Hybridization of Acoustic and Visual Features of Polish Sibilants Produced by Children for Computer Speech Diagnosis.

Speech disorders are significant barriers to the balanced development of a child. Many children in Poland are affected by lisps (sigmatism)-the incorrect articulation of sibilants. Since speech therapy diagnostics is complex and multifaceted, developing computer-assisted methods is crucial. This paper presents the results of assessing the usefulness of hybrid feature vectors extracted based on multimodal (video and audio) data for the place of articulation assessment in sibilants /s/ and /ʂ/. We used acoustic features and, new in this field, visual parameters describing selected articulators' texture and shape. Analysis using statistical tests indicated the differences between various sibilant realizations in the context of the articulation pattern assessment using hybrid feature vectors. In sound /s/, 35 variables differentiated dental and interdental pronunciation, and 24 were visual (textural and shape). For sibilant /ʂ/, we found 49 statistically significant variables whose distributions differed between speaker groups (alveolar, dental, and postalveolar articulation), and the dominant feature type was noise-band acoustic. Our study suggests hybridizing the acoustic description with video processing provides richer diagnostic information.

Tomographic reconstruction from planar thermal imaging using convolutional neural network.

In this study, we investigate perspectives for thermal tomography based on planar infrared thermal images. Volumetric reconstruction of temperature distribution inside an object is hardly applicable in a way similar to ionizing-radiation-based modalities due to its non-penetrating character. Here, we aim at employing the autoencoder deep neural network to collect knowledge on the single-source heat transfer model. For that purpose, we prepare a series of synthetic 3D models of a cylindrical phantom with assumed thermal properties with various heat source locations, captured at different times. A set of planar thermal images taken around the model is subjected to initial backprojection reconstruction, then passed to the deep model. This paper reports the training and testing results in terms of five metrics assessing spatial similarity between volumetric models, signal-to-noise ratio, or heat source location accuracy. We also evaluate the assumptions of the synthetic model with an experiment involving thermal imaging of a real object (pork) and a single heat source. For validation, we investigate objects with multiple heat sources of a random location and temperature. Our results show the capability of a deep model to reconstruct the temperature distribution inside the object.

Automated segmentation of epidermis in high-frequency ultrasound of pathological skin using a cascade of DeepLab v3+ networks and fuzzy connectedness.

This study proposes a novel, fully automated framework for epidermal layer segmentation in different skin diseases based on 75 MHz high-frequency ultrasound (HFUS) image data. A robust epidermis segmentation is a vital first step to detect changes in thickness, shape, and intensity and therefore support diagnosis and treatment monitoring in inflammatory and neoplastic skin lesions. Our framework links deep learning and fuzzy connectedness for image analysis. It consists of a cascade of two DeepLab v3+ models with a ResNet-50 backbone and a fuzzy connectedness analysis module for fine segmentation. Both deep models are pre-trained on the ImageNet dataset and subjected to transfer learning using our HFUS database of 580 images with atopic dermatitis, psoriasis and non-melanocytic skin tumors. The first deep model is used to detect the appropriate region of interest, while the second stands for the main segmentation procedure. We use the softmax layer of the latter twofold to prepare the input data for fuzzy connectedness analysis: as a reservoir of seed points and a direct contribution to the input image. In the experiments, we analyze different configurations of the framework, including region of interest detection, deep model backbones and training loss functions, or fuzzy connectedness analysis with parameter settings. We also use the Dice index and epidermis thickness to compare our results to state-of-the-art approaches. The Dice index of 0.919 yielded by our model over the entire dataset (and exceeding 0.93 in inflammatory diseases) proves its superiority over the other methods.

Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation.

This study presents the first application of convolutional neural networks to high-frequency ultrasound skin image classification. This type of imaging opens up new opportunities in dermatology, showing inflammatory diseases such as atopic dermatitis, psoriasis, or skin lesions. We collected a database of 631 images with healthy skin and different skin pathologies to train and assess all stages of the methodology. The proposed framework starts with the segmentation of the epidermal layer using a DeepLab v3+ model with a pre-trained Xception backbone. We employ transfer learning to train the segmentation model for two purposes: to extract the region of interest for classification and to prepare the skin layer map for classification confidence estimation. For classification, we train five models in different input data modes and data augmentation setups. We also introduce a classification confidence level to evaluate the deep model's reliability. The measure combines our skin layer map with the heatmap produced by the Grad-CAM technique designed to indicate image regions used by the deep model to make a classification decision. Moreover, we propose a multicriteria model evaluation measure to select the optimal model in terms of classification accuracy, confidence, and test dataset size. The experiments described in the paper show that the DenseNet-201 model fed with the extracted region of interest produces the most reliable and accurate results.

Deep learning approach to skin layers segmentation in inflammatory dermatoses.

Monitoring skin layers with medical imaging is critical to diagnosing and treating patients with chronic inflammatory skin diseases. The high-frequency ultrasound (HFUS) makes it possible to monitor skin condition in different dermatoses. Accurate and reliable segmentation of skin layers in patients with atopic dermatitis or psoriasis enables the assessment of the treatment effect by the layer thickness measurements. The epidermis and the subepidermal low echogenic band (SLEB) are the most important for further diagnosis since their appearance is an indicator of different skin problems. In medical practice, the analysis, including segmentation, is usually performed manually by the physician with all drawbacks of such an approach, e.g., extensive time consumption and lack of repeatability. Recently, HFUS becomes common in dermatological practice, yet it is barely supported by the development of automated analysis tools. To meet the need for skin layer segmentation and measurement, we developed an automated segmentation method of both epidermis and SLEB layers. It consists of a fuzzy c-means clustering-based preprocessing step followed by a U-shaped convolutional neural network. The network employs batch normalization layers adjusting and scaling the activation to make the segmentation more robust. The obtained segmentation results are verified and compared to the current state-of-the-art methods addressing the skin layer segmentation. The obtained Dice coefficient equal to 0.87 and 0.83 for the epidermis and SLEB, respectively, proves the developed framework's efficiency, outperforming the other approaches.

Automated size-specific dose estimates using deep learning image processing.

An automated vendor-independent system for dose monitoring in computed tomography (CT) medical examinations involving ionizing radiation is presented in this paper. The system provides precise size-specific dose estimates (SSDE) following the American Association of Physicists in Medicine regulations. Our dose management can operate on incomplete DICOM header metadata by retrieving necessary information from the dose report image by using optical character recognition. For the determination of the patient's effective diameter and water equivalent diameter, a convolutional neural network is employed for the semantic segmentation of the body area in axial CT slices. Validation experiments for the assessment of the SSDE determination and subsequent stages of our methodology involved a total of 335 CT series (60 352 images) from both public databases and our clinical data. We obtained the mean body area segmentation accuracy of 0.9955 and Jaccard index of 0.9752, yielding a slice-wise mean absolute error of effective diameter below 2 mm and water equivalent diameter at 1 mm, both below 1%. Three modes of the SSDE determination approach were investigated and compared to the results provided by the commercial system GE DoseWatch in three different body region categories: head, chest, and abdomen. Statistical analysis was employed to point out some significant remarks, especially in the head category.

Supporting diagnostics and therapy planning for percutaneous ablation of liver and abdominal tumors and pre-clinical evaluation.

Percutaneous ablation methods are used to treat primary and metastatic liver tumors. Image guided navigation support minimally invasive interventions of rigid anatomical structures. When working with the displacement and deformation of soft tissues during surgery, as in the abdomen, imaging navigation systems are in the preliminary implementation stage. In this study a multi-stage approach has been developed to support percutaneous liver tumors ablation. It includes CT image acquisition protocol with the amplitude of respiratory motion that yields images subjected to a semi-automatic method able to deliver personalized abdominal model. Then, US probe and ablation needle calibration, as well as patient position adjustment method during the procedure for the preoperative anatomy model, have been combined. Finally, an advanced module for fusion of the preoperative CT with intraoperative US images was designed. These modules have been tested on a phantom and in the clinical environment. The final average Spatial calibration error was 1,7 mm, the average error of matching the position of the markers was about 2 mm during the entire breathing cycle, and average markers fusion error 495 mm. The obtained results indicate the possibility of using the developed method of navigation in clinical practice.

Virtual bacterium colony in 3D image segmentation.

Several heuristic, biologically inspired strategies have been discovered in recent decades, including swarm intelligence algorithms. So far, their application to volumetric imaging data mining is, however, limited. This paper presents a new flexible swarm intelligence optimization technique for segmentation of various structures in three- or two-dimensional images. The agents of a self-organizing colony explore their host, use stigmergy to communicate themselves, and mark regions of interest leading to the object extraction. Detailed specification of the bacterium colony segmentation (BCS) technique in terms of both individual and social behaviour is described in this paper. The method is illustrated and evaluated using several experiments involving synthetic data, computed tomography studies, and ultrasonography images. The obtained results and observations are discussed in terms of parameter settings and potential application of the method in various segmentation tasks.

Time-Of-Flight Camera, Optical Tracker and Computed Tomography in Pairwise Data Registration.

PURPOSE: A growing number of medical applications, including minimal invasive surgery, depends on multi-modal or multi-sensors data processing. Fast and accurate 3D scene analysis, comprising data registration, seems to be crucial for the development of computer aided diagnosis and therapy. The advancement of surface tracking system based on optical trackers already plays an important role in surgical procedures planning. However, new modalities, like the time-of-flight (ToF) sensors, widely explored in non-medical fields are powerful and have the potential to become a part of computer aided surgery set-up. Connection of different acquisition systems promises to provide a valuable support for operating room procedures. Therefore, the detailed analysis of the accuracy of such multi-sensors positioning systems is needed. METHODS: We present the system combining pre-operative CT series with intra-operative ToF-sensor and optical tracker point clouds. The methodology contains: optical sensor set-up and the ToF-camera calibration procedures, data pre-processing algorithms, and registration technique. The data pre-processing yields a surface, in case of CT, and point clouds for ToF-sensor and marker-driven optical tracker representation of an object of interest. An applied registration technique is based on Iterative Closest Point algorithm. RESULTS: The experiments validate the registration of each pair of modalities/sensors involving phantoms of four various human organs in terms of Hausdorff distance and mean absolute distance metrics. The best surface alignment was obtained for CT and optical tracker combination, whereas the worst for experiments involving ToF-camera. CONCLUSION: The obtained accuracies encourage to further develop the multi-sensors systems. The presented substantive discussion concerning the system limitations and possible improvements mainly related to the depth information produced by the ToF-sensor is useful for computer aided surgery developers.

Accelerometric signals in automatic balance assessment.

The paper presents the automatic computer-aided balance assessment system for supporting and monitoring the diagnosis and rehabilitation process of patients with limited mobility or disabled in home environment. The system has adopted seven Berg Balance Scale activities. The assessment approach is based on the accelerometric signals acquired by the inertial sensors worn by the patient. Several specific, mostly medium frequency features of signals are introduced and discussed. The reduction of the feature vector has been performed using the multilevel Fisher's linear discriminant. The classification employs the multilayer perceptron artificial neural network. The direct assessment effectiveness ranges from 75% to 94% for various activities.

Acceleration trajectory analysis in remote gait monitoring.

The study demonstrates part of an ambient assisted living system developed for the remote care of the elderly. Described methods and experiments involve acceleration-based trajectories analysis that yields a feature vector to be subjected to an expert system able to create an individual patient's model by learning high-level features of her/his motion. At this stage we have implemented a footstep detector that permits each foot movement to be analyzed separately and described in terms of predefined features. By mounting the sensors at five various locations on the subjects body, we have indicated areas that feature a high sensitivity to the measurement of abnormal step incidents. Our experiments demonstrate also features able to distinguish abnormal patient motion.

Role of radiologists in CAD life-cycle.

A modern CAD (computer-aided diagnosis) system development involves a multidisciplinary team whose members are experts in medical and technical fields. This study indicates the activities of medical experts at various stages of the CAD design, testing, and implementation. Those stages include a medical analysis of the diagnostic problem, data collection, image analysis, evaluation, and clinical verification. At each stage the physicians knowledge and experience are indispensable. The final implementation involves integration with the existing Picture Archiving and Communication System. The term CAD life-cycle describes an overall process of the design, testing, and implementation of a system that in its final form assists the radiologists in their daily clinical routine. Four CAD systems (applied to the bone age assessment, Multiple Sclerosis detection, lung nodule detection, and pneumothorax measurement) developed in our laboratory are given as examples of how consecutive stages are developed by the multidisciplinary team. Specific advantages of the CAD implementation that include the daily clinical routine as well as research and education activities are discussed.