Article
Engineering, Electrical & Electronic
Kushangi Atrey, Bikesh Kumar Singh, Abhijit Roy, Narendra Kuber Bodhey
Summary: Existing studies show limitations of single imaging modalities (MG or US) in detecting breast lesions, prompting the development of a CAS system using CNN and a bimodal database for improved detection. Results indicate that US can be used as a complementary technique to MG in segmenting breast lesions, showing promising potential for clinical application.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Article
Geography, Physical
Michael Ying Yang, Saumya Kumaar, Ye Lyu, Francesco Nex
Summary: In this paper, a Context Aggregation Network is proposed for pixelwise semantic segmentation, utilizing a dual-branch convolutional neural network with lower computational costs and competitive prediction accuracy. By combining a high-resolution branch for spatial detailing and a context branch with lightweight global aggregation and local distribution blocks, the model can capture both long-range and local contextual dependencies efficiently.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Engineering, Industrial
Jaemin Cho, Sangseung Kang, Kyekyung Kim
Summary: This paper proposes a precision object segmentation method to accurately detect objects moving on a conveyor belt. By designing a new backbone network and using a multi-level pooling layer, lightweight and stable real-time detection and precise segmentation are achieved. The experimental results confirm the superior performance of this method.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Civil
Guoan Xu, Juncheng Li, Guangwei Gao, Huimin Lu, Jian Yang, Dong Yue
Summary: This paper introduces a lightweight real-time semantic segmentation network called LETNet, which combines U-shaped CNN with Transformer effectively to compensate for respective deficiencies. The elaborately designed Lightweight Dilated Bottleneck (LDB) module and Feature Enhancement (FE) module simultaneously have a positive impact on training from scratch. Extensive experiments on challenging datasets demonstrate that LETNet achieves superior performances in accuracy and efficiency balance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Lazaros Tsochatzidis, Panagiota Koutla, Lena Costaridou, Ioannis Pratikakis
Summary: This study proposed a method to integrate segmentation information of mammographic lesions into convolutional neural networks for improved breast cancer diagnosis. Experimental results demonstrated that the proposed method achieved better performance in diagnosis.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Computer Science, Software Engineering
Emre Cicek, Sezer Goren
Summary: The article introduces a vision-based mobile cloud parking management solution that can automatically find roadside parking spots in crowded cities without the need for manual labeling for different streets. By employing road segmentation and object detection methods, the system is able to differentiate between parked and moving cars to guide drivers to available parking spots efficiently, showing promising potential for city-wide applications.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Automation & Control Systems
Liguo Zhou, Guang Chen, Lian Liu, Ruining Wang, Alois Knoll
Summary: This paper proposes an encoder-decoder network model based on the Cross Stage Partial (CSP) block for real-time semantic segmentation in traffic scenes. The model combines context information and detailed information effectively while maintaining high inference speed. Experimental results demonstrate that our method achieves high mIOU and fast frame rates on the Cityscapes and CamVid datasets using the NVIDIA RTX 3090.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Civil
Mengxu Lu, Zhenxue Chen, Chengyun Liu, Sile Ma, Lei Cai, Hao Qin
Summary: This paper proposes a Multi-Feature Fusion Network (MFNet) that has real-time efficient prediction capacity without sacrificing accuracy, and it performs well on multiple datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Lu Zhang, Fengling Jiang, Bin Kong, Jing Yang, Can Wang
Summary: This paper proposes a real-time lane detection method using attention mechanism, and comparative experiments on two benchmark datasets show that the method is independent of lane number and pattern, running at high speed with superior performance.
COGNITIVE COMPUTATION
(2021)
Article
Computer Science, Information Systems
Meng Lou, Runze Wang, Yunliang Qi, Wenwei Zhao, Chunbo Xu, Jie Meng, Xiangyu Deng, Yide Ma
Summary: In this study, a novel multi-level global-guided branch-attention network (MGBN) is proposed for breast masses classification, aiming to leverage the global contextual information to refine feature representation. Experimental results demonstrate that the proposed method achieves promising results on two public mammographic mass classification databases.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Faizan Ahmad, Wenguo Hou, Jing Xiong, Zeyang Xia
Summary: This article proposes a fully automatic pipeline for segmenting the right ventricle (RV), myocardium (MYO), and left ventricle (LV) using short-axis CMRI sequence images. A dilated residual network (DRN) is introduced to capture features at full resolution in the bottleneck of UNet, significantly increasing spatial and temporal information and maintaining localization accuracy. The method achieves superior performance and outperforms state-of-the-art methods in terms of accuracy and segmentation.
Article
Computer Science, Information Systems
Supriya Suresh, Subaji Mohan
Summary: This paper proposes a method for automated tumor stage classification of pulmonary lung nodules using a deep convolutional neural network. By analyzing and extracting self-learned features from the nodules, the method improves the classification accuracy of DCNN and enhances the early detection and prognosis of lung cancer.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Xiaogen Zhou, Xingqing Nie, Zhiqiang Li, Xingtao Lin, Ensheng Xue, Luoyan Wang, Junlin Lan, Gang Chen, Min Du, Tong Tong
Summary: Skin lesions and thyroid cancer are common diseases, and a computer-aided diagnosis system can improve accuracy. This study proposes a novel dual encoder-decoder network (H-Net) for automated segmentation of thyroid nodules and skin lesions. Experimental results show that H-Net outperforms other methods on multiple datasets.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Megha Chhabra, Kiran Kumar Ravulakollu, Manoj Kumar, Abhay Sharma, Anand Nayyar
Summary: Latent fingerprint segmentation is a complex process of accurately separating fingerprints from poor quality latent fingerprint images. By using a non-learning technique to detect potentially relevant areas and a deep learning approach to separate imposter regions from fingerprint regions, better segmentation results can be achieved.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Shu Yang, Lu Zhang, Shuai Liu, Huchuan Lu, Hao Chen
Summary: In this article, a densely aggregated bilateral network (DAB-Net) is proposed for real-time semantic segmentation. The network captures local semantic contextual information through a patch wise context enhancement (PCE) module in the context path, and exploits more spatial information through a context-guided spatial path (CGSP). Experimental results demonstrate that the proposed method achieves high accuracy with limited decay in speed.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Biomedical
Sua Bae, Bae-Hyung Kim, Azra Alizad, Mostafa Fatemi, Tai-Kyong Song
Summary: This study demonstrates the feasibility and advantage of aperiodic plane wave imaging (APWI) for ultrafast three-dimensional ultrasonic imaging. Experimental results show that APWI enhances contrast without compromising spatial resolution and frame rate. It is significant for the advancement of ultrafast 3-D ultrasonic imaging.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Engineering, Biomedical
David P. Rosen, Nicholas B. Larson, Azra Alizad, Mostafa Fatemi
Summary: In this study, a mechanical analysis is proposed to estimate the internal pressure of a finitely deformed spherical compartment using Lamb wave measurements. The analysis shows a dispersion relation between Lamb wave speed and pressure, using limited material parameters. The effectiveness of the proposed analysis is validated through experiments, and potential improvements are discussed.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Giovanna Ferraioli, Viksit Kumar, Arinc Ozturk, Kibo Nam, Chris L. de Korte, Richard G. Barr
Summary: The translation is about nonalcoholic fatty liver disease (NAFLD), which is the most common chronic liver disease worldwide. The evaluation of liver fat content is crucial in identifying and monitoring patients with NAFLD. The American Institute of Ultrasound in Medicine-RSNA Quantitative Imaging Biomarkers Alliance has developed initiatives to standardize ultrasound-based fat quantification and understand its influencing factors.
Review
Medicine, General & Internal
Smiksha Munjral, Mahesh Maindarkar, Puneet Ahluwalia, Anudeep Puvvula, Ankush Jamthikar, Tanay Jujaray, Neha Suri, Sudip Paul, Rajesh Pathak, Luca Saba, Renoh Johnson Chalakkal, Suneet Gupta, Gavino Faa, Inder M. Singh, Paramjit S. Chadha, Monika Turk, Amer M. Johri, Narendra N. Khanna, Klaudija Viskovic, Sophie Mavrogeni, John R. Laird, Gyan Pareek, Martin Miner, David W. Sobel, Antonella Balestrieri, Petros P. Sfikakis, George Tsoulfas, Athanasios Protogerou, Durga Prasanna Misra, Vikas Agarwal, George D. Kitas, Raghu Kolluri, Jagjit Teji, Mustafa Al-Maini, Surinder K. Dhanjil, Meyypan Sockalingam, Ajit Saxena, Aditya Sharma, Vijay Rathore, Mostafa Fatemi, Azra Alizad, Vijay Viswanathan, Padukode R. Krishnan, Tomaz Omerzu, Subbaram Naidu, Andrew Nicolaides, Mostafa M. Fouda, Jasjit S. Suri
Summary: Diabetes can lead to retinopathy and cardiovascular diseases, making early identification of cardiovascular complications crucial for DR patients. Utilizing low-cost, high-resolution imaging techniques like carotid B-mode ultrasound can help in arterial tissue characterization and risk stratification in DR patients. The application of artificial intelligence techniques enables the identification of atherosclerotic plaque features in arterial ultrasound for timely CVD risk assessment and risk stratification in DR patients.
Review
Medicine, General & Internal
Jasjit S. Suri, Mahesh A. Maindarkar, Sudip Paul, Puneet Ahluwalia, Mrinalini Bhagawati, Luca Saba, Gavino Faa, Sanjay Saxena, Inder M. Singh, Paramjit S. Chadha, Monika Turk, Amer Johri, Narendra N. Khanna, Klaudija Viskovic, Sofia Mavrogeni, John R. Laird, Martin Miner, David W. Sobel, Antonella Balestrieri, Petros P. Sfikakis, George Tsoulfas, Athanase D. Protogerou, Durga Prasanna Misra, Vikas Agarwal, George D. Kitas, Raghu Kolluri, Jagjit S. Teji, Mustafa Al-Maini, Surinder K. Dhanjil, Meyypan Sockalingam, Ajit Saxena, Aditya Sharma, Vijay Rathore, Mostafa Fatemi, Azra Alizad, Padukode R. Krishnan, Tomaz Omerzu, Subbaram Naidu, Andrew Nicolaides, Kosmas Paraskevas, Mannudeep Kalra, Zoltan Ruzsa, Mostafa M. Fouda
Summary: This study presents a novel investigation into using deep learning models to predict CVD/stroke risk in PD patients affected by COVID-19. The study found that deep neural networks can effectively stratify CVD/stroke risk and suggested appropriate model designs. Additionally, the study explored artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients.
Article
Medicine, General & Internal
Jasjit S. Suri, Sushant Agarwal, Gian Luca Chabert, Alessandro Carriero, Alessio Pasche, Pietro S. C. Danna, Luca Saba, Armin Mehmedovic, Gavino Faa, Inder M. Singh, Monika Turk, Paramjit S. Chadha, Amer M. Johri, Narendra N. Khanna, Sophie Mavrogeni, John R. Laird, Gyan Pareek, Martin Miner, David W. Sobel, Antonella Balestrieri, Petros P. Sfikakis, George Tsoulfas, Athanasios D. Protogerou, Durga Prasanna Misra, Vikas Agarwal, George D. Kitas, Jagjit S. Teji, Mustafa Al-Maini, Surinder K. Dhanjil, Andrew Nicolaides, Aditya Sharma, Vijay Rathore, Mostafa Fatemi, Azra Alizad, Pudukode R. Krishnan, Ferenc Nagy, Zoltan Ruzsa, Mostafa M. Fouda, Subbaram Naidu, Klaudija Viskovic, Mannudeep K. Kalra
Summary: This study presents a cloud-based explainable AI system, COVLIAS 2.0-cXAI, using four kinds of CAM models for lesion localization in lung CT scans. The system achieved high performance and stability, and received a high score in clinical settings.
Article
Biology
Shuhang Wang, Vivek Kumar Singh, Eugene Cheah, Xiaohong Wang, Qian Li, Shinn-Huey Chou, Constance D. Lehman, Viksit Kumar, Anthony E. Samir
Summary: Researchers proposed two improvements for U-Net: replacing consecutive convolutions with stacked dilated operation, and using an asymmetric structure with fewer channels in the decoder path. Experiments confirmed that these improvements can enhance the performance of U-Net and its variants while using fewer parameters.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Vivek Kumar Singh, Elham Yousef Kalafi, Shuhang Wang, Alex Benjamin, Mercy Asideu, Viksit Kumar, Anthony E. Samir
Summary: Medical image segmentation is crucial for diagnosing and staging diseases. We propose a robust and lightweight deep learning real-time segmentation network called MISegNet, which outperforms state-of-the-art methods on multiple datasets, demonstrating its versatility and effectiveness.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Medicine, General & Internal
Narendra N. Khanna, Mahesh A. Maindarkar, Vijay Viswanathan, Anudeep Puvvula, Sudip Paul, Mrinalini Bhagawati, Puneet Ahluwalia, Zoltan Ruzsa, Aditya Sharma, Raghu Kolluri, Padukone R. Krishnan, Inder M. Singh, John R. Laird, Mostafa Fatemi, Azra Alizad, Surinder K. Dhanjil, Luca Saba, Antonella Balestrieri, Gavino Faa, Kosmas Paraskevas, Durga Prasanna Misra, Vikas Agarwal, Aman Sharma, Jagjit S. Teji, Mustafa Al-Maini, Andrew Nicolaides, Vijay Rathore, Subbaram Naidu, Kiera Liblik, Amer M. Johri, Monika Turk, David W. Sobel, Martin Miner, Klaudija Viskovic, George Tsoulfas, Athanasios D. Protogerou, Sophie Mavrogeni, George D. Kitas, Mostafa M. Fouda, Mannudeep K. Kalra, Jasjit S. Suri
Summary: This article proposes a novel investigation using deep learning solutions to predict cardiovascular disease/stroke risk in patients with diabetic foot infection (DFI). The research confirms the viability of cardiovascular disease/stroke risk stratification in DFI patients using deep neural networks such as Long Short-Term Memory and Recurrent Neural Networks. The article also discusses AI bias and strategies for early diagnosis of cardiovascular disease/stroke in DFI patients.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Medicine, General & Internal
Vivek Kumar Singh, Elham Yousef Kalafi, Eugene Cheah, Shuhang Wang, Jingchao Wang, Arinc Ozturk, Qian Li, Yonina C. Eldar, Anthony E. Samir, Viksit Kumar
Summary: A novel Harmonic Attention-based U-Net network (HaTU-Net) is proposed for precise segmentation of ovaries and follicles in ultrasound images. Experimental results demonstrate that the network performs better than the standard U-Net in recognizing ovaries and follicles.
Review
Oncology
Humayra Afrin, Nicholas B. Larson, Mostafa Fatemi, Azra Alizad
Summary: Breast cancer is a leading cause of cancer death among women. Ultrasound is a useful tool for breast cancer management but has limitations like high false positivity. Deep learning may be helpful in reducing the workload of ultrasound operators in resource-limited settings. There is a need for more research on the impact of deep learning beyond breast cancer diagnosis and on the use of different ultrasound methods.
Article
Oncology
Melisa Kurti, Soroosh Sabeti, Kathryn A. Robinson, Lorenzo Scalise, Nicholas B. Larson, Mostafa Fatemi, Azra Alizad
Summary: Low specificity in current ultrasound modalities for thyroid cancer detection necessitates the development of new imaging modalities for optimal characterization of thyroid nodules. Here, we evaluated the quantitative biomarkers of a new high-definition microvessel imaging (HDMI) for discrimination of benign from malignant thyroid nodules. The HDMI technique provides quantitative measures of tumor microvasculature morphological features as new imaging biomarkers, and its analysis can detect thyroid malignancy with high sensitivity and specificity.
Article
Multidisciplinary Sciences
Yuyang Gu, Viksit Kumar, E. G. Sunethra K. Dayavansha, Scott Schoen Jr, Ernest Feleppa, Rimon Tadross, Michael H. Wang, Michael J. Washburn, Kai Thomenius, Anthony E. Samir
Summary: ADAPT is an acoustic diffraction-resistant adaptive profile technology that can generate a propagation-invariant beam with high flexibility. It has applications in various fields such as medicine, biology, and material science.
Article
Health Care Sciences & Services
Narendra N. Khanna, Mahesh A. Maindarkar, Vijay Viswanathan, Jose Fernandes E. Fernandes, Sudip Paul, Mrinalini Bhagawati, Puneet Ahluwalia, Zoltan Ruzsa, Aditya Sharma, Raghu Kolluri, Inder M. Singh, John R. Laird, Mostafa Fatemi, Azra Alizad, Luca Saba, Vikas Agarwal, Aman Sharma, Jagjit S. Teji, Mustafa Al-Maini, Vijay Rathore, Subbaram Naidu, Kiera Liblik, Amer M. Johri, Monika Turk, Lopamudra Mohanty, David W. Sobel, Martin Miner, Klaudija Viskovic, George Tsoulfas, Athanasios D. Protogerou, George D. Kitas, Mostafa M. Fouda, Seemant Chaturvedi, Mannudeep K. Kalra, Jasjit S. Suri
Summary: The study aims to evaluate the cost of AI technology in the healthcare field and compare it to traditional methods. The results show significant cost savings in diagnosis and treatment using AI tools. Further improvement in the economics of AI can be achieved through pruning, reducing AI bias, enhancing explainability, and obtaining regulatory approvals.
Review
Cardiac & Cardiovascular Systems
Narendra N. Khanna, Mahesh Maindarkar, Anudeep Puvvula, Sudip Paul, Mrinalini Bhagawati, Puneet Ahluwalia, Zoltan Ruzsa, Aditya Sharma, Smiksha Munjral, Raghu Kolluri, Padukone R. Krishnan, Inder M. Singh, John R. Laird, Mostafa Fatemi, Azra Alizad, Surinder K. Dhanjil, Luca Saba, Antonella Balestrieri, Gavino Faa, Kosmas I. Paraskevas, Durga Prasanna Misra, Vikas Agarwal, Aman Sharma, Jagjit Teji, Mustafa Al-Maini, Andrew Nicolaides, Vijay Rathore, Subbaram Naidu, Kiera Liblik, Amer M. Johri, Monika Turk, David W. Sobel, Gyan Pareek, Martin Miner, Klaudija Viskovic, George Tsoulfas, Athanasios D. Protogerou, Sophie Mavrogeni, George D. Kitas, Mostafa M. Fouda, Manudeep K. Kalra, Jasjit S. Suri
Summary: This study explores the deep-driven vascular damage caused by SARS-CoV-2, specifically in the pulmonary, renal, coronary, and carotid vessels. Using artificial intelligence technology for tissue characterization through medical imaging, important insights regarding the pathophysiology of vascular damage are revealed, along with recommendations for improving vascular research architecture.
JOURNAL OF CARDIOVASCULAR DEVELOPMENT AND DISEASE
(2022)
