Article
Radiology, Nuclear Medicine & Medical Imaging
Wilfrido Gomez-Flores, Maria Julia Gregorio-Calas, Wagner Coelho de Albuquerque Pereira
Summary: The development of breast ultrasound CAD systems requires a set of annotated images, and this publicly available BUS dataset greatly increases the number of annotated cases and includes standardized partitions for objective evaluation and comparison of CAD systems.
Article
Radiology, Nuclear Medicine & Medical Imaging
Qi Wei, Yu-Jing Yan, Ge-Ge Wu, Xi-Rong Ye, Fan Jiang, Jie Liu, Gang Wang, Yi Wang, Juan Song, Zhi-Ping Pan, Jin-Hua Hu, Chao-Ying Jin, Xiang Wang, Christoph F. Dietrich, Xin-Wu Cui
Summary: The study found that CAD software on ultrasound has high accuracy, sensitivity, and specificity in distinguishing benign and malignant breast masses, and can reduce unnecessary biopsies. After the application of CAD software, there was a significant decrease in unnecessary biopsy rate and an increase in malignant biopsy rate in BI-RADS category 4a.
EUROPEAN RADIOLOGY
(2022)
Article
Surgery
Ping He, Wen Chen, Ming-Yu Bai, Jun Li, Qing-Qing Wang, Li-Hong Fan, Jian Zheng, Chun-Tao Liu, Xiao-Rong Zhang, Xi-Rong Yuan, Peng-Jie Song, Li-Gang Cui
Summary: This study analyzed the diagnostic performance of a computer-aided diagnosis (CAD) system in differentiating breast lesions and reducing unnecessary biopsies in non-university hospitals in less-developed regions of China. The results showed that the CAD system can be an effective tool in improving accuracy and specificity, and reducing unnecessary biopsies.
WORLD JOURNAL OF SURGERY
(2023)
Article
Acoustics
Qi Wei, Shu-E Zeng, Li-Ping Wang, Yu-Jing Yan, Ting Wang, Jian-Wei Xu, Meng-Yi Zhang, Wen-Zhi Lv, Christoph F. Dietrich, Xin-Wu Cui
Summary: The study suggests that less experienced radiologists can benefit more from using the S-Detect software in improving diagnostic accuracy and reducing unnecessary biopsy rates, compared to experienced radiologists.
JOURNAL OF ULTRASOUND IN MEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ping He, Wen Chen, Ming-Yu Bai, Jun Li, Qing-Qing Wang, Li-Hong Fan, Jian Zheng, Chun-Tao Liu, Xiao-Rong Zhang, Xi-Rong Yuan, Peng-Jie Song, Li-Gang Cui
Summary: This study evaluated the usefulness of deep learning-based CAD software in breast ultrasound diagnosis and found that CAD significantly improved the diagnostic performance of radiologists, particularly in reducing the frequency of benign breast biopsies.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2023)
Article
Oncology
Ying Zhu, Weiwei Zhan, Xiaohong Jia, Juan Liu, Jianqiao Zhou
Summary: This study investigated factors that may lead to discordant results in radial and antiradial planes when applying a computer-aided diagnostic system for breast ultrasound. The results showed that BI-RADS category 4A-4B lesions and less invasive malignant lesions were more likely to have discordant CAD results.
CANCER MANAGEMENT AND RESEARCH
(2022)
Article
Chemistry, Multidisciplinary
Haojun Qin, Lei Zhang, Quan Guo
Summary: This study developed a computer-aided diagnostic system based on deep learning to classify benign and malignant tumors in breast ultrasound images from paper reports. The proposed method achieved an accuracy of 89.31%, recall rate of 88.65%, specificity of 89.57%, F1 score of 89.42%, and AUC of 94.53% when the input images contained noise. This approach is more suitable for practical applications and can assist patients in obtaining prompt and accurate classification results of ultrasound reports.
APPLIED SCIENCES-BASEL
(2023)
Review
Biology
Zicheng Guo, Jiping Xie, Yi Wan, Min Zhang, Liang Qiao, Jiaxuan Yu, Sijing Chen, Bingxin Li, Yongqiang Yao
Summary: Breast cancer, a common cancer among females worldwide, can be diagnosed through computer-aided diagnosis (CAD) systems using various imaging modalities. CAD systems have the potential to enhance traditional histopathological image analysis and are in high demand for early detection and diagnosis.
OPEN LIFE SCIENCES
(2022)
Article
Biology
Nonhlanhla Chambara, Shirley Yuk Wah Liu, Xina Lo, Michael Ying
Summary: The study compared the performance of computer-assisted diagnosis and subjective assessments in thyroid nodule diagnosis, finding that subjective assessments performed better than CAD. Future larger studies are needed to validate these findings.
Article
Automation & Control Systems
Venkata Sunil Srikanth, S. Krithiga
Summary: This paper proposes an ensemble pre-trained DNN-based breast tumor diagnosis method using global and local ROI structures. Experimental results show that using both global and local ROI structures significantly improves diagnostic accuracy and reduces computational complexity.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2023)
Article
Biotechnology & Applied Microbiology
Ahmed M. Zaalouk, Gamal A. Ebrahim, Hoda K. Mohamed, Hoda Mamdouh Hassan, Mohamed M. A. Zaalouk
Summary: In this paper, a computer-aided diagnosis system based on deep learning is developed to assist pathologists in diagnosing breast cancer. Multiple pre-trained convolutional neural network models are analyzed and tested, and a new approach for transfer learning is introduced. The experimental results show that the Xception model performs the best among the tested models.
BIOENGINEERING-BASEL
(2022)
Article
Engineering, Biomedical
Zahra Assari, Ali Mahloojifar, Nasrin Ahmadinejad
Summary: This paper proposes a novel bimodal deep residual learning model for the diagnosis of breast cancer. The model can effectively integrate information from different modalities and achieves recognition results superior to other state-of-the-art models.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Review
Oncology
Xin Yu Liew, Nazia Hameed, Jeremie Clos
Summary: Early detection and timely treatment of breast cancer can reduce the risk of death, with histopathology images and CAD systems being key technologies. Machine learning methods are increasingly applied in diagnosing breast cancer, helping to improve accuracy.
Article
Radiology, Nuclear Medicine & Medical Imaging
Luca Nicosia, Francesca Addante, Anna Carla Bozzini, Antuono Latronico, Marta Montesano, Lorenza Meneghetti, Francesca Tettamanzi, Samuele Frassoni, Vincenzo Bagnardi, Rossella De Santis, Filippo Pesapane, Cristiana Iuliana Fodor, Mauro Giuseppe Mastropasqua, Enrico Cassano
Summary: The study evaluated if US CAD system can improve diagnostic performance of inexperienced radiologists. Results showed significant advantage of CAD over inexperienced group, while lower performance compared to experienced group. There was good agreement in lesion evaluation among expert and non-expert radiologists.
Article
Computer Science, Artificial Intelligence
Shi Qiu, Yi Jin, Songhe Feng, Tao Zhou, Yidong Li
Summary: Dwarfism refers to the condition where children of the same gender and age are lower than two standard deviations of normal height in the same environment. A computer-aided diagnosis model based on brain image data and clinical features is established for the first time, along with a dwarfism prediction algorithm using multimodal pyradiomics.
INFORMATION FUSION
(2022)
Article
Surgery
Kicheol Yoon, Sung-Min Cho, Kwang Gi Kim, Young Woo Cheon
Summary: This paper proposes a remote monitoring technology to observe a patient's condition in real time, addressing the inconvenience of daily observation required in free flap surgery. The camera system captures images of the surgical site every 2 seconds and transmits them to the attending physician or nurse via Wi-Fi. Results show that high-quality images are obtained without any storage errors during the shooting process.
SURGICAL INNOVATION
(2023)
Article
Multidisciplinary Sciences
Jae Won Seo, Suyoung Park, Young Jae Kim, Jung Han Hwang, Sung Hyun Yu, Jeong Ho Kim, Kwang Gi Kim
Summary: Early diagnosis of deep venous thrombosis is crucial for reducing complications. This study evaluated the performance of an artificial intelligence algorithm in detecting iliofemoral deep venous thrombosis on computed tomography angiography. The results demonstrated the effectiveness of the clinical approach in improving the reporting efficiency of critical cases.
SCIENTIFIC REPORTS
(2023)
Article
Multidisciplinary Sciences
So Hyun Park, Young Jae Kim, Kwang Gi Kim, Jun-Won Chung, Hyun Cheol Kim, In Young Choi, Myung-Won You, Gi Pyo Lee, Jung Han Hwang
Summary: This study aimed to develop a CNN using the EfficientNet algorithm for automated classification of acute appendicitis, acute diverticulitis, and normal appendix on CT images, and evaluate its diagnostic performance. The results showed that the RGB serial image method had slightly higher sensitivity, accuracy, and specificity for classifying normal appendix and acute diverticulitis compared to the single image method. Additionally, the mean areas under the ROC curve were significantly higher with the RGB serial image method for all three conditions. Therefore, the model accurately distinguished these conditions on CT images, particularly when using the RGB serial image method.
Article
Surgery
Min Chan Kim, Kicheol Yoon, Kwang Gi Kim
Summary: Testing the fluorescence emission of the indocyanine green (ICG) fluorescence contrast agent is crucial for validating system performance. This study proposes a method for manufacturing an ICG phantom, which utilizes ICG and silicone rubber to create a phantom with high fluorescence expression.
SURGICAL INNOVATION
(2023)
Article
Dentistry, Oral Surgery & Medicine
Seok Oh, Young Jae Kim, Jeseong Kim, Joon Hyeok Jung, Hun Jun Lim, Bong Chul Kim, Kwang Gi Kim
Summary: This study investigated the possibility of predicting the osseointegration of dental implants using deep learning based on plain radiography. The results showed that deep learning models can predict the degree of osseointegration to some extent, which is expected to complement the currently widely used evaluation methods.
Article
Medicine, General & Internal
Myoung Seok Lee, Young Jae Kim, Min Hoan Moon, Kwang Gi Kim, Jeong Hwan Park, Chang Kyu Sung, Hyeon Jeong, Hwancheol Son
Summary: This study explores the performance of texture-based machine learning and image-based deep learning for enhancing the detection of transitional-zone prostate cancer in the background of benign prostatic hyperplasia. The results show that texture-based machine learning algorithms have high specificity, while image-based deep learning algorithms have high sensitivity.
Article
Chemistry, Analytical
Kicheol Yoon, Sangyun Lee, Tae-Hyeon Lee, Kwang Gi Kim
Summary: After surgery for ovarian cancer or colorectal cancer, residual tumors are left. A practical way to treat residual tumors is to destroy them with heat by injecting high-temperature drugs into the abdominal cavity. This study compares and assesses the temperature needed to maintain the heat for treatment and transmits a command signal to the heat exchanger through a look-up table (LUT).
Article
Surgery
Seung Yeob Ryu, Sangyun Lee, Kicheol Yoon, Jeong-Heum Baek, Kwang Gi Kim
Summary: This paper proposes a small-sized hologram system for 3D imaging of lesions in a clinical environment. The system utilizes a beam prism and a full reflection mirror to reduce the beam divergence distance and achieve accurate imaging. Experimental results show that the designed hologram system successfully images lesions such as lung, liver, and colon in a clinical environment.
SURGICAL INNOVATION
(2023)
Article
Surgery
Hyeon-Woong Seo, Kicheol Yoon, Sangyun Lee, Won-Suk Lee, Kwang Gi Kim
Summary: This study proposes a miniature observation robot design that offers adjustable working distance and rotational radius, along with zoom-in/zoom-out functionality. Experimental results demonstrate that the robot has good performance and can be used for rapid and accurate detection of fresh lymph nodes and diagnosis of minute lymph nodes. The design is cost-effective and highly adjustable.
SURGICAL INNOVATION
(2023)
Article
Surgery
Kicheol Yoon, Sangyun Lee, Kwang Gi Kim
Summary: This study successfully solves the problem of wire length mismatch in the wire-driven method used in surgical robots by applying the looper-tension technology. By inserting stands and adding looper-tension to adjust the wire length, the error in wire pull and push operation is reduced, achieving accurate operation.
SURGICAL INNOVATION
(2023)
Article
Medicine, General & Internal
Minki Ju, Kicheol Yoon, Sangyun Lee, Kwang Gi Kim
Summary: To remove tumors with the same blood vessel color, observation is performed using a surgical microscope through fluorescent staining. This study proposes to increase the beam width and power of LED by utilizing the quasi-symmetrical beam irradiation method. The result shows a significant enhancement in fluorescence emission probability and approximately four times increase in mirror light power.
Article
Radiology, Nuclear Medicine & Medical Imaging
Su Min Ha, Ann Yi, Dahae Yim, Myoung-jin Jang, Bo Ra Kwon, Sung Ui Shin, Eun Jae Lee, Soo Hyun Lee, Woo Kyung Moon, Jung Min Chang
Summary: This study compared the outcomes of DBT screening combined with US and DM screening combined with US in women with dense breasts. The results showed that the cancer detection rate was comparable between the DBT and DM cohorts, but the DBT cohort had a higher false-positive rate.
KOREAN JOURNAL OF RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yong-Tae Kim, Tae Seok Jeong, Young Jae Kim, Woo Seok Kim, Kwang Gi Kim, Gi Taek Yee
Summary: Radiographic examination is essential for diagnosing spinal disorders. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Medical Informatics
Juhui Lee, Soyoon Kwon, Jong Hoon Kim, Kwang Gi Kim
Summary: This paper proposes a system that can automatically generate pill image data from various angles. The system consists of three components: structure, controller, and graphical user interface. The system is manufactured using a 3D printer for lightweight and easy manufacturing. The workflow of the pill filming system generates 300 pill images with a total collection time of 21 minutes and 25 seconds. The high-quality, large quantity of data generated by this system can contribute to various studies using pill images.
HEALTHCARE INFORMATICS RESEARCH
(2023)
Article
Oncology
Heera Yoen, Jung Min Chang
Summary: Despite recent advances in AI software for mammography screening, this study found that AI software-assisted mammography could provide additional value in identifying breast cancers detected through supplemental screening ultrasound, especially for cases with indiscernible abnormalities and interpretive errors.
JOURNAL OF BREAST CANCER
(2023)