Optical Coherence Tomography (OCT) is an imaging modality that is used extensively for ophthalmic diagnosis, near-histological visualization and quantification of retinal abnormalities such as cysts, exudates, retinal layer disorganization, etc. Intra-retinal cysts (IRCs) occur in several macular disorders such as, diabetic macular edema, retinal vascular disorders, age-related macular degeneration, and inflammatory disorders. Automated segmentation of IRCs poses challenges owing to variations in the acquisition system scan intensities, speckle noise, and imaging artifacts. Several segmentation methods have been proposed in the literature for IRC segmentation on vendor-specific OCT images that lack generalizability across imaging systems. In this work, we propose a fully convolutional network (FCN) model for vendor-independent IRC segmentation. The proposed method counteracts image noise variabilities and trains FCN models on OCT sub-images from the OPTIMA cyst segmentation challenge dataset (with four different vendor-specific images, namely, Cirrus, Nidek, Spectralis, and Topcon). Further, optimal data augmentation and model hyper-parametrization is shown to prevent over-fitting for IRC area segmentation. The proposed method is evaluated on the test data set with a recall/precision rate of 0.66/0.79 across imaging vendors. The Dice correlation coefficient of the proposed method outperforms that of the published algorithms in the OPTIMA cyst segmentation challenge with a Dice rate of 0.71 across the vendors.

Medical image-based research requires heavy computational workload associated with image analysis and collaborative device independent platforms to incorporate expert opinions from multiple institutions. Cloud-based resources such as Microsoft Azure Machine Learning Studio (MAMLS) provide such a platform that is conducive to the medical-image-based data analysis. This paper fosters the advantages of the cloud-based computing frameworks (such as MAMLS) and presents a practical work-flow well-suited for the standard machine learning tasks seen in medical image research viz., binary classification, multi-class learning, regression and so on. The proposed automated generalized workflow allows medical researchers/practitioners to focus on data inferencing rather than dealing with the intricate details of predictive modeling, such as feature and model selection. The scalable architecture of the proposed flow utilizes the MAMLS framework to processes data sets that require partial core storage space in the virtual machine to one complete core storage space in a common flow. Also, the proposed flow invokes multiple feature ranking and predictive models in parallel for automated selection and parameterization of the optimal data model. The performance of the proposed flow is bench-marked on 14 public data sets and four local medical image data sets (~0.12 MB-1.22 GB) using a single common flow, while ensuring better (~8% improvement) or atleast similar generalization capability with respect to existing works.

Customer purchasing behavior analysis plays a key role in developing insightful communication strategies between online vendors and their customers. To support the recent increase in online shopping trends, in this work, we present a customer purchasing behavior analysis system using supervised, unsupervised and semi-supervised learning methods. The proposed system analyzes session and user-journey level purchasing behaviors to identify customer categories/clusters that can be useful for targeted consumer insights at scale. We observe higher sensitivity to the design of online shopping portals for session-level purchasing prediction with accuracy/recall in range 91-98%/73-99%, respectively. The user-journey level analysis demonstrates five unique user clusters, wherein New Shoppers are most predictable and Impulsive Shoppers are most unique with low viewing and high carting behaviors for purchases. Further, cluster transformation metrics and partial label learning demonstrates the robustness of each user cluster to new/unlabelled events. Thus, customer clusters can aid strategic targeted nudge models.

This paper presents a novel automated system that denoises and segments seven sub-retinal layers in optical coherence tomography (OCT) images. First, the OCT images are subjected to Wiener deconvolution by varying the noise variance from 10 ^-1 to 10 ^-15 . A new Fourier-domain structural error is introduced in this paper, and the deconvolved OCT image with the least structural error is selected as the denoised image. The properties of the structural error metric are studied, and it is shown that the error metric satisfies convexity property. For each image, the proposed denoising method increases the image SNR by 6.9 dB on average compared to 5 dB increase reported so far, and attains a mean peak SNR (PSNR) of 23.036 dB. Next, highpass filters are applied to the denoised images in an iterative manner to extract the seven sub-retinal layers. The proposed system requires on average 10.65 seconds for denoising an image and 22.07 seconds for segmenting seven sub-retinal layers. This is a significant improvement over manual segmentation that requires up to 12 minutes per image.

Increasing costs of diagnostic healthcare have necessitated the development of hardware independent non-invasive Point of Care (POC) systems. Although anemia prevalence rates in global populations vary between 10% and 60% in various demographic groups, smart monitoring systems have not yet been developed for screening and tracking anemia-like pallor. In this work, we present two cloud platform-hosted POC applications that are directed towards smart monitoring of anemia-like pallor through eye and tongue pallor site images. The applications consist of a front-end graphical user interface (GUI) module and two different back-end image processing and machine learning modules. Both applications are hosted on a browser accessible tomcat server ported to an Azure Virtual Machine (VM). We observe that the first application spatially segments regions of interest from pallor site images with higher pallor classification accuracy and relatively longer processing times when compared to the lesser accurate yet faster second application. Also, both applications achieve 65%–98% accuracy in separating normal images from images with pallor or abnormalities. The optimized front-end module is significantly light-weight with a run-through time ratio of 10−5 with respect to the back-end modules. Thus, the proposed applications are portable and hardware independent, allowing for their use in pallor monitoring and screening tasks.

The semantic segmentation of 3D medical image stacks enables accurate volumetric reconstructions, computer-aided diagnostics and follow-up treatment planning. In this work, we present a novel variant of the Unet model, called the NUMSnet, that transmits pixel neighborhood features across scans through nested layers to achieve accurate multi-class semantic segmentation with minimal training data. We analyzed the semantic segmentation performance of the NUMSnet model in comparison with several Unet model variants in the segmentation of 3–7 regions of interest using only 5–10% of images for training per Lung-CT and Heart-CT volumetric image stack. The proposed NUMSnet model achieves up to 20% improvement in segmentation recall, with 2–9% improvement in $Dice$ scores for Lung-CT stacks and 2.5–16% improvement in $Dice$ scores for Heart-CT stacks when compared to the Unet++ model. The NUMSnet model needs to be trained with ordered images around the central scan of each volumetric stack. The propagation of image feature information from the six nested layers of the Unet++ model are found to have better computation and segmentation performance than the propagation of fewer hidden layers or all ten up-sampling layers in a Unet++ model. The NUMSnet model achieves comparable segmentation performance to previous works while being trained on as few as 5–10% of the images from 3D stacks. In addition, transfer learning allows faster convergence of the NUMSnet model for multi-class semantic segmentation from pathology in Lung-CT images to cardiac segmentation in Heart-CT stacks. Thus, the proposed model can standardize multi-class semantic segmentation for a variety of volumetric image stacks with a minimal training dataset. This can significantly reduce the cost, time and inter-observer variability associated with computer-aided detection and treatment.