Browsing by Author "Datta, Sajeeb"

Now showing 1 - 3 of 3

A Comparative Study Of Lung Cancer Detection Using Deep Transfer Learning With Keras Tuner
(Daffodil International University, 2024-02-04) Datta, Sajeeb
Lung cancer is a type of cancer that begins in the cells of the lungs. It is one of the most common forms of cancer worldwide and is a leading cause of cancer-related deaths. Lung cancer usually develops in the cells lining the air passages of the lungs.There are two main types of lung cancer: non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). NSCLC is the most prevalent, comprising about 85% of all lung cancer cases, while SCLC is generally more aggressive and tends to spread quickly. The need for early detection is underscored by the fact that lung cancer symptoms often manifest at advanced stages, limiting treatment options and reducing the likelihood of successful intervention. This thesis presents a comprehensive study on the application of six pre-trained convolutional neural network models, namely MobileNetV2, InceptionV3, ResNet50, VGG16, VGG19, and NASHNetMobile, for the classification of lung cancer categories. The dataset used in this research consists of 15,000 images, spanning three distinct classes: Lung Adenocarcinoma, Lung Benign Tissue, and Lung Squamous Cell Carcinoma. To optimize model performance, hyperparameter tuning is employed using the Keras Tuner framework. This approach allows for the systematic exploration of hyperparameter configurations to enhance the models' accuracy and generalization. The hyperparameters include learning rates, dropout rates, and other key parameters crucial for model training. The results indicate that MobileNetV2 achieved the highest accuracy among the tested models, with an impressive 98.47%. Following closely, VGG16 demonstrated the second-best performance, achieving an accuracy of 98.40%. The study contributes valuable insights into the practical application of deep learning models for medical image classification tasks, particularly in the context of lung cancer diagnosis. The reported accuracies demonstrate the potential of leveraging pre-trained models to enhance the efficiency and accuracy of computer-aided diagnostic systems for early detection of lung cancer.
Peripheral Blood Smear Image-Based Blood Cancer Detection Using Transfer Learning
(Springer Nature, 2024-03-30) Shaha, Sonjoy Prosad; Datta, Sajeeb; Mahmud, Md. Nadim; Ahmad, Md. Hassan; Johora, Fatema Tuj; Rahman, Md. Atiqur
The lymphatic, bone marrow, and blood systems are all affected by hematological malignancy, also known as blood cancer. Early detection is essential for improved blood medical care and better patient outcomes. In the recent past, deep learning algorithms have developed as useful tools for the analysis and diagnosis of medical images. Deep learning algorithms are used in this study to introduce a cutting-edge technique for identifying blood cancer. Our method involves training a convolutional neural network (CNN) with a large dataset of blood cell data to identify the presence of cancerous cells. We compare our CNN-based approach’s effectiveness with some other CNN-based approaches and demonstrate that it is more effective at detecting blood cancer. We used a variety of preprocessing techniques to provide highly trainable data for our algorithms in order to do this. Five CNN-based algorithms—VGG-19, VGG-16, MobileNet, InceptionV3, and ResNet50—as well as healthy and fragmented data are used in this study. With an accuracy of 95%, ResNet50 achieved the highest accuracy. Our study’s results suggest that deep learning algorithms could be helpful in detecting blood cancer early, leading to a more precise diagnosis and course of treatment for this fatal condition.
Peripheral Blood Smear Image-Based Blood Cancer Detection Using Transfer Learning
(2024-03-30) Shaha, Sonjoy Prosad; Datta, Sajeeb; Mahmud, Md. Nadim; Ahmad, Md. Hassan; Tuj Johora, Fatema; Rahman, Md. Atiqur
The lymphatic, bone marrow, and blood systems are all affected by hematological malignancy, also known as blood cancer. Early detection is essential for improved blood medical care and better patient outcomes. In the recent past, deep learning algorithms have developed as useful tools for the analysis and diagnosis of medical images. Deep learning algorithms are used in this study to introduce a cutting-edge technique for identifying blood cancer. Our method involves training a convolutional neural network (CNN) with a large dataset of blood cell data to identify the presence of cancerous cells. We compare our CNN-based approach’s effectiveness with some other CNN-based approaches and demonstrate that it is more effective at detecting blood cancer. We used a variety of preprocessing techniques to provide highly trainable data for our algorithms in order to do this. Five CNN-based algorithms—VGG-19, VGG-16, MobileNet, InceptionV3, and ResNet50—as well as healthy and fragmented data are used in this study. With an accuracy of 95%, ResNet50 achieved the highest accuracy. Our study’s results suggest that deep learning algorithms could be helpful in detecting blood cancer early, leading to a more precise diagnosis and course of treatment for this fatal condition.