Dense pixel matching between unrectified and distorted images using dynamic programming

In this paper, a novel framework for dense pixel matching based on dynamic programming is introduced. Unlike most techniques proposed in the literature, our approach assumes neither known camera geometry nor the availability of rectified images. Under such conditions, the matching task cannot be reduced to finding correspondences between a pair of scanlines. We propose to extend existing dynamic programming methodologies to a larger dimensional space by using a 3D scoring matrix so that correspondences between a line and a whole image can be calculated. After assessing our framework on a standard evaluation dataset of rectified stereo images, experiments are conducted on unrectified and non-linearly distorted images. Results validate our new approach and reveal the versatility of our algorithm.

Reversal of optic disc cupping after glaucoma surgery analyzed with a scanning laser tomograph

Objective: To detect and quantitate changes in optic nerve morphology after glaucoma surgery using the Heidelberg Retina Tomograph (HRT, Heidelberg Instruments, Heidelberg, Germany). Design: Nonconsecutive observational case series. Participants and Intervention: The authors prospectively enrolled 21 adult patients undergoing incisional glaucoma surgery for progressive glaucoma damage. Quantitative analysis of the optic nerve head by scanning laser tomography and automated perimetry were performed before and after glaucoma surgery. Main Outcome Measures: Changes in optic nerve parameters were subjected to linear regression analysis with respect to percent of postoperative reduction of intraocular pressure (IOP), as well as with respect to age, refraction, preoperative cup:disc ratio, and change in visual field parameters. Results: Seventeen patients had pre- and postoperative images suitable for analysis. Mean IOP at the time of image acquisition before surgery was 30.5 ± 12 mmHg, and after surgery 11.8 ± 5.2 mmHg (mean follow-up, 26 ± 7 weeks). Eleven of 13 (85%) patients having IOP reduction of greater than 40% showed improvement in optic disc parameters. All four patients with less than 25% reduction in IOP showed worsening of most parameters. Changes in optic disc parameters were highly correlated with percent IOP reduction and with age. The parameters in which change most strongly correlated with percent change of IOP were cup area, rim area, cup:disc ratio, and mean cup depth (each, P <0.005). The age of the patient correlated highly with change in maximum cup depth (P <0.005). Refraction and clinically determined cup:disc ratio correlated poorly with changes in measured optic disc parameters. Clinical improvement in visual fields was correlated with the degree of improvement of cup:disc ratio (P = 0.025). Conclusion: Most patients showing a 40% lowering of IOP after glaucoma surgery show improved optic nerve morphology as measured by the HRT. The amount of improvement correlated highly with the percent reduction of IOP.

Automatic Analysis of Digital Retinal Images for Glaucoma Detection

In this paper we propose a novel automated glaucoma detection framework for mass-screening that operates on inexpensive retinal cameras. The proposed methodology is based on the assumption that discriminative features for glaucoma diagnosis can be extracted from the optical nerve head structures,
such as the cup-to-disc ratio or the neuro-retinal rim variation. After automatically segmenting the cup and optical disc, these features are feed into a machine learning classifier. Experiments were performed using two different datasets and from the obtained results the proposed technique provides
better performance than approaches based on appearance. A main advantage of our approach is that it only requires a few training samples to provide high accuracy over several different glaucoma stages.

Diagnostic performance on briefly presented digital pathology images

Background: Identifying new and more robust assessments of proficiency/expertise (finding new "biomarkers of expertise") in histopathology is desirable for many reasons. Advances in digital pathology permit new and innovative tests such as flash viewing tests and eye tracking and slide navigation analyses that would not be possible with a traditional microscope. The main purpose of this study was to examine the usefulness of time-restricted testing of expertise in histopathology using digital images.
Methods: 19 novices (undergraduate medical students), 18 intermediates (trainees), and 19 experts (consultants) were invited to give their opinion on 20 general histopathology cases after 1 s and 10 s viewing times. Differences in performance between groups were measured and the internal reliability of the test was calculated.
Results: There were highly significant differences in performance between the groups using the Fisher's least significant difference method for multiple comparisons. Differences between groups were consistently greater in the 10-s than the 1-s test. The Kuder-Richardson 20 internal reliability coefficients were very high for both tests: 0.905 for the 1-s test and 0.926 for the 10-s test. Consultants had levels of diagnostic accuracy of 72% at 1 s and 83% at 10 s.
Conclusions: Time-restricted tests using digital images have the potential to be extremely reliable tests of diagnostic proficiency in histopathology. A 10-s viewing test may be more reliable than a 1-s test. Over-reliance on "at a glance" diagnoses in histopathology is a potential source of medical error due to over-confidence bias and premature closure.