No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

Early assessment of tumour response has lately acquired big interest in the medical field, given the possibility to modify treatments during their delivery. Radiomics aims to quantitatively describe images in radiology by automatically extracting a large number of image features. In this context, PET/CT (Positron Emission Tomography/Computed Tomography) images are of great interest since they encode functional and anatomical information, respectively. In order to assess the patients' responses from many image features appropriate methods should be applied. Machine learning offers different procedures that can deal with this, possibly high dimensional, problem. The main objective of this work was to develop a method to classify lung cancer patients as responding or not to chemoradiation treatment, relying on repeated PET/CT images. Patients were divided in two groups, based on the type of chemoradiation treatment they underwent (sequential or concurrent radiation therapy with respect to chemotherapy), but image features were extracted using the same procedure. Support vector machines performed classification using features from the Radiomics field, mostly describing tumour texture, or from handcrafted features, which described image intensity changes as a function of tumour depth. Classification performance was described by the area under the curve (AUC) of ROC (Receiving Operator Characteristic) curves after leave-one-out cross-validation. For sequential patients, 0.98 was the best AUC obtained, while for concurrent patients 0.93 was the best one. Handcrafted features were comparable to those from Radiomics and from previous studies, as for classification results. Also, features from PET alone and CT alone were found to be suitable for the task, entailing a performance better than random.

Electromyography (EMG) is a common tool in electrical muscle activity measurement and can be used in multiple areas of clinical and biomedical applications, mainly in identifying neuromuscular diseases, analyzing movement or in human machine interfaces. Traditionally a pair of electrodes were used to measure the signals, but in recent years the use of high density surface EMG (HD-sEMG) gained more popularity as it can sample myoelectric activities from multiple electrodes in an array on a single muscle and provide more information. In this thesis a measurement setup and protocol is proposed that can provide a reliably measurement, furthermore multiple features are extracted from the collected signals to characterise the major muscles around the ankle. 5 healthy subjects were tested using an ankle dynamometer with 5 HD-sEMG placed on the Tibialis Anterior, the Gastrocnemius Medialis, the Soleus, the Gastrocnemius Lateralis, and on the Peroneus Longus. Several tests were conducted using different initial angle of the ankle joint and different percentages of the maximum voluntary contraction. The reliability of the setup was assessed by comparing the variance between the collected signals of the same subject in a repeated test, and by comparing different subjects to each other. Results show a reasonably good reliability with less than $10\%$ variance, and adequate selectivity as well. To examine the muscle characteristics, 7 features were extracted from the collected and processed signals, then the features were plotted and compared to signs for muscle characteristics such as muscle fatigue, activation, and spatial distribution of activation. Correlations between features of mean average value (MAV) and zero crossing (ZC), and different muscle characteristics could be observed.

yes / This paper describes a technique for automatic recognition of off-line printed Arabic text using Hidden Markov Models. In this work different sizes of overlapping and non-overlapping hierarchical windows are used to generate 16 features from each vertical sliding strip. Eight different Arabic fonts were used for testing (viz. Arial, Tahoma, Akhbar, Thuluth, Naskh, Simplified Arabic, Andalus, and Traditional Arabic). It was experimentally proven that different fonts have their highest recognition rates at different numbers of states (5 or 7) and codebook sizes (128 or 256). Arabic text is cursive, and each character may have up to four different shapes based on its location in a word. This research work considered each shape as a different class, resulting in a total of 126 classes (compared to 28 Arabic letters). The achieved average recognition rates were between 98.08% and 99.89% for the eight experimental fonts. The main contributions of this work are the novel hierarchical sliding window technique using only 16 features for each sliding window, considering each shape of Arabic characters as a separate class, bypassing the need for segmenting Arabic text, and its applicability to other languages.