A Framework for White Blood Cell Segmentation in Microscopic Blood Images Using Digital Image Processing

Evaluation of blood smear is a commonly clinical test these days. Most of the time, the hematologists are interested on white blood cells (WBCs) only. Digital image processing techniques can help them in their analysis and diagnosis. For example, disease like acute leukemia is detected based on the amount and condition of the WBC. The main objective of this paper is to segment the WBC to its two dominant elements: nucleus and cytoplasm. The segmentation is conducted using a proposed segmentation framework that consists of an integration of several digital image processing algorithms. Twenty microscopic blood images were tested, and the proposed framework managed to obtain 92% accuracy for nucleus segmentation and 78% for cytoplasm segmentation. The results indicate that the proposed framework is able to extract the nucleus and cytoplasm region in a WBC image sample.     

Monte Carlo Simulations for the Detection of Buried Objects Using Single Sided Backscattered Radiation

Background

Detection of buried improvised explosive devices (IEDs) is a delicate task, leading to a need to develop sensitive stand-off detection technology. The shape, composition and size of the IEDs can be expected to be revised over time in an effort to overcome increasingly sophisticated detection methods. As an example, for the most part, landmines are found through metal detection which has led to increasing use of non-ferrous materials such as wood or plastic containers for chemical based explosives being developed.

Methodology

Monte Carlo simulations have been undertaken considering three different commercially available detector materials (hyperpure-Ge (HPGe), lanthanum(III) bromide (LaBr) and thallium activated sodium iodide (NaI(Tl)), applied at a stand-off distance of 50 cm from the surface and burial depths of 0, 5 and 10 cm, with sand as the obfuscating medium. Target materials representing medium density wood and mild steel have been considered. Each detector has been modelled as a 10 cm thick cylinder with a 20 cm diameter.

Principal Findings

It appears that HPGe represents the most promising detector for this application. Although it was not the highest density material studied, its excellent energy resolving capability leads to the highest quality spectra from which detection decisions can be inferred.

Conclusions

The simulation work undertaken here suggests that a vehicle-born threat detection system could be envisaged using a single betatron and a series of detectors operating in parallel observing the space directly in front of the vehicle path. Furthermore, results show that non-ferrous materials such as wood can be effectively discerned in such remote-operated detection system, with the potential to apply a signature analysis template matching technique for real-time analysis of such data.     

Segmentation of Extrapulmonary Tuberculosis Infection Using Modified Automatic Seeded Region Growing

In the image segmentation process of positron emission tomography combined with computed tomography (PET/CT) imaging, previous works used information in CT only for segmenting the image without utilizing the information that can be provided by PET. This paper proposes to utilize the hot spot values in PET to guide the segmentation in CT, in automatic image segmentation using seeded region growing (SRG) technique. This automatic segmentation routine can be used as part of automatic diagnostic tools. In addition to the original initial seed selection using hot spot values in PET, this paper also introduces a new SRG growing criterion, the sliding windows. Fourteen images of patients having extrapulmonary tuberculosis have been examined using the above-mentioned method. To evaluate the performance of the modified SRG, three fidelity criteria are measured: percentage of under-segmentation area, percentage of over-segmentation area, and average time consumption. In terms of the under-segmentation percentage, SRG with average of the region growing criterion shows the least error percentage (51.85%). Meanwhile, SRG with local averaging and variance yielded the best results (2.67%) for the over-segmentation percentage. In terms of the time complexity, the modified SRG with local averaging and variance growing criterion shows the best performance with 5.273 s average execution time. The results indicate that the proposed methods yield fairly good performance in terms of the over- and under-segmentation area. The results also demonstrated that the hot spot values in PET can be used to guide the automatic segmentation in CT image.