This research focuses on the depression states classification of EEG signals using the EEGNet model optimized with Optuna. The purpose was to increase model performance by combining data from healthy and depressed subjects, which ensured model robustness across datasets. The methodology comprised the construction of a preprocessing pipeline, which included noise filtering, artifact removal, and signal segmentation. Additive extraction from time and frequency domains further captured important features of EEG signals. The model was developed on a merged dataset (DepressionRest and MDD vs. Control) and evaluated on an independent dataset, 93.27% (±0.0610) accuracy with a 34.16 KB int8 model, ideal for portable EEG diagnostics. These results are promising in terms of model performance and depression state-of-the-art classification accuracy. The results suggest that the hyperparameter-optimized Optuna model performs adequately to cope with the variability of real-world data. Furthermore, the model will need improvement before generalization to other datasets, such as the DepressionRest dataset, can be realized. The research identifies the advantages of EEGNet models and optimization using Optuna for clinical diagnostics, with remarkable performance for deployed real-world models. Future work includes the incorporation of the model into portable clinical systems while ensuring compatibility with current EEG devices, as well as the continuous improvement of model performance.

Infantile hemangiomas (IHs) are a type of vascular tumors that affect around 10% of newborns. The measurement of the lesion size and the assessment of the evolution is done manually by the physician. This paper presents an algorithm for the automatic computation of the IH lesion surface. The image scale is computed by using the Hough transform and the total variation. As pre-processing, a geometric correction step is included, which ensures that the lesions are viewed as perpendicular to the camera. The image segmentation is based on K-means clustering applied on a five-plane image; the five planes being selected from seven planes with the use of the Karhunen-Loeve transform. Two of the seven planes are 2D total variation filters, based on symmetrical kernels, designed to highlight the IH specific texture. The segmentation performance was assessed on 30 images, and a mean border error of 9.31% was obtained.

Cutaneous melanoma is one of the most aggressive skin cancers, and early detection is critical for effective treatment. Although traditional imaging techniques such as dermoscopy improve diagnostic accuracy, many cases remain undetected. Recent advancements in non-invasive imaging, including multispectral imaging and infrared thermal imaging, offer new opportunities for early diagnosis. In this study, we introduce MelanoDet, a multimodal imaging system integrating three cameras corresponding to different spectra: visible, near-infrared, and long-wavelength infrared. To ensure accurate lesion inspection, an analytical method based on the optical cameras parameters estimated the cameras’ common field of view, to capture the same region of interest. Since the acquired images differ in resolution, angle, and orientation, a second refined registration step has been applied. A standardized image acquisition protocol was established in collaboration with an experienced team of dermatologists from Elias Emergency University Hospital, Bucharest. The MelanoDet system, along with its protocol and image processing techniques, was validated on 25 cases of suspicious nevi, demonstrating its potential for improving melanoma screening.

Infantile hemangiomas (IH) are a type of benign vascular tumors that appear within the first 5 months of life. The assessment of lesion size and its evolution in time is done manually by the physician, using a ruler, and this measurement is not very accurate. This paper presents a method for automatic measurement of the IH size. The work is divided in two parts: automatic computation of the size of one millimeter in pixels, based on the Hough transform and the total variation, and automatic segmentation based on K-means clustering and a 2D total variation filtered image. The segmentation performance was evaluated on 20 IH images and a mean border error of 13.56% was obtained.