Download the Free Unbound MEDLINE PubMed App to your smartphone or tablet.
Available for iPhone, iPad, iPod touch, and Android.
- A Malaria Diagnostic Tool Based on Computer Vision Screening and Visualization of Plasmodium falciparum Candidate Areas in Digitized Blood Smears. [Journal Article]
- PLoS One 2014; 9(8):e104855.
Microscopy is the gold standard for diagnosis of malaria, however, manual evaluation of blood films is highly dependent on skilled personnel in a time-consuming, error-prone and repetitive process. In this study we propose a method using computer vision detection and visualization of only the diagnostically most relevant sample regions in digitized blood smears.Giemsa-stained thin blood films with P. falciparum ring-stage trophozoites (n = 27) and uninfected controls (n = 20) were digitally scanned with an oil immersion objective (0.1 µm/pixel) to capture approximately 50,000 erythrocytes per sample. Parasite candidate regions were identified based on color and object size, followed by extraction of image features (local binary patterns, local contrast and Scale-invariant feature transform descriptors) used as input to a support vector machine classifier. The classifier was trained on digital slides from ten patients and validated on six samples.The diagnostic accuracy was tested on 31 samples (19 infected and 12 controls). From each digitized area of a blood smear, a panel with the 128 most probable parasite candidate regions was generated. Two expert microscopists were asked to visually inspect the panel on a tablet computer and to judge whether the patient was infected with P. falciparum. The method achieved a diagnostic sensitivity and specificity of 95% and 100% as well as 90% and 100% for the two readers respectively using the diagnostic tool. Parasitemia was separately calculated by the automated system and the correlation coefficient between manual and automated parasitemia counts was 0.97.We developed a decision support system for detecting malaria parasites using a computer vision algorithm combined with visualization of sample areas with the highest probability of malaria infection. The system provides a novel method for blood smear screening with a significantly reduced need for visual examination and has a potential to increase the throughput in malaria diagnostics.
- Color vision. The “geopolitics” of basic color terms. [Comment, News]
- Atten Percept Psychophys 2014 Jul; 76(5):1255-6.
- Johannes Vermeer of Delft [1632-1675] and vision in neuroendoscopy. [Journal Article, Review]
- Surg Neurol Int 2014.:123.
Johannes Vermeer of Delft [1632-1675] was one of the greatest Masters of the Dutch Golden Age who was intensely preoccupied with the behavior of light and other optical effects and was entitled "The Master of Light". He fastidiously attended to the subtleties of visual expression through geometry, composition, and precise mastery of the rules of perspective. It has been our impression that some visual similarity does exist between neuroendoscopic images and some of Vermeer's paintings. Such a relation could be explained by the fact that optical devices are utilized in producing both types of display.We reviewed the pertinent medical and art literature, observed some video clips of our endoscopy cases, and inspected digital high resolution images of Vermeer's paintings in order to elaborate on shared optical phenomena between neuroendoscopic views and Vermeer's paintings.Specific optical phenomena are indeed shared by Johannes Vermeer's works and neuroendoscopic vision, namely light and color effects as well as the rules of perspective.From the physical point of view, the possibility that a camera obscura inspired Vermeer's artistic creation makes the existence of a visual link between his paintings and the endoscopic views of the intracranial cavity comprehensible.
- Feature integration and object representations along the dorsal stream visual hierarchy. [Journal Article, Review]
- Front Comput Neurosci 2014.:84.
a ventral stream that receives color and form information and a dorsal stream that receives motion information. Each stream processes that information hierarchically, with each stage building upon the previous. In the ventral stream this leads to the formation of object representations that ultimately allow for object recognition regardless of changes in the surrounding environment. In the dorsal stream, this hierarchical processing has classically been thought to lead to the computation of complex motion in three dimensions. However, there is evidence to suggest that there is integration of both dorsal and ventral stream information into motion computation processes, giving rise to intermediate object representations, which facilitate object selection and decision making mechanisms in the dorsal stream. First we review the hierarchical processing of motion along the dorsal stream and the building up of object representations along the ventral stream. Then we discuss recent work on the integration of ventral and dorsal stream features that lead to intermediate object representations in the dorsal stream. Finally we propose a framework describing how and at what stage different features are integrated into dorsal visual stream object representations. Determining the integration of features along the dorsal stream is necessary to understand not only how the dorsal stream builds up an object representation but also which computations are performed on object representations instead of local features.
- Gestalt grouping via closure degrades suprathreshold depth percepts. [Journal Article]
- J Vis 2014; 14(9)
It is well known that the perception of depth is susceptible to changes in configuration. For example, stereoscopic precision for a pair of vertical lines can be dramatically reduced when these lines are connected to form a closed object. Here, we extend this paradigm to suprathreshold estimates of perceived depth. Using a touch-sensor, observers made quantitative estimates of depth between a vertical line pair presented in isolation or as edges of a closed rectangular object with different figural interpretations. First, we show that the amount of depth estimated within a closed rectangular object is consistently reduced relative to the vertical edges presented in isolation or when they form the edges of two segmented objects. We then demonstrate that the reduction in perceived depth for closed objects is modulated by manipulations that influence perceived closure of the central figure. Depth percepts were most disrupted when the horizontal connectors and vertical lines matched in color. Perceived depth increased slightly when the connectors had opposite contrast polarity, but increased dramatically when flankers were added. Thus, as grouping cues were added to counter the interpretation of a closed object, the depth degradation effect was systematically eliminated. The configurations tested here rule out explanations based on early, local interactions such as inhibition or cue conflict; instead, our results provide strong evidence of the impact of Gestalt grouping, via closure, on depth magnitude percepts from stereopsis.
- Chicken embryos as a potential new model for early onset type I diabetes. [Journal Article]
- J Diabetes Res 2014.:354094.
Diabetic retinopathy (DR) is the leading cause of blindness among the American working population. The purpose of this study is to establish a new diabetic animal model using a cone-dominant avian species to address the distorted color vision and altered cone pathway responses in prediabetic and early diabetic patients. Chicken embryos were injected with either streptozotocin (STZ), high concentration of glucose (high-glucose), or vehicle at embryonic day 11. Cataracts occurred in varying degrees in both STZ- and high glucose-induced diabetic chick embryos at E18. Streptozotocin-diabetic chicken embryos had decreased levels of blood insulin, glucose transporter 4 (Glut4), and phosphorylated protein kinase B (pAKT). In STZ-injected E20 embryos, the ERG amplitudes of both a- and b-waves were significantly decreased, the implicit time of the a-wave was delayed, while that of the b-wave was significantly increased. Photoreceptors cultured from STZ-injected E18 embryos had a significant decrease in L-type voltage-gated calcium channel (L-VGCC) currents, which was reflected in the decreased level of L-VGCCα1D subunit in the STZ-diabetic retinas. Through these independent lines of evidence, STZ-injection was able to induce pathological conditions in the chicken embryonic retina, and it is promising to use chickens as a potential new animal model for type I diabetes.
- Medical management of hereditary optic neuropathies. [Journal Article, Review]
- Front Neurol 2014.:141.
Hereditary optic neuropathies are diseases affecting the optic nerve. The most common are mitochondrial hereditary optic neuropathies, i.e., the maternally inherited Leber's hereditary optic neuropathy (LHON) and dominant optic atrophy (DOA). They both share a mitochondrial pathogenesis that leads to the selective loss of retinal ganglion cells and axons, in particular of the papillo-macular bundle. Typically, LHON is characterized by an acute/subacute loss of central vision associated with impairment of color vision and swelling of retinal nerve fibers followed by optic atrophy. DOA, instead, is characterized by a childhood-onset and slowly progressive loss of central vision, worsening over the years, leading to optic atrophy. The diagnostic workup includes neuro-ophthalmologic evaluation and genetic testing of the three most common mitochondrial DNA mutations affecting complex I (11778/ND4, 3460/ND1, and 14484/ND6) for LHON and sequencing of the nuclear gene OPA1 for DOA. Therapeutic strategies are still limited including agents that bypass the complex I defect and exert an antioxidant effect (idebenone). Further strategies are aimed at stimulating compensatory mitochondrial biogenesis. Gene therapy is also a promising avenue that still needs to be validated.
- The Use of Smart phones in Ophthalmology. [Journal Article, Review]
- Acta Inform Med 2014 Jun; 22(3):206-9.
Smart phones are being increasingly used among health professionals. Ophthalmological applications are widely available and can turn smart phones into sophisticated medical devices. Smart phones can be useful instruments for the practice of evidence-based medicine, professional education, mobile clinical communication, patient education, disease self-management, remote patient monitoring or as powerful administrative tools. Several applications are available for different ophthalmological examinations that can assess visual acuity, color vision, astigmatism, pupil size, Amsler grid test and more. Smart phones can be useful ophthalmic devices for taking images of anterior and posterior eye segment. Professional literature and educational material for patients are easily available with use of smart phones. Smart phones can store great amount of informations and are useful for long term monitoring with caution for patient confidentiality. The use of smart phones especially as diagnostic tools is not standardized and results should be carefully considered. Innovative role of smartphone technology and its use in research, education and information sharing makes smart phones a future of ophthalmology and medicine.
- SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY FINDINGS IN LONG-TERM SILICONE OIL-RELATED VISUAL LOSS. [JOURNAL ARTICLE]
- Retina 2014 Aug 14.
To investigate spectral domain optical coherence tomography findings in long-term silicone oil-related visual loss.Four symptomatic patients were reviewed 4 years to 9 years after vitrectomy with silicone oil tamponade for macula-on retinal detachment. Three lost vision with oil in situ, with one at the time of oil removal. Eleven control eyes with good vision were included. Patients underwent assessment of best-corrected visual acuity, contrast sensitivity, Farnsworth-Munsell 100 Hue testing, static perimetry, and spectral domain optical coherence tomography imaging of the macula and disk.Long-term best-corrected visual acuity was significantly reduced in affected eyes (range, 0.44-1.02), as was contrast sensitivity (0.75-1.35) and color discrimination (Farnsworth-Munsell-100 Hue score, 151-390). Static perimetry showed a central scotoma in all affected eyes. Optical coherence tomography revealed microcystic macular changes in the inner nuclear layer of all affected eyes associated with severe loss of the papillofoveal retinal nerve fiber layer. In one patient, serial optical coherence tomography images showed development of microcystic macular changes 18 months after oil removal. Control eyes lacked these features, except two asymptomatic eyes that showed microcystic changes on optical coherence tomography with a corresponding paracentral scotoma.We have demonstrated microcystic macular changes in the inner nuclear layer of affected eyes, as well as focal severe loss of the papillofoveal projection. These changes share significant morphologic features reported in multiple sclerosis-associated optic neuritis and Leber hereditary optic neuropathy.
- A Novel Video Dataset for Change Detection Benchmarking. [JOURNAL ARTICLE]
- IEEE Trans Image Process 2014 Aug 7.
Change detection is one of the most commonly encountered low-level tasks in computer vision and video processing. A plethora of algorithms have been developed to date, yet no widely accepted, realistic, large-scale video dataset exists for benchmarking different methods. Presented here is a unique change detection video dataset consisting of nearly 90,000 frames in 31 video sequences representing 6 categories selected to cover a wide range of challenges in 2 modalities (color and thermal IR). A distinguishing characteristic of this benchmark video dataset is that each frame is meticulously annotated by hand for ground-truth foreground, background, and shadow area boundaries - an effort that goes much beyond a simple binary label denoting the presence of change. This enables objective and precise quantitative comparison and ranking of video-based change detection algorithms. This paper discusses various aspects of the new dataset, quantitative performance metrics used, and comparative results for over two dozen change detection algorithms. It draws important conclusions on solved and remaining issues in change detection, and describes future challenges for the scientific community. The dataset, evaluation tools, and algorithm rankings are available to the public on a website1 and will be updated with feedback from academia and industry in the future.