KINSPECTOR (Inspecting your blood)

4 min readFeb 9, 2023

ABSTRACT

Division and checking of platelets are considered significant advance that assists with extricating highlights to analyze some particular illnesses like intestinal sickness or leukemia. The manual checking of white platelets (WBCs) and red platelets (RBCs) in tiny pictures is an incredibly dreary, tedious, and mistaken cycle. The automatic analysis will allow hematologist — pathologists experts to perform faster and more accurately.

Thus, KINSPECTOR is a web application used to detect Acute Lymphoblastic Leukaemia using deep learning models and image segmentation modules of smeared blood images.

AIM

To detect blood disease Acute lymphoblastic leukemia (ALL) using the microscopic images of blood capillaries.

Problem Statement

How to easily predict WBC’s with Acute Lymphoblastic Leukaemia?

Detecting WBC in a blood smeared images and classfiying healthy and blast cells.

TOOLS and TECHNOLOGIES

Tensorflow Object Detection (TFOD): TFOD is used for masking of wbc in whole blood sample.

Keras API: This API is used in this project for classification of blood smeared images.

Python: All backend scripts are written in python.

Flask: Web application is made through flask.

Acute lymphoblastic leukemia

Acute Lymphocytic Leukemia is basically a type of cancer that does not form tumors as other cancers do.
This mostly occurs in children and can also occur in adults.
For the diagnosis of ALL, the CBC test, which is a complete blood count test is performed.
Basically, All affects WBC’s more rather than RBC’s.
It decreases the counts of RBC’s and creates too many lymphocytes(WBC).
It progresses rapidly in blood and replaces all healthy lymphocytes with leukemia cells which can’t mature properly.
Acute lymphocytic leukemia occurs when a bone marrow cell develops changes (mutations) in its genetic material or DNA. A cell’s DNA contains the instructions that tell a cell what to do. Normally, the DNA tells the cell to grow at a set rate and to die at a set time. In acute lymphocytic leukemia, the mutations tell the bone marrow cell to continue growing and dividing. When this happens the production of Blood cells happens at a higher rate and they may crowd out healthy blood cells.

Keras API

Keras is the high-level API of TensorFlow 2: an approachable, highly-productive interface for solving machine learning problems, with a focus on modern deep learning. It provides essential abstractions and building blocks for developing and shipping machine-learning solutions with high iteration velocity.

Image thresholding

Image thresholding is a simple, yet effective, way of partitioning an image into a foreground and background. This image analysis technique is a type of image segmentation that isolates objects by converting grayscale images into binary images. Image thresholding is most effective in images with high levels of contrast.

Basic Steps of Image Processing

Image Acquisition: Image acquisition is the creation of digital images, such as of a physical scene or of the interior structure of an object.

Image preprocessing: The technique of enhancing data images which involves removing low-frequency background noise, normalizing the intensity of the individual particles images, removing reflections, and masking portions of images.

Image segmentation: The process of partitioning a digital image into multiple segments.

Object recognition: The task of finding and identifying objects in an image or video sequence.