A DenseNet CNN-based liver lesion prediction and classification for future medical diagnosis

Prakash, N Nanda; Rajesh, V; Inthiyaz, Syed; Pande, Sandeep Dwarkanath; Ahammad, Sk Hasane

doi:10.1016/j.sciaf.2023.e01629

Cited by 18 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study conducted on detecting liver disease lesions used a very highly sought-after and upcoming CNN architecture, DenseNet which was trained with around 10000 real-time samples of liver Xrays. The resulting model had an accuracy of 98.34, higher than previous works due to DenseNet's unique dropout layer [1].…”

Section: Literature Reviewmentioning

confidence: 72%

Unlocking the Potential of Machine Learning in Osteoporosis Detection: A Comparative Study of Multilayer Perceptron, Convolutional Neural Network and Dropout Models

Ramakrishnan,

Yeturu,

Sheeba

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

Osteoporosis is a chronic condition characterized by low bone density and an increased risk of fractures. It is a common problem among older adults and can significantly impact the quality of life and healthcare costs. Early diagnosis of osteoporosis is crucial for the implementation of effective treatment and prevention strategies. However, current methods for detecting osteoporosis, such as Dual-energy X-ray Absorptiometry (DXA), are not always reliable and can be inconvenient for patients. In this article, we explore the application of machine learning methods for osteoporosis detection and have evaluated it using a few models, like the Multilayer Perceptron, Convolutional Neural Network A -3 Conv. layers, (16 32 64), Convolutional Neural Network B -4Conv. layers, (32 64 128 128) and Convolutional Neural Network+ Dropout (over Dense Layer only) to see which one might give us the best result. We used a dataset of bone scans compiled and categorized by Mendeley data and used this data to train the models. Our results demonstrate that these models can effectively identify individuals with osteoporosis with some accuracy and sensitivity, some more than others. Overall, our study shows that the best-trained model found during cross-validation has an accuracy of 89.34%.

show abstract

Section: Literature Reviewmentioning

confidence: 72%

Unlocking the Potential of Machine Learning in Osteoporosis Detection: A Comparative Study of Multilayer Perceptron, Convolutional Neural Network and Dropout Models

Ramakrishnan,

Yeturu,

Sheeba

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

show abstract

“…Novel CNN architectures offer the potential for improved feature extraction and representation learning, enabling better discrimination between AD and non-AD brain images. Recent studies have shown the efficacy of deep learning approaches, such as CNNs, in various medical imaging tasks [44], [45], [46], [47], including AD classification. Moreover, advancements in deep learning techniques, coupled with the availability of large-scale medical imaging datasets, have forced the exploration of innovative CNN architectures for AD detection [48].…”

Section: E Importance Of Novel Cnnmentioning

confidence: 99%

ConvADD: Exploring a Novel CNN Architecture for Alzheimer's Disease Detection

Alsubaiea,

Luo,

Shaukat

2024

IJACSA

View full text Add to dashboard Cite

Alzheimer's disease (AD) poses a significant healthcare challenge, with an escalating prevalence and a forecasted surge in affected individuals. The urgency for precise diagnostic tools to enable early interventions and improved patient care is evident. Despite advancements, existing detection frameworks exhibit limitations in accurately identifying AD, especially in its early stages. Model optimisation and accuracy are other issues. This paper aims to address this critical research gap by introducing ConvADD, an advanced Convolutional Neural Network architecture tailored for AD detection. By meticulously designing ConvADD, this study endeavours to surpass the limitations of current methodologies and enhance accuracy metrics, optimisation, and reliability of AD diagnosis. The dataset was collected from Kaggle and consists of preprocessed 2D images extracted from 3D images. Through rigorous experimentation, ConvADD demonstrates remarkable performance metrics, showcasing its potential as a robust and effective. The proposed model shows remarkable results with a tool for AD detection accuracy of 98.01%, precision of 98%, recall of 98%, and an F1-Score of 98%, with only 2.1 million parameters. However, despite its promising results, several challenges and limitations remain, such as generalizability across diverse populations and the need for further validation studies. By elucidating these gaps and challenges, this paper contributes to the ongoing discourse on improving AD detection methodologies and lays the groundwork for future research endeavours in this domain.

show abstract

“…In fact, the CNN technique has extensive applications in disease diagnosis. The performance of CNNs in a variety of cancer detection and classification tasks, such as breast cancer [10], prostate cancer [11], liver lesions [12], and lung cancer [13], is particularly encouraging. According to Sudharshan et al [14], employing CNN models enhances the performance of diagnostic systems.…”

Section: Introductionmentioning

confidence: 99%

Skin cancer classification based on an optimized convolutional neural network and multicriteria decision-making

Saleh,

Hassan,

Salaheldin

2024

Preprint

View full text Add to dashboard Cite

Skin cancer can be treated if it is detected early. Many artificial intelligence-based models have been developed for skin cancer detection and classification. Considering the development of multiple models according to various scenarios and selecting the optimum model, these models were rarely considered in previous works. This study aimed to develop multiple models for skin cancer classification and select the optimum model. Convolutional neural networks (CNNs) in the form of AlexNet, Inception V3, MobileNet V2, and ResNet 50 were used for feature extraction. Feature reduction was carried out using two algorithms of the gray wolf optimizer (GWO) in addition to using the original features. Skin cancer images were classified into four classes based on six machine learning (ML) classifiers. As a result, 51 models were developed with different combinations of CNN algorithms, without GWO algorithms, with two GWO algorithms, and with six ML classifiers. To select the optimum model with the best results, the multicriteria decision-making approach was utilized in the recent form of ranking the alternatives by perimeter similarity (RAPS). Model training and testing were conducted using the International Skin Imaging Collaboration (ISIC) 2017 dataset. Based on nine evaluation metrics and according to the RAPS method, the AlexNet algorithm with GWO yielded the optimum model, achieving a classification accuracy of 94.5%. This work presents the first study on benchmarking skin cancer classification with a large number of models. Feature reduction not only reduces the time spent on training but also improves classification accuracy. The RAPS method has proven its robustness in the problem of selecting the best model for skin cancer classification.

show abstract

A DenseNet CNN-based liver lesion prediction and classification for future medical diagnosis

Cited by 18 publications

References 22 publications

Unlocking the Potential of Machine Learning in Osteoporosis Detection: A Comparative Study of Multilayer Perceptron, Convolutional Neural Network and Dropout Models

Unlocking the Potential of Machine Learning in Osteoporosis Detection: A Comparative Study of Multilayer Perceptron, Convolutional Neural Network and Dropout Models

ConvADD: Exploring a Novel CNN Architecture for Alzheimer's Disease Detection

Skin cancer classification based on an optimized convolutional neural network and multicriteria decision-making

Contact Info

Product

Resources

About