Deep learning techniques, particularly convolutional neural networks, have shown great potential in computer vision and medical imaging applications. However, deep learning models are computationally demanding as they require enormous computational power and specialized processing hardware for model training. To make these models portable and compatible for prototyping, their implementation on low-power devices is imperative. In this work, we present the implementation of Modified U-Net on Intel/Movidius Neural Compute Stick 2 (NCS-2) for the segmentation of medical images. We selected U-Net because, in medical image segmentation, U-Net is a prominent model that provides improved performance for medical image segmentation even if the dataset size is small. The modified U-Net model is evaluated for performance in terms of dice score. Experiments are reported for segmentation task on three medical imaging datasets: BraTs dataset of brain MRI, heart MRI dataset, and Ziehl–Neelsen sputum smear microscopy image (ZNSDB) dataset. For the proposed model, we reduced the number of parameters from 30 million in the U-Net model to 0.49 million in the proposed architecture. Experimental results show that the modified U-Net provides comparable performance while requiring significantly lower resources and provides inference on the NCS-2. The maximum dice scores recorded are 0.96 for the BraTs dataset, 0.94 for the heart MRI dataset, and 0.74 for the ZNSDB dataset.

Eye and systemic diseases are known to manifest themselves in retinal vasculature. Segmentation of retinal vessel is one of the important steps in retinal image analysis. A simple unsupervised method based on Gabor wavelet and Multiscale Line Detector is proposed for retinal vessel segmentation. Vessels are enhanced by linear superposition of first scale Gabor wavelet image and complemented Green channel. Multiscale Line Detector is used to segment the blood vessels. Finally, a simple post processing scheme based on median filtering is deployed to remove false positives. The proposed scheme was evaluated with publicly available datasets called DRIVE, STARE and HRF, obtaining an accuracy of 0.9470, 0.9472, and 0.9559, and a sensitivity of 0.7421, 0.8004, and 0.7207, respectively. These results are comparable to the state-of-the-art methods, albeit with a simpler approach.

Fundus imaging is one of the crucial methods that help ophthalmologists for diagnosing the various eye diseases in modern medicine. An accurate vessel segmentation method can be a convenient tool to foresee and analyze fatal diseases, including hypertension or diabetes, which damage the retinal vessel’s appearance. This work suggests an unsupervised approach for vessels segmentation out of retinal images. The proposed method includes multiple steps. Firstly, from the colored retinal image, green channel is extracted and preprocessed utilizing Contrast Limited Histogram Equalization as well as Fuzzy Histogram Based Equalization for contrast enhancement. To expel geometrical articles (macula, optic disk) and noise, top-hat morphological operations are used. On the resulted enhanced image, matched filter and Gabor wavelet filter are applied, and the outputs from both is added to extract vessels pixels. The resulting image with the now noticeable blood vessel is binarized using human visual system (HVS). A final image of segmented blood vessel is obtained by applying post-processing. The suggested method is assessed on two public datasets (DRIVE and STARE) and showed comparable results with regard to sensitivity, specificity and accuracy. The results we achieved with respect to sensitivity, specificity together with accuracy on DRIVE database are 0.7271, 0.9798 and 0.9573, and on STARE database these are 0.7164, 0.9760, and 0.9560, respectively, in less than 3.17 s on average per image.

In most of the medical treatments, intravenous catheterization is considered as a first crucial phase, in which health practitioners find the superficial vein to conduct blood sampling or medication procedures. In some patients these veins are hard to localize due to different physiological characteristics such as dark skin tone, scars, vein depth etc., which mostly results in multiple attempts for needle insertion. This causes pain, delayed treatment, bleeding, and even infections. To reduce these risks, an automated veins detection method is needed that can efficiently segment the veins and produce realistic results for cannulation purposes. For this purpose, many imaging modalities such as Photoacoustic, Trans-illumination, ultrasound, Near-Infrared etc. are used. Among these modalities Near-Infrared (NIR) imaging modality is considered most suitable due to its lower cost and non-ionizing nature. Over the past few years, subcutaneous veins localization using NIR have attracted increasing attention in the field of health care and biomedical engineering. Therefore, the proposed research work is based on NIR images for forearm subcutaneous veins segmentation. This paper presents a deep learning-based approach called Generative Adversarial Networks (GAN) for segmentation/localization of forearm veins. GANs have shown exciting results in the medical imaging field recently. These are used for unsupervised feature learning and image-to-image translation applications. These networks generate realistic results by learning data mapping from one state to another. Since GANs can produce state of the art results, therefore we have proposed a Pix2Pix GAN for segmentation of forearm veins. The proposed algorithm is trained and tested on forearm subcutaneous veins image dataset. The proposed model outperforms traditional approaches with the mean accuracy and sensitivity, values obtained are 0.971 and 0.862 respectively. The dice coefficient and IoU score are respectively 0.962 and 0.936 which are better than the state-of-the-art methods.

In order to perform the standard Intravenous (IV) catheterization, subcutaneous veins must be localized. It is a difficult task, especially in the cases when veins are hard to localize. The factors which affect the veins localization process are the physiological characteristics of patients, mainly darker skin tone, scars, hair, dehydration and low blood pressure. With the help of Near Infrared imaging, subcutaneous veins can be envisioned. This is due to the higher absorption of NIR light energy by Hemoglobin (Hb) found in the veins. Besides a superficial view, the veins depth information is also important in order to avoid their rupture by piercing through the walls during IV catheterization process. Diffused reflectance, measured with a camera sensor, can be used for the depth estimation of blood vessels. In this paper, a method to measure the depth of veins using diffused reflectance parameter, is presented. The well-known Monte Carlo model of light propagation in human tissues is used for the mathematical representation. A four-layered skin model is presented with varying vessel depths to describe the diffused reflectance of light while propagating inside skin tissues. The results are validated with Monte Carlo simulations for light propagation in layered medium. A sensitivity analysis of proposed method is also performed with a 5% alteration in the optical parameters of skin due to the change in operating conditions. The results showed a marginal error of maximum value 6.23% in vessel depth estimation using the standard optical parameters, 1.6% for −5% and 10.74% for +5% change in optical parameters.

Domain-specific accelerators for signal processing, image processing, and machine learning are increasingly being implemented on SRAM-based field-programmable gate arrays (FPGAs). Owing to the inherent error tolerance of such applications, approximate arithmetic operations, in particular, the design of approximate multipliers, have become an important research problem. Truncation of lower bits is a widely used approximation approach; however, analyzing and limiting the effects of carry-propagation due to this approximation has not been explored in detail yet. In this article, an optimized carry-aware approximate radix-4 Booth multiplier design is presented that leverages the built-in slice look-up tables (LUTs) and carry-chain resources in a novel configuration. The proposed multiplier simplifies the computation of the upper and lower bits and provides significant benefits in terms of FPGA resource usage (LUTs saving 38.5%–42.9%), Power Delay Product (PDP saving 49.4%–53%), performance metric (LUTs × critical path delay (CPD) × PDP saving 68.9%–73.1%) and errors (70% improvement in mean relative error distance) compared to the latest state-of-the-art designs. Therefore, the proposed designs are an attractive choice to implement multiplication on FPGA-based accelerators.