Benign and Malignant Breast Tumor Classification in Ultrasound and Mammography Images via Fusion of Deep Learning and Handcraft Features.

Breast cancer is a disease that affects women in different countries around the world. The real cause of breast cancer is particularly challenging to determine, and early detection of the disease is necessary for reducing the death rate, due to the high risks associated with breast cancer. Treatment in the early period can increase the life expectancy and quality of life for women. CAD (Computer Aided Diagnostic) systems can perform the diagnosis of the benign and malignant lesions of breast cancer using technologies and tools based on image processing, helping specialist doctors to obtain a more precise point of view with fewer processes when making their diagnosis by giving a second opinion. This study presents a novel CAD system for automated breast cancer diagnosis. The proposed method consists of different stages. In the preprocessing stage, an image is segmented, and a mask of a lesion is obtained; during the next stage, the extraction of the deep learning features is performed by a CNN-specifically, DenseNet 201. Additionally, handcrafted features (Histogram of Oriented Gradients (HOG)-based, ULBP-based, perimeter area, area, eccentricity, and circularity) are obtained from an image. The designed hybrid system uses CNN architecture for extracting deep learning features, along with traditional methods which perform several handcraft features, following the medical properties of the disease with the purpose of later fusion via proposed statistical criteria. During the fusion stage, where deep learning and handcrafted features are analyzed, the genetic algorithms as well as mutual information selection algorithm, followed by several classifiers (XGBoost, AdaBoost, Multilayer perceptron (MLP)) based on stochastic measures, are applied to choose the most sensible information group among the features. In the experimental validation of two modalities of the CAD design, which performed two types of medical studies-mammography (MG) and ultrasound (US)-the databases mini-DDSM (Digital Database for Screening Mammography) and BUSI (Breast Ultrasound Images Dataset) were used. Novel CAD systems were evaluated and compared with recent state-of-the-art systems, demonstrating better performance in commonly used criteria, obtaining ACC of 97.6%, PRE of 98%, Recall of 98%, F1-Score of 98%, and IBA of 95% for the abovementioned datasets.

Explainable CAD System for Classification of Acute Lymphoblastic Leukemia Based on a Robust White Blood Cell Segmentation.

Leukemia is a significant health challenge, with high incidence and mortality rates. Computer-aided diagnosis (CAD) has emerged as a promising approach. However, deep-learning methods suffer from the "black box problem", leading to unreliable diagnoses. This research proposes an Explainable AI (XAI) Leukemia classification method that addresses this issue by incorporating a robust White Blood Cell (WBC) nuclei segmentation as a hard attention mechanism. The segmentation of WBC is achieved by combining image processing and U-Net techniques, resulting in improved overall performance. The segmented images are fed into modified ResNet-50 models, where the MLP classifier, activation functions, and training scheme have been tested for leukemia subtype classification. Additionally, we add visual explainability and feature space analysis techniques to offer an interpretable classification. Our segmentation algorithm achieves an Intersection over Union (IoU) of 0.91, in six databases. Furthermore, the deep-learning classifier achieves an accuracy of 99.9% on testing. The Grad CAM methods and clustering space analysis confirm improved network focus when classifying segmented images compared to non-segmented images. Overall, the proposed visual explainable CAD system has the potential to assist physicians in diagnosing leukemia and improving patient outcomes.

DETERMINATION OF SOMATIC, NEUROLOGICAL AND PSYCHO-EMOTIONAL MANIFESTATIONS OF THE ACUTE AND POSTCOVID PERIOD IN PATIENTS WITH A MILD COURSE OF COVID-19 IN WARTIME.

OBJECTIVE: The aim: To analyze the typical symptom complex at the stage of COVID-19 acute phase in the systemic relationship with somatic, psychosomatic, and neurological manifestations. PATIENTS AND METHODS: Materials and methods: The collection of primary material was performed by clinical-anamnestic method, laboratory, and sociological examination of patients treated out patiently. Summarizing of the results was performed according to the analysis of 100 completed cases of COVID-19 in patients aged 35-45 years (50 men and 50 women) who had no concomitant chronic pathology, and patients did not receive any vaccine dose before the disease (acute COVID-19) and during the next follow-up period (6 months). RESULTS: Results: The data of the analysis allowed us to make a grounded conclusion about the syndromic heterogeneity of COVID 19 in a standardized patients group with a mild course. CONCLUSION: Conclusions: the highest number of symptoms in the postcovid period by frequency, polymorphism, and life quality impact was found in the group of patients with subjectively tolerate acute COVID-19 most easily. Patients whose acute episode meets the mild criteria have pronounced neurological and psychoemotional manifestations during the postcovid period.

FUNCTIONAL CHARACTERISTICS OF THE CARDIOVASCULAR SYSTEM OF PATIENTS WITH ISCHEMIC HEART DISEASE WITH OBESITY.

OBJECTIVE: The aim: To determine the features of the functional characteristics of the cardiovascular system of patients with ischemic heart disease with obesity. PATIENTS AND METHODS: Materials and methods: Examined 130 persons (mostly military personnel and persons who were in the zone of active hostilities): 65 patients (the main group, 62,67±8,93 years) with coronary heart disease and obesity and 45 people of the control group (virtually healthy people, randomized by age and sex, 58,76±14,6 years). RESULTS: Results: Coronary heart disease and obesity compared to healthy individuals probably the exceed all values of the functional state of the cardiovascular system: systolic blood pressure (152.72±14.61 and 119.03±7.94 mmHg; p<0.001); diastolic blood pressure (90.74±7.36 and 80.36±6.74 mmHg; p<0.001); end-diastolic volume (103.17±40.84 and 52.48±8.58 mm3; р<0.001); end-systolic volume (47.98±29.92 and 31.47±8.42 mm3; р=0.001); end-diastolic size (4.74±0.81 and 4.12 ± 0.27 cm; р<0.001); end-systolic size (3.34±0.76 and 3.17±0.59 cm; р=0.014). CONCLUSION: Conclusions: The identified functional disorders of the heart in the comorbid course of coronary heart disease and obesity can be used for early diagnosis of cardiovascular complications in such patients and for the development of adequate therapeutic schemes.

Despeckling of Ultrasound Images Using Block Matching and SVD in Sparse Representation.

This work proposes a novel scheme for speckle suppression on medical images acquired by ultrasound sensors. The proposed method is based on the block matching procedure by using mutual information as a similarity measure in grouping patches in a clustered area, originating a new despeckling method that integrates the statistical properties of an image and its texture for creating 3D groups in the BM3D scheme. For this purpose, the segmentation of ultrasound images is carried out considering superpixels and a variation of the local binary patterns algorithm to improve the performance of the block matching procedure. The 3D groups are modeled in terms of grouped tensors and despekled with singular value decomposition. Moreover, a variant of the bilateral filter is used as a post-processing step to recover and enhance edges' quality. Experimental results have demonstrated that the designed framework guarantees a good despeckling performance in ultrasound images according to the objective quality criteria commonly used in literature and via visual perception.

PRACTICAL ASPECTS AND RESULTS OF COGNITIVE THERAPY IN THE EARLY RECOVERY PERIOD OF ISCHEMIC STROKE.

OBJECTIVE: The aim: To determine the impact of cognitive training on the degree of cognitive functions recovery and quality of life in the early recovery period of ischemic stroke. PATIENTS AND METHODS: Materials and methods: 108 patients with cerebral infarction were examined outpatiently, follow-up from 1 to 3 months from the onset of the disease. Basic assessment methods: screening index of cognitive disorders according to the Montreal Cognitive Assessment Scale (MoCA), SF-36 questionnaire. RESULTS: Results and Conclusions: Comprehensive rehabilitation measures for the early recovery period of ischemic stroke achieve improvement of the cognitive sphere: a significant increase in the average score on the Montreal scale of cognitive functions assessment (MoCA scale) in both observation groups.

5-HT3 SEROTONIN RECEPTOR BLOCKERS FOR INTENSIVE THERAPY OF TRAUMATIC DISEASE IN PATIENTS WITH MULTIPLE TRAUMA.

OBJECTIVE: The aim: To find the most rational choice of drugs that have anti-emetic effect in patients with polytrauma in acute and early periods. PATIENTS AND METHODS: Materials and methods: We examined 82 patients with polytrauma, 62 men and 20 women. The age of patients ranged from 19 to 50 years. Patients were divided into the main and control group with 36 and 46 people respectively, who did not differ significantly by sex, age, anthropometric data, the nature and severity of injuries, and the time from injury to admission to hospital. RESULTS: Results: Full antiemetic effect was achieved in 72.4% of patients, where metoclopramide was used. Сomplete antiemetic effect was achieved in 96.3% of patients, where sturgeon was used. Decrease of peristaltic activity does not increase postoperative intestinal paresis, and also prevents irritable bowel syndrome and diarrhea caused by dysbacteriosis on the background of antibiotic therapy. Anxiolytic effect without sedative effect and impairment of motor coordination, decrease of the somatic and psychopathological symptoms intensity in alcohol-toxic withdrawal syndrome contributes to the correct interpretation of the traumatic disease. CONCLUSION: Conclusions: Use of drugs with antiemetic effect is an important part of the complex of traumatic disease treatment in patients with polytrauma. The use of osetron is rational in patients with polytrauma with cranio-abdominal injuries.

Melanoma and Nevus Skin Lesion Classification Using Handcraft and Deep Learning Feature Fusion via Mutual Information Measures.

In this paper, a new Computer-Aided Detection (CAD) system for the detection and classification of dangerous skin lesions (melanoma type) is presented, through a fusion of handcraft features related to the medical algorithm ABCD rule (Asymmetry Borders-Colors-Dermatoscopic Structures) and deep learning features employing Mutual Information (MI) measurements. The steps of a CAD system can be summarized as preprocessing, feature extraction, feature fusion, and classification. During the preprocessing step, a lesion image is enhanced, filtered, and segmented, with the aim to obtain the Region of Interest (ROI); in the next step, the feature extraction is performed. Handcraft features such as shape, color, and texture are used as the representation of the ABCD rule, and deep learning features are extracted using a Convolutional Neural Network (CNN) architecture, which is pre-trained on Imagenet (an ILSVRC Imagenet task). MI measurement is used as a fusion rule, gathering the most important information from both types of features. Finally, at the Classification step, several methods are employed such as Linear Regression (LR), Support Vector Machines (SVMs), and Relevant Vector Machines (RVMs). The designed framework was tested using the ISIC 2018 public dataset. The proposed framework appears to demonstrate an improved performance in comparison with other state-of-the-art methods in terms of the accuracy, specificity, and sensibility obtained in the training and test stages. Additionally, we propose and justify a novel procedure that should be used in adjusting the evaluation metrics for imbalanced datasets that are common for different kinds of skin lesions.

Fuzzy filtering method for color videos corrupted by additive noise.

A novel method for the denoising of color videos corrupted by additive noise is presented in this paper. The proposed technique consists of three principal filtering steps: spatial, spatiotemporal, and spatial postprocessing. In contrast to other state-of-the-art algorithms, during the first spatial step, the eight gradient values in different directions for pixels located in the vicinity of a central pixel as well as the R, G, and B channel correlation between the analogous pixels in different color bands are taken into account. These gradient values give the information about the level of contamination then the designed fuzzy rules are used to preserve the image features (textures, edges, sharpness, chromatic properties, etc.). In the second step, two neighboring video frames are processed together. Possible local motions between neighboring frames are estimated using block matching procedure in eight directions to perform interframe filtering. In the final step, the edges and smoothed regions in a current frame are distinguished for final postprocessing filtering. Numerous simulation results confirm that this novel 3D fuzzy method performs better than other state-of-the-art techniques in terms of objective criteria (PSNR, MAE, NCD, and SSIM) as well as subjective perception via the human vision system in the different color videos.

Wavelet transform fuzzy algorithms for dermoscopic image segmentation.

This paper presents a novel approach to segmentation of dermoscopic images based on wavelet transform where the approximation coefficients have been shown to be efficient in segmentation. The three novel frameworks proposed in this paper, W-FCM, W-CPSFCM, and WK-Means, have been employed in segmentation using ROC curve analysis to demonstrate sufficiently good results. The novel W-CPSFCM algorithm permits the detection of a number of clusters in automatic mode without the intervention of a specialist.

3D video visualization employing wavelet multilevel decomposition.

This study analyzed the implementation and performance of a framework that can be efficiently applied to three-dimensional (3D) video sequence visualization. The proposed algorithm is based on wavelets and wavelet atomic functions used in the computation of disparity maps. The proposed algorithm employs wavelet multilevel decomposition and 3D visualization via color anaglyphs synthesis. Simulations were run on synthetic images, synthetic video sequences, and real-life video sequences. Results shows that this novel approach performs better in depth and spatial perception tasks compared to existing methods, both in terms of objective criteria such as quantity of bad disparities and similarity structural index measure and the more subjective measure of human vision.

Medical image processing using novel wavelet filters based on atomic functions: optimal medical image compression.

The analysis of different Wavelets including novel Wavelet families based on atomic functions are presented, especially for ultrasound (US) and mammography (MG) images compression. This way we are able to determine with what type of filters Wavelet works better in compression of such images. Key properties: Frequency response, approximation order, projection cosine, and Riesz bounds were determined and compared for the classic Wavelets W9/7 used in standard JPEG2000, Daubechies8, Symlet8, as well as for the complex Kravchenko-Rvachev Wavelets ψ(t) based on the atomic functions up(t),  fup (2)(t), and eup(t). The comparison results show significantly better performance of novel Wavelets that is justified by experiments and in study of key properties.