Tuberculosis (TB) is one of the major global health threats especially in developing countries. Although newly diagnosed TB patients can be recovered with high cure rate, many curable TB patients in the developing countries are obliged to die because of delayed diagnosis, partly by the lack of radiography and radiologists. Therefore, developing a computer-aided diagnosis (CAD) system for TB screening can contribute to early diagnosis of TB, which results in prevention of deaths from TB. Currently, most CAD algorithms adopt carefully designed morphological features distinguishing different lesion types to improve screening performances. However, such engineered features cannot be guaranteed to be the best descriptors for TB screening. Deep learning has become a majority in machine learning society. Especially in computer vision fields, it has been verified that deep convolutional neural networks (CNN) is a very promising algorithm for various visual tasks. Since deep CNN enables end-to-end training from feature extraction to classification, it does not require objective-specific manual feature engineering. In this work, we designed CAD system based on deep CNN for automatic TB screening. Based on large-scale chest X-rays (CXRs), we achieved viable TB screening performance of 0.96, 0.93 and 0.88 in terms of AUC for three real field datasets, respectively, by exploiting the effect of transfer learning.
We present an optical system for small animal imaging that can combine various in vivo imaging modalities, including
fluorescence (intensity and lifetime), spectral, and trans-illumination imaging. This system consists of light-tight box
with ultrafast pulsed or cw laser light excitation, motorized translational and rotational stages, a telecentric lens for
detection, and a cooled CCD camera that can be coupled to an ultrafast time-gated intensifier. All components are
modular, making possible laser excitation at various wavelengths and pulse lengths, and signal detection in a variety of
ways (multimode). Results of drug nanoconjugate carrier delivery studies in mice are presented. Conventional and
spectrally-resolved fluorescence images reveal details of in vivo drug nanoconjugate carrier accumulation within the
tumor region and several organs in real time. By multi-spectral image analysis of ex vivo specimens from the same mice,
we were able to evaluate the extent and topology of drug nanoconjugate carrier distribution into specific organs and the
Multi-spectral imaging provides digital images of a scene or object at a large, usually sequential number of wavelengths,
generating precise optical spectra at every pixel. We use the term "spectral signature" for a quantitative plot of optical
property variations as a function of wavelengths. We present here intelligent spectral signature bio-imaging methods we
developed, including automatic signature selection based on machine learning algorithms and database search-based
automatic color allocations, and selected visualization schemes matching these approaches. Using this intelligent spectral
signature bio-imaging method, we could discriminate normal and aganglionic colon tissue of the Hirschsprung's disease
mouse model with over 95% sensitivity and specificity in various similarity measure methods and various anatomic
organs such as parathyroid gland, thyroid gland and pre-tracheal fat in dissected neck of the rat in vivo.
Spectral imaging has recently been introduced in the biomedical field as a noninvasive, quantitative means of studying biological tissues. Many of its potential applications have been demonstrated (in vitro and, to a lesser degree, in vivo) with the use of stains or dyes. Successful translation to the clinical environment has been largely lagging, due to safety considerations and regulatory limitations preventing use of contrast agents in humans. We report experiments showing the feasibility of high-resolution spectral imaging of breast cancer without the use of contrast agents, thus completing the continuum of translational research, to in vivo imaging that will be directly applicable in the clinical environment. Our initial work focused on image acquisition using Fourier transform microinterferometry and subsequent segmentation of both stained and unstained breast cancer slides-derived image sets. We then applied our techniques to imaging fresh unstained ex vivo specimens of rat breast cancer and sentinel lymph nodes. We also investigated multiple methods of classification to optimize our image analyses, and preliminary results for the best algorithm tested yielded an overall sensitivity of 96%, and a specificity of 92% for cancer detection. Using spectral imaging and classification techniques, we were able to demonstrate that reliable detection of breast cancer in fixed and fresh unstained specimens of breast tissue is possible.