IEEE BASE PAPER TITLE:
Kidney Cancer Detection using Deep Learning Models
OUR PROPOSED PROJECT TITLE:
AI Kidney Cancer Diagnosis: A Deep Learning Approach Integrating CT Scan and Blood Test Analysis
IEEE BASE PAPER ABSTRACT:
This study presents two types of Kidney cancer detection one is with the help of images and another one is with the help of blood test samples value. Kidney disease is condition caused either by renal disease of the kidneys. In the present study, Kidney cancer is one of the critical diseases for patient’s diagnosis and classification. Early detection and good treatment can avoid or decrease the growth of cancer disease into the final stage where dialysis or renal transplantation is the only way of saving the life of the patient. And another way is with machine learning models with this model the disease at an early stage can be detected, is one of the important tasks in today’s world. This research proposed kidney images detection through deep learning models like Convolutional Neural Networks (CNNs), and blood samples dataset values through Artificial Neural Network (ANN) models that can be helpful for the early diagnosis of cancer. The existing studies have mainly used only simple CNN models and have done another classification of kidney images. This research consists of CNN with more convolution layers for classifying images of cancer kidneys and normal kidneys and ANN is used for kidney cancer prediction using dataset values. This research will be helpful for early and accurate diagnosis of kidney cancer to save the lives of many patients. Lastly, there is an application page that contains a code in the backend that predicts whether a person is suffering from a kidney cancer or not.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
MobileNet Architecture + Artificial Neural Network (ANN).
OUR PROPOSED PROJECT ABSTRACT:
Kidney cancer is a formidable health challenge worldwide, demanding innovative diagnostic solutions for early and accurate detection. In this pioneering project, we introduce a dual-pronged approach to kidney cancer detection, utilizing state-of-the-art deep learning models, Python programming, and a user-friendly web interface developed with Flask. The first facet of our approach involves the analysis of CT scan images. We employed the cutting-edge MobileNet architecture to develop a deep learning model that exhibits remarkable prowess in distinguishing kidney tumor tissues. Our model achieved a remarkable training accuracy of 99.00% and a validation accuracy of 99.00%. This robust performance is crucial for ensuring the highest level of confidence in identifying cancerous growths. The CT scan dataset comprises 5,077 normal class images and 2,283 tumor class images, making it a comprehensive and well-structured resource for training and testing our model. In addition to CT scan analysis, we have implemented a complementary method for kidney cancer detection based on blood test samples. Leveraging an Artificial Neural Network (ANN) model, we attained a training accuracy of 90% and a validation accuracy of 97%, underlining the efficacy of our approach in utilizing both imaging and biochemical data. The blood test dataset comprises 400 individual records, each featuring 26 essential attributes, including age, blood pressure, glucose levels, and various clinical markers. This extensive dataset allows us to harness diverse patient information for more accurate and holistic diagnosis. To make our innovative kidney cancer detection system accessible and user-friendly, we have created a web interface using Flask. This interface empowers healthcare professionals and patients alike to easily input CT scan images or blood test data and obtain rapid and reliable results. The web interface enhances the practicality and usability of our deep learning models, ultimately contributing to the early diagnosis and management of kidney cancer. In summary, our project presents a groundbreaking approach to kidney cancer detection, harnessing the power of Python-based deep learning models and a user-friendly web interface. By combining CT scan image analysis and blood test data, we provide a comprehensive diagnostic solution with the potential to revolutionize kidney cancer diagnosis and treatment.
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
- Operating system : Windows 10 Pro.
- Coding Language : Python 3.10.9.
- Web Framework :
Rajkumar; Ravi Teja Sri Ramoju; Tharun Balelly; Sravan Ashadapu; Ch.Rajendra Prasad, Yalabaka Srikanth, “Kidney Cancer Detection using Deep Learning Models”, 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), IEEE Conference, 2023.