Predictive modeling for corrective maintenance of imaging devices from machine logs.

In the cost sensitive healthcare industry, an unplanned downtime of diagnostic and therapy imaging devices can be a burden on the financials of both the hospitals as well as the original equipment manufacturers (OEMs). In the current era of connectivity, it is easier to get these devices connected to a standard monitoring station. Once the system is connected, OEMs can monitor the health of these devices remotely and take corrective actions by providing preventive maintenance thereby avoiding major unplanned downtime. In this article, we present an overall methodology of predicting failure of these devices well before customer experiences it. We use data-driven approach based on machine learning to predict failures in turn resulting in reduced machine downtime, improved customer satisfaction and cost savings for the OEMs. One of the use-case of predicting component failure of PHILIPS iXR system is explained in this article.

Intra and Inter-Observer Variability of Transformation Zone Assessment in Colposcopy: A Qualitative and Quantitative Study.

INTRODUCTION: Colposcopy is an important tool in the diagnosis of cervical precancer and early cancer. The assessment of women with abnormal cytology and selection of those who require further therapy or follow up depends on the colposcopic assessment of the Transformation Zone (TZ). Identification of the TZ is thus an important part of this examination. Intra and inter-observer variability is known to be relatively high in the colposcopic interpretation of abnormal features. However, there are hardly any studies on the observer variability in the assessment of the type of TZ. AIM: The present study was conducted with the aim to compare the intra and inter-observer variability of the TZ type classification and the Squamo-Columnar Junction (SCJ) visibility and to quantitatively measure the intra and inter-observer correlations of tracing of the TZ contours. MATERIALS AND METHODS: Colposcopy images were obtained for a total of 170 cases. They were reviewed by three colposcopists independently. The colposcopists classified the TZ type and also marked the SCJ contours on the images. Each observer independently reviewed the cases on two different instances (few weeks apart) and the result was compiled for intra-observer variation. The intra and inter observer variability on the TZ type was compared using Cohen's Kappa. This was followed by a quantitative measurement of TZ observation variability using Hausdorff distance. RESULTS: The inter-observer agreement for the TZ type classification was moderate (Kappa= 0.53 to 0.66). The Intra-observer agreement was moderate to strong (0.60 to 0.86). CONCLUSION: Colposcopic in vivo examination increases the variability in the identification of the TZ when compared to the analysis of recorded images. The disagreement in the TZ type was mostly in categories Type 2 vs Type 3 followed by Type 1 vs Type 2. A computerized quantification method can be used for quality control and training purpose in colposcopy.

Doppler based identification of uterine artery and umbilical artery for monitoring pregnancy.

In this paper, we present an algorithm to identify umbilical and uterine arteries from a set of four different maternal and fetal arteries using their Doppler signatures. To distinguish these arteries, we use 132 Doppler signals collected from pregnant women with gestational ages between 24 to 40 weeks. Initially we filter them to remove noise; spectrograms are generated to extract good cycles, which are then analyzed to derive independent features that could uniquely represent an artery. A non-linear classification technique using k-NN (k-nearest neighbor) classifier is further applied to identify umbilical and uterine arteries. The proposed algorithm achieves sensitivity and specificity of above 95% and 97% for identification of uterine artery and above 63% and 80% for umbilical artery.

Optical screening of oral cancer: technology for emerging markets.

Oral cancer is the sixth most common cancer in the world. It is one of the most prevalent cancers in the developing countries of South Asia accounting for one third of the world burden. Sixty percent of the cancers are advanced by the time they are detected. Two methods of optical spectroscopy for detection of oral cancer have been discussed here. These methods are simple, easy to handle and non-invasive. The evaluation of the data is done automatically using pattern recognition techniques, making the screening subjective.

Distinct multicolored region descriptors for object recognition.

The problem of object recognition has been considered here. Color descriptions from distinct regions covering multiple segments are considered for object representation. Distinct multicolored regions are detected using edge maps and clustering. Performance of the proposed methodologies has been evaluated on three data sets and the results are found to be better than existing methods when a small number of training views is considered.

Standardization of edge magnitude in color images.

Edge detection is a useful task in low-level image processing. The efficiency of many image processing and computer vision tasks depends on the perfection of detecting meaningful edges. To get a meaningful edge, thresholding is almost inevitable in any edge detection algorithm. Many algorithms reported in the literature adopt ad hoc schemes for this purpose. These algorithms require the threshold values to be supplied and tuned by the user. There are many high-level tasks in computer vision which are to be performed without human intervention. Thus, there is a need to develop a scheme where a single set of threshold values would give acceptable results for many color images. In this paper, an attempt has been made to devise such an algorithm. Statistical variability of partial derivatives at each pixel is used to obtain standardized edge magnitude and is thresholded using two threshold values. The advantage of standardization is evident from the results obtained.

Hue-preserving color image enhancement without gamut problem.

The first step in many techniques for processing intensity and saturation in color images keeping hue unaltered is the transformation of the image data from RGB space to other color spaces such as LHS, HSI, YIQ, HSV, etc. Transforming from one space to another and processing in these spaces usually generate a gamut problem, i.e., the values of the variables may not be in their respective intervals. We study enhancement techniques for color images theoretically in a generalized setup. A principle is suggested to make the transformations gamut-problem free. Using the same principle, a class of hue-preserving, contrast-enhancing transformations is proposed; they generalize existing grey scale contrast intensification techniques to color images. These transformations are also seen to bypass the above mentioned color coordinate transformations for image enhancement. The developed principle is used to generalize the histogram equalization scheme for grey scale images to color images.