• Journal of Gastric Cancer
• /
• v.23 no.3
• /
• pp.400-409
• /
• 2023

Artificial intelligence (AI) has made significant progress in recent years, and many medical fields are attempting to introduce AI technology into clinical practice. Currently, much research is being conducted to evaluate that AI can be incorporated into surgical procedures to make them safer and more efficient, subsequently to obtain better outcomes for patients. In this paper, we review basic AI research regarding surgery and discuss the potential for implementing AI technology in gastric cancer surgery. At present, research and development is focused on AI technologies that assist the surgeon's understandings and judgment during surgery, such as anatomical navigation. AI systems are also being developed to recognize in which the surgical phase is ongoing. Such a surgical phase recognition systems is considered for effective storage of surgical videos and education, in the future, for use in systems to objectively evaluate the skill of surgeons. At this time, it is not considered practical to let AI make intraoperative decisions or move forceps automatically from an ethical standpoint, too. At present, AI research on surgery has various limitations, and it is desirable to develop practical systems that will truly benefit clinical practice in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.9-17
• /
• 2022

The state-of-the-art AI systems pose many ethical issues ranging from massive data collection to bias in algorithms. In response, this paper proposes a more ethic-friendly AI architecture by combining Federated Learning(FL) and Blockchain. We discuss the importance of each issues and provide requirements for an ethical AI system to show how our solutions can achieve more ethical paradigms. By committing to our design, adopters can perform AI services more ethically.

• Journal of Gastric Cancer
• /
• v.11 no.3
• /
• pp.155-161
• /
• 2011

Purpose: To determine the diagnostic utility of a frozen section biopsy in patients undergoing endoscopic submucosal dissection (ESD) for early gastric neoplasms with obscure margins even with chromoendoscopy using acetic acid and indigo carmine (AI chromoendoscopy). Materials and Methods: The lateral spread of early gastric neoplasms was unclear even following AI chromoendoscopy in 38 patients who underwent ESD between June 2007 and May 2011. Frozen section biopsies were obtained by agreement of the degree of lateral spread between two endoscopists. Thus, frozen section biopsies were obtained from 23 patients (FBx group) and not in the other 15 patients (AI group). Results: No significant differences were observed for size, histology, invasive depth, and location of lesions between the AI and FBx groups. No false positive or false negative results were observed in the frozen section diagnoses. Adenocarcinoma was revealed in three patients and tubular adenoma in one, thereby changing the delineation of lesion extent and achieving free lateral margins. The rates of free lateral resection margins and curative resection were significantly higher in the FBx group than those in the AI group. Conclusions: Frozen section biopsy can help endoscopists perform more safe and accurate ESD in patients with early gastric neoplasm.

• Journal of Korean Neurosurgical Society
• /
• v.61 no.1
• /
• pp.75-80
• /
• 2018

Objective : Among the various sacropelvic fixation methods, S2 alar-iliac (S2AI) screw fixation has several advantages compared to conventional iliac wing screw. However, the placement of S2AI screw still remains a challenge. The purpose of this study was to describe a novel technique of free hand S2AI screw insertion using a K-wire and cannulated screw, and to evaluate the accuracy of the technique. Methods : S2AI screw was inserted by free hand technique in sixteen consecutive patients without any fluoroscopic guidance. The gearshift was advanced to make a pilot hole passing through the sacroiliac joint and directing the anterior inferior iliac spine. A K-wire was placed through the pilot hole. After introducing a cannulated tapper along with the K-wire, a cannulated S2AI screw was installed over the K-wire. Results : Thirty-three S2AI screws were placed in sixteen consecutive patients. Thirty-two screws were cannulated screws, and one screw was a conventional non-cannulated screw. Thirty out of 32 (93.8%) cannulated screws were accurately positioned, whereas two cannulated screws and one non-cannulated screw violated lateral cortex of the ilium. Conclusion : The technique using K-wire and cannulated screw can provide accurate placement of free hand S2AI screw.

• Journal of Korean Neurosurgical Society
• /
• v.58 no.6
• /
• pp.578-581
• /
• 2015

A rigid spino-pelvic fixation to anchor long constructs is crucial to maintain the stability of long fusion in spinal deformity surgery. Besides obtaining immediate stability and proper biomechanical strength of constructs, the S2 alar-iliac (S2AI) screws have some more advantages. Four Korean fresh-frozen human cadavers were procured. Free hand S2AI screw placement is performed using anatomic landmarks. The starting point of the S2AI screw is located at the midpoint between the S1 and S2 foramen and 2 mm medial to the lateral sacral crest. Gearshift was advanced from the desired starting point toward the sacro-iliac joint directing approximately $20^{\circ}$ angulation caudally in sagittal plane and $30^{\circ}$ angulation horizontally in the coronal plane connecting the posterior superior iliac spine (PSIS). We made a S2AI screw trajectory through the cancellous channel using the gearshift. We measured caudal angle in the sagittal plane and horizontal angle in the coronal plane. A total of eight S2AI screws were inserted in four cadavers. All screws inserted into the iliac crest were evaluated by C-arm and naked eye examination by two spine surgeons. Among 8 S2AI screws, all screws were accurately placed (100%). The average caudal angle in the sagittal plane was $17.3{\pm}5.4^{\circ}$. The average horizontal angle in the coronal plane connecting the PSIS was $32.0{\pm}1.8^{\circ}$. The placement of S2AI screws using the free hand technique without any radiographic guidance appears to an acceptable method of insertion without more radiation or time consuming.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• Journal of the Korean Vacuum Society
• /
• v.6 no.S1
• /
• pp.16-22
• /
• 1997

ion beam processing of materials for medical application has gained increasing interest in the last decade and the implantation of nitrogen into TI-6AI-4V to improve corrosive-wear performance is currently used for processing of total hip and knee joints. Oxides and nitrides of Ti, Zr, Al, Cr were deposited on TI-6AI-4V substrates by DC magnetron sputtering dual ion beam sputtering and ion beam assisted deposition. The cytotoxicity of these films were investigated by MTT method and showed comparable to untreated TI-6AI-4V Plasm-sprayed hydroxyapatite(HAp) coatings showed excellent cytotoxicity regardless of heat treatment. intermediate layer coatings of nitrides and oxides increased the bond strength of HAp to substrate by intrdducing chemical bond at interface. Heat treatment of HAp coatings also improved the chemical bond at interfaces and increased the bond strength of untreated TI-6AI-4V to 16.4 kg/$\textrm{cm}^2$ but still lower than 33.1 kg./$\textrm{cm}^2$ of ir oxide as a imtermediate layer caoting.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.191-206
• /
• 2022

Recently, it is a de-facto approach to utilize a pre-trained language model(PLM) to achieve the state-of-the-art performance for various natural language tasks(called downstream tasks) such as sentiment analysis and question answering. However, similar to any other machine learning method, PLM tends to depend on the data distribution seen during the training phase and shows worse performance on the unseen (Out-of-Distribution) domain. Due to the aforementioned reason, there have been many efforts to develop domain-specified PLM for various fields such as medical and legal industries. In this paper, we discuss the training of a finance domain-specified PLM for the Korean language and its applications. Our finance domain-specified PLM, KB-BERT, is trained on a carefully curated financial corpus that includes domain-specific documents such as financial reports. We provide extensive performance evaluation results on three natural language tasks, topic classification, sentiment analysis, and question answering. Compared to the state-of-the-art Korean PLM models such as KoELECTRA and KLUE-RoBERTa, KB-BERT shows comparable performance on general datasets based on common corpora like Wikipedia and news articles. Moreover, KB-BERT outperforms compared models on finance domain datasets that require finance-specific knowledge to solve given problems.

• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.224-242
• /
• 2024

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.