Interactive content-based image retrieval with deep learning for CT abdominal organ recognition.

Recognizing the most relevant seven organs in an abdominal computed tomography (CT) slice requires sophisticated knowledge. This study proposed automatically extracting relevant features and applying them in a content-based image retrieval (CBIR) system to provide similar evidence for clinical use.A total of 2827 abdominal CT slices, including 638 liver, 450 stomach, 229 pancreas, 442 spleen, 362 right kidney, 424 left kidney and 282 gallbladder tissues, were collected to evaluate the proposed CBIR in the present study.

Long-wavelength mid-infrared reflectors using guided-mode resonance.

We have proposed and fabricated a new mid-infrared reflector using the guided-mode resonance (GMR). The GMR reflector consists of subwavelength Ge grating on GaAs substrate with a low-refractive-index SiOx layer in between. With a total thickness of about 2 μm, a near-100% reflectivity at 8 μm has been obtained both theoretically and experimentally.