Dissertations/Theses - Department of Biomedical Engineering

Impact of hematological and morphological variations at circle of willis on cerebrovascular hemodynamics

2025-05-19T00:00:00Z

Impact of hematological and morphological variations at circle of willis on cerebrovascular hemodynamics Tarik Arafat, Dr. Muhammad; Jafrin Sultana; 0421182028; 612.1181/JAF/2025 Cerebrovascular diseases, including ischemic stroke and intracranial hemorrhage, remain leading global health burdens. The Circle of Willis (CoW), a critical arterial network for cerebral perfusion, is highly influenced by hematological factors, such as blood viscosity and hematocrit levels, as well as anatomical variations like hypoplasia, agenesis, and asymmetry. This study employs Computational Fluid Dynamics (CFD) simulations on patient-specific CoWs’ geometries to investigate the combined impact of hematocrit variation, stenosis morphology, and anatomical abnormalities on intracranial hemodynamics. Using ANSYS software and modeling blood as a non-Newtonian Carreau fluid under pulsatile flow, key hemodynamic indices as wall shear stress (WSS), time average wall shear stress, oscillatory shear index, velocity, translesional pressure ratio, pressure drop index, and stroke risk index, were computed to characterize cerebrovascular behavior under diverse physiological and pathological states. The influence of varying hematocrit levels on wall shear stress and cerebral perfusion is observed using computational fluid dynamics models in normal and aneurysmal geometries. Elevated hematocrit increased blood viscosity and WSS, while lower hematocrit led to reduced shear forces. The WSS-viscosity relationship was nonlinear: low WSS regions were linked to endothelial apoptosis and aneurysm formation, whereas high WSS areas correlated with increased rupture risk. Stenosis geometry and CoW integrity as key determinants of hemodynamic cooperation were identified through nine design of experiments framework. Irregular stenosis and anatomical incompleteness impaired collateral flow, particularly during occlusion, elevating ischemic susceptibility. Hemodynamic metrics indicated that local stress variations promoted atherogenesis and increased thromboembolic risk. Results emphasize the correlation among CoW morphology, hematological factors, and flow dynamics in cerebrovascular pathology. CFD modeling, integrated with clinical data, offers a robust platform for individualized risk assessment and therapeutic planning. Future research incorporating real-time imaging and AI-driven analysis may enhance predictive accuracy and improve stroke prevention strategies. Keywords: Stroke; Ischemic Stroke; Hematological and Morphological Variation; Circle of Willis; Cerebrovascular Hemodynamics; Computational Fluid Dynamics

Diagnosis-oriented learned image compression system for chest radiographs with Regions-of-interest control

2025-05-28T00:00:00Z

Diagnosis-oriented learned image compression system for chest radiographs with Regions-of-interest control Hasan Al Banna, Dr. Taufiq; Ibn Sabur Khan Nuhash, Shoyad.; 0421182004; 616.0754/IBN/2025 This thesis presents DiagLIC, a diagnosis-oriented learned image compression (LIC) framework specifically designed for chest radiographs. Unlike conventional codecs and general-purpose LIC models that prioritize visual fidelity or bitrate efficiency alone, the proposed method in- corporates both diagnostic awareness and region-of-interest (ROI) preservation directly into the compression objective. Leveraging a transformer-based architecture with prompt-conditioned Swin Transformer blocks, the system supports variable-rate compression through a single model and allocates higher representational capacity to clinically significant regions such as lesions, opacities, or cardiomegaly zones. The framework is jointly optimized using a composite loss function that integrates rate-distortion and classification performance, ensuring that compressed images retain features essential for downstream diagnosis. Empirical evaluation on NIH and VinDr-CXR subsets demonstrates that DiagLIC significantly outperforms classical codecs (e.g., JPEG, WebP, JPEG2000) and state-of-the-art learned compression baselines in both PSNR and diagnostic accuracy. Across six quality levels, DiagLIC consistently achieves higher PSNR (e.g., 40.42 dB at 0.0951 bpp) and yields an average weighted PSNR of up to 52.49 dB, with ROI-specific PSNRs exceeding NROI PSNRs by over 1 dB at all levels. For diagnostic classifi- cation, DiagLIC maintains high fidelity, with only a minimal drop in average AUC (0.014) com- pared to uncompressed images, achieving AUC scores above 0.70 across all 8 tested patholo- gies and no degradation in certain categories such as Nodule/Mass. Statistical analysis confirms that the improvements in rate-distortion performance over baselines are significant, while the reduction in diagnostic performance remains clinically negligible. Qualitative comparisons fur- ther reveal that DiagLIC effectively suppresses artifacts and preserves lesion-level details, even at aggressive compression. This work demonstrates the feasibility and clinical value of inte- grating semantic objectives into image compression models, laying the groundwork for future diagnosis-preserving compression techniques in medical imaging.

Leveraging frequency domain attributes for multi-modal medical image segmentation using convolutional neural networks

2025-05-28T00:00:00Z

Leveraging frequency domain attributes for multi-modal medical image segmentation using convolutional neural networks Hasan Al Banna, Dr. Taufiq; Shams Nafisa Ali; 0422182001; 616.0754/SHA/2025 Recent advances in deep learning have significantly enhanced medical image segmen- tation. As medical data becomes increasingly diverse and complex, the need for ar- chitectures that can generalize across modalities and anatomical structures has grown paramount. While CNNs, Transformers, and their hybrid architectures have addressed issues such as limited receptive fields and redundant feature representations, most mod- els remain confined to the spatial domain—overlooking the frequency domain’s rich structural cues. Some recent studies have explored spectral information at the feature level; however, frequency-domain integration at the supervision level remains largely untapped. To this end, we propose Phi-SegNet, a CNN-based architecture that incor- porates phase-aware cues at both architectural and optimization levels. The network integrates Bi-Feature Mask Former (BFMF) modules that blend neighboring encoder features to reduce semantic gaps, and Reverse Fourier Attention (RFA) blocks that re- fine decoder outputs using phase-regularized embeddings. A dedicated phase-aware loss aligns these embeddings with structural priors, forming a closed feedback loop that emphasizes boundary precision. Evaluated on five public datasets spanning ultra- sound, X-ray, histopathology, MRI, and colonoscopy, Phi-SegNet consistently achieves state-of-the-art performance, particularly excelling in fine-grained boundary segmen- tation tasks. On average, across these five datasets, Phi-SegNet achieves a relative improvement of 1.54% ± 1.26% in IoU and 1.10% ± 0.69% in F1-score over the next best-performing model for each dataset. Additionally, under generalized training using a unified dataset comprising all five modalities, as well as in cross-dataset generaliza- tion scenarios involving unseen datasets from the known domain, Phi-SegNet exhibits robust and superior performance—highlighting its adaptability and modality-agnostic design. These findings demonstrate the potential of leveraging spectral priors in both learning and supervision, offering a new direction toward generalized, universal, and anatomically precise segmentation frameworks.

Automated denoising and classification of lung sounds using end-to-end deep learning models

2025-04-19T00:00:00Z

Automated denoising and classification of lung sounds using end-to-end deep learning models Hasan Al Banna, Dr. Taufiq; Samiul Based Shuvo; 0422182002; 623.822/SAM/2025 Lung sound auscultation is essential for monitoring respiratory health, especially in regions facing a shortage of skilled healthcare workers. Automated analysis of respi- ratory sounds has the potential to provide significant clinical support in such settings. However, lung sounds (LS) are frequently contaminated by various noise sources such as heart sounds, background conversations, and movement artifacts which makes accu- rate interpretation challenging. Conventional denoising techniques often fail to address these challenges due to the spectral overlap between noise and respiratory signals in real-world clinical recordings. In addition to that, while respiratory sound classification has been widely studied in adults, its application in pediatric populations, particularly in children aged <=6 years, remains a complex and underexplored area. The developmen- tal changes in pediatric lungs considerably alter the acoustic properties of respiratory sounds, necessitating specialized classification approaches tailored to this age group. To address these challenges and advance automated lung sound analysis, this thesis is divided into two major components. In the first part, a specialized deep-denoiser model (Uformer) has been proposed for lung sound denoising. The proposed Uformer model consists of three modules: a Convolutional Neural Network (CNN) encoder module dedicated to extracting latent features, a Transformer encoder module employed to en- hance the encoding of unique LS features further and effectively capture intricate long- range dependencies, and a CNN decoder module employed to generate the denoised signals. The performance of the proposed Uformer model has been evaluated on lung sounds induced with different types of synthetic and real-world noise. The proposed model showed an average output SNR of 16.51 dB when evaluated with -12 dB LS signals. Our end-to-end model, with an average output SNR of 19.31 dB, outperforms the existing model, achieving nearly double the performance, when evaluated with am- bient noise and fewer parameters. Based on the qualitative and quantitative findings in this study, it can be stated that the proposed denoising model is robust and gener- alized to assist with monitoring respiratory conditions. The second part of the thesis focuses on the classification of pediatric respiratory sounds. A multistage hybrid CNN- Transformer architecture has been proposed for detecting respiratory diseases from both entire recordings and individual breath cycles using scalogram images of the signals. To fill the gap in pediatric classification, the SPRSound dataset, comprising recordings from children with an average age of 5.5 years, has been utilized for two-level classifica- tion tasks. The proposed classification model utilizes CNN-extracted respiratory sound features from scalogram images, integrating an attention framework to improve predic- tive performance. The proposed framework achieved a score of 0.9039 in binary event classification and 0.8448 in multiclass event classification. At the record level, ternary classification yielded a score of 0.720, while multiclass record classification attained 0.571. However, our proposed method consistently demonstrates a 3.81% and 5.94% performance gain over the existing best model, respectively, in these record-level clas- sification tasks. These proposed approaches can significantly aid in the diagnosis and prediction of the severity of respiratory diseases in both developing and underdeveloped nations.