Advanced search

Showing result 1 - 5 of 26 essays matching the above criteria.

1. 1. Exploring adaptation of self-supervised representation learning to histopathology images for liver cancer detection

   University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Author : Markus Jonsson; [2024]
   Keywords : Self-supervised learning; Representation learning; Computer vision;

   Abstract : This thesis explores adapting self-supervised representation learning to visual domains beyond natural scenes, focusing on medical imaging. The research addresses the central question: "How can self-supervised representation learning be specifically adapted for detecting liver cancer in histopathology images?" The study utilizes the PAIP 2019 dataset for liver cancer segmentation and employs a self-supervised approach based on the VICReg method. READ MORE

3. 2. Enhancement-basedSmall TargetDetection for InfraredImages

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Yang Hanqi; [2023]
   Keywords : Infrared Images; Small targets; Dilated Convolution; Infraröda bilder; Små mål; Dilaterad konvolution;

   Abstract : Infrared small target detection is widely used in fields such as military and security. UNet, which is a classical semantic segmentation method proposed in 2015, has shown excellent performance and robustness. However, U-Net suffers from the problem of losing small targets in deep layers after multiple down-sampling operations. READ MORE

4. 3. Performance Evaluation of Lumen Segmentation in Ultrasound Images

   University essay from Umeå universitet/Institutionen för datavetenskap

   Author : Alexander Kadeby; [2023]
   Keywords : Image Segmentation; Atherosclerosis; VIPVIZA; Lumen Segmentation; Threshold Algorithms;

   Abstract : Automatic segmentation of the lumen of carotid arteries in ultrasound images is a starting step in providing preventive care for patients with atherosclerosis. To perform the segmentation this paper introduces a model utilizing a threshold algorithm. READ MORE

5. 4. Exploration of performance evaluation metrics with deep-learning-based generic object detection for robot guidance systems

   University essay from Linköpings universitet/Institutionen för datavetenskap

   Author : Helena Gustafsson; [2023]
   Keywords : performance evaluation; robot guidance system; deep learning; object detection; instance segmentation;

   Abstract : Robots are often used within the industry for automated tasks that are too dangerous, complex, or strenuous for humans, which leads to time and cost benefits. Robots can have an arm and a gripper to manipulate the world and sensors for eyes to be able to perceive the world. READ MORE

6. 5. Feasibility of quantitative 99mTc-DPD scintigraphy SPECT/CT for assessing the burden of ATTR cardiac amyloidosis

   University essay from Umeå universitet/Radiofysik

   Author : Sajad Kadhim Khalaf; [2023]
   Keywords : QSPECT; Amyloidosis; ATTR; LVMI; Recovery Coefficient; SUV; Calibration;

   Abstract : Background: Amyloid transthyretin (ATTR) cardiomyopathy is caused by the deposition of misfolded proteins, known as amyloid fibrils, in the myocardium. Quantitative Single Photon Emission Computed Tomography (QSPECT) utilizing 99mTc-DPD scintigraphy has the potential to assess ATTR-suspected cardiac amyloidosis (CA). READ MORE