A deep learning approach for automatic detection, segmentation and classification of breast lesions from thermal images

ÇİVİLİBAL, Soner; Çevik, Kerim Kürşat; Bozkurt, Ahmet

doi:10.1016/j.eswa.2022.118774

Cited by 39 publications

(15 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Breast cancer globally represents the most diagnosed malignancy among women and carries a substantial mortality burden. In 2020 the World Health Organization, Indonesia recorded 68,858 new cancer cases out of 396,914 new cancer cases worldwide with the death rate of 22,000 [1]. It is proven that developing countries have a risk of getting cancer almost twice as much as some existing studies where the ratio of the incidence of death in developed countries is around 0.2; while in developing countries, it is 0.37 [2].…”

Section: Introductionmentioning

confidence: 99%

A systematic review of breast cancer detection on thermal images

Aqil Aqthobirrobbany,

Dian Nova Kusuma Hardani,

Indah Soesanti

et al. 2023

CST

View full text Add to dashboard Cite

Breast cancer poses a substantial global health concern, primarily regarding its impact on women. Thermal imaging has emerged as a promising tool for early detection with notable technological advancements between 2013 and 2023 in enhancing diagnostic capabilities. However, existing literature reviews often lack adherence to specific scholarly standards and may provide incomplete insights into research trends. This systematic literature review (SLR) addresses these issues by comprehensively analyzing research trends, publication types, contributions, datasets, methodologies, and effective approaches for breast cancer detection using thermal imaging. The review encompasses an examination of 40 articles from reputable digital libraries, revealing a predominant emphasis on deep learning algorithms among 25 applied methods. These algorithms consistently achieve commendable performance, frequently surpassing 90% accuracy rates. Consequently, current research in breast cancer detection via thermal imaging is marked by a strong focus on artificial intelligence, particularly machine and deep learning, recognized as the most promising and effective avenues for investigation.

show abstract

Section: Introductionmentioning

confidence: 99%

A systematic review of breast cancer detection on thermal images

Aqil Aqthobirrobbany,

Dian Nova Kusuma Hardani,

Indah Soesanti

et al. 2023

CST

View full text Add to dashboard Cite

show abstract

“…Thermograms have played a significant role in diagnostic imaging studies. They serve as a source for developing image processing activities, which include segmentation tasks for separating the regions under study, as presented in [ [5] , [6] , [7] , [8] , [9] , [10] ] and identification of descriptive features and classification, as published [ [11] , [12] , [13] , [14] , [15] , [16] , [17] ]. Although most studies reported before 2014 were conducted without public access images sets that prevented reproducibility and comparison of results, it was until 2014 that the first public database of breast thermographic images was presented.…”

Section: Introductionmentioning

confidence: 99%

Dataset of breast thermography images for the detection of benign and malignant masses

Rodriguez-Guerrero,

Loaiza-Correa,

Restrepo-Girón

et al. 2024

Data in Brief

View full text Add to dashboard Cite

“…Therefore, it’s important to compare identified cancer ultrasound images with the standard Breast Imaging Reporting and Data System (BI-RADS) from a clinical perspective. BI-RADS provides standardised terms, known as a lexicon, that describe the characteristics of breast masses and effectively differentiate between benign and malignant tumours [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Improving Breast Cancer Detection and Diagnosis through Semantic Segmentation Using the Unet3+ Deep Learning Framework

et al. 2023

View full text Add to dashboard Cite

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide a more accurate and objective diagnosis of breast cancer, leading to improved patient outcomes.

show abstract

A deep learning approach for automatic detection, segmentation and classification of breast lesions from thermal images

Cited by 39 publications

References 29 publications

A systematic review of breast cancer detection on thermal images

A systematic review of breast cancer detection on thermal images

Dataset of breast thermography images for the detection of benign and malignant masses

Improving Breast Cancer Detection and Diagnosis through Semantic Segmentation Using the Unet3+ Deep Learning Framework

Contact Info

Product

Resources

About