Article
Engineering, Biomedical
Tarun Agrawal, Prakash Choudhary
Summary: This study explores the application of a parameter-efficient attention based lightweight convolutional neural network (ALCNN) for pneumothorax detection in CXR images. Compared to other architectures, ALCNN achieves comparable results with 10x fewer parameters. Results show that transfer learning has minimal impact on the performance of pneumothorax detection in CXR.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Biochemical Research Methods
Yaqi Wang, Lingling Sun, Qun Jin
Summary: This paper proposes an image classification algorithm based on deep convolutional neural network for high-resolution medical image analysis of pneumothorax X-rays. The experimental results demonstrate that the method effectively increases the correct diagnosis rate of pneumothorax, with AUC values of 0.9844 and 0.9906 on test data sets. Additionally, a large number of pleural samples were visualized and analyzed based on the experimental results and algorithm's deep learning characteristics, verifying the validity of feature extraction for the network.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Chemistry, Analytical
Muhammad Tahir Naseem, Tajmal Hussain, Chan-Su Lee, Muhammad Adnan Khan
Summary: This study proposes a method for automatic detection of COVID-19 and other chest-related diseases using digital chest X-ray images. By applying transfer learning algorithms and data augmentation for training, the model achieved high accuracy in multiple classification tasks.
Article
Multidisciplinary Sciences
Yongil Cho, Jong Soo Kim, Tae Ho Lim, Inhye Lee, Jongbong Choi
Summary: This study evaluated the diagnostic performance of using fully-connected small artificial neural networks and the Kim-Monte Carlo algorithm to detect pneumothorax in chest X-rays. Results showed that this approach accurately detected pneumothorax locations, significantly reducing time delays in diagnosing urgent diseases. Additionally, the fully-connected small ANN outperformed the convolutional neural network in this task.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Information Systems
Shashwat Sanket, M. Vergin Raja Sarobin, L. Jani Anbarasi, Jayraj Thakor, Urmila Singh, Sathiya Narayanan
Summary: This paper introduces a Convolutional Neural Network (CNN) based model, CovCNN, for COVID-19 detection using chest X-ray images, aiming to expedite the diagnostic process under high workload conditions. By incorporating multiple folds of CNN and depth wise convolution, the model efficiently extracts diversified features from X-rays, achieving a classification accuracy of 98.4%.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Mathematics
Mohammad Khishe, Fabio Caraffini, Stefan Kuhn
Summary: This study introduces a framework that automatically designs classifiers for the early detection of COVID-19 from chest X-ray images, optimising the model iteratively to achieve high accuracy while minimising redundant layers. The proposed implementation achieves accuracy up to 99.11%, making it particularly suitable for early detection of COVID-19.
Article
Chemistry, Multidisciplinary
Atsushi Teramoto, Tomoyuki Shibata, Hyuga Yamada, Yoshiki Hirooka, Kuniaki Saito, Hiroshi Fujita
Summary: By utilizing the novel U-Net R-CNN object detection model along with DenseNet169 convolutional neural network for box classification, the efficiency and accuracy of automated detection of early gastric cancer from endoscopic images can be improved.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Himadri Mukherjee, Subhankar Ghosh, Ankita Dhar, Sk Md Obaidullah, K. C. Santosh, Kaushik Roy
Summary: A lightweight Convolutional Neural Network (CNN) was proposed for automatically detecting COVID-19 positive cases in Chest X-rays with high accuracy. The model was also validated for different types of pneumonia cases and showed promising results in experimental tests.
COGNITIVE COMPUTATION
(2021)
Article
Oncology
Sandhya Sharma, Sheifali Gupta, Deepali Gupta, Junaid Rashid, Sapna Juneja, Jungeun Kim, Mahmoud M. Elarabawy
Summary: Recent advancements in deep learning have shown promising results for the analysis of medical images. This study implements a Convolutional Neural Network (CNN) model to recognize chest X-ray images for pneumonia detection. The model is trained and validated using a publicly available dataset, achieving a maximum recognition accuracy of 98%. The results are compared with those obtained by other researchers in the field of biomedical image recognition.
FRONTIERS IN ONCOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Aravind Krishnaswamy Rangarajan, Hari Krishnan Ramachandran
Summary: The outbreak of COVID-19 has had catastrophic effects on both the public health system and the global economy. Utilizing Artificial Intelligence (AI) with chest X-ray images for rapid diagnosis of COVID-19 cases can improve accuracy and contact tracing. Training and testing five pre-trained CNN models with publicly available chest X-ray image datasets revealed that VGG16 and Xception, trained with synthetic GAN images, performed better compared to models trained with augmented images.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Yunpeng Wang, Kang Wang, Xueqing Peng, Lili Shi, Jing Sun, Shibao Zheng, Fei Shan, Weiya Shi, Lei Liu
Summary: This paper presents a new learning framework DeepSDM that effectively perceives the boundary of pneumothorax and outperforms other methods in pneumothorax segmentation.
Article
Computer Science, Interdisciplinary Applications
Felix Busch, Lina Xu, Dmitry Sushko, Matthias Weidlich, Daniel Truhn, Gustav Mueller-Franzes, Maurice M. Heimer, Stefan M. Niehues, Marcus R. Makowski, Markus Hinsche, Janis L. Vahldiek, Hugo J. W. L. Aerts, Lisa C. Adams, Keno K. Bressem
Summary: This study aims to develop an efficient convolutional neural network for automatic anatomy segmentation of bedside chest radiographs (CXRs). By using a human-in-the-loop segmentation workflow with an active learning approach, the performance of artificial intelligence in diagnosing cardiothoracic disease and invasive therapy devices is improved. The final model achieved comparable performance to state-of-the-art approaches.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Medicine, General & Internal
Cheng-Yi Kao, Chiao-Yun Lin, Cheng-Chen Chao, Han-Sheng Huang, Hsing-Yu Lee, Chia-Ming Chang, Kang Sung, Ting-Rong Chen, Po-Chang Chiang, Li-Ting Huang, Bow Wang, Yi-Sheng Liu, Jung-Hsien Chiang, Chien-Kuo Wang, Yi-Shan Tsai
Summary: The study successfully designed a deep learning model for pneumothorax detection in chest radiographs and set up an ARAS with improved efficiency and overall diagnostic performance.
Article
Computer Science, Theory & Methods
Helena Liz, Javier Huertas-Tato, Manuel Sanchez-Montanes, Javier Del Ser, David Camacho
Summary: Convolutional neural networks (CNNs) have dominated computer vision field due to their feature extraction ability and excellent performance in classification problems. However, they are considered black-box algorithms and lack interpretability. This paper proposes a deep learning methodology for imbalanced, multilabel chest X-ray datasets, establishing a baseline for the underutilized PadChest dataset and introducing a new explainable AI technique based on heatmaps.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Khaled Almezhghwi, Sertan Serte, Fadi Al-Turjman
Summary: The study proposes two artificial intelligence approaches utilizing deep learning for the classification of chest X-ray images. These methods, based on the AlexNet model and VGGNet16 method, can accurately identify lung diseases.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Urology & Nephrology
Thomas Chi, Manint Usawachintachit, Stefanie Weinstein, Maureen P. Kohi, Andrew Taylor, David T. Tzou, Helena C. Chang, Marshall Stoller, John Mongan
JOURNAL OF UROLOGY
(2017)
Article
Radiology, Nuclear Medicine & Medical Imaging
Andrew Phelps, Andrew L. Callen, Peter Marcovici, David M. Naeger, John Mongan, Emily M. Webb
ACADEMIC RADIOLOGY
(2018)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sivan G. Marcus, Susana Candia, Marc D. Kohli, John Mongan, Ronald J. Zagoria, Spencer C. Behr, Derek Sun, Antonio C. Westphalen
Article
Radiology, Nuclear Medicine & Medical Imaging
John Mongan, David Avrin
JOURNAL OF DIGITAL IMAGING
(2018)
Review
Radiology, Nuclear Medicine & Medical Imaging
K. Kallianos, J. Mongan, S. Antani, T. Henry, A. Taylor, J. Abuya, M. Kohli
CLINICAL RADIOLOGY
(2019)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jahan Fahinzi, Hemal K. Kanzaria, John Mongan, Katherine L. Kahn, Ralph Charles Wang
Article
Medicine, General & Internal
Keith D. Hentel, Andrew Menard, John Mongan, Jeremy C. Durack, Pamela T. Johnson, Ali S. Raja, Ramin Khorasani
ANNALS OF INTERNAL MEDICINE
(2019)
Letter
Medicine, General & Internal
Keith D. Hentel, Andrew Menard, John Mongan, Jeremy C. Durack, Ali S. Raja, Ramin Khorasani
ANNALS OF INTERNAL MEDICINE
(2019)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ross W. Filice, John Mongan, Marc D. Kohli
JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY
(2020)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Emily M. Webb, John Mongan
ACADEMIC RADIOLOGY
(2022)
Review
Oncology
Sara Merkaj, Ryan C. Bahar, Tal Zeevi, MingDe Lin, Ichiro Ikuta, Khaled Bousabarah, Gabriel I. Cassinelli Petersen, Lawrence Staib, Seyedmehdi Payabvash, John T. Mongan, Soonmee Cha, Mariam S. Aboian
Summary: Despite their prevalence in research, ML tools that can predict glioma grade from medical images have not been incorporated clinically. The reporting quality of ML glioma grade prediction studies is low, but current efforts to create reporting guidelines and risk of bias tools may help address this. There are also other deficiencies in ML model data and glioma classification, but promising efforts are being made to overcome these challenges and encourage implementation in clinical settings.
Article
Computer Science, Artificial Intelligence
John Mongan, Jayashree Kalpathy-Cramer, Adam Flanders, Marius George Linguraru
Summary: The MICCAI and RSNA societies held a virtual panel discussion to facilitate collaboration between radiologists and machine learning scientists for the advancement of medical imaging techniques. The discussion covered innovation and clinical success of imaging technology, emphasizing the importance of collaboration.
RADIOLOGY-ARTIFICIAL INTELLIGENCE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Roozbeh Houshyar, Karen Tran-Harding, Justin Glavis-Bloom, Michael Nguyentat, John Mongan, Chantal Chahine, Thomas W. Loehfelm, Marc D. Kohli, Edward J. Zaragoza, Paul M. Murphy, Rony Kampalath
EMERGENCY RADIOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Adam E. Flanders, Luciano M. Prevedello, George Shih, Safwan S. Halabi, Jayashree Kalpathy-Cramer, Robyn Ball, John T. Mongan, Anouk Stein, Felipe C. Kitamura, Matthew P. Lungren, Gagandeep Choudhary, Lesley Cala, Luiz Coelho, Monique Mogensen, Fanny Moron, Elka Miller, Ichiro Ikuta, Vahe Zohrabian, Olivia McDonnell, Christie Lincoln, Lubdha Shah, David Joyner, Amit Agarwal, Ryan K. Lee, Jaya Nath
RADIOLOGY-ARTIFICIAL INTELLIGENCE
(2020)