Sökning: "Medical image processing"

Visar resultat 1 - 5 av 77 uppsatser innehållade orden Medical image processing.

  1. 1. Real-time Autofocus Algorithm in Laser Speckle Contrast Imaging

    Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

    Författare :Giovanni Russo; [2023]
    Nyckelord :Laser speckle contrast imaging; Autofocus; Blind image sharpness assessment; Speckle noise; Perimed’s Perfusion Speckle Imager;

    Sammanfattning : Microcirculation is defined as the blood flow in the smallest blood vessels. Laser speckle contrast imaging (LSCI) is a full field imaging technique that provides instantaneous 2-D perfusion maps of illuminated tissues based on speckle contrast. LÄS MER

  3. 2. Methods for determining focal point and delay for ultrasound arrays and multichannel electronics

    Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknik

    Författare :Svante Rosenlind; [2023]
    Nyckelord :Focusing algorithms; k-wave; Spatiotemporal inverse filter; Gerchberg- Saxton algorithm; Focused ultrasound; Technology and Engineering;

    Sammanfattning : High intensity focused ultrasound is a growing technique for tissue ablation, among other uses, and given its destructive capabilities, there is a need for control of where the energy is delivered. There exist a number of methods for focusing such ultrasound arrays, but these often assume prior knowledge of the impulse response, or require extensive full-system simulations. LÄS MER

  4. 3. Multiclass Brain Tumour Tissue Classification on Histopathology Images Using Vision Transformers

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Christoforos Spyretos; [2023]
    Nyckelord :medical imaging; deep learning; classification; CNN; Vision Transformer; glioblastoma; GBM; IvyGAP; brain tumour; histopathology; digital pathology; histology;

    Sammanfattning : Histopathology refers to inspecting and analysing tissue samples under a microscope to identify and examine signs of diseases. The manual investigation procedure of histology slides by pathologists is time-consuming and susceptible to misconceptions. LÄS MER

  5. 4. Comparative Analysis of Transformer and CNN Based Models for 2D Brain Tumor Segmentation

    Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

    Författare :Henrik Träff; [2023]
    Nyckelord :Machine Learning; ML; AI; Computer vision; Vision Transformer; Swin Transformer; U-Net; nnU-Net; Brain Tumor Segmentation; Deep Learning;

    Sammanfattning : A brain tumor is an abnormal growth of cells within the brain, which can be categorized into primary and secondary tumor types. The most common type of primary tumors in adults are gliomas, which can be further classified into high-grade gliomas (HGGs) and low-grade gliomas (LGGs). LÄS MER

  7. 5. Phase Unwrapping MRI Flow Measurements

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3

    Författare :Mio Liljeblad; [2023]
    Nyckelord :phase unwrapping; computer vision; cine MRI; NMR; flow measurements; velocity encoding; venc; energy minimization; magnetic resonance; cardiac MRI; sinotubuar junction; pulmonary artery; ascending descending aorta; laplacian algorithm; iterative graph cuts; IGC; sequential tree-reweighted message passing; TRW-S; velocity to noise ratio; VNR; retrospective wrapping; energy formulation;

    Sammanfattning : Magnetic resonance images (MRI) are acquired by sampling the current of induced electromotiveforce (EMF). EMF is induced due to flux of the net magnetic field from coherent nuclear spins with intrinsic magnetic dipole moments. LÄS MER