Automatic Detection of White Blood Cancer and Lung Cancer Using Machine Learning

Abstract

When abnormal white blood cells multiply cancerously, leukaemia results, harming the bone marrow and blood. The body\'s immune system is disturbed by the body\'s excessive generation of immature white blood cells, or lymphoblast, and its capacity to create red blood cells and platelets is decreased in the bone marrow as a result. Early diagnosis of these cells is crucial for preventing health issues in patients. In the past, the procedure was manually completed by an expert in a sizable amount of time. On a short dataset, the proposed model uses an improved Dense Convolutional neural network framework to predict the kind of cancer in a generic manner. which is able to locate both lung cancer and leukemia. Tumors can spread to other organs and grow quickly in lung cancer. An aberrant cell proliferation that can harm other normal tissue cells marks the beginning of cancer. Using tiny images to identify the white blood cancer, the imaging technology known as computerized tomography (CT) is frequently used to diagnose lung cancer.

Introduction

I. INTRODUCTION

Cancer is clearly the most important health concern in the globe. This leads to the cellular overgrowth in numerous body areas that causes cancer. Cancer is the riskiest disease kind. This is extremely true when you consider that it is one of the major causes of mortality for both men and women. This initiative's two main focus areas are lung cancer and white blood cell cancer. cancer of white blood cells Blood cancer is mostly brought on by the formation of abnormal blood cells. The three main types are leukemia, lymphoma, and blood malignancies. Blood tumors mostly come in three different forms:

1. leukemia,
2. myeloma, and
3. lymphoma.

The bone marrow is where Acute Lymphocytic Leukemia, a kind of white blood cell malignancy, is infected (ALL)Because it guarantees survival, blood is the most important part of every human body. In order to maintain a healthy metabolism, it performs a number of essential jobs like transporting minerals, carbon dioxide, oxygen, and other gases throughout the body. The three primary components of blood are RBC, WBC, and platelets. The metabolism can be significantly harmed by insufficient blood, which can be quite harmful if immediate treatment is not administered. One of the most common disorders of the blood is leukemia. Leukemia is the type of cancer that affects kids the most frequently. Leukemia is a kind of cancer that begins in blood cells, as do all malignancies.

Lymphocytes and other blood cells are created in the bone marrow. It is a spongy tissue that may be found inside many of the body's big bones. Three different blood cell types are created in the bone marrow: Hemoglobin-containing RBCs deliver oxygen and other substances to the body's tissues; platelets aid in the formation of clots; and WBCs aid in the body's defense against infections. The bone marrow malfunctions in a person with leukemia. Leukemia cells, which are aberrant, immature cells, are created in the bone marrow. In most cases, "blasts" are used to describe leukemia cells. These developing cancer cells in the bone marrow displace other blood-forming cells. A youngster may have anemia and extreme fatigue if the bone marrow is unable to produce enough RBCs to transport oxygen. Blood won't clot correctly and the patient may bleed readily if not enough platelets are created. When WBCs are insufficiently abundant, the body cannot combat pathogens, and the person may have recurrent infections.

There are two types of leukemia: acute and chronic. Cancer is a condition in which the body's cells proliferate uncontrollably. A group of different blood cell types are collectively referred to as white blood cells (WBCs). These cells don't give any symptoms or other crucial information for diagnosing a disease. Generally speaking, leukemia diagnosis and treatment essential concerns

Therefore, eliminating the background using conventional techniques is rather difficult. Additionally, established industrial and medical practices are unable to withstand noise and intricate computations. It is difficult to develop an automated method for counting and identifying blood components using microscopic pictures in the field of medical image processing.

In the bone marrow, these immature chronic lymphocytic leukemia cells wrap other blood-forming cells. A child's bone marrow cannot make enough blood cells if it is not receiving enough oxygen. The children thus grow anemic and frequently feel fatigued. Blood can not clot in the lack of enough platelets, which can lead to internal bleeding or recurrent bleeding. When WBCs are not created in adequate numbers, the immune system is unable to keep bacteria, viruses, and other foreign organisms from entering the body. As a result, a typical infection manifests itself. Lung cancer is the term used when cancer first appears in the lungs. The biggest cause of cancer mortality is lung cancer.

According to estimates, lung cancer accounts for around 19 percent of deaths worldwide, mainly as a result of alcohol and cigarette use. Only 15% of endurance possibilities, for an endurance time of 5 years, ensure the speed of endurance. The primary cause of such a high passing rate is the later detection, which leads to delayed treatment. The likelihood of survival can increase by up to 50–70% if lung cancer is discovered at an earlier stage. Assembling the lung disease depending on the phone trademark might result in either non-little cell lung mischief or little cell lung disease Around 85–90% of instances with full-scale lung threatening development are caused by non–little cell lung hazardous development, whereas the remaining 10–15% of cases are determined to have little cell lung harmful development. There are different types of lung cancer, and these cancers can be identified by doctors using their procedures. To minimize human effort or error, we have created a code that analyses CT scan images, defines their properties, and uses a number of algorithms to determine whether or not the images are cancerous. In this universe, the same terrible sickness affects both men and women. The youngster may have anemia and extreme exhaustion if the bone marrow is unable to produce enough RBCs to transport oxygen.

 Blood will not clot correctly and the patient may bleed readily if there are insufficient platelets generated. WBCs must be present in sufficient numbers for the body to be able to fight against pathogens; otherwise, infections may become common. An acute or chronic form of leukemia is possible. The illness known as cancer is characterized by unchecked cellular growth.

An assortment of blood cell types are referred to together as white blood cells (WBCs). When a disease is being diagnosed, these cells don't show any symptoms or vital details. Leukemia detection and treatment significant difficulties in general

Types of Lung Cancer:

Based on how lung cancer cells look under a microscope, doctors classify the disease into two main categories. Depending on the primary form of lung cancer you have, your doctor will decide how to proceed with therapy.

Small cell lung cancer: Heavy smokers are virtually always diagnosed with small cell lung cancer.

Non-small cell lung cancer: The term "non-small cell lung cancer" refers to a variety of lung malignancies that have a common pattern of behavior. Squamous cell carcinoma, adenocarcinoma, and large cell carcinoma are examples of non-small cell lung malignancies.

Symptoms: Early-stage lung cancer often doesn't present with any symptoms. Lung cancer signs and symptoms often only appear once the condition has progressed.

Lung cancer signs and symptoms may include the following: persistent coughing, coughing up blood, shortness of breath, chest discomfort, wheezing, hoarseness, unexplained weight loss, bone pain, and headache.

Factors at Risk for Lung Cancer Include: Smoking: The quantity of cigarettes you smoke each day raises your chance of developing lung cancer.

II. IMPLEMENTATION

The project's implementation phase is where a theoretical design is transformed into a functional system. The user department is now responsible for the majority of the workload and the majority of the effects on the current system. If the implementation is not well planned and managed, it may result in confusion and anarchy.

Compared to the design phase, implementation is less imaginative. All of the processes that are used to switch from one system to another are referred to as implementation. A manual that was previously used with an automated system may be completely replaced by the new system. It could involve a significant overhaul of the current setup.

For a system to be reliable and satisfy organizational needs, good implementation is crucial in both scenarios. The implementation requires the following tasks. Careful planning. Investigation of the system and constraints. Design of methods to achieve the changeover. Evaluation of changeover method.

A. Implementation Strategies

1. Documentation:  A written account of each stage of a particular project is known as documentation. It establishes the performance and design, which are crucial for the project's phase. In order to test the software and continue maintenance after the application has been deployed, documentation is crucial.
2. Conversion: To convert is to switch from one system to another. The goal is to launch the tested system with the fewest possible risks and employee annoyances. Because conversion is the final stage before the candidate system starts to display the results, it must be eciting.
3. Post Implementation Review:  A post-implementation assessment assesses the system's performance in relation to how well it achieves its stated goals. The system performance is compared to predetermined requirements during the post-implementation evaluation.

B. Module Implementation

There are 4 main modules in our project.

C. Image-Input Module

The acquisition of images is another name for this phase. It is necessary to enter microscope pictures in order to detect illnesses like blood cancer and lung cancer. This informative index or data collection includes extremely small images of blood smears and lung CT scans.

D. Preprocessing Module

Preprocessing is the third step that is taken once the picture has been successfully loaded.

E. Feature Extraction

The segmented cancer object's area value is calculated during the feature extraction step based on shape, and the color of the original picture is then recreated using this technique, which reduces the dimensionality of the data by turning it into a series of highlights. If the highlights are correctly extracted, the feature set will be able to distinguish the important data from the input data.

F. Module for classification

The final phase of the procedure is classification. It helps identify the presence of white blood cancer cells in a blood image. After receiving the input image's values for area, contrast, energy, entropy, and homogeneity, which are then compared to the data for the parameter values in the training process' outcome database, the decision-making step is completed.

III. ADVANTAGES

1. The likelihood of a cancer diagnosis being made early increases significantly.
2. This therapy is frequently easier to administer and is more likely to be successful.
3. The systems that are being suggested are more effective and produce better results.
4. Offers improved picture accuracy and quality.

IV. APPLICATIONS

1. Include the early diagnosis of cancer in several medical specialties. Consequently, the patient will receive the appropriate care.
2. This processing method may be utilized to research tumors and other cancers that affect our body parts.

Conclusion

A potentially lethal condition is cancer. For physicians, detecting cancer is increasingly difficult. Cancer that is discovered in its early stages can be treated. This system\'s primary goal is to detect cancer in its earliest stages, allowing for timely patient treatment. We have suggested a technique that uses machine learning to automatically identify cancer. Both men and women may get cancer, but the three most prevalent types in women are blood, lung, and breast cancer. Although the signs and symptoms of each type of cancer might differ or not always be present, cancer still exists. Therefore, it is always preferable to detect cancer in its earliest stages. Cancer stages often rely on the size, location, and which organs are diseased.

References

[1] Lung Cancer Detection and Classification from Chest CT Scans Using Machine Learning Techniques Amjad Rehman; Muhammad Kashif; Ibrahim Abunadi; Noor Ayesha 11 May 2021 10.1109/CAIDA51941.2021.9425269 [2] Analysis of Lung Cancer Detection Based on the Machine Learning Algorithm and IOT K. Karthick; S. Rajkumar; N. Selvanathan; U.K.Balaji Saravanan; M. Murali; B. Dhiyanesh02 August 202110.1109/ICCES51350.2021.9489084 [3] Detection of Blood Cancer-Leukemia using K-means Algorithm Ranjitha P; Sudharshan Duth P26 May 2021 10.1109/ICICCS51141.2021.9432244 [4] Computer based diagnosis of Leukemia in blood smear images Raghav Kandhari; Anupama Bhan; Parth Bhatnagar; Ayush Goyal 31 March 2021 10.1109/ICICV50876.2021.9388546 [5] Investigation of Lung Cancer detection Using 3D Convolutional Deep Neural Network Srinivas Arukonda; S. Sountharrajan 10.1109/ICACCCN51052.2020.9362857 01 March 2021 [6] [4] R. Wulandari, R. Sigit, and S. Wardhana, \"Automatic lung cancer detection using color histogram calculation,\" 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), Surabaya, 2017, pp. 120-126. [7] L. Anifah, Haryanto, R. Harimurti, Z. Permatasari, P. W. Rusimamto, and A. R. Muhamad, \"Cancer lung detection on CT scan image using artificial neural network backpropagation based gray level cooccurrence matrices feature,\" 2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Bali, 2017, pp. 327-332. [8] D. P. Kaucha, P. W. C. Prasad, A. Alsadoon, A. Elchouemi, and S. Sreedharan, \"Early detection of lung cancer using SVM classifier in biomedical image processing,\" 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), Chennai, 2017, pp. 3143-3148. [9] F. Taher, N. Werghi, and H. Al-Ahmad, \"Computer-aided diagnosis system for early lung cancer detection,\" 2015 International Conference on Systems, Signals and Image Processing (IWSSIP), London, 2015. [10] E. Rendon-Gonzalez and V. Ponomaryov, \"Automatic Lung nodule segmentation and classification in CT images based on SVM,\" 2016 9th International Kharkiv Symposium on Physics and Engineering of Microwaves, Millimeter and Submillimeter Waves (MSMW), Kharkiv, 2016, pp. 1-4. [11] Kulkarni and A. Panditrao, \"Classification of lung cancer stages on CT scan images using image processing,\" 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies, Ramanathapuram, 2014, pp. 1384-1388. [12] S. A. El-Regaily, M. A. M. Salem, M. H. A. Aziz and M. I. Roushdy, \"Lung nodule segmentation and detection in computed tomography,\" 2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS), Cairo, 2017, pp. 72-78. [13] M. H. Jony, F. Tuj Johora, P. Khatun and H. K. Rana, \"Detection of Lung Cancer from CT Scan Images using GLCM and SVM,\" 2019 1st International Conference on Advances in Science, Engineering and

Copyright

Copyright © 2022 Chandana V J, Kavya Shree S, Rashmi G, Soundarya K S, Anusha S Aradhya. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.