Dissertation and Thesis
Permanent URI for this communityhttp://164.52.219.250:4000/handle/10263/2146
Browse
3 results
Search Results
Item On Automated Analysis of Lung Images with Deep Learning for Healthcare(Indian Statistical Institute, Kolkata, 2025-06) Pal, SurochitaAutomated detection and diagnosis of lung diseases through medical image analysis offers a noninvasive alternative to invasive procedures, especially considering the challenges and potential risks associated with repeat lung operations. Noninvasive image-guided diagnostic techniques, such as lung imaging, have become essential in clinical practice. This thesis focuses on the development of a computer-aided system aimed at enhancing the classification, detection, and segmentation of lung diseases, specifically caused by COVID-19 and lung tumors, leveraging advanced computational methods. Novel segmentation algorithms, such as EFMC and WDU-Net, are devised based on encoder-decoder architectures within deep convolution networks. These algorithms undergo rigorous validation against ground truth or manual segmentation by radiologists, ensuring their accuracy and reliability. The EFMC algorithm employs a selective focus mechanism with multi-resolution blocks, allowing for precise delineation of COVID-19 affected regions in lung CT scans. Its performance is validated through extensive comparison with expert annotations, demonstrating its effectiveness in capturing subtle abnormalities while accurately segmenting lung anomalies. Similarly, WDU-Net integrates weighted deformable convolution. Here the deformable convolution modules enhance its ability to capture irregular shapes and features in COVID-19 and lung tumors. Validation against manual segmentation reveals its robustness and accuracy in segmenting COVID-19 and lung tumors from CT images; thereby, showcasing its potential for aiding clinical diagnosis and treatment planning. Next automated classification of lung tumors is devised, in the multi-modal PET-CT framework, using the innovative DEMF model. The network leverages deep convolution networks, in conjunction with dimensionality reduction, to efficiently detect and classify lung abnormalities. This demonstrates superior performance in lung cancer classification across multimodal images. Finally, the DGMC is developed to enhance diagnosis and classification of diseases, by co-learning from multimodal images. Utilizing a novel multihead classifier, the DGMC can efficiently distinguish between COVID-19, tumors, and healthy slices of the lung. The input signal encompasses CT, along with EIT-processed CT scans, in order to provide a multimodal flavour. It captures granular details of the infection, while visualizing the activation regions. Together, these advancements represent significant progress in the automated analysis of lung diseases, by providing valuable tools for the early detection and diagnosis in clinical settings.Item Few shot segmentation for COVID-19 infected lung CT slices(Indian Statistical Institute, Kolkata, 2022-07) Chatterjee, SohamThe last 2 years have been adversely affected by the COVID-19 pandemic. Doctors usually detect Covid from CT slices from features such as ground glass, consolidation and pleural effusion. These features usually have complex contours, irregular shapes and rough boundaries. With increasing number of cases the workload on the radiologists have increased by leaps and bounds to analyze the lung CT scans for tracking the disease progression in the patient. Moreover manual analysis of the CT scans is also prone to human error. So automated segmentation of infected lung CT slices can help the doctors to diagnose the disease faster. With the advent of deep learning, various approaches have been built to tackle this problem of automated biomedical image segmentation. One such architecture is the U-Net by Ronnenberger et al. [14]. Various other approaches have been proposed which are all variations of the U-Net to achieve better segmentation performance. However, the U-Net and its variations suffer from high model complexity, due to which they easily overfit on limited labelled dataset which is a serious issue in medical image domain. To cater this problem of data scarcity, research in “few shot segmentation” has gained significant importance in the recent years. In this work, we have developed a deep neural network model called Few Shot Conditioner Segmenter Covid (FSCS-cov), an architecture to tackle the problem of segmenting different COVID- 19 lesions from limited number of COVID-19 infected lung CT slices using few - shot learning paradigm.Item Deep Learning for Classification of COVID-19 Chest CT Scan(Indian Statistical Institute, Kolkata., 2021-07) Ghosh, SubhadipThe latest threat to global health is COVID-19. It has a tremendous diffusion rate and to combat with this pandemic, large scale testing and diagnosis is required. RT-PCR is the most accurate screening for validating COVID19 infection, but it is highly dependent on swab technique and needs time and resources. Thus, we need to find an alternative way to predict COVID19. Many researchers already conclude that COVID-19 is very related to Pneumonia and lungs feature of COVID is related to that of Pneumonia. There is ongoing research to detect Pneumonia [13] from Chest CT scans. Lung segmentation can help us to detect pulmonary abnormalities[10]. In this article first we try to segment lungs from chest CT scan and investigate the problems we face for COVID cases in deep learning architectures for lung segmentation. We propose an classical image processing algorithm to detect Lung from chest CT. As already mentioned that CNN is a great architecture to classify images, we are going to use a deep CNN model for lung classification. Covid is a new disease and we have to move faster to detect it. Hence, we are going to use transfer learning approach and use knowledge of pneumonia detection to classify COVID-19. In deep learning weight initialization for deep neural network is a major factor and can lead us to very different performance. In this article we are going to propose an weight initialization technique for transfer learning that can use not only the information about the architecture but also the information of the new class with respect to other known classes.