A multi-stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four-view mammograms.

BACKGROUND: Developing computer aided diagnosis (CAD) schemes of mammograms to classify between malignant and benign breast lesions has attracted a lot of research attention over the last several decades. However, unlike radiologists who make diagnostic decisions based on the fusion of image features extracted from multi-view mammograms, most CAD schemes are single-view-based schemes, which limit CAD performance and clinical utility. PURPOSE: This study aims to develop and test a novel CAD framework that optimally fuses information extracted from ipsilateral views of bilateral mammograms using both deep transfer learning (DTL) and radiomics feature extraction methods. METHODS: An image dataset containing 353 benign and 611 malignant cases is assembled. Each case contains four images: the craniocaudal (CC) and mediolateral oblique (MLO) view of the left and right breast. First, we extract four matching regions of interest (ROIs) from images that surround centers of two suspicious lesion regions seen in CC and MLO views, as well as matching ROIs in the contralateral breasts. Next, the handcrafted radiomics (HCRs) features and VGG16 model-generated automated features are extracted from each ROI resulting in eight feature vectors. Then, after reducing feature dimensionality and quantifying the bilateral and ipsilateral asymmetry of four ROIs to yield four new feature vectors, we test four fusion methods to build three support vector machine (SVM) classifiers by an optimal fusion of asymmetrical image features extracted from four view images. RESULTS: Using a 10-fold cross-validation method, results show that a SVM classifier trained using an optimal fusion of four view images yields the highest classification performance (AUC = 0.876 ± 0.031), which significantly outperforms SVM classifiers trained using one projection view alone, AUC = 0.817 ± 0.026 and 0.792 ± 0.026 for the CC and MLO view of bilateral mammograms, respectively (p < 0.001). CONCLUSIONS: The study demonstrates that the shift from single-view CAD to four-view CAD and the inclusion of both DTL and radiomics features significantly increases CAD performance in distinguishing between malignant and benign breast lesions.

Quantifying Intracellular Nanoparticle Distributions with Three-Dimensional Super-Resolution Microscopy.

Super-resolution microscopy can transform our understanding of nanoparticle-cell interactions. Here, we established a super-resolution imaging technology to visualize nanoparticle distributions inside mammalian cells. The cells were exposed to metallic nanoparticles and then embedded within different swellable hydrogels to enable quantitative three-dimensional (3D) imaging approaching electron-microscopy-like resolution using a standard light microscope. By exploiting the nanoparticles' light scattering properties, we demonstrated quantitative label-free imaging of intracellular nanoparticles with ultrastructural context. We confirmed the compatibility of two expansion microscopy protocols, protein retention and pan-expansion microscopy, with nanoparticle uptake studies. We validated relative differences between nanoparticle cellular accumulation for various surface modifications using mass spectrometry and determined the intracellular nanoparticle spatial distribution in 3D for entire single cells. This super-resolution imaging platform technology may be broadly used to understand the nanoparticle intracellular fate in fundamental and applied studies to potentially inform the engineering of safer and more effective nanomedicines.

Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction.

Breast cancer remains the most diagnosed cancer in women. Advances in medical imaging modalities and technologies have greatly aided in the early detection of breast cancer and the decline of patient mortality rates. However, reading and interpreting breast images remains difficult due to the high heterogeneity of breast tumors and fibro-glandular tissue, which results in lower cancer detection sensitivity and specificity and large inter-reader variability. In order to help overcome these clinical challenges, researchers have made great efforts to develop computer-aided detection and/or diagnosis (CAD) schemes of breast images to provide radiologists with decision-making support tools. Recent rapid advances in high throughput data analysis methods and artificial intelligence (AI) technologies, particularly radiomics and deep learning techniques, have led to an exponential increase in the development of new AI-based models of breast images that cover a broad range of application topics. In this review paper, we focus on reviewing recent advances in better understanding the association between radiomics features and tumor microenvironment and the progress in developing new AI-based quantitative image feature analysis models in three realms of breast cancer: predicting breast cancer risk, the likelihood of tumor malignancy, and tumor response to treatment. The outlook and three major challenges of applying new AI-based models of breast images to clinical practice are also discussed. Through this review we conclude that although developing new AI-based models of breast images has achieved significant progress and promising results, several obstacles to applying these new AI-based models to clinical practice remain. Therefore, more research effort is needed in future studies.

Improving mammography lesion classification by optimal fusion of handcrafted and deep transfer learning features.

Objective.Handcrafted radiomics features or deep learning model-generated automated features are commonly used to develop computer-aided diagnosis schemes of medical images. The objective of this study is to test the hypothesis that handcrafted and automated features contain complementary classification information and fusion of these two types of features can improve CAD performance.Approach.We retrospectively assembled a dataset involving 1535 lesions (740 malignant and 795 benign). Regions of interest (ROI) surrounding suspicious lesions are extracted and two types of features are computed from each ROI. The first one includes 40 radiomic features and the second one includes automated features computed from a VGG16 network using a transfer learning method. A single channel ROI image is converted to three channel pseudo-ROI images by stacking the original image, a bilateral filtered image, and a histogram equalized image. Two VGG16 models using pseudo-ROIs and 3 stacked original ROIs without pre-processing are used to extract automated features. Five linear support vector machines (SVM) are built using the optimally selected feature vectors from the handcrafted features, two sets of VGG16 model-generated automated features, and the fusion of handcrafted and each set of automated features, respectively.Main Results.Using a 10-fold cross-validation, the fusion SVM using pseudo-ROIs yields the highest lesion classification performance with area under ROC curve (AUC = 0.756 ± 0.042), which is significantly higher than those yielded by other SVMs trained using handcrafted or automated features only (p < 0.05).Significance.This study demonstrates that both handcrafted and automated futures contain useful information to classify breast lesions. Fusion of these two types of features can further increase CAD performance.

Improved pentamethine cyanine nanosensors for optoacoustic imaging of pancreatic cancer.

Optoacoustic imaging is a new biomedical imaging technology with clear benefits over traditional optical imaging and ultrasound. While the imaging technology has improved since its initial development, the creation of dedicated contrast agents for optoacoustic imaging has been stagnant. Current exploration of contrast agents has been limited to standard commercial dyes that have already been established in optical imaging applications. While some of these compounds have demonstrated utility in optoacoustic imaging, they are far from optimal and there is a need for contrast agents with tailored optoacoustic properties. The synthesis, encapsulation within tumor targeting silica nanoparticles and applications in in vivo tumor imaging of optoacoustic contrast agents are reported.

Molecular Imaging of Inflammatory Disease.

Inflammatory diseases include a wide variety of highly prevalent conditions with high mortality rates in severe cases ranging from cardiovascular disease, to rheumatoid arthritis, to chronic obstructive pulmonary disease, to graft vs. host disease, to a number of gastrointestinal disorders. Many diseases that are not considered inflammatory per se are associated with varying levels of inflammation. Imaging of the immune system and inflammatory response is of interest as it can give insight into disease progression and severity. Clinical imaging technologies such as computed tomography (CT) and magnetic resonance imaging (MRI) are traditionally limited to the visualization of anatomical information; then, the presence or absence of an inflammatory state must be inferred from the structural abnormalities. Improvement in available contrast agents has made it possible to obtain functional information as well as anatomical. In vivo imaging of inflammation ultimately facilitates an improved accuracy of diagnostics and monitoring of patients to allow for better patient care. Highly specific molecular imaging of inflammatory biomarkers allows for earlier diagnosis to prevent irreversible damage. Advancements in imaging instruments, targeted tracers, and contrast agents represent a rapidly growing area of preclinical research with the hopes of quick translation to the clinic.

The neutral red assay can be used to evaluate cell viability during autophagy or in an acidic microenvironment in vitro.

Harsh conditions within the tumor microenvironment, such as hypoxia and extracellular acidic pH (pHe), inactivate some chemotherapies, which results in limited or no cytotoxicity. Standard MTT, ATPlite and protease assays that are used to determine the potency of newly developed drugs often give erroneous results when applied under hypoxic or acidic conditions. Therefore, development of a cytotoxicity assay that does not yield false positive or false negative results under circumstances of both hypoxia and acidic pHe is needed. We evaluated currently used cell viability assays as well as neutral red staining to assess viability of ovarian and pancreatic cancer cells grown in an acidic pHe microenvironment after treatment with carboplatin, gemcitabine or chloroquine. We validated cell viability using western blotting of pro-caspase-9 and cleaved-caspase-9, and LC3-I and - II. Standard cell viability assays indicated cell viability accurately at pHe 7.4, but was not correlated with induction of apoptosis or autophagy at acidic pHe. By contrast, our modified neutral red assay detected cell viability accurately over a range of pHe as demonstrated by its correlation with induction of apoptosis and autophagy. Neutral red staining is effective for evaluating the effect of chemotherapeutic agents on cell viability under acidic pHe or hypoxic conditions.

Development of Multispectral Optoacoustic Tomography as a Clinically Translatable Modality for Cancer Imaging.

The use of optoacoustic imaging takes advantage of the photoacoustic effect to generate high-contrast, high-resolution medical images at penetration depths of up to 5 cm. Multispectral optoacoustic tomography (MSOT) is a type of optoacoustic imaging system that has seen promising preclinical success with a recent emergence into the clinic. Multiwavelength illumination of tissue allows for the mapping of multiple chromophores, which are generated endogenously or exogenously. However, translation of MSOT to the clinic is still in its preliminary stages. For successful translation, MSOT requires refinement of probes and data-acquisition systems to tailor to the human body, along with more intuitive, real-time visualization settings. The possibilities of optoacoustic imaging, namely MSOT, in the clinic are reviewed here. ©RSNA, 2020.

Imaging Inflammation and Infection in the Gastrointestinal Tract.

A variety of seemingly non-specific symptoms manifest within the gastrointestinal (GI) tract, particularly in the colon, in response to inflammation, infection, or a combination thereof. Differentiation between symptom sources can often be achieved using various radiologic studies. Although it is not possible to provide a comprehensive survey of imaging gastrointestinal GI tract infections in a single article, the purpose of this review is to survey several topics on imaging of GI tract inflammation and infections. The review discusses such modalities as computed tomography, positron emission tomography, ultrasound, endoscopy, and magnetic resonance imaging while looking at up-an-coming technologies that could improve diagnoses and patient comfort. The discussion is accomplished through examining a combination of organ-based and organism-based approaches, with accompanying selected case examples. Specific focus is placed on the bacterial infections caused by Shigella spp., Escherichia coli, Clostridium difficile, Salmonella, and inflammatory conditions of diverticulitis and irritable bowel disease. These infectious and inflammatory diseases and their detection via molecular imaging will be compared including the appropriate differential diagnostic considerations.

GABAergic signaling in young granule cells in the adult rat and mouse dentate gyrus.

Throughout most of the developing brain, including the hippocampus, GABAergic synapses are the first to become functional. Several features of GABAergic signaling change across development, suggesting that this signaling in the immature brain may play important roles in the growth of young neurons and the establishment of networks. To determine whether GABA(A) receptor (GABA(A)R)-containing synapses in new neurons born in the adult dentate gyrus have similar immature features, we examined spontaneous and evoked GABA(A)R-mediated synaptic currents in young (POMC-EGFP or doublecortin-immunostained) granule cells in acute slice preparations from adult mice and rats. Spontaneous inhibitory postsynaptic currents (IPSCs) were observed in nearly all immature granule cells, but their frequency was considerably lower and their decay time constant was nearly two times longer than in neighboring mature (doublecortin-non-immunoreactive or EGFP-non-expressing) granule cells within the sub-granular zone. Evoked IPSCs (eIPSCs) in mature granule cells, but not immature granule cells, were sensitive to zolpidem, suggesting a maturational increase in GABA(A)R alpha1-subunit expression. Perforated-patch recording revealed that eIPSCs depolarized young neurons, but hyperpolarized mature neurons. The early establishment of synaptic GABAergic inputs slow IPSC decay time, and depolarizing action of eIPSCs are remarkably similar to features previously seen in neurons during development, suggesting that they are intrinsic features of immature neurons and not functions of the surrounding circuitry. These developmental features in adult-born granule cells could play a role in maturational processes such as developmental cell death. However, treatment of adult mice with GABA(A)R agonists and an inverse agonist did not significantly alter the number of 4- to 14-day-old BrdU-labeled cells.