Melanoma is one of the deadliest forms of cancer. Unfortunately, its incidence rates have been increasing all over the world. One of the techniques used by dermatologists to diagnose melanomas is an imaging modality called dermoscopy. The skin lesion is inspected using a magnification device and a light source. This technique makes it possible for the dermatologist to observe subcutaneous structures that would be invisible otherwise. However, the use of dermoscopy is not straightforward, requiring years of practice. Moreover, the diagnosis is many times subjective and challenging to reproduce. Therefore, it is necessary to develop automatic methods that will help dermatologists provide more reliable diagnoses.  Since this cancer is visible on the skin, it is potentially detectable at a very early stage when it is curable. Recent developments have converged to make fully automatic early melanoma detection a real possibility. First, the advent of dermoscopy has enabled a dramatic boost in the clinical diagnostic ability to the point that it can detect melanoma in the clinic at the earliest stages. This technology’s global adoption has allowed the accumulation of extensive collections of dermoscopy images. The development of advanced technologies in image processing and machine learning has given us the ability to distinguish malignant melanoma from the many benign mimics that require no biopsy. These new technologies should allow earlier detection of melanoma and reduce a large number of unnecessary and costly biopsy procedures. Although some of the new systems reported for these technologies have shown promise in preliminary trials, a widespread implementation must await further technical progress in accuracy and reproducibility.  This thesis provides an overview of our deep learning (DL) based methods used in the diagnosis of melanoma in dermoscopy images. First, we introduce the background. Then, this paper gives a brief overview of the state-of-art article on melanoma interpret. After that, a review is provided on the deep learning models for melanoma image analysis and the main popular techniques to improve the diagnose performance. We also made a summary of our research results. Finally, we discuss the challenges and opportunities for automating melanocytic skin lesions’ diagnostic procedures. We end with an overview of a conclusion and directions for the following research plan.

This report introduces the multislice method for modeling the interaction between an electron and the atoms in the specimen (electron-specimen interaction). The multislice method is an approximation to the full quantum mechanical model for this interaction. After introducing the theory, we discuss how the multislice method is implemented and integrated into TEM-simulator, a software for simulation of Transmission Electron Microscope (TEM) images.

Single photon emission tomography (SPECT) data from myocardial perfusion imaging (MPI) are normally displayed as a set of three slices orthogonal to the left ventricular (LV) long axis for both ECG-gated (GSPECT) and non-gated SPECT studies. The total number of slices presented for assessment depends on the size of the heart, but is typically in excess of 30.  A requirement for data presentation is that images should be orientated about the LV axis; therefore, a set of radial slice would fulfill this need. Radial slices are parallel to the LV long axis and arranged diametrically. They could provide a suitable alternative to standard orthogonal slices, with the advantage of requiring far fewer slices to adequately represent the data. In this study a semi-automatic method was developed for displaying MPI SPECT data as a set of radial slices orientated about the LV axis, with the aim of reducing the number of slices viewed, without loss of information and independent on the size of the heart. Input volume data consisted of standard short axis slices orientated perpendicular to the LV axis chosen at the time of reconstruction.  The true LV axis was determined by first determining the boundary on a central long axis slice, the axis being in the direction of the y-axis in the matrix. The skeleton of the myocardium were found and the true LV axis determined for that slice. The angle of this axis with respect to the y-axis was calculated. The process was repeated for an orthogonal long axis slice. The input volume was then rotated by the angles calculated. Radial slices generated for presentation were integrated over a sector equivalent to the imaging resolution (1.2 cm); assuming the diameter of the heart is about 8cm then non-gated data could be represented by 20 radial slices integrated over an 18 degree section. Gated information could be represented with four slices spaced at 45 intervals, integrated over a 30 degree sector.

In contemporary IT industry, Multi-tasking solutions are highly regarded as optimal solutions, because hardware is equipped with multi-core CPUs.  With Multi-Core technology, CPUs run with lower frequencies while giving same or better performance as a whole system of processing. This thesis work takes advantage of multi-threading architecture in order to run different tasks under different cores such as SIP signaling and messaging to establish one or more SIP calls, capture voice, medical data, and packetize them to be streamed over internet to other SIP agents. VoIP is designed to stream voice over IP. There is inter-protocol communication and cooperation such as between the SIP, SDP, RTP, and RTCP protocols in order to establish a SIP connection and- afterwards- stream media over the internet. We use the Microsoft COM technology in order to better the C++ component design. It allows us to design and develop code once and run it anywhere on different platforms. Using VC++ helps us reduce software design time and development time. Moreover, we follow software design standards setup by software engineers’ society. VoIP technology uses protocols such as the SIP signaling protocol to locate the user agents that communicate with each other. Pjsip is a library that allows developers to extend their design with SIP capability. We use the PJSIP library in order to sign up our own developed VoIP module to a SIP server over the Internet and locate other user agents. We implement and use the already-designed iRTP protocol instead of the RTP to stream media over the Internet. Thus, we can improve RTP packet delays and improve Quality of Service (QoS). Since medical data is critical and must not be lost, the iRTP guarantees no loss of medical data. If we want to stream voice only, we would not need iRTP, because RTP is a good protocol for voice applications. Due to the increasing Internet traffic, we need to use a reliable protocol that can detect packet loss of medical data. iRTP resolves the issue and leverages QoS. This thesis work focuses on streaming medical data and medical voice-calls using VoIP, even over small bandwidths and in high traffic periods. The main contribution of this thesis is in the parallel design of iRTP and the implementation of this very design in order to be used with Multi-Core technology. We do so via multi-threading technology to speed up the streaming of medical data and medical voice-calls. According to our tests, measurements, and result analyses, the parallel design of iRTP and the multithreaded implementation on VC++ leverage performance to a level where the average decrease in delay is 71.1% when using iRTP for audio and medical data instead of the nowadays applied case of using an RTP stream for audio and multiple TCPs streams for medical data .

Brain tumors present the second highest cause of death among pediatric cancers. About 60% are located in the posterior fossa region of the brain; among the most frequent types the ones considered for this project were astrocytomas, medulloblastomas, and ependymomas. Diagnosis can be done either through invasive histopathology exams or by non-invasive magnetic resonance (MR) scans. The tumors listed can be difficult to diagnose, even for trained radiologists, so machine learning methods, in particular deep learning, can be useful in helping to assess a diagnosis. Deep learning has been investigated only in a few other studies.The dataset used included 115 different subjects, some with multiple scan sessions, for which there were 142 T2-w, 119 T1Gd-w, and 89 volumes that presented both MR modalities. 2D slices have been manually extracted from the registered and skull-stripped volumes in the transversal, sagittal, and frontal anatomical plane and have been preprocessed by normalizing them and selecting the slices containing the tumor. The scans employed are T2-w, T1Gd-w, and a combination of the two referred to as multimodal images. The images were divided session-wise into training, validation, and testing, using stratified cross-validation and have also been augmented. The convolutional neural networks (CNN) investigated were ResNet50, VGG16, and MobileNetV2. The model performances were evaluated for two-class and three-class classification tasks by computing the confusion matrix, accuracy, receiver operating characteristic curve (ROC), the area under the curve (AUROC), and F1-score. Moreover,  explanations for the behavior of networks were investigated using GradCAMs and occlusion maps. Preliminary investigations showed that the best plane and modality were the transversal one and T2-w images. Overall the best model was VGG16, for the two-class tasks the best classification was between astrocytomas and medulloblastomas which reached an F1-score of 0.86 for both classes on multimodal images, followed by astrocytomas and ependymomas with an F1-score of 0.76 for astrocytomas and 0.74 for ependymomas on T2-w, and last F1-score of 0.30 for ependymomas and 0.65 for medulloblastomas on multimodal images. The three-class classification reached F1-score values of 0.59 for astrocytomas, 0.46 for ependymomas, and 0.64 for medulloblastomas on T2-w images. GradCAMs and occlusion maps showed that VGG16 was able to focus mostly on the tumor region but that there also seemed to be other information in the background of the images that contributed to the final classification.To conclude, the classification of infratentorial pediatric brain tumors can be achieved with acceptable results by means of deep learning and using a single MR modality, though one might have to account for the dataset size, number of classes and class imbalance. GradCAMs and occlusion maps offer important insights into the decision process of the networks

Brain and nervous system tumors were responsible for around 250,000 deaths in 2020 worldwide. Correctly identifying different tumors is very important, because treatment options largely depend on the diagnosis. This is an expert task, but recently machine learning, and especially deep learning models have shown huge potential in tumor classification problems, and can provide fast and reliable support for pathologists in the decision making process. This thesis investigates classification of two brain tumors, glioblastoma multiforme and lower grade glioma in high-resolution H&E-stained histology images using deep learning. The dataset is publicly available from TCGA, and 220 whole slide images were used in this study. Ground truth labels were only available on whole slide level, but due to their large size, they could not be processed by convolutional neural networks. Therefore, patches were extracted from the whole slide images in two sizes and fed into separate networks for training. Preprocessing steps ensured that irrelevant information about the background was excluded, and that the images were stain normalized. The patch-level predictions were then combined to slide level, and the classification performance was measured on a test set. Experiments were conducted about the usefulness of pre-trained CNN models and data augmentation techniques, and the best method was selected after statistical comparisons. Following the patch-level training, five slide aggregation approaches were studied, and compared to build a whole slide classifier model. Best performance was achieved when using small patches (336 x 336 pixels), pre-trained CNN model without frozen layers, and mirroring data augmentation. The majority voting slide aggregation method resulted in the best whole slide classifier with 91.7% test accuracy and 100% sensitivity. In many comparisons, however, statistical significance could not be shown because of the relatively small size of the test set.

This thesis investigates the use of Convolutional Neural Networks (CNNs) toperform semantic segmentation of feet during endovascular surgery in patientswith Critical Limb Threatening Ischemia (CLTI). It is currently being investigatedwhether objective assessment of perfusion can aid surgeons during endovascularsurgery. By segmenting feet, it is possible to perform automatic analysis of perfusion data which could give information about the impact of the surgery in specificRegions of Interest (ROIs). The CNN was developed in Python with a U-net architecture which has shownto be state of the art when it comes to medical image segmentation. An imageset containing approximately 78 000 images of feet and their ground truth segmentation was manually created from 11 videos taken during surgery, and onevideo taken on three healthy test subjects. All videos were captured with a MultiExposure Laser Speckle Contrast Imaging (MELSCI) camera developed by Hultman et al. [1]. The best performing CNN was an ensemble model consisting of10 sub-models, each trained with different sets of training data. An ROI tracking algorithm was developed based on the Unet output, by takingadvantage of the simplicity of edge detection in binary images. The algorithmconverts images into point clouds and calculates a transformation between twopoint clouds with the use of the Iterative Closest Point (ICP) algorithm. The resultis a system that perform automatic tracking of manually selected ROIs whichenables continuous measurement of perfusion in the ROIs during endovascularsurgery.

Bakgrund: Uträkning av vänsterkammarens (VK) volymer (Enddiastolisk volym, EDV; Endsystolisk volym, ESV; Slagvolym, SV) och ejektionsfraktion (EF) går att göra med elektrokardiografi (EKG)-styrd gating vid positronemissionstomografi (PET) med spårämnet 15O-vatten. Metoden behöver utredas noggrannare och optimeras för att kunna introduceras i klinisk rutinverksamhet. Syfte: Syftet med denna studie var att undersöka bildanalys av PET-rekonstruktioner med olika spatial och temporal upplösning i samband med 15O-vatten-PET utförd med EKG-gating, samt jämföra analysutfallen av VK-volymer och EF mot CMR och sinsemellan, för att utreda möjligheten att optimera metoden. Metod: Totalt 25 patienter som genomgått en 15O-vatten-PET, varav n=11 hade undersökts med CMR samma dag, inkluderades. Olika gating-rekonstruktioner med varierande upplösning utfördes retrospektivt och analyserades automatiskt samt manuellt. Analysutfallen för VK-volymer och EF för PET och CM jämfördes statistiskt. Resultat: I studien fanns en stark till mycket stark korrelation mellan PET och CMR för EDV, stark korrelation för ESV, medel till stark korrelation för SV och svag till medel korrelation för EF. Rekonstruktion med 12 gating-bins och 256x256 matrisstorlek hade starkast korrelation för SV och EF. Samtliga PET-rekonstruktioner korrelerade starkt-till mycket starkt med varandra för VK-volymer och EF. Bland-Altman-analyser visade på en god repeterbarhet, framförallt vid manuell analys, för beräkning av EF med 15O-vatten-PET. Slutsats: VK-volymer och EF kan beräknas med 15O-vatten-PET med en repeterbarhet liknande den för andra, mer använda modaliteter. Att använda en högre upplösning än vad som tidigare testats gav högre värden för EF, och starkare korrelation i jämförelse mot CMR. / Background: Calculation of left ventricle (LV)-volumes (End Diastolic Volume, EDV; End Systolic Volume, ESV; Stroke Volume, SV) and ejection fraction (EF) is possible with electrocardiography (ECG)-gated Positron Emission Tomography (PET) using 15O-water, but the method needs to be further investigated and optimized before clinical routine implementation. Purpose: The purpose of this study was to investigate how altered image resolution affects the analysis and values of LV-volumes and ejection fraction on 15O-water-PET and compare the results against Cardiac Magnetic Resonance imaging (CMR) to enable optimization of the PET-method.  Method: In total, 25 patients who previously underwent a 15O-water-PET, where n=11 also performed CMR on the same day were included in the study. Different gating-reconstructions with varying resolution were performed retrospectively and underwent analysis, both automatically and manually.  Results: Correlation analysis found a strong to very strong correlation comparing PET against CMR for EDV, a strong correlation for ESV, a moderate to strong correlation for SV and a weak to moderate correlation for EF. The reconstruction containing 12 gating-bins and a 256x256 matrix size showed the strongest correlation for SV and EF. All PET-reconstructions correlated strong to very strong against each other for all LV-volumes and EF. Bland-Altman-plots showed good repeatability, especially for manual analysis, when calculating EF on 15O-water-PET.  Conclusion: LV-volumes and EF can be calculated on 15O-water-PET, with repeatability close to that of other modalities. Using an increased resolution than previously tested resulted in higher EF and stronger correlation in comparison with CMR.

Challenges within the field of pathology leads to a high workload for pathologists. Machine learning has the ability to assist pathologists in their daily work and has shown good performance in a research setting. Anomaly detection is useful for preventing machine learning models used for classification and segmentation to be applied on data outside of the training distribution of the model. The purpose of this work was to create an optimal anomaly detection pipeline for digital pathology data using a latent diffusion model and various image similarity metrics. An anomaly detection pipeline was created which used a partial diffusion process, a combined similarity metric containing the result of multiple other similarity metrics and a contrast matching strategy for better anomaly detection performance. The anomaly detection pipeline had a good performance in an out-of-distribution detection task with an ROC-AUC score of 0.90. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

In digital pathology, hematoxylin &amp; eosin (H&amp;E) is a routine stain which is performed on most clinical cases and it often provides clinicians with sufficient information for diagnosis. However, when making decisions on how to guide breast cancer treatment, immunohistochemical staining of human epidermal growth factor 2 (HER2 staining) is also needed. Over-expression of the HER2 protein plays a significant role in the progression of breast cancer and is therefore important to consider during treatment planning. However, the downside of HER2 staining is that it is both time consuming and rather expensive. This thesis explores the possibility for H&amp;E-to-HER2 stain translation using generative adversarial networks (GANs). If effective, this has the potential to reduce the costs and time spent on tissue processing while still providing clinicians with the images necessary to make a complete diagnosis. To explore this area two supervised (Pix2Pix, PyramidPix2Pix) and one unsupervised (cycleGAN) GAN structure was implemented and trained on digital pathology images from the MIST dataset. These models were trained two times, with 256x256 and 512x512 patches, to see which effect patch size has on stain translation performance as well. In addition, a methodology for evaluating the quality of the generated HER2 patches was also presented and utilized. This methodology consists of structural similarity index (SSIM) and peak signal to noise ratio (PSNR) comparison to the ground truth, and a HER2 status classification protocol. In the latter a classification tool provided by Sectra was used to assign each patch with a HER2 status of No tumor, 1+, 2+ or 3+ and the statuses of the generated patches were then compared to the statuses of the ground truths. The results show that the supervised Pyramid Pix2Pix model trained on 512x512 patches performs the best according to the SSIM and PSNR metrics. However, the unsupervised cycleGAN model shows more promising results when it comes to both visual assessment and the HER2 status classification protocol. Especially when trained on 256x256 patches for 200 epochs which gave an accuracy of 0.655, F1-score of 0.674 and MCC of 0.490. In conclusion the HER2 status classification protocol is deemed as a suitable way to evaluate H&amp;E-to-HER2 stain translation and thereby the unsupervised method is considered to be better than the supervised. Moreover, it is also concluded that a smaller patch size result in worse translation of cellular structure for the supervised methods. Further studies should focus on incorporating HER2 status classification in the cycleGAN loss function and more extensive training runs to further improve the quality of H&amp;E-to-HER2 stain translation.