity, 94.4% specificity, and 97.8% positive predictive value. A total of 57/71 (80%) lesions had correlating kinetic patterns and showed good agreement (weighted kappa = 0.66) between CEUS and DCE-MRI. Benign lesions showed excellent agreement (weighted kappa = 0.84), and invasive ductal carcinoma (IDC) showed good agreement (weighted kappa = 0.69). Conclusion The diagnostic performance of CEUS for additional MR-detected breast lesions was excellent. Accurate kinetic pattern assessment, fairly comparable to DCE-MRI, can be obtained for benign and IDC lesions using CEUS.

• Journal of the Daesoon Academy of Sciences
• /
• v.48
• /
• pp.41-155
• /
• 2024

Among the records that attest to the period from July to August of 1863, when Suwun was believed to have transmitted the orthodox lineage to Haewol, the oldest documents are The Collection of Suwun's Literary Works (水雲文集), The Collection of Great Master Lord's Literary Works (大先生主文集), and The Records of Dao Origin of Master Choe's Literary Collection (崔先生文集道源記書, hereafter referred to as The Records of Dao Origin). The records regarding Suwun in these three documents are considered to have originated from the same context. The variances embedded in the three documents have led to arguments about which documents accurately reflect the fact of orthodox lineage transmission. Additionally, these variances highlight the necessity of a review regarding the characteristics of early Eastern Learning, such as its faith and organizational systems. Accordingly, by thoroughly examining these three documents, it is possible to elucidate the chronological order, establishment-date, accuracy, descriptive direction, and characteristics of the faith system of early Eastern Learning as these are reflected in each document. If successful, this examination would provide a clearer description of the developmental process of Eastern Learning from 1860 to 1880, facilitating a more in-depth analysis of the significance embedded in various forms of discourse on the movement's orthodox lineage transmission. In comparing the three documents and contrasting them with related sources, the results of the textual examination assert that the documents within the lineage of The Collection of Suwun's Literary Works, given they lack a clear record of the event regarding Haewol's orthodox lineage succession, may be the first draft of The Collection of Great Master Lord's Literary Works and The Records of Dao Origin, as these texts distinctly include that record. This reflects that Haewol's succession was not precisely recognized within and outside of the Eastern Learning order until the time when The Collection of Great Master Lord's Literary Works and The Records of Dao Origin were published. This is further attested to by the fact that during the late 1870s, when various Yeonwon (fountainhead) factions of Eastern Learning began to converge around Haewol, and his Yeonwon became the largest organization within Eastern Learning. At that point, the order's doctrine was reinterpreted, and its organization was reestablished. In this regard, it is necessary to view Eastern Learning after Suwun-especially the orthodox lineage transmission to Haewol-from a perspective that considers it more as competing forms of discourse than as a historical fact. This view enables a new perspective on Haewol's Eastern Learning, which forms a distinct layer from Suwun's, shedding light on the relationship between Haewol and the new religious movements in modern-day Korea.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.4
• /
• pp.373-384
• /
• 2023

This study aims to confirm the average chronologic age according to the developmental stages of the mandibular canine (L3), first and second premolars (L4, L5), and second and third molars (L7, L8) in children and adolescents, and to confirm the developmental stage of L3, L4, L5, and L7, which can estimate the development of L8. A total of 1,956 digital panoramic radiographs of healthy individuals aged between 6 and 15 years who visited Seoul National University Dental Hospital from January 2019 to December 2020 were selected. The developmental stages of L3, L4, L5, L7, and L8 on both sides were evaluated using the dental maturity scoring system proposed by Demirjian and Goldstein. The average age at which the follicle of L8 was first observed was around 9.34 ± 1.35 years and varied from 6 to 12 years. The possibility of agenesis of L8 was high when no traces of L8 were observed after the following stages: L3, L4, and L5 at the developmental stage F and L7 at the developmental stage E; the age was about 10 years. In estimating the development of L8, when only one tooth was considered, estimation accuracy with L5 was the highest, and there was no significant difference when all four teeth were included. This study showed the age distribution according to the developmental stages of L3, L4, L5, L7, and L8 in children and adolescents and confirmed the developmental stages of L3, L4, L5, and L7, which can be used to estimate the development of L8.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.99-107
• /
• 2024

Along with economic growth and industrial development, there is an increasing demand for various electronic components and device production of semiconductor, SMT component, and electrical battery products. However, these products may contain foreign substances coming from manufacturing process such as iron, aluminum, plastic and so on, which could lead to serious problems or malfunctioning of the product, and fire on the electric vehicle. To solve these problems, it is necessary to determine whether there are foreign materials inside the product, and may tests have been done by means of non-destructive testing methodology such as ultrasound ot X-ray. Nevertheless, there are technical challenges and limitation in acquiring X-ray images and determining the presence of foreign materials. In particular Small-sized or low-density foreign materials may not be visible even when X-ray equipment is used, and noise can also make it difficult to detect foreign objects. Moreover, in order to meet the manufacturing speed requirement, the x-ray acquisition time should be reduced, which can result in the very low signal- to-noise ratio(SNR) lowering the foreign material detection accuracy. Therefore, in this paper, we propose a five-step approach to overcome the limitations of low resolution, which make it challenging to detect foreign substances. Firstly, global contrast of X-ray images are increased through histogram stretching methodology. Second, to strengthen the high frequency signal and local contrast, we applied local contrast enhancement technique. Third, to improve the edge clearness, Unsharp masking is applied to enhance edges, making objects more visible. Forth, the super-resolution method of the Residual Dense Block (RDB) is used for noise reduction and image enhancement. Last, the Yolov5 algorithm is employed to train and detect foreign objects after learning. Using the proposed method in this study, experimental results show an improvement of more than 10% in performance metrics such as precision compared to low-density images.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.40 no.2
• /
• pp.72-81
• /
• 2024

Purpose: This study aimed to assess the marginal and internal fit of 3-unit monolithic zirconia fixed partial dentures (FPDs) fabricated via computer-aided design and computer-aided manufacturing (CAD/CAM) from solid working casts and removable die system. Materials and Methods: The tooth preparation protocol for a zirconia crown was executed on the mandibular right first premolar and mandibular right first molar, with the creation of a reference cast featuring an absent mandibular right second premolar. The reference cast was duplicated using polyvinyl siloxane impression, from which 20 working casts were fabricated following typical dental laboratory procedures. For comparative analysis, 10 FPDs were produced from a removable die system (RD group) and the remaining 10 FPDs from the solid working casts (S group). The casts were digitized using a dental desktop scanner to establish virtual casts and design the FPDs using CAD. The definitive 3-unit monolithic zirconia FPDs were fabricated via a CAM milling process. The seated FPDs on the reference cast underwent digital evaluation for marginal and internal fit. The Mann-Whitney U test was applied for statistical comparison between the two groups (α = 0.05). Results: The RD group showed significantly higher discrepancies in fit for both premolars and molars compared to the S group (P < 0.05), particularly in terms of marginal and occlusal gaps. Color mapping also highlighted more significant deviations in the RD group, especially in the marginal and occlusal regions. Conclusion: The study found that the discrepancies in marginal and occlusal fits of 3-unit monolithic zirconia FPDs were primarily associated with those fabricated using the removable die system. This indicates the significant impact of the fabrication method on the accuracy of FPDs.

• The Korean Society of Law and Medicine
• /
• v.24 no.4
• /
• pp.67-101
• /
• 2023

The utilization of generative AI in the medical field is also being rapidly researched. Access to vast data sets reduces the time and energy spent in selecting information. However, as the effort put into content creation decreases, there is a greater likelihood of associated issues arising. For example, with generative AI, users must discern the accuracy of results themselves, as these AIs learn from data within a set period and generate outcomes. While the answers may appear plausible, their sources are often unclear, making it challenging to determine their veracity. Additionally, the possibility of presenting results from a biased or distorted perspective cannot be discounted at present on ethical grounds. Despite these concerns, the field of generative AI is continually advancing, with an increasing number of users leveraging it in various sectors, including biomedical and life sciences. This raises important legal considerations regarding who bears responsibility and to what extent for any damages caused by these high-performance AI algorithms. A general overview of issues with generative AI includes those discussed above, but another perspective arises from its fundamental nature as a large-scale language model ('LLM') AI. There is a civil law concern regarding "the memorization of training data within artificial neural networks and its subsequent reproduction". Medical data, by nature, often reflects personal characteristics of patients, potentially leading to issues such as the regeneration of personal information. The extensive application of generative AI in scenarios beyond traditional AI brings forth the possibility of legal challenges that cannot be ignored. Upon examining the technical characteristics of generative AI and focusing on legal issues, especially concerning the protection of personal information, it's evident that current laws regarding personal information protection, particularly in the context of health and medical data utilization, are inadequate. These laws provide processes for anonymizing and de-identification, specific personal information but fall short when generative AI is applied as software in medical devices. To address the functionalities of generative AI in clinical software, a reevaluation and adjustment of existing laws for the protection of personal information are imperative.

• Asia pacific journal of information systems
• /
• v.18 no.3
• /
• pp.123-145
• /
• 2008

Recently, as the information communication technology develops, the discussion regarding the ubiquitous environment is occurring in diverse perspectives. Ubiquitous environment is an environment that could transfer data through networks regardless of the physical space, virtual space, time or location. In order to realize the ubiquitous environment, the Pervasive Sensing technology that enables the recognition of users' data without the border between physical and virtual space is required. In addition, the latest and diversified technologies such as Context-Awareness technology are necessary to construct the context around the user by sharing the data accessed through the Pervasive Sensing technology and linkage technology that is to prevent information loss through the wired, wireless networking and database. Especially, Pervasive Sensing technology is taken as an essential technology that enables user oriented services by recognizing the needs of the users even before the users inquire. There are lots of characteristics of ubiquitous environment through the technologies mentioned above such as ubiquity, abundance of data, mutuality, high information density, individualization and customization. Among them, information density directs the accessible amount and quality of the information and it is stored in bulk with ensured quality through Pervasive Sensing technology. Using this, in the companies, the personalized contents(or information) providing became possible for a target customer. Most of all, there are an increasing number of researches with respect to recommender systems that provide what customers need even when the customers do not explicitly ask something for their needs. Recommender systems are well renowned for its affirmative effect that enlarges the selling opportunities and reduces the searching cost of customers since it finds and provides information according to the customers' traits and preference in advance, in a commerce environment. Recommender systems have proved its usability through several methodologies and experiments conducted upon many different fields from the mid-1990s. Most of the researches related with the recommender systems until now take the products or information of internet or mobile context as its object, but there is not enough research concerned with recommending adequate store to customers in a ubiquitous environment. It is possible to track customers' behaviors in a ubiquitous environment, the same way it is implemented in an online market space even when customers are purchasing in an offline marketplace. Unlike existing internet space, in ubiquitous environment, the interest toward the stores is increasing that provides information according to the traffic line of the customers. In other words, the same product can be purchased in several different stores and the preferred store can be different from the customers by personal preference such as traffic line between stores, location, atmosphere, quality, and price. Krulwich(1997) has developed Lifestyle Finder which recommends a product and a store by using the demographical information and purchasing information generated in the internet commerce. Also, Fano(1998) has created a Shopper's Eye which is an information proving system. The information regarding the closest store from the customers' present location is shown when the customer has sent a to-buy list, Sadeh(2003) developed MyCampus that recommends appropriate information and a store in accordance with the schedule saved in a customers' mobile. Moreover, Keegan and O'Hare(2004) came up with EasiShop that provides the suitable tore information including price, after service, and accessibility after analyzing the to-buy list and the current location of customers. However, Krulwich(1997) does not indicate the characteristics of physical space based on the online commerce context and Keegan and O'Hare(2004) only provides information about store related to a product, while Fano(1998) does not fully consider the relationship between the preference toward the stores and the store itself. The most recent research by Sedah(2003), experimented on campus by suggesting recommender systems that reflect situation and preference information besides the characteristics of the physical space. Yet, there is a potential problem since the researches are based on location and preference information of customers which is connected to the invasion of privacy. The primary beginning point of controversy is an invasion of privacy and individual information in a ubiquitous environment according to researches conducted by Al-Muhtadi(2002), Beresford and Stajano(2003), and Ren(2006). Additionally, individuals want to be left anonymous to protect their own personal information, mentioned in Srivastava(2000). Therefore, in this paper, we suggest a methodology to recommend stores in U-market on the basis of ubiquitous environment not using personal information in order to protect individual information and privacy. The main idea behind our suggested methodology is based on Feature Matrices model (FM model, Shahabi and Banaei-Kashani, 2003) that uses clusters of customers' similar transaction data, which is similar to the Collaborative Filtering. However unlike Collaborative Filtering, this methodology overcomes the problems of personal information and privacy since it is not aware of the customer, exactly who they are, The methodology is compared with single trait model(vector model) such as visitor logs, while looking at the actual improvements of the recommendation when the context information is used. It is not easy to find real U-market data, so we experimented with factual data from a real department store with context information. The recommendation procedure of U-market proposed in this paper is divided into four major phases. First phase is collecting and preprocessing data for analysis of shopping patterns of customers. The traits of shopping patterns are expressed as feature matrices of N dimension. On second phase, the similar shopping patterns are grouped into clusters and the representative pattern of each cluster is derived. The distance between shopping patterns is calculated by Projected Pure Euclidean Distance (Shahabi and Banaei-Kashani, 2003). Third phase finds a representative pattern that is similar to a target customer, and at the same time, the shopping information of the customer is traced and saved dynamically. Fourth, the next store is recommended based on the physical distance between stores of representative patterns and the present location of target customer. In this research, we have evaluated the accuracy of recommendation method based on a factual data derived from a department store. There are technological difficulties of tracking on a real-time basis so we extracted purchasing related information and we added on context information on each transaction. As a result, recommendation based on FM model that applies purchasing and context information is more stable and accurate compared to that of vector model. Additionally, we could find more precise recommendation result as more shopping information is accumulated. Realistically, because of the limitation of ubiquitous environment realization, we were not able to reflect on all different kinds of context but more explicit analysis is expected to be attainable in the future after practical system is embodied.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.1
• /
• pp.7-16
• /
• 2016

Purpose : This study aimed to compare and evaluate between the efficiency of two respective devices, 3D-bolus and step-bolus when the devices were used for the treatment of patients whose chest walls were required to undergo the electron beam therapy after the surgical procedure of modified radical mastectomy, MRM. Materials and Methods : The treatment plan of reverse hockey stick method, using the photon beam and electron beam, had been set for six breast cancer patients and these 6 breast cancer patients were selected to be the subjects for this study. The prescribed dose of electron beam for anterior chest wall was set to be 180 cGy per treatment and both the 3D-bolus, produced using 3D printer(CubeX, 3D systems, USA) and the self-made conventional step-bolus were used respectively. The surface dose under 3D-bolus and step-bolus was measured at 5 measurement spots of iso-center, lateral, medial, superior and inferior point, using GAFCHROMIC EBT3 film (International specialty products, USA) and the measured value of dose at 5 spots was compared and analyzed. Also the respective treatment plan was devised, considering the adoption of 3D-bolus and stepbolus and the separate treatment results were compared to each other. Results : The average surface dose was 179.17 cGy when the device of 3D-bolus was adopted and 172.02 cGy when step-bolus was adopted. The average error rate against the prescribed dose of 180 cGy was -(minus) 0.47% when the device of 3D-bolus was adopted and it was -(minus) 4.43% when step-bolus was adopted. It was turned out that the maximum error rate at the point of iso-center was 2.69%, in case of 3D-bolus adoption and it was 5,54% in case of step-bolus adoption. The maximum discrepancy in terms of treatment accuracy was revealed to be about 6% when step-bolus was adopted and to be about 3% when 3D-bolus was adopted. The difference in average target dose on chest wall between 3D-bolus treatment plan and step-bolus treatment plan was shown to be insignificant as the difference was only 0.3%. However, to mention the average prescribed dose for the part of lung and heart, that of 3D-bolus was decreased by 11% for lung and by 8% for heart, compared to that of step-bolus. Conclusion : It was confirmed through this research that the dose uniformity could be improved better through the device of 3D-bolus than through the device of step-bolus, as the device of 3D-bolus, produced in consideration of the contact condition of skin surface of chest wall, could be attached to patients' skin more nicely and the thickness of chest wall can be guaranteed more accurately by the device of 3D-bolus. It is considered that 3D-bolus device can be highly appreciated clinically because 3D-bolus reduces the dose on the adjacent organs and make the normal tissues protected, while that gives no reduction of dose on chest wall.