Modern microwave thermometry for breast cancer

Vesnin, Sergey; Goryanin, Igor

doi:10.1109/iciibms.2017.8279720

Cited by 9 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that randomly selecting samples to expand the dataset will introduce more noise information, which will affect the recognition performance of the model, try to choose samples with high confidence to expand the existing dataset, and reduce the impact of noise on recognition. Therefore, this paper designs a more targeted sample selection strategy, which spans different mammography image datasets, selects high-quality samples (confidence by a set of classifiers), and makes full use of the pathological knowledge contained in new instances [ 33 , 34 ] to train a more effective and robust recognition model. To sum up, in the RMD model, the basic idea of the sample selection algorithm is to select a set of classifiers with the best performance and use a complex voting mechanism to choose samples from the source dataset; that is, the source dataset can be correctly classified by this set of classifiers.…”

Section: Rmd Model Frameworkmentioning

confidence: 99%

[Retracted] Deep Learning‐Based Real‐Time Discriminate Correlation Analysis for Breast Cancer Detection

Bhende¹,

Thakare²,

Pant

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Breast cancer is the most common cancer in women, and the breast mass recognition model can effectively assist doctors in clinical diagnosis. However, the scarcity of medical image samples makes the recognition model prone to overfitting. A breast mass recognition model integrated with deep pathological information mining is proposed: constructing a sample selection strategy, screening high-quality samples across different mammography image datasets, and dealing with the scarcity of medical image samples from the perspective of data enhancement; mining the pathology contained in limited labeled models from shallow to deep information; and dealing with the shortage of medical image samples from the perspective of feature optimization. The multiview effective region gene optimization (MvERGS) algorithm is designed to refine the original image features, improve the feature discriminate and compress the feature dimension, better match the number of samples, and perform discriminate correlation analysis (DCA) on the advanced new features; in-depth cross-modal correlation between heterogeneous elements, that is, the deep pathological information, can be mined to describe the breast mass lesion area accurately. Based on deep pathological information and traditional classifiers, an efficient breast mass recognition model is trained to complete the classification of mammography images. Experiments show that the key technical indicators of the recognition model, including accuracy and AUC, are better than the mainstream baselines, and the overfitting problem caused by the scarcity of samples is alleviated.

show abstract

Section: Rmd Model Frameworkmentioning

confidence: 99%

[Retracted] Deep Learning‐Based Real‐Time Discriminate Correlation Analysis for Breast Cancer Detection

Bhende¹,

Thakare²,

Pant

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

Section: Angiogenesis and Glycolysis Processes Related To Temperature...mentioning

confidence: 99%

“…An important aspect that also affects the temperature is that cells in the tumoral zone use anaerobic glycolysis to generate energy (Warburg effect), which produces a significant amount of heat [37]. It has been shown that tumors with an accelerated growth rate, generally associated with malignant tumors in the pre-clinical stage, present a higher level of heat delivery than those that grow slowly [37,38]. Lymph node metastasis was also related with metabolic heat production, showing that, in the major cases, patients with tumors that present high levels of emissions of heat have developed lymph node metastasis [37].…”

Section: Angiogenesis and Glycolysis Processes Related To Temperature...mentioning

confidence: 99%

Analyzing Temperature Distributions and Gradient Behaviors for Early-Stage Tumor Lesions in 3D Computational Model of Breast

Acero Mendoza,

Bazán,

Ramírez-García

2024

Applied Sciences

View full text Add to dashboard Cite

The computational modelling and analysis of internal and external temperature distributions and their gradients, associated with the first stage of mammary tumors, was performed to relate thermal parameters to relevant tumor characteristics. A realistic 3D geometric model of breast anatomy was used to simulate tumor cases that were characterized in real life at their primary clinical stage. The thermophysical parameters of three tumors were extracted to implement the models; a fourth case without a tumor was used as a reference to provide quantitative measurements of temperature increases and gradient changes. The analysis considered superficial and internal temperature distributions and gradients, computed throughout specific paths. Finally, an evaluation was made of the ability of the thermometric technologies available today to detect the changes estimated in simulations. Maximum temperature increments in the range of 2.30 to 3.20 °C and in the range of 0.15 to 0.30 °C were found on internal and superficial paths, respectively. Internal gradient peak magnitudes fluctuated within the range of 0.34 to 1.14 °C/mm. Thermal results indicated a direct correlation between tumor size and temperature rise. Nevertheless, gradient results showed that the heat generation rate, an indicator of tumor malignancy, was directly proportional to internal gradient maximum peaks, which were related to tumor boundaries regardless of tumor size.

show abstract

“…Outside of research, radio wave thermometry is currently rarely used in regular clinical applications. Studies of breast cancer have suggested that it may be beneficial to include microwave thermometry in screening programs and in examination of patients with breast pathologies [115]. However, based on the previously mentioned studies, it is not possible to determine the uncertainty of microwavederived internal temperatures and further research is warranted.…”

Section: Microwave Radiometry In Practicementioning

confidence: 99%

Imaging-based internal body temperature measurements: The journal Temperature toolbox

2020

View full text Add to dashboard Cite

Noninvasive imaging methods of internal body temperature are in high demand in both clinical medicine and physiological research. Thermography and thermometry can be used to assess tissue temperature during thermal therapies: ablative and hyperthermia treatments to ensure adequate temperature rise in target tissues but also to avoid collateral damage by heating healthy tissues. In research use, measurement of internal body temperature enables us the production of thermal maps on muscles, internal organs, and other tissues of interest. The most used methods for noninvasive imaging of internal body temperature are based on different parameters acquired with magnetic resonance imaging, ultrasound, computed tomography, microwave radiometry, photoacoustic imaging, and near-infrared spectroscopy. In the current review, we examine the aforementioned imaging methods, their use in estimating internal body temperature in vivo with their advantages and disadvantages, and the physical phenomena the thermography or thermometry modalities are based on.

show abstract

Modern microwave thermometry for breast cancer

Cited by 9 publications

References 8 publications

[Retracted] Deep Learning‐Based Real‐Time Discriminate Correlation Analysis for Breast Cancer Detection

[Retracted] Deep Learning‐Based Real‐Time Discriminate Correlation Analysis for Breast Cancer Detection

Analyzing Temperature Distributions and Gradient Behaviors for Early-Stage Tumor Lesions in 3D Computational Model of Breast

Imaging-based internal body temperature measurements: The journal Temperature toolbox

Contact Info

Product

Resources

About