Detection and differentiation of breast cancer using neural classifiers with first warning thermal sensors

A Computational Method for the Estimation of the Geometrical and Thermophysical Properties of Tumor Using Contact Thermometry

Contact thermometry is the measurement of surface temperature using sensors in contact with the medium. These surface temperatures can be potential indicators of any abnormality possibly a tumor. This research work aims to present a computation method that makes use of contact thermometry to estimate the geometric center, size, and thermophysical properties of breast tumor. Wearable thermal sensors captured real-time surface temperature readings from discrete point locations. The continuous heat distribution over the domain was formulated using forward heat transfer analysis. The optimization method estimated tumor parameters of the breast, and a three-dimensional thermal model was developed from the estimated parameters. Laboratory experiments on breast phantoms were done to validate the estimation method. Furthermore, real-time temperature readings of human subjects were recorded, and the estimated location and size were then compared with the mammogram results. It was found that the estimated two-dimensional geometric center and the size in diameter of the tumor closely match with the mammogram results. Further, the thermophysical properties estimated using the proposed method had a higher order in subjects having a tumor making it a tool for breast cancer screening.

[Connected bras for breast cancer detection in 2021: Analysis and perspectives]

OBJECTIVES

Breast cancer is the leading cancer in women worldwide with about 2 million new cases and 685,000 deaths each year. Mammography is the most widely used screening and diagnostic method. Currently, digital technologies advances facilitate the development of connected and portable devices. To overcome some of the disadvantages of mammography (breast compression, difficulty in analyzing dense breasts, radiation, limited accessibility in some countries, etc.), portable devices, conventionally known as connected bras (CB), have been created to offer an alternative method to mammography. The objective of our review was to list all the published CBs in order to know their main characteristics, their potential indications and their possible limitations.

METHOD

A bibliographical search in the PUBMED database selecting only articles written in French or English, between 2011 and 2020, found 7 CBs under development.

RESULTS

These CBs use thermal, ultrasonic and impedance sensors. Their advantages are an absence of irradiation, an absence of breast compression and a flexibility of use (outside an X-ray cabinet). Mammary gland analysis times vary, depending on the device, between 30min and 24h. They are all connected to data transmission systems and models that analyze the results.

DISCUSSION AND CONCLUSION

These CBs are mostly still undergoing clinical validation (only [iTBra] has been evaluated in a clinical trial) and require evaluation steps that will eventually allow their future use for breast cancer detection in high-risk women, particularly in women with dense breasts and in women between screening waves.

Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction

The diagnosis of diseases is decisive for planning proper treatment and ensuring the well-being of patients. Human error hinders accurate diagnostics, as interpreting medical information is a complex and cognitively challenging task. The application of artificial intelligence (AI) can improve the level of diagnostic accuracy and efficiency. While the current literature has examined various approaches to diagnosing various diseases, an overview of fields in which AI has been applied, including their performance aiming to identify emergent digitalized healthcare services, has not yet been adequately realized in extant research. By conducting a critical review, we portray the AI landscape in diagnostics and provide a snapshot to guide future research. This paper extends academia by proposing a research agenda. Practitioners understand the extent to which AI improves diagnostics and how healthcare benefits from it. However, several issues need to be addressed before successful application of AI in disease diagnostics can be achieved.

SurvNet: A Novel Deep Neural Network for Lung Cancer Survival Analysis With Missing Values

Survival analysis is important for guiding further treatment and improving lung cancer prognosis. It is a challenging task because of the poor distinguishability of features and the missing values in practice. A novel multi-task based neural network, SurvNet, is proposed in this paper. The proposed SurvNet model is trained in a multi-task learning framework to jointly learn across three related tasks: input reconstruction, survival classification, and Cox regression. It uses an input reconstruction mechanism cooperating with incomplete-aware reconstruction loss for latent feature learning of incomplete data with missing values. Besides, the SurvNet model introduces a context gating mechanism to bridge the gap between survival classification and Cox regression. A new real-world dataset of 1,137 patients with IB-IIA stage non-small cell lung cancer is collected to evaluate the performance of the SurvNet model. The proposed SurvNet achieves a higher concordance index than the traditional Cox model and Cox-Net. The difference between high-risk and low-risk groups obtained by SurvNet is more significant than that of high-risk and low-risk groups obtained by the other models. Moreover, the SurvNet outperforms the other models even though the input data is randomly cropped and it achieves better generalization performance on the Surveillance, Epidemiology, and End Results Program (SEER) dataset.

Breast tumor parameter estimation and interactive 3D thermal tomography using discrete thermal sensor data

This work uses a simple low-cost wearable device embedded with discrete thermal sensors to map the breast skin surface temperature. A methodology has been developed to estimate diameter, blood perfusion, metabolic heat generation and location in X, Y, Z coordinate of tumor from this discrete set of data. An interactive 3D thermal tomography was developed which provides a detailed 3D thermal view of the breast anatomy. Using this system, the user can interactively rotate and slice the 3D thermal image of the breast for a detailed study of the tumor. Finite element method (FEM) and an evolution-based inverse method were used for the parameter estimation. The method was first validated using phantom experiments and the results obtained were within an error of 10% (0.005 W cm^-3) for heat generation and 15% (0.3 cm) for heater location. Further validation was carried out through clinical trials on 60 human subjects. Estimated blood perfusion rate and metabolic heat generation rate exhibit distinguishable difference between cancerous and non-cancerous breast. Estimated diameter and location of tumor in cancerous breast shows good agreement with the actual clinical reports. We have obtained a sensitivity of 82.78% and specificity of 87.09%. Proposed breast tumor parameter estimation methodology with interactive 3D thermal tomography is a good screening tool for breast cancer detection and also useful for clinicians to find out location including depth.

An introduction to the Cyrcadia Breast Monitor: A wearable breast health monitoring device

BACKGROUND

The most common breast cancer detection modalities are generally limited by radiation exposure, discomfort, high costs, inter-observer variabilities in image interpretation, and low sensitivity in detecting cancer in dense breast tissue. Therefore, there is a clear need for an affordable and effective adjunct modality that can address these limitations. The Cyrcadia Breast Monitor (CBM) is a non-invasive, non-compressive, and non-radiogenic wearable device developed as an adjunct to current modalities to assist in the detection of breast tissue abnormalities in any type of breast tissue.

METHODS

The CBM records thermodynamic metabolic data from the breast skin surface over a period of time using two wearable biometric patches consisting of eight sensors each and a data recording device. The acquired multi-dimensional temperature time series data are analyzed to determine the presence of breast tissue abnormalities. The objective of this paper is to present the scientific background of CBM and also to describe the history around the design and development of the technology.

RESULTS

The results of using the CBM device in the initial clinical studies are also presented. Twenty four-hour long breast skin temperature circadian rhythm data was collected from 93 benign and 108 malignant female study subjects in the initial clinical studies. The predictive model developed using these datasets could differentiate benign and malignant lesions with 78% accuracy, 83.6% sensitivity and 71.5% specificity. A pilot study of 173 female study subjects is underway, in order to validate this predictive model in an independent test population.

CONCLUSIONS

The results from the initial studies indicate that the CBM may be valuable for breast health monitoring under physician supervision for confirmation of any abnormal changes, potentially prior to other methods, such as, biopsies. Studies are being conducted and planned to validate the technology and also to evaluate its ability as an adjunct breast health monitoring device for identifying abnormalities in difficult-to-diagnose dense breast tissue.

Biosensors for Personal Mobile Health: A System Architecture Perspective

Advances in mobile biosensors, integrating developments in materials science and instrumentation, are fueling an expansion in health data being collected and analyzed in decentralized settings. For example, semiconductor-based sensors are enabling measurement of vital signs, and microfluidic-based sensors are enabling measurement of biochemical markers. As biosensors for mobile health are becoming increasingly paired with smart devices, it will become critical for researchers to design biosensors - with appropriate functionalities and specifications - to work seamlessly with accompanying connected hardware and software. This article describes recent research in biosensors, as well as current mobile health devices in use, as classified into four distinct system architectures that take into account the biosensing and data processing functions required in personal mobile health devices. We also discuss the path forward for integrating biosensors into smartphone-based mobile health devices.

Breast Cancer Identification via Thermography Image Segmentation with a Gradient Vector Flow and a Convolutional Neural Network

Breast cancer is the most common cancer among women worldwide with about half a million cases reported each year. Mammary thermography can offer early diagnosis at low cost if adequate thermographic images of the breasts are taken. The identification of breast cancer in an automated way can accelerate many tasks and applications of pathology. This can help complement diagnosis. The aim of this work is to develop a system that automatically captures thermographic images of breast and classifies them as normal and abnormal (without cancer and with cancer). This paper focuses on a segmentation method based on a combination of the curvature function k and the gradient vector flow, and for classification, we proposed a convolutional neural network (CNN) using the segmented breast. The aim of this paper is to compare CNN results with other classification techniques. Thus, every breast is characterized by its shape, colour, and texture, as well as left or right breast. These data were used for training as well as to compare the performance of CNN with three classification techniques: tree random forest (TRF), multilayer perceptron (MLP), and Bayes network (BN). CNN presents better results than TRF, MLP, and BN.