Review
Computer Science, Information Systems
Nada M. Hassan, Safwat Hamad, Khaled Mahar
Summary: This survey presents a structured overview of current deep learning and traditional machine learning based CAD systems for breast cancer detection and classification. It provides information about publicly available mammographic datasets and evaluation metrics, and discusses the pros, limitations, challenges and limitations in the current literature.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Jayesh George Melekoodappattu, Perumal Sankar Subbian, M. P. Flower Queen
Summary: Mammography is an essential technique for diagnosing breast malignancy in women, with mass lesions and microcalcifications being the most common features associated with breast tumors. The Glowworm Swarm Optimization (GSO) algorithm is effective in optimizing feature sets obtained from multiscale feature extraction procedures. The system developed using GSO-ELM-FOA can accurately detect calcifications and tumors with a high level of precision.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Article
Engineering, Biomedical
Debendra Muduli, Ratnakar Dash, Banshidhar Majhi
Summary: The study suggests an enhanced automated CAD model for accurate breast disease identification. By utilizing FDCT-WRP for feature extraction, combined with PCA and LDA for feature reduction, and implementing MODPSO-ELM algorithm for classification, the CAD model achieved high accuracy on different datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Grzegorz Surowka, Maciej Ogorzalek
Summary: Proper diagnosis of cutaneous melanoma is crucial and efficient wavelet-based features can serve as signals of neoplastic changes. Classification performance strongly depends on wavelet number, image resolution, and image compression. Some wavelets can enhance learning performance at reduced image resolutions, consistent with other melanoma feature-extraction studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Hamid El Malali, Abdelhadi Assir, Vikrant Bhateja, Azeddine Mouhsen, Mohammed Harmouchi
Summary: The paper developed a contrast enhancement model for mammograms to improve the contrast of lesions and increase various Image Quality Assessment parameters. This model utilizes the properties of genetic algorithm and Sigmoid function to effectively distinguish different types of breast lesions and is validated through simulations on mammograms.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Biomedical
Adyasha Sahu, Pradeep Kumar Das, Sukadev Meher
Summary: Breast cancer is a major cause of cancer death in women worldwide. In this study, we propose five new deep hybrid convolutional neural network-based breast cancer detection frameworks, which outperform traditional methods and demonstrate excellent accuracy even in small datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Linh T. Duong, Cong Q. Chu, Phuong T. Nguyen, Son T. Nguyen, Binh Q. Tran
Summary: This study proposes a practical solution for classifying mammograms using the synergy between graph neural networks and image processing techniques. The experimental results demonstrate that the proposed approach achieves optimal prediction performance on the dataset, achieving 100% accuracy and 1.0 precision and recall in the classification of BI-RADS scores and breast density types. The proposed approach is anticipated to be deployed as a non-invasive pre-screening tool to assist doctors in their diagnosis activities.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Naglaa F. Soliman, Naglaa S. Ali, Mahmoud Aly, Abeer D. Algarni, Walid El-Shafai, Fathi E. Abd El-Samie
Summary: Early diagnosis of breast cancer is crucial for effective treatment. Mammography, aided by computer-aided detection systems, is the preferred method for breast cancer screening. This paper presents an efficient framework for processing mammogram images and introduces an algorithm for segmenting images to detect tumors. Results show that the proposed technique performs exceptionally well in comparison with conventional methods.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Sujata Kulkarni, Rinku Rabidas
Summary: In this paper, a deep learning architecture based on U-Net is proposed for the detection and characterization of breast masses. The proposed architecture achieves a true positive rate of 99.64% with 0.25 false positives per image for the INbreast dataset, and 97.36% with 0.38 false positives per image for the DDSM dataset in the detection task. In the mass characterization task, the proposed architecture achieves an accuracy of 97.39% with an AUC of 0.97 for INbreast, and 96.81% with an AUC of 0.96 for DDSM. The introduced scheme outperforms state-of-the-art techniques in both tasks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Asma Baccouche, Begonya Garcia-Zapirain, Yufeng Zheng, Adel S. Elmaghraby
Summary: This study investigated the effectiveness of an end-to-end fusion model based on YOLO architecture to detect and classify suspicious breast lesions on digital mammograms. The methodology showed high accuracy rates for detecting and classifying different types of lesions on both current and prior mammograms.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Automation & Control Systems
V. Swetha, G. Vadivu
Summary: The number of women affected by breast tumors is increasing worldwide every year. Detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The proposed cancer region detection methods in this paper resolve the drawbacks of conventional methods and achieve higher performance.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2023)
Article
Multidisciplinary Sciences
Yang Li, Hewei Zheng, Xiaoyu Huang, Jiayue Chang, Debiao Hou, Huimin Lu
Summary: This paper mainly focuses on the research of feature extraction, feature fusion, and nodule recognition in lung CAD systems, and proposes an improved algorithm model. Through experiments, it demonstrates that the proposed system has high accuracy and sensitivity, reducing the risk of misdiagnosis and missed diagnosis.
SCIENTIFIC REPORTS
(2022)
Article
Biology
Qiong Lou, Yingying Li, Yaguan Qian, Fang Lu, Jinlian Ma
Summary: Early accurate mammography screening and diagnosis can reduce the mortality of breast cancer. The proposed two-stage method combines image preprocessing and model optimization to address the challenges of low signal-to-noise ratio and physiological characteristics in mammogram diagnosis. The method achieved satisfactory performance with improved accuracy, recall, and precision compared to the ResNet50 model.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Hardware & Architecture
Adyasha Rath, Debahuti Mishra, Ganapati Panda, Suresh Chandra Satapathy, Kaijian Xia
Summary: This paper focuses on the detection of coronary artery disease (CAD) using deep learning models. The experimental results demonstrate that the proposed autoencoder (AE) model outperforms other models in terms of accuracy, F1-score, and area under the curve (AUC). The ensemble model combining AE and self organizing map (SOM) also achieves better performance.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS
(2022)
Article
Oncology
Gelan Ayana, Jinhyung Park, Se-woon Choe
Summary: In this study, a novel deep-learning method based on multi-stage transfer learning (MSTL) from ImageNet and cancer cell line image pre-trained models is proposed for the classification of mammographic masses as either benign or malignant. The proposed method addresses the challenge of obtaining large amounts of labeled mammogram training data by utilizing cancer cell line microscopic images as an intermediate domain of learning. The findings of this study are crucial for early diagnosis of breast cancer in young women with dense breasts.
Article
Health Care Sciences & Services
Jayesh George Melekoodappattu, Perumal Sankar Subbian
JOURNAL OF MEDICAL SYSTEMS
(2019)
Article
Engineering, Electrical & Electronic
T. Roshini, Ranjith Ravi, A. Reema Mathew, Anoop Balakrishnan Kadan, Perumal Sankar Subbian
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
V. Anoop, P. R. Bipin
NEURAL PROCESSING LETTERS
(2020)
Article
Energy & Fuels
Vinu Sundararaj, V Anoop, Priyanka Dixit, Arundhati Arjaria, Uday Chourasia, Pankaj Bhambri, M. R. Rejeesh, Regu Sundararaj
PROGRESS IN PHOTOVOLTAICS
(2020)
Article
Computer Science, Artificial Intelligence
Jayesh George Melekoodappattu, Perumal Sankar Subbian
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2020)
Article
Engineering, Electrical & Electronic
Jayesh George Melekoodappattu, Perumal Sankar Subbian, M. P. Flower Queen
Summary: Mammography is an essential technique for diagnosing breast malignancy in women, with mass lesions and microcalcifications being the most common features associated with breast tumors. The Glowworm Swarm Optimization (GSO) algorithm is effective in optimizing feature sets obtained from multiscale feature extraction procedures. The system developed using GSO-ELM-FOA can accurately detect calcifications and tumors with a high level of precision.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Anoop Balakrishnan Kadan, Perumal Sankar Subbian
Summary: Diabetic retinopathy is a global obstacle of diabetes, and research efforts have been introduced for automatic detection. The proposal aims to develop a new contribution based on four main stages: image pre-processing, blood vessels segmentation, feature extraction and dimension reduction, and diabetic retinopathy recognition.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Jayesh George Melekoodappattu, Anto Sahaya Dhas, Binil K. Kumar, K. S. Adarsh
Summary: Breast cancer is detected using medical image processing techniques and deep learning methods for automatic detection of malignancy. The ensemble approach shows excellent performance in improving classification efficiency and measurement metrics.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Review
Telecommunications
Anoop Balakrishnan Kadan, Perumal Sankar Subbian
Summary: The paper focuses on one of the signs of non-proliferative DR called exudates and various methods introduced to detect them in the retina. It includes algorithms, outcomes, datasets used, and other related results. The results are compared through tabulating evaluations and procedures.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Jayesh George Melekoodappattu, Anto Sahaya Dhas, Binil Kumar Kandathil, K. S. Adarsh
Summary: Customized deep neural networks and image texture attribute extraction are used in this study to autonomously diagnose cancer based on digital mammography images. The findings show that the combination method improves the accuracy and specificity of classification.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2022)
Article
Biochemistry & Molecular Biology
Jayesh George Melekoodappattu, Chaithanya Kandambeth Puthiyapurayil, Anoop Vylala, Anto Sahaya Dhas
Summary: This manuscript presents an advanced approach that combines multimodal feature fusion and dual-path network. By leveraging pretrained models and a custom convolutional neural network, salient features are effectively extracted from the data using nonlinear mapping and expansive perception. The resulting two-stage ensemble hybrid CNN model achieves a high accuracy of 99.63% in brain tumor classification.
CELL BIOCHEMISTRY AND FUNCTION
(2023)
Proceedings Paper
Materials Science, Multidisciplinary
Padmanayana, B. K. Anoop
Summary: With the increasing cases of diabetes, controlling blood sugar and regular eye examinations are important for preventing blindness. Diabetic Retinopathy (DR) is a common complication of diabetes caused by high blood sugar levels. In this study, a deep learning model using a Convolutional Neural Network architecture was proposed for the detection of DR. The model classified images into two classes: no diabetic retinopathy and diabetic retinopathy. High-resolution retinal images from the APTOS-2019 Blindness Detection dataset were used for training. A web-based interface was also created for easy interaction with the model.
MATERIALS TODAY-PROCEEDINGS
(2022)