Mobile Microscope for the

Detection of Pathogenic cells

using Image Processing
Surya Meghana P S, Kannan C, Lingeshwaran K, Raghavendran V and Priya C
Department of Electronics and Instrumentation Engineering & Computer Science
Engineering
Sri Sai Ram Engineering College, West Tambaram, Chennai, India.
psmeghana@gmail.com

                                                       
Abstract. With the improving technology, the need for
portable, economic and user-friendly bio-instruments is on
high demand. This work aims at the detection of pathogens in
blood, using a mobile phone and communicating the
necessary information to a doctor by means of a mobile
application. Since the most basic step towards the curing of a
malady is the diagnosis of the disease itself, this paper
elucidates how a small part of this challenge can be solved
with cell phones, which prove to be the immediate solution for
most of the modern day needs with the development of
wireless infrastructure allowing us to compute and
communicate on the move. The idea explicates the
development of novel imaging, sensing, and diagnostic
techniques using mobile phones as an underlying platform to
address the global demand for accurate, sensitive, cost-
effective, and field-portable measurement devices, especially
for regions with less or no access to diagnostic services.
2) Investigation of the potential of this multi-level
classification in differentiating healthy from the pathogens.
Accurate and consistent cellular level classification results for
several patients to illustrate the robustness of our framework,
and suggest potential applications in assessing growth and in
computer-guided surgery [4].
The performance of the model is based on the magnifying
property of the lens which is used to distinguish the property
of the cells based on the image being processed in the mobile
application. Thus, it is necessary for the device to be
compatible with the growing population and be answerable to
the needs of the society [5].

Keywords: cellular, hand-held, image processing, malarial

parasites, microscope, mobile application

I. Introduction

The developments in the application of communication and

information technology have completely changed the world.
The obvious reason for the introduction of computer systems
is: reliability, accuracy, simplicity and ease of use. Besides,
Fig. 1. A representative model from which the profile is developed.
the customization and optimization features of a computer
system stand among the major driving forces in adopting and
III. Modelling
subsequently strengthening the computer aided systems (D. N.
Breslauer, 2009).
Cells of the body depend on one another, either directly or
indirectly, to keep the body functioning as one unit (Aydın
II. Analysis and Proposal Arpa, 2012) [8]. The hardware of the module includes the lens,
To address healthcare needs in low-resource regions, research the slot for slide insertion and illumination for viewing the
has shown that mobile phones can bring traditional diagnostic slide, as shown in Fig.2.
assays to inadequately served populations. This work takes the
advantage of the imaging, connectivity, and processing
capabilities of the phone for various applications which
includes microscopic imaging, image-based quantification of
diagnostic tests (A.Davis, 2011)[1].
In this application, manual examination of samples to observe Holder Setup
the tissue and cellular-level disorders, are often done with the
C
aid of optical dyes (A. C. Kak and M. Slaney, 1988) [2]. In this
A
paper, these issues are addressed and alleviated by combining
M
structural images into a multimodality tissue profile, which
E
paves the way for classifying healthy and pathogenic cells. Slot to insert slide with blood
R
A
The contributions of this work are:

1) Creation of a multi-modality profile by integration images Fig. 2. External Setup / Design Drawing
with conventional structural images, using cellular data from
several patients [3]; III.I Lens
The heart of the module is a small spherical lens held close to
the eye of the camera lens of the mobile phone. The proposed
model uses a 140x magnification lens placed the customised
module and can be adjusted for perfect viewing (Manu
Prakash, 2014) [9]. As observed by Contreras-Naranjo et al.,
2016, it is to be noted that the choice of iPhone as the camera
for this work is driven primarily by the desire to have a
camera placement that allowed easy lens attachment and
sample viewing, as well as a touch screen interface to avoid
motion[10].

IV. Software

Open CV Implementation:

The images recorded by cell phone microscope based on

spherical ball lens have high noise ratio and intensity
variations compared to images acquired by our optical
microscope and hence requires image processing to enhance
the images [11]. OpenCV library which provides a common
infrastructure for computer vision application is used to
process the input image from the mobile camera. The methods
available in OpenCV library were used on the images
recorded by cell phone microscope. Initially, the images are
converted to Hue Saturation Value(HSV) and the average
filter is applied to obtain a uniform background. Then,
according to Kao W (2006) [12], the background subtraction
operations of OpenCV are implemented. Fig 3 and Fig 4.
show the basic packages and JNI Libraries used respectively.

Fig. 3. Basic Packages Used

Fig. 4. Java Native Interface(JNI) Libraries
The pathogenic cells are filtered out when the colour range
of the pathogenic cells (for malarial diagnosis) lies in a
specific range.
For this purpose, we make use of inrang() function. Prior to
that we need to know the colorspaces, ranges and
thresholds[13]. For that, MAT class provided in OpenCV library
has been used. The RGB colour system is the most common
as our eyes use something similar, but OpenCV display
system uses BGR colours. So, it is better convert the input
Fig. 5. OpenCV Library & the basic packages used
Fig. 6. HSV(Hue-Saturation-Val
frame (image) it into HSV/HSL colorspace (Krupinski E et
al., 2012) [14]. The HSV and HSL decomposes colours into
their hue, saturation and value/luminance components. There
are more than 150 colour spaces in OpenCV, here RGB to
HSV is used. The function used for conversion is
cv2.cvtColor(input_image, flag) where flag determines the
conversion type, here it is cv2.COLOR_BGR2HSV. The
OpenCV library requires OpenCV Manager installed on the
target machine. This provides the best OpenCV bundle based
on the hardware, as discussed by McKay C, 2008[15].
The overall scenario can be put into work in a GUI using the
GUIDE (Graphical User Interface Development
Environment).
This gives an interactive user experience. The given code can
be further put onto the coder and can be converted into a .c
file. This helps to create an android application for similar
implementation in a Mobile phone. [16]
V. Results
There are many research based projects emerging in the
recent years to diagnose diseases in the fastest means possible.
Many important medical decisions are still based on opinion
of a lab expert or technician [17]. This can reduce the number of
people to doctor ratio. Since prevention is better than cure it is
preferred to give the patient diagnosis kit. [18] Replacing some
of these costly laboratory-based instruments with cheaper,
portable devices that can achieve similar performance will see
for the option of reducing the cost and infrastructure burdens
that quality health care situations in the society. The Fig. 8 and
Fig. 7(a) and Fig. 7(b) illustrate the onion cells and the sample
tap water taken for testing purposes.
 regard to size or shape, the CellC algorithm which can be used
to improve the quality or one similar could be easily used to
report morphometric parameters that could enable an
approximate count of the RBC, discriminating the cells into
several blood cell classes efficiently. [19]

VI. Observations
Initial attempt has been made at performing a red cell
count of a blood sample imaged by the cell phone microscope.
The first step is to eliminate the count of the pathogenic cells
by detecting them via colour-based image processing. This is
showcased in Fig. 8 (the appearance of the falciparum in blue
stains taken as an image by the cell phone microscope). The
detected image as seen on XPS vision is shown in Fig. 8.

Fig. 7: Human Blood

Fig. 8(a): Malarial Parasites in the Mobile Phone

Fig. 7(a): Tap Water Fig7(b): Onion Cell

The is a cell phone-based instrument, with a microscope

embedded in it as shown. It is devised to have a resolution of
good enough in the centre of its field-of-view. Although the
image quality can rapidly degrade in a raw image due to the
use of a single ball micro lens, the images can still be used to
accurately diagnose a variety of blood diseases using a ball
lens of longer focal length.
Additionally, we have shown that although the field-of-
view has field dependent distortion and defocus when using
the 1 mm ball, the aberrations are amenable to image
processing. Furthermore, we have made an initial attempt at
performing a red cell count of a blood sample imaged by the
cell phone microscope. Although in this case we only report Fig. 8(b): Malarial Parasites in the Mobile Phone
results of an algorithm locating and counting cells without
 The results of MATLAB implementation can also be added
to these results. The Fig 9 a) shows the Image that is fed into
the MATLAB code and Fig 9 b) shows the RBC count and the
Fig 9 c) gives the infected cell count. The infected cells are
inside a bounding box.
VII. Potential Benefits
The bulky nature of the detection machines used these
days in the laboratories is a major drawback. Being a portable,
hand-held device, Microble makes it possible for easy
detection of malaria right at home. Another major advantage is
the cost, which is much lower than the tedious laboratory
detection procedure and is affordable even in the
economically backward regions. Microble enables lesser time
and energy consuming diagnosis of malaria from home. This
entire setup behaves like a Shell, which could be fed any
domain specific knowledge to make it work on that domain.
VIII. Conclusion
The paper presents two devices built through adding simple
and inexpensive attachments to a standard cell phone. This is
a demonstration of the basic clinical utility of these devices
through some initial experiments. It is to note that the choice
of the iPhone mobile as the device with camera for this work
was driven primarily by the desire to have a camera placement
that allowed easy lens attachment and sample viewing, as well
as a touch screen interface that can be used to avoid motion
due to button pressing. Further, the work presented in this
paper has the potential to make disease diagnosis and
screening accessible in parts of the world that have no
adequate access to healthcare. [21] However, it should not be
taken that the choice of phone to be crucial for this setup. This
replicates some of these experiments using other phones from
different manufacturers with qualitatively similar results (not
shown), indicating that the choice of phone and camera
specifications are not the limiting factors in the performance
of our system [20].
IX. References
[1] D. N. Breslauer, R. N. Maamari, N. A. Switz, W. A.
Lam, and D. A. Fletcher. Mobile Phone Based Clinical
Microscopy for Global Health Applications. PLoS ONE,
4(7):e6320, 07 2009.
[2] Quantitative Imaging with a Mobile Phone
Microscope Arunan Skandarajah, Clay D. Reber, Neil A.
Switz, Daniel A. Fletcher
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4019540/
[3] A. C. Kak and M. Slaney. Principles of Computerized
Tomographic Imaging.
[4] Foldscope: Origami-Based Paper Microscope James
S. Cybulski, James Clements, Manu Prakash Accessed
(2017)
March
[5] Quantitative Phase Imaging Techniques for the
Study of Cell Pathophysiology: From Principles to
Applications
KyeoReh Lee, Kyoohyun Kim, Jaehwang Jung , JiHan
Heo
[6] Tuijn CJ, Hoefman BJ, van Beijma H, Oskam L,
Chevrollier N (2011) Data and Image Transfer Using
Mobile Phones to Strengthen Microscopy-Based
Diagnostic Services in Low and Middle-Income
Country Laboratories. PLoS One 6: e28348.
[7] Aptamer biosensor for label-free impedance
spectroscopy detection of proteins based on
recognition-induced switching of the surface charge
Marcela C. Rodriguez, Abdel-Nasser Kawde and Joseph
Wan.
[8] Smith ZJ, Chu K, Espenson AR, Rahimzadeh M,
Gryshuk A, et al. (2011) Cell-phone-based platform for
biomedical device development and education
applications. PLoS One 6: e17150.
[9] Tseng D, Mudanyali O, Oztoprak C, Isikman SO,
Sencan I, et al. (2010) Lens free microscopy on a cell
phone. Lab Chip 10: 1787–1792.
[10] Long K, Gallegos D, Yu H, Clark P, Lin Y (2013)
Label-Free Bio detection using a Smartphone. Lab Chip
13: 2124–2132.
[11] Tech Explore – Accessed 201 7 September 03
https://techxplore.com/news/2017-01-whirligig-toy-
bioengineers-cent-hand-powered.html
[12] Stanford bioengineers develop a 20-cent, hand-
powered blood centrifuge – Accessed 2017 March 24
https://news.stanford.edu/2017/01/10/whirligig-toy-
bioengineers-develop-20-cent-hand-powered-blood-
centrifuge/
[13] World Health Organization (2011) Universal Access
to Malaria Diagnostic Testing. Geneva: WHO Press.
[14] Omnivision (2012) OV8830 8-megapixel product
brief.
[15] Kao W, Wang S, Chen L, Lin S (2006) Design
considerations of color image processing pipeline for
digital cameras. Consume Electron IEEE Trans 52:
1144–1152.
[16] Krupinski E, Silverstein LD, Hashmi SF, Graham AR,
Weinstein RS, et al. (2012) Observer performance using
virtual pathology slides: impact of LCD color
reproduction accuracy. J Digit Imaging 25: 738–743.
[17] McKay C, Swaminathan A, Wu M (2008) Image
acquisition forensics: Forensic analysis to identify
imaging source. 2008 IEEE Int Conf Acoust Speech
Signal Process: 1657–1660.
[18] Hirakawa K, Parks TTW (2006) Joint demosaicing
and denoising. Image Process IEEE Trans 15: 1–4.
[19] Cell-Phone-Based Platform for Biomedical Device
Development and Education Applications-Zachary J.
Smith, Kaiqin Chu, Alyssa R. Espenson, Mehdi
Rahimzadeh, Amy Gryshuk, Marco Molinaro
http://journals.plos.org/plosone/article?
id=10.1371/journal.pone.0017150
[20] Cell Scope: Mobile Microscopy
Available at: http://cellscope.berkeley.edu/. Accessed 2013
November 27.
[21] Single Lens Off-Chip Cell phone Microscopy Aydın
Arpa, MIT Media Lab; Gordon Wetzstein, MIT Media
Lab; Douglas Lanman, MIT Media Lab; Ramesh Raskar,
MIT Media Lab - http://studylib.net/doc/12447085/single-
lens-off-chip-cellphone-microscopy-please-share