Metastasis is the primary cause of death in breast cancer patients. Early detection of high-risk breast cancer, including micrometastasis, is critical in tailoring appropriate and effective interventional therapies. Increased fibronectin expression, a hallmark of epithelial-to-mesenchymal transition, is associated with high-risk breast cancer and metastasis. We have previously developed a penta-peptide CREKA (Cys-Arg-Glu-Lys-Ala)-targeted gadolinium-based magnetic resonance imaging (MRI) contrast agent, CREKA-Tris(Gd-DOTA)₃ (Gd-DOTA (4,7,10-tris(carboxymethyl)-1,4,7,10-tetraazacyclododecyl gadolinium), which binds to fibrin–fibronectin complexes that are abundant in the tumour microenvironment of fast-growing breast cancer. Here we assess the capability of CREKA-Tris(Gd-DOTA)₃ to detect micrometastasis with MRI in co-registration with high-resolution fluorescence cryo-imaging in female mice bearing metastatic 4T1 breast tumours. We find that CREKA-Tris(Gd-DOTA)₃ provides robust contrast enhancement in the metastatic tumours and enables the detection of micrometastases of size <0.5 mm, extending the detection limit of the current clinical imaging modalities. These results demonstrate that molecular MRI with CREKA-Tris(Gd-DOTA)₃ may facilitate early detection of high-risk breast cancer and micrometastasis in the clinic.

Intravascular optical coherence tomography (iOCT) is being used to assess viability of new coronary artery stent designs. We developed a highly automated method for detecting stent struts and measuring tissue coverage. We trained a bagged decision trees classifier to classify candidate struts using features extracted from the images. With 12 best features identified by forward selection, recall (precision) were 90%–94% (85%–90%). Including struts deemed insufficiently bright for manual analysis, precision improved to 94%. Strut detection statistics approached variability of manual analysis. Differences between manual and automatic area measurements were 0.12 ± 0.20 mm² and 0.11 ± 0.20 mm² for stent and tissue areas, respectively. With proposed algorithms, analyst time per stent should significantly reduce from the 6–16 hours now required.

We developed the Case Cryo‐imaging system that provides information rich, very high‐resolution, color brightfield, and molecular fluorescence images of a whole mouse using a section‐and‐image block‐face imaging technology. The system consists of a mouse‐sized, motorized cryo‐microtome with special features for imaging, a modified, brightfield/fluorescence microscope, and a robotic xyz imaging system positioner, all of which is fully automated by a control system. Using the robotic system, we acquired microscopic tiled images at a pixel size of 15.6 μm over the block face of a whole mouse sectioned at 40 μm, with a total data volume of 55 GB. Viewing 2D images at multiple resolutions, we identified small structures such as cardiac vessels, muscle layers, villi of the small intestine, the optic nerve, and layers of the eye. Cryo‐imaging was also suitable for imaging embryo mutants in 3D. A mouse, in which enhanced green fluorescent protein was expressed under gamma actin promoter in smooth muscle cells, gave clear 3D views of smooth muscle in the urogenital and gastrointestinal tracts. With cryo‐imaging, we could obtain 3D vasculature down to 10 μm, over very large regions of mouse brain. Software is fully automated with fully programmable imaging/sectioning protocols, email notifications, and automatic volume visualization. With a unique combination of field‐of‐view, depth of field, contrast, and resolution, the Case Cryo‐imaging system fills the gap between whole animal in vivo imaging and histology. histology. Anat Rec, 292:342–351, 2009.

Accurate identification of coronary plaque is very important for cardiologists when treating patients with advanced atherosclerosis. We developed fully-automated semantic segmentation of plaque in intravascular OCT images. We trained/tested a deep learning model on a folded, large, manually annotated clinical dataset. The sensitivities/specificities were 87.4%/89.5% and 85.1%/94.2% for pixel-wise classification of lipidous and calcified plaque, respectively. Automated clinical lesion metrics, potentially useful for treatment planning and research, compared favorably (<4%) with those derived from ground-truth labels. When we converted the results to A-line classification, they were significantly better (p < 0.05) than those obtained previously by using deep learning classifications of A-lines.

Coronary calcified plaque (CP) is both an important marker of atherosclerosis and major determinant of the success of coronary stenting. Intracoronary optical coherence tomography (OCT) with high spatial resolution can provide detailed volumetric characterization of CP. We present a semiautomatic method for segmentation and quantification of CP in OCT images. Following segmentation of the lumen, guide wire, and arterial wall, the CP was localized by edge detection and traced using a combined intensity and gradient-based level-set model. From the segmentation regions, quantification of the depth, area, angle fill fraction, and thickness of the CP was demonstrated. Validation by comparing the automatic results to expert manual segmentation of 106 in vivo images from eight patients showed an accuracy of 78±9%. For a variety of CP measurements, the bias was insignificant (except for depth measurement) and the agreement was adequate when the CP has a clear outer border and no guide-wire overlap. These results suggest that the proposed method can be used for automated CP analysis in OCT, thereby facilitating our understanding of coronary artery calcification in the process of atherosclerosis and helping guide complex interventional strategies in coronary arteries with superficial calcification.

For intravascular OCT (IVOCT) images, we developed an automated atherosclerotic plaque characterization method that used a hybrid learning approach, which combined deep-learning convolutional and hand-crafted, lumen morphological features. Processing was done on innate A-line units with labels fibrolipidic (fibrous tissue followed by lipidous tissue), fibrocalcific (fibrous tissue followed by calcification), or other. We trained/tested on an expansive data set (6,556 images), and performed an active learning, relabeling step to improve noisy ground truth labels. Conditional random field was an important post-processing step to reduce classification errors. Sensitivities/specificities were 84.8%/97.8% and 91.4%/95.7% for fibrolipidic and fibrocalcific plaques, respectively. Over lesions, en face classification maps showed automated results that agreed favorably to manually labeled counterparts. Adding lumen morphological features gave statistically significant improvement (p < 0.05), as compared to classification with convolutional features alone. Automated assessments of clinically relevant plaque attributes (arc angle and length), compared favorably to those from manual labels. Our hybrid approach gave statistically improved results as compared to previous A-line classification methods using deep learning or hand-crafted features alone. This plaque characterization approach is fully automated, robust, and promising for live-time treatment planning and research applications.