A Study of Fine-Tuning CNN Models Based on Thermal Imaging for Breast Cancer Classification

Roslidar, Roslidar; Saddami, Khairun; Arnia, Fitri; Syukri, Maimun; Munadi, Khairul

doi:10.1109/cyberneticscom.2019.8875661

Cited by 59 publications

(26 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Meanwhile, the traditional Convolutional Neural Network (CNN) with the L layer has an L relationship, where the relationship with each other has a direct relationship L (L + 1) / 2. DenseNet contains a very narrow layer (12 filters per layer) with a small set of feature maps included in the network's collective information [11]. The advantages of DenseNet are that it is light on the problem of gradients, feature deployment, encourages feature reuse, and its functionality reduces the number of parameters [16].…”

Section: Densenet201mentioning

confidence: 99%

“…Recently, several researchers often use transfer learning techniques for image data classification. Researchers Roslidar et al [11] reviewed several transfer learning models (ResNet101, DenseNet201, MobileNetV2), resulting in 100% accuracy with the DenseNet201 model for classifying the thermal breast image. Researchers from Mporas and Naronglerdrit [12] also analyzed the use of several transfer learning models to identify the coronavirus through Chest X-ray images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

Adhinata¹,

Rakhmadani²,

Wibowo³

et al. 2021

Jurnal Informatika

View full text Add to dashboard Cite

The use of masks on the face in public places is an obligation for everyone because of the Covid-19 pandemic, which claims victims. Indonesia made 3M policies, one of which is to use masks to prevent coronavirus transmission. Currently, several researchers have developed a masked or non-masked face detection system. One of them is using deep learning techniques to classify a masked or non-masked face. Previous research used the MobileNetV2 transfer learning model, which resulted in an F-Measure value below 0.9. Of course, this result made the detection system not accurate enough. In this research, we propose a model with more parameters, namely the DenseNet201 model. The number of parameters of the DenseNet201 model is five times more than that of the MobileNetV2 model. The results obtained from several up to 30 epochs show that the DenseNet201 model produces 99% accuracy when training data. Then, we tested the matching feature on video data, the DenseNet201 model produced an F-Measure value of 0.98, while the MobileNetV2 model only produced an F-measure value of 0.67. These results prove the masked or non-masked face detection system is more accurate using the DenseNet201 model.

show abstract

Section: Densenet201mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

Adhinata¹,

Rakhmadani²,

Wibowo³

et al. 2021

Jurnal Informatika

View full text Add to dashboard Cite

show abstract

“…meme kanseri sınıflandırması için termal görüntülemeye dayalı ince ayar ESA modellerine ilişkin bir çalışma ortaya koymuştur. Resnet101, Densenet210, MobilenetV2, ShufflenetV2 modellerini kullanarak gerçekleştirilen çalışmada %100 doğrulukla hasta-sağlıklı sınıflandırması elde edilmiştir [45]. Gomez ve ark.…”

Section: Meme Kanseriunclassified

Kızılötesi Termal Görüntülemenin Yapay Zeka Tabanlı Biyomedikal Uygulamaları

Ervural

Ceylan

2021

jai

View full text Add to dashboard Cite

Kızılötesi termal görüntüleme, vücut sıcaklığı dağılımının ve değişiminin izlenmesine izin veren invazif olmayan, zararlı radyasyon içermeyen, temassız bir modalitedir. Periferik kan akışı, otonom sinir sistemi, vazokonstrüksiyon / vazodilatasyon, iltihaplanma, terleme veya diğer süreçler hakkında fizyolojik bilgiler sağlaması medikal alanda kullanımını yaygınlaştırmıştır. Yapay zekâ alanında yaşanan gelişmeler medikal uygulamalarda da karşılık bulmuş ve makine öğrenimi metotları; karar verme, hastalık takibi, cerrahi planlama gibi birçok görev için kullanılır hâle gelmiştir. Termal verilerin yorumlanması için yapay zekâ yöntemlerinin kullanılması, bir tanı, tedavi planlama veya cerrahi değerlendirme senaryosunda doktorlara ikinci bir görüş sağlamak için etkin bir çözüm olabilir. Bu araştırmanın amacı: Literatür kaynaklarının incelenerek termal görüntülemenin medikal uygulamalardaki sınıflandırma, karar verme gibi süreçlerde yapay zekâ yöntemlerinin işleyişlerini değerlendirmek ve literatür hakkında bilgi sunmaktır.Infrared thermal imaging is a non-invasive, harmless radiation-free non-contact modality that allows monitoring of body temperature distribution and change. Providing physiological information about peripheral blood flow, autonomic nervous system, vasoconstriction / vasodilation, inflammation, sweating or other processes has expanded its use in the medical field. Developments in the field of artificial intelligence have also found response in medical applications, and machine learning methods have become used for many tasks such as decision making, disease monitoring, and surgical planning. Using artificial intelligence methods to interpret thermal data can be an effective solution to provide doctors with a second opinion in a diagnosis, treatment planning or surgical evaluation scenario. The purpose of this research; To evaluate the functioning of artificial intelligence methods in medical applications such as classification and decision making of thermal imaging by examining the literature sources and to provide information about the literature.

show abstract

“…Another study compared CNN performance between dense and lightweight NNs [122]. The comparative study was performed by fine-tuning the pre-trained networks using the MatLab DL toolbox [90].…”

Section: Research On Breast Thermogram Classificationmentioning

confidence: 99%

A Review on Recent Progress in Thermal Imaging and Deep Learning Approaches for Breast Cancer Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

Developing a breast cancer screening method is very important to facilitate early breast cancer detection and treatment. Building a screening method using medical imaging modality that does not cause body tissue damage (non-invasive) and does not involve physical touch is challenging. Thermography, a non-invasive and non-contact cancer screening method, can detect tumors at an early stage even under precancerous conditions by observing temperature distribution in both breasts. The thermograms obtained on thermography can be interpreted using deep learning models such as convolutional neural networks (CNNs). CNNs can automatically classify breast thermograms into categories such as normal and abnormal. Despite their demostrated utility, CNNs have not been widely used in breast thermogram classification. In this study, we aimed to summarize the current work and progress in breast cancer detection based on thermography and CNNs. We first discuss of breast thermography potential in early breast cancer detection, providing an overview of the availability of breast thermal datasets together with publicly accessible. We also discuss characteristics of breast thermograms and the differences between healthy and cancerous thermographic patterns. Breast thermogram classification using a CNN model is described step by step including a simulation example illustrating feature learning. We cover most research related to the implementation of deep neural networks for breast thermogram classification and propose future research directions for developing representative datasets, feeding the segmented image, assigning a good kernel, and building a lightweight CNN model to improve CNN performance. INDEX TERMS breast cancer; convolutional neural network; deep learning; early detection; thermogram

show abstract

A Study of Fine-Tuning CNN Models Based on Thermal Imaging for Breast Cancer Classification

Cited by 59 publications

References 13 publications

A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

Kızılötesi Termal Görüntülemenin Yapay Zeka Tabanlı Biyomedikal Uygulamaları

A Review on Recent Progress in Thermal Imaging and Deep Learning Approaches for Breast Cancer Detection

Contact Info

Product

Resources

About