METHODS: The morphological features of the disc that is characteristic of glaucoma are clearly seen in the fundus images. However, manual inspection of the acquired fundus images may be prone to inter-observer variation. Therefore, a computer-aided detection (CAD) system is proposed to make an accurate, reliable and fast diagnosis of glaucoma based on the optic nerve features of fundus imaging. In this paper, we reviewed existing techniques to automatically diagnose glaucoma.

RESULTS: The use of CAD is very effective in the diagnosis of glaucoma and can assist the clinicians to alleviate their workload significantly. We have also discussed the advantages of employing state-of-art techniques, including deep learning (DL), when developing the automated system. The DL methods are effective in glaucoma diagnosis.

OBJECTIVES: To examine the accessibility of malignant SPNs in all segments of the lungs using either the 0.6mm or 1.4 mm probe and to assess the quality and inter observer interpretation of SPN confocal imaging obtained from either miniprobes.

METHODS: Radial(r)-EBUS was used to locate and sample the SPN. In-vivo pCLE analysis of the SPN was performed using either CholangioFlex (apical and posterior segments of the upper lobes) or AlveoFlex (other segments) introduced into the guide sheath before sampling. pCLE features were compared between the two probes.

RESULTS: Fourty-eight patients with malignant SPN were included (NCT01931579). The diagnostic accuracy for lung cancer using r-EBUS coupled with pCLE imaging was 79.2%. All the SPNs were successfully explored with either one of the probes (19 and 29 subjects for CholangioFlex and AlveoFlex, respectively). A specific solid pattern in the SPN was found in 30 pCLE explorations. Comparison between the two probes found no differences in the axial fibers thickness, cell size and specific solid pattern in the nodules. Extra-alveolar microvessel size appeared larger using CholangioFlex suggesting less compression effect. The kappa test for interobserver agreement for the identification of solid pattern was 0.74 (p = 0.001).

RESULTS: Mycobacterium smegmatis was used as a model organism to provide a proof of principle for a method to recover bacteria from a stained sample on a glass slide using a laser capture system. Ziehl-Neelsen (ZN) stained cells were excised and catapulted into tubes. Recovered cells were subjected to DNA extraction and pre-amplified with multiple displacement amplification (MDA). This system allowed a minimum of 30 catapulted cells to be detected following a nested real-time PCR assay, using rpoB specific primers. The combination of MDA and nested real-time PCR resulted in a 30-fold increase in sensitivity for the detection of low numbers of cells isolated using LCM.