ABCanDroid: A Cloud Integrated Android App for Noninvasive Early Breast Cancer Detection Using Transfer Learning

Chowdhury, Deepraj; Das, Anik; Dey, Aritra; Sarkar, Shreya; Dwivedi, Ashutosh Dhar; Mukkamala, Raghava Rao; Murmu, Lakhindar

doi:10.3390/s22030832

Cited by 30 publications

(14 citation statements)

References 43 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve the best classification results, numerous tests and hyper parameter adjustments have been conducted. e suggested frameworks seek to be an efficient approach for all clinicians and society at large and assist the user in breast cancer early diagnosis [9]. is research emphasizes how blockchain can help prevent pandemics in the future.…”

Section: Review Of Literaturementioning

confidence: 99%

Investigation of Diabetes Care in Elder Individuals Using Artificial Intelligence

Vyas

Gupta

Tarar

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

The term blockchain is mainly regarded as the distributed transaction which is mainly comprised of different blocks, and each set tends to represent the data that are being associated with the previous blocks. The blockchain is mainly managed through peer-to-peer networks which comparatively involves in adhering to the protocol of authenticating various blocks to form the blockchain. The usage of blockchain technology has been increasingly used in different fields, and healthcare services are now using blockchain for better patient delivery, detecting disease, and other aspects. The scope of the proposed study is that this study has exploited the function of a blockchain-enabled big data network to support medical professionals in giving better treatment modalities and delivering better patient care. The application of a new generation of smart block chains such as Ethereum and NEM is now offering better services and features in creating blockchain-based healthcare data management and hence support healthcare centers, medical practitioners, nurses, radiologists, and patients for better healthcare management. The application of blockchain technology in big data networks supports adding more value as it results in enhanced data quality, accessibility, and support in creating better security and safety of data and information, which is highly essential in the medical industry. Blockchain technology enables big data technologies enabled in supporting medical practitioners in addressing various healthcare ailments; one of the major diseases impacting many people around the world is diabetes. Patients with such ailments tend to generate more data and information related to the disease and health-related aspects. Hence, this information requires being maintained and analyzed, so that superior healthcare services can be provided. This study is more involved in the investigation of blockchain technology through a big data network enabled in offering better care for elderly individuals who have been affected due to diabetes, the researchers propose to choose a questionnaire method to collect the data from nearly 169 respondents, and these data were then analyzed using SPSS data package. The analyst used percentage analysis, correlation analysis, and chi-square test to analyze the data which has been collated by the researchers. The results and discussion show in detail the major aspects of blockchain technology in supporting healthcare professionals for better diabetes care management for elderly individuals.

show abstract

Section: Review Of Literaturementioning

confidence: 99%

Investigation of Diabetes Care in Elder Individuals Using Artificial Intelligence

Vyas

Gupta

Tarar

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

show abstract

“…Federal learning can model data usage and machine learning under the requirements of user privacy protection, data security and government, which can effectively solve the problem of data islands. According to different modes, federal learning can be divided into horizontal federal learning, vertical federal learning and transfer federal learning [ 26 ].…”

Section: Methodsmentioning

confidence: 99%

Trusted Data Storage Architecture for National Infrastructure

Wang

Rui

Xiao-long

et al. 2022

Sensors

View full text Add to dashboard Cite

National infrastructure is a material engineering facility that provides public services for social production and residents’ lives, and a large-scale complex device or system is used to ensure normal social and economic activities. Due to the problems of difficult data collection, long project period, complex data, poor security, difficult traceability and data intercommunication, the archives management of most national infrastructure is still in the pre-information era. To solve these problems, this paper proposes a trusted data storage architecture for national infrastructure based on blockchain. This consists of real-time collection of national infrastructure construction data through sensors and other Internet of Things devices, conversion of heterogeneous data source data into a unified format according to specific business flows, and timely storage of data in the blockchain to ensure data security and persistence. Knowledge extraction of data stored in the chain and the data of multiple regions or fields are jointly modeled through federal learning. The parameters and results are stored in the chain, and the information of each node is shared to solve the problem of data intercommunication.

show abstract

“…Using MLP, SVM, and KNN classifiers, they attained average accuracies of 93.85%, 93.21%, and 83.87%, respectively. Chowdhury et al (2022) developed a breast cancer classification system that uses pretrained transfer learning models to extract fine-tuned characteristics prior to training on histopathological images. It assists users in classifying tissues by allowing them to upload a single histopathological image at a time.…”

Section: Related Studiesmentioning

confidence: 99%

“…For medical image analysts, the diagnosis process is complex, time-consuming, and monotonous. Medical image analysis is one of the most exciting research areas that have gained significant attention in academia and the medical sector, allowing for the detection and treatment of various illnesses, including breast cancer ( Dewangan et al, 2022 ; Zerouaoui & Idri, 2022 ; Chowdhury et al, 2022 ; Mohamed et al, 2022 ). Breast cancers are classified into five stages according to Peiris et al (2015) .…”

Section: Introductionmentioning

confidence: 99%

Classification of breast cancer using a manta-ray foraging optimized transfer learning framework

Baghdadi

Malki

Balaha

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Due to its high prevalence and wide dissemination, breast cancer is a particularly dangerous disease. Breast cancer survival chances can be improved by early detection and diagnosis. For medical image analyzers, diagnosing is tough, time-consuming, routine, and repetitive. Medical image analysis could be a useful method for detecting such a disease. Recently, artificial intelligence technology has been utilized to help radiologists identify breast cancer more rapidly and reliably. Convolutional neural networks, among other technologies, are promising medical image recognition and classification tools. This study proposes a framework for automatic and reliable breast cancer classification based on histological and ultrasound data. The system is built on CNN and employs transfer learning technology and metaheuristic optimization. The Manta Ray Foraging Optimization (MRFO) approach is deployed to improve the framework’s adaptability. Using the Breast Cancer Dataset (two classes) and the Breast Ultrasound Dataset (three-classes), eight modern pre-trained CNN architectures are examined to apply the transfer learning technique. The framework uses MRFO to improve the performance of CNN architectures by optimizing their hyperparameters. Extensive experiments have recorded performance parameters, including accuracy, AUC, precision, F1-score, sensitivity, dice, recall, IoU, and cosine similarity. The proposed framework scored 97.73% on histopathological data and 99.01% on ultrasound data in terms of accuracy. The experimental results show that the proposed framework is superior to other state-of-the-art approaches in the literature review.

show abstract

ABCanDroid: A Cloud Integrated Android App for Noninvasive Early Breast Cancer Detection Using Transfer Learning

Cited by 30 publications

References 43 publications

Investigation of Diabetes Care in Elder Individuals Using Artificial Intelligence

Investigation of Diabetes Care in Elder Individuals Using Artificial Intelligence

Trusted Data Storage Architecture for National Infrastructure

Classification of breast cancer using a manta-ray foraging optimized transfer learning framework

Contact Info

Product

Resources

About