American Cancer Society estimates that in 2021 nearly 300,000 women in the United States will be diagnosed with invasive breast cancer, and about 43,600 women will die from breast cancer. While many have access to health care and cancer screening, women from rural or underdeveloped communities often have limited access. Therefore, there is a need for an inexpensive and easy-to-use breast cancer identification device, which can be employed in small clinics to provide support to primary care physicians. This work aims to develop a method to characterize breast tumors and tissue using non-invasive imaging modalities. The proposed bimodal imaging system has tactile and multispectral imaging capabilities. Tactile imaging modality characterizes tumors by esti-mating their depth, size, and stiffness, along with the Tactile Index. Multispectral imaging modality identifies breast asymmetry, texture, and inflammation changes, together with the Spectral Index. These indices are combined with the BCRAT Index, the risk score devel¬oped by the National Institute of Health, to form the Multimodal Index for personalized breast cancer risk assessment. In this study, we will describe the development of the bimodal imaging system. We will present the algorithms for tactile and multispectral modalities. Tactile and Multispec¬tral Profile Diagrams are developed to capture broad imaging signals in a compact and application-specific way. A Tactile Profile Diagram is a pictorial representation of the rel¬ative depth, size, and stiffness of the imaged tumor. A Multispectral Profile Diagram is a representative pattern image for breast tissue superficial optical properties. To classify the profile diagrams, we employ the Convolutional Neural Network deep learning method. We will describe the results of the experiments conducted using tissue-mimicking phan¬toms and human in-vivo experiments. The results demonstrate the ability of the method to classify and quantify tumor and tissue characteristics. Finally, we describe the method to calculate Multimodal Index for the malignancy risk assessment via tactile and multispectral imaging modalities and the risk probability based on the health records. / Electrical and Computer Engineering

Breast cancer is the most common cancer and the second most common cause of cancer death in women. In 2008 there were 182,460 women diagnosed with breast cancer, and 40,480 women died of this disease. Breast cancer can be prevented by medical (tamoxifen or raloxifene) or surgical approaches (bilateral mastectomy or oophorectomy). Prevention is only recommended for women at high risk for developing breast cancer; therefore, proper risk calculation is essential in identifying women that may benefit from prevention measures. There is an easy-to-use and easily accessible risk calculation tool for determining a woman's risk of developing breast cancer and need for referral for counseling, gene testing, and possibly preventive therapy. This article reviews the components of risk assessment, the most frequently used risk calculation tool, and approaches to breast cancer risk reduction including medical and surgical therapies. The use of these therapies results in a risk reduction of 50-90%.

Many medical devices have been shifting to personal platforms such as smartphones due to its ubiquitous availability, variety of included sensors, robust communication, and user-friendliness. By utilizing smartphones as a medical sensing device should improve the early detection of abnormalities and the long-term monitoring of health conditions. Tissue abnormalities will be detected by touch sensation due to mechanical property changes within the tissue. However, touch sensation is unquantifiable and subjective. We integrate the smartphone with a tactile sensor to build a portable and personalized tissue assessment device based on changes in mechanical properties. The Smartphone Tactile Imaging Probe (STIP) is developed to quantify the mechanical properties of the tissue. The proposed system has a dual-sensing mode: compression-based sensing (STIP-C) and indentation-based sensing (STIP-I). STIP–C is designed to detect and measure the size and hardness of the inclusion. It assesses mechanical property changes caused by the tumor inside the tissue. STIP–I is designed to measure the pitting parameters and viscoelastic properties of the tissue. This system will assess the viscoelasticity changes caused by fluid retention within the tissue. STIP estimates mechanical and viscoelastic behavior changes in the tissue and provides the risk evaluation of an underlying health problem. Breast cancer risk assessment and edema severity level classification are the main applications of STIP. We estimate the breast cancer risk by incorporating the patient’s personal risk value into the STIP-C data associated with the tumor mechanical properties to improve the risk assessment accuracy. To classify the edema severity level, the STIP-I measures the pitting parameters and viscoelastic properties of the tissue. From these parameters, we build a Viscoelastic Pitting Recovery (VPR) model. The model illustrates the changes in tissue viscoelastic behavior associated with the edema severity level. Using the VPR model, we use the thresholding method to classify the edema cases. We also developed customized phantoms representing the different amounts of fluid retention in the tissue. The experimental result found a relationship between the amounts of pitted depth from STIP-I and the fluid amount of a phantom. In this dissertation, we developed and tested a portable tissue mechanical property estimation system. The interchangeable dual-mode STIP sensing probe and risk assessment methods were developed for the breast tumor malignancy and edema severity applications. / Electrical and Computer Engineering