A new software for automated counting of glistenings in intraocular lenses in vivo

AIM:To assess the performance of a bespoke software for automated counting of intraocular lens(IOL)glistenings in slit-lamp images.METHODS:IOL glistenings from slit-lamp-derived digital images were counted manually and automatically by the bespoke software.The images of one randomly selected eye from each of 34 participants were used as a training set to determine the threshold setting that gave the best agreement between manual and automatic grading.A second set of 63 images,selected using randomised stratified sampling from 290 images,were used for software validation.The images were obtained using a previously described protocol.Software-derived automated glistenings counts were compared to manual counts produced by three ophthalmologists.RESULTS:A threshold value of 140 was determined that minimised the total deviation in the number of glistenings for the 34 images in the training set.Using this threshold value,only slight agreement was found between automated software counts and manual expert counts for the validating set of 63 images(κ=0.104,95%CI,0.040-0.168).Ten images(15.9%)had glistenings counts that agreed between the software and manual counting.There were 49 images(77.8%)where the software overestimated the number of glistenings.CONCLUSION:The low levels of agreement show between an initial release of software used to automatically count glistenings in in vivo slit-lamp images and manual counting indicates that this is a non-trivial application.Iterative improvement involving a dialogue between software developers and experienced ophthalmologists is required to optimise agreement.The results suggest that validation of software is necessary for studies involving semi-automatic evaluation of glistenings.

Clinical utility of automated platelet clump count in the screening for ethylene diamine tetraacetic acid-dependent pseudothrombocytopenia

Background Platelet （PLT） clumping occurring in pseudothrombocytopenia （PTCP） can result in inaccurate PLT. Automated platelet clump count （APCC） is a quantitative parameter of platelet aggregation. In this study, we evaluated the clinical utility of APCC in the screening for platelet aggregation related ethylene diamine tetraacetic acid （EDTA）-dependent PTCP （EDTA-PTCP）. Methods A total of 105 patients and 200 healthy individuals were enrolled in this study. Blood samples were collected with dipotassium EDTA and sodium citrate respectively. ADVIA 2120 hematology analyzer was used to perform complete blood count （CBC） and APCC. Blood smears of both EDTA- and citrate-anticoagulated samples were made for microscope observation and manual PLT counting. Results In 25 patients with EDTA-PTCP patients, for EDTA-2K anticoagulated-blood, PLT was （55±6）×10^9/L, significantly lower than citrate anticoagulated blood （（186±13）×10^9/L））. APCC was （905±694）×10^9/L, significantly higher than citrate anticoagulated blood （98±37）×10^9/L. In true thrombocytopenia and healthy control groups, APCC was （63±60）×10^9/L and （69±59）×10^9/L respectively and there was no significant difference between EDTA and citrate anticoagulants. Receiver operator characteristic （ROC） curve showed both sensitivity and specificity of APCC were 96% when the cutoff value of APCC was set as 182×10^9/L. Other platelet parameters had poor performance. Conclusion The APCC has a good sensitivity and specificity in differentiating EDTA-PTCP from true thrombocytopenia compared with other platelet parameters.

Automatic greenhouse pest recognition based on multiple color space features

Recognition and counting of greenhouse pests are important for monitoring and forecasting pest population dynamics.This study used image processing techniques to recognize and count whiteflies and thrips on a sticky trap located in a greenhouse environment.The digital images of sticky traps were collected using an image-acquisition system under different greenhouse conditions.If a single color space is used,it is difficult to segment the small pests correctly because of the detrimental effects of non-uniform illumination in complex scenarios.Therefore,a method that first segments object pests in two color spaces using the Prewitt operator in I component of the hue-saturation-intensity(HSI)color space and the Canny operator in the B component of the Lab color space was proposed.Then,the segmented results for the two-color spaces were summed and achieved 91.57%segmentation accuracy.Next,because different features of pests contribute differently to the classification of pest species,the study extracted multiple features(e.g.,color and shape features)in different color spaces for each segmented pest region to improve the recognition performance.Twenty decision trees were used to form a strong ensemble learning classifier that used a majority voting mechanism and obtains 95.73%recognition accuracy.The proposed method is a feasible and effective way to process greenhouse pest images.The system accurately recognized and counted pests in sticky trap images captured under real greenhouse conditions.