Assessment of Hypoxia in Breast Cancer: Emerging Functional MR Imaging and Spectroscopy Techniques and Clinical Applications.

Breast cancer is one of the most prevalent forms of cancer affecting women worldwide. Hypoxia, a condition characterized by insufficient oxygen supply in tumor tissues, is closely associated with tumor aggressiveness, resistance to therapy, and poor clinical outcomes. Accurate assessment of tumor hypoxia can guide treatment decisions, predict therapy response, and contribute to the development of targeted therapeutic interventions. Over the years, functional magnetic resonance imaging (fMRI) and magnetic resonance spectroscopy (MRS) techniques have emerged as promising noninvasive imaging options for evaluating hypoxia in cancer. Such techniques include blood oxygen level-dependent (BOLD) MRI, oxygen-enhanced MRI (OE) MRI, chemical exchange saturation transfer (CEST) MRI, and proton MRS (1H-MRS). These may help overcome the limitations of the routinely used dynamic contrast-enhanced (DCE) MRI and diffusion-weighted imaging (DWI) techniques, contributing to better diagnosis and understanding of the biological features of breast cancer. This review aims to provide a comprehensive overview of the emerging functional MRI and MRS techniques for assessing hypoxia in breast cancer, along with their evolving clinical applications. The integration of these techniques in clinical practice holds promising implications for breast cancer management. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research.

Artificial intelligence (AI) has the potential to bring transformative improvements to the field of radiology; yet, there are barriers to widespread clinical adoption. One of the most important barriers has been access to large, well-annotated, widely representative medical image datasets, which can be used to accurately train AI programs. Creating such datasets requires time and expertise and runs into constraints around data security and interoperability, patient privacy, and appropriate data use. Recognizing these challenges, several institutions have started curating and providing publicly available, high-quality datasets that can be accessed by researchers to advance AI models. The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. Despite being an emerging field, a simple internet search for open MRI datasets presents an overwhelming number of results. Therefore, we decided to create a survey of the major publicly accessible MRI datasets in different subfields of radiology (brain, body, and musculoskeletal), and list the most important features of value to the AI researcher. To complete this review, we searched for publicly available MRI datasets and assessed them based on several parameters (number of subjects, demographics, area of interest, technical features, and annotations). We reviewed 110 datasets across sub-fields with 1,686,245 subjects in 12 different areas of interest ranging from spine to cardiac. This review is meant to serve as a reference for researchers to help spur advancements in the field of AI for radiology. LEVEL OF EVIDENCE: Level 4 TECHNICAL EFFICACY: Stage 6.

Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model.

OBJECTIVES: The aim of the study is to develop and evaluate the performance of a deep learning (DL) model to triage breast magnetic resonance imaging (MRI) findings in high-risk patients without missing any cancers. MATERIALS AND METHODS: In this retrospective study, 16,535 consecutive contrast-enhanced MRIs performed in 8354 women from January 2013 to January 2019 were collected. From 3 New York imaging sites, 14,768 MRIs were used for the training and validation data set, and 80 randomly selected MRIs were used for a reader study test data set. From 3 New Jersey imaging sites, 1687 MRIs (1441 screening MRIs and 246 MRIs performed in recently diagnosed breast cancer patients) were used for an external validation data set. The DL model was trained to classify maximum intensity projection images as "extremely low suspicion" or "possibly suspicious." Deep learning model evaluation (workload reduction, sensitivity, specificity) was performed on the external validation data set, using a histopathology reference standard. A reader study was performed to compare DL model performance to fellowship-trained breast imaging radiologists. RESULTS: In the external validation data set, the DL model triaged 159/1441 of screening MRIs as "extremely low suspicion" without missing a single cancer, yielding a workload reduction of 11%, a specificity of 11.5%, and a sensitivity of 100%. The model correctly triaged 246/246 (100% sensitivity) of MRIs in recently diagnosed patients as "possibly suspicious." In the reader study, 2 readers classified MRIs with a specificity of 93.62% and 91.49%, respectively, and missed 0 and 1 cancer, respectively. On the other hand, the DL model classified MRIs with a specificity of 19.15% and missed 0 cancers, highlighting its potential use not as an independent reader but as a triage tool. CONCLUSIONS: Our automated DL model triages a subset of screening breast MRIs as "extremely low suspicion" without misclassifying any cancer cases. This tool may be used to reduce workload in standalone mode, to shunt low suspicion cases to designated radiologists or to the end of the workday, or to serve as base model for other downstream AI tools.

Deep learning in breast imaging.

Millions of breast imaging exams are performed each year in an effort to reduce the morbidity and mortality of breast cancer. Breast imaging exams are performed for cancer screening, diagnostic work-up of suspicious findings, evaluating extent of disease in recently diagnosed breast cancer patients, and determining treatment response. Yet, the interpretation of breast imaging can be subjective, tedious, time-consuming, and prone to human error. Retrospective and small reader studies suggest that deep learning (DL) has great potential to perform medical imaging tasks at or above human-level performance, and may be used to automate aspects of the breast cancer screening process, improve cancer detection rates, decrease unnecessary callbacks and biopsies, optimize patient risk assessment, and open up new possibilities for disease prognostication. Prospective trials are urgently needed to validate these proposed tools, paving the way for real-world clinical use. New regulatory frameworks must also be developed to address the unique ethical, medicolegal, and quality control issues that DL algorithms present. In this article, we review the basics of DL, describe recent DL breast imaging applications including cancer detection and risk prediction, and discuss the challenges and future directions of artificial intelligence-based systems in the field of breast cancer.

Portable, handheld, and affordable blood perfusion imager for screening of subsurface cancer in resource-limited settings.

Precise information on localized variations in blood circulation holds the key for noninvasive diagnostics and therapeutic assessment of various forms of cancer. While thermal imaging by itself may provide significant insights on the combined implications of the relevant physiological parameters, viz. local blood perfusion and metabolic balance due to active tumors as well as the ambient conditions, knowledge of the tissue surface temperature alone may be somewhat inadequate in distinguishing between some ambiguous manifestations of precancer and cancerous lesions, resulting in compromise of the selectivity in detection. This, along with the lack of availability of a user-friendly and inexpensive portable device for thermal-image acquisition, blood perfusion mapping, and data integration acts as a deterrent against the emergence of an inexpensive, contact-free, and accurate in situ screening and diagnostic approach for cancer detection and management. Circumventing these constraints, here we report a portable noninvasive blood perfusion imager augmented with machine learning-based quantitative analytics for screening precancerous and cancerous traits in oral lesions, by probing the localized alterations in microcirculation. With a proven overall sensitivity >96.66% and specificity of 100% as compared to gold-standard biopsy-based tests, the method successfully classified oral cancer and precancer in a resource-limited clinical setting in a double-blinded patient trial and exhibited favorable predictive capabilities considering other complementary modes of medical image analysis as well. The method holds further potential to achieve contrast-free, accurate, and low-cost diagnosis of abnormal microvascular physiology and other clinically vulnerable conditions, when interpreted along with complementary clinically evidenced decision-making perspectives.

A portable spinning disc for complete blood count (CBC).

Complete Blood Count (CBC) is a collection of the most commonly required clinical tests to assess the manifestations of pathological conditions in blood. The existing clinical methods for this test are prohibitively expensive for the underprivileged global population due to the requirements of sophisticated instrumentation and trained personnel. To overcome these, we propose a unique low cost device as a blood cell counting platform. The method exploits the difference in densities of cells for separation in transparent microfluidic channels and implements label-free imaging method for counting the separated cells within the microfluidic disc. The device is a simple spinning disc to estimate the parameters such as hematocrit, hemoglobin, red blood cell (RBC), white blood cell (WBC), and platelet counts with an accuracy > 95% as compared to an automated hematology analyzer. The major advantages of this device over state of the art include multiple sample testing within a single biodegradable disc, simple design and fabrication techniques, potential automation thereby making it portable and eliminating the need of trained personnel, and most significantly, eliminating any need for downstream processing of the separated blood. These results may turn out to be of immense consequence towards developing novel point-of-care hematological analyzers for resource-constrained settings.

Can spherical eukaryotic microalgae cells be treated as optically homogeneous?

This study aims to answer the question of whether spherical unicellular photoautotrophic eukaryotic microalgae cells, consisting of various intracellular compartments with their respective optical properties, can be modeled as homogeneous spheres with some effective complex index of refraction. The spectral radiation characteristics in the photosynthetically active region of a spherical heterogeneous microalgae cell, representative of Chlamydomonas reinhardtii and consisting of spherical compartments corresponding to the cell wall, cytoplasm, chloroplast, nucleus, and mitochondria, were estimated using the superposition T-matrix method. The effects of the presence of intracellular lipids and/or starch accumulation caused by stresses, such as nitrogen limitation, were explored. Predictions by the T-matrix method were qualitatively and quantitatively consistent with experimental measurements for various microalgae species. The volume-equivalent homogeneous sphere approximation with volume-averaged effective complex index of refraction gave accurate estimates of the spectral (i) absorption and (ii) scattering cross sections of the heterogeneous cells under both nitrogen-replete and nitrogen-limited conditions. In addition, the effect of a strongly refracting cell wall, representative of Chlorella vulgaris, was investigated. In this case, for the purpose of predicting their integral radiation characteristics, the microalgae should be represented as a coated sphere with a coating corresponding to the cell wall and a homogeneous core with volume-averaged complex index of refraction for the rest of the cell. However, both homogeneous sphere and coated sphere approximations predicted strong resonances in the scattering phase function and spectral backscattering cross section that were not observed in that of the heterogeneous cells.

Thermal analysis of induced damage to the healthy cell during RFA of breast tumor.

Effective pre-clinical computational modeling strategies have been demonstrated in this article to enable risk free clinical application of radiofrequency ablation (RFA) of breast tumor. The present study (a) determines various optimal regulating parameters required for RFA of tumor and (b) introduces an essential clinical monitoring scheme to minimize the extent of damage to the healthy cell during RFA of tumor. The therapeutic capabilities offered by RFA of breast tumor, viz., the rise in local temperature and induced thermal damage have been predicted by integrating the bioheat transfer model, the electric field distribution model and the thermal damage model. The mathematical model has been validated with the experimental results available in the literature. The results revealed that, the effective damage of tumor volume sparing healthy tissue essentially depends on the voltage, the exposure time, the local heat distribution, the tumor stage and the electrode geometric configuration. It has been confirmed that, the assessment of damage front can accurately determine the extent of damage as compared to the thermal front. The study further evaluates the damaged healthy and tumor volumes due to RFA of different stages of breast cancer. The assessment of cell survival and damage fractions discloses the propensity of reappearance/healing of tumor cells after treatment.

Simple and accurate expressions for diffuse reflectance of semi-infinite and two-layer absorbing and scattering media: erratum.

A previous paper [Appl. Opt.48, 6670 (2009)] presented analytical expressions for the diffuse reflectance of semi-infinite homogeneous and two-layer refracting, absorbing, and anisotropically scattering media exposed to normal and collimated light. It also reported various regression coefficients associated with the analytical expressions obtained by fitting the diffuse reflectance predicted from Monte Carlo (MC) simulations. Although the formulation and the MC simulation results were correct, the values of some regression coefficients were erroneously reported. This erratum points out the error in the original paper and reports the correct values. It also presents alternative expressions for when the medium has an index of refraction of 1.44, corresponding to the human skin in the visible portion of the spectrum.

Suitability of frequency modulated thermal wave imaging for skin cancer detection-A theoretical prediction.

A theoretical study on the quantification of surface thermal response of cancerous human skin using the frequency modulated thermal wave imaging (FMTWI) technique has been presented in this article. For the first time, the use of the FMTWI technique for the detection and the differentiation of skin cancer has been demonstrated in this article. A three dimensional multilayered skin has been considered with the counter-current blood vessels in individual skin layers along with different stages of cancerous lesions based on geometrical, thermal and physical parameters available in the literature. Transient surface thermal responses of melanoma during FMTWI of skin cancer have been obtained by integrating the heat transfer model for biological tissue along with the flow model for blood vessels. It has been observed from the numerical results that, flow of blood in the subsurface region leads to a substantial alteration on the surface thermal response of the human skin. The alteration due to blood flow further causes a reduction in the performance of the thermal imaging technique during the thermal evaluation of earliest melanoma stages (small volume) compared to relatively large volume. Based on theoretical study, it has been predicted that the method is suitable for detection and differentiation of melanoma with comparatively large volume than the earliest development stages (small volume). The study has also performed phase based image analysis of the raw thermograms to resolve the different stages of melanoma volume. The phase images have been found to be clearly individuate the different development stages of melanoma compared to raw thermograms.

Thermographic evaluation of early melanoma within the vascularized skin using combined non-Newtonian blood flow and bioheat models.

A theoretical study on vascularized skin model to predict the thermal evaluation criteria of early melanoma using the dynamic thermal imaging technique is presented in this article. Thermographic evaluation of melanoma has been carried out during the thermal recovery of skin from undercooled condition. During thermal recovery, the skin has been exposed to natural convection, radiation, and evaporation. The thermal responses of melanoma have been evaluated by integrating the bioheat model for multi-layered skin with the momentum as well as energy conservation equations for blood flow. Differential changes in the surface thermal response of various melanoma stages except that of the early stage have been determined. It has been predicted that the thermal response due to subsurface blood flow overpowers the response of early melanoma. Hence, the study suggests that the quantification of early melanoma diagnosis using thermography has not reached a matured stage yet. Therefore, the study presents a systematic analysis of various intermediate melanoma stages to determine the thermal evaluation criteria of early melanoma. The comprehensive modeling effort made in this work supports the prediction of the disease outcome and relates the thermal response with the variation in patho-physiological, thermal and geometrical parameters.