Differentiation of lung and breast cancer brain metastases: Comparison of texture analysis and deep convolutional neural networks.

PURPOSE: Metastases are the most common neoplasm in the adult brain. In order to initiate the treatment, an extensive diagnostic workup is usually required. Radiomics is a discipline aimed at transforming visual data in radiological images into reliable diagnostic information. We aimed to examine the capability of deep learning methods to classify the origin of metastatic lesions in brain MRIs and compare the deep Convolutional Neural Network (CNN) methods with image texture based features. METHODS: One hundred forty three patients with 157 metastatic brain tumors were included in the study. The statistical and texture based image features were extracted from metastatic tumors after manual segmentation process. Three powerful pre-trained CNN architectures and the texture-based features on both 2D and 3D tumor images were used to differentiate lung and breast metastases. Ten-fold cross-validation was used for evaluation. Accuracy, precision, recall, and area under curve (AUC) metrics were calculated to analyze the diagnostic performance. RESULTS: The texture-based image features on 3D volumes achieved better discrimination results than 2D image features. The overall performance of CNN architectures with 3D inputs was higher than the texture-based features. Xception architecture, with 3D volumes as input, yielded the highest accuracy (0.85) while the AUC value was 0.84. The AUC values of VGG19 and the InceptionV3 architectures were 0.82 and 0.81, respectively. CONCLUSION: CNNs achieved superior diagnostic performance in differentiating brain metastases from lung and breast malignancies than texture-based image features. Differentiation using 3D volumes as input exhibited a higher success rate than 2D sagittal images.

A physiological signal database of children with different special needs for stress recognition.

This study presents a new dataset AKTIVES for evaluating the methods for stress detection and game reaction using physiological signals. We collected data from 25 children with obstetric brachial plexus injury, dyslexia, and intellectual disabilities, and typically developed children during game therapy. A wristband was used to record physiological data (blood volume pulse (BVP), electrodermal activity (EDA), and skin temperature (ST)). Furthermore, the facial expressions of children were recorded. Three experts watched the children's videos, and physiological data is labeled "Stress/No Stress" and "Reaction/No Reaction", according to the videos. The technical validation supported high-quality signals and showed consistency between the experts.

The validity of an objective measurement method using the Leap Motion Controller for fingers wrist, and forearm ranges of motion.

The present study aimed to validate the Leap Motion Controller (LMC)-based Fizyosoft® HandROM System developed by our team to evaluate range of motion (ROM) for fingers, wrist, and forearm in a new clinical setting. Thirty-five healthy individuals participated in the study (all right-handed, 20-30 years old). The LMC-based Fizyosoft® HandROM System is a licensed software ROM-measurement developed by our team. Pronation/supination, wrist flexion/extension, ulnar/radial deviation and metacarpophalangeal (MCP) flexion/extension of all fingers were measured with both the Fizyosoft® HandROM System and a universal goniometer. No significant differences were found between the two measurement methods for almost all mean ROMs except for ulnar and radial deviation (p > 0.05). Highly significant correlations were found between all ROMs of the forearm, wrist, and thumb (p < 0.01). MCP flexion showed significant correlation only in the index finger (r = 0.516, p = 0.003) and little finger (r = 0.517, p = 0.004). Besides, for both measures, the intraclass correlations were good to excellent on all ROMs of the forearm, wrist, and fingers except for MCP of the middle and ring fingers (0.68-0.88). The present study results indicated that the LMC-based Fizyosoft® HandROM System could sensitively track changes in the active motion of the thumb, wrist, and forearm. It is a viable alternative for assessing ROMs of the forearm, wrist, and thumb in patient follow-up.

Automatic detection, localization and segmentation of nano-particles with deep learning in microscopy images.

With the growing amount of high resolution microscopy images automatic nano-particle detection, shape analysis and size determination have gained importance for providing quantitative support that gives important information for the evaluation of the material. In this paper, we present a new method for detection of nano-particles and determination of their shapes and sizes simultaneously with deep learning. The proposed method employs multiple output convolutional neural networks (MO-CNN) and has two outputs: first is the detection output that gives the locations of the particles and the other one is the segmentation output for providing the boundaries of the nano-particles. The final sizes of particles are determined with the modified Hough algorithm that runs on the segmentation output. The proposed method is tested and evaluated on a dataset containing 17 TEM images of Fe3O4 and silica coated nano-particles. Also, we compared these results with U-net algorithm which is a popular deep learning method. The experiments showed that the proposed method has 98.23% accuracy for detection and 96.59% accuracy for segmentation of nano-particles.

Nintendo Wii assessment of Hoehn and Yahr score with Parkinson's disease tremor.

OBJECTIVE: Diagnosis of Parkinson's Disease (PD) by analyzing the resting tremor were much studied by using different accelerometer based methods, however the quantitative assessment of Hoehn and Yahr Scale (HYS) score with a machine learning based system has not been previously addressed. In this study, we aimed to propose a system to automatically assess the HYS score of patients with PD. METHODS: The system was evaluated and tested on a dataset containing 55 subjects where 35 of them were patients and 20 of them were healthy controls. The resting tremor data were gathered with the 3 axis accelerometer of the Nintendo Wii (Wiimote). The clinical disability of the PD was graded from 1 to 5 by the HYS and tremor was recorded twice from the more affected side in each patient and from the dominant extremity in each control for a 60 seconds period. The HYS scores were learned with Support Vector Machines (SVM) from the features of the tremor data. RESULTS: Thirty-two of the subjects with PD were classified correctly and 18 of the normal subjects were also classified correctly by our system. The system had average 0.89 accuracy rate (Range: 81-100% changing according to grading by HYS). CONCLUSIONS: We compared quantitative measurements of hand tremor in PD patients, with staging of PD based on accelerometer data gathered using the Wii sensor. Our results showed that the machine learning based system with simple features could be helpful for diagnosis of PD and estimate HYS score. We believed that this portable and easy-to-use Wii sensor measure might also be applicable in the continuous monitoring of the resting tremor with small modifications in routine clinical use.

Computer aided diagnosis of degenerative intervertebral disc diseases from lumbar MR images.

This paper presents a novel method for the automated diagnosis of the degenerative intervertebral disc disease in midsagittal MR images. The approach is based on combining distinct disc features under a machine learning framework. The discs in the lumbar MR images are first localized and segmented. Then, intensity, shape, context, and texture features of the discs are extracted with various techniques. A Support Vector Machine classifier is applied to classify the discs as normal or degenerated. The method is tested and validated on a clinical lumbar spine dataset containing 102 subjects and the results are comparable to the state of the art.

Simultaneous localization of lumbar vertebrae and intervertebral discs with SVM-based MRF.

This paper presents a method for localizing and labeling the lumbar vertebrae and intervertebral discs in mid-sagittal MR image slices. The approach is based on a Markov-chain-like graphical model of the ordered discs and vertebrae in the lumbar spine. The graphical model is formulated by combining local image features and semiglobal geometrical information. The local image features are extracted from the image by employing pyramidal histogram of oriented gradients (PHOG) and a novel descriptor that we call image projection descriptor (IPD). These features are trained with support vector machines (SVM) and each pixel in the target image is locally assigned a score. These local scores are combined with the semiglobal geometrical information like the distance ratio and angle between the neighboring structures under the Markov random field (MRF) framework. An exact localization of discs and vertebrae is inferred from the MRF by finding a maximum a posteriori solution efficiently using dynamic programming. As a result of the novel features introduced, our system can scale-invariantly localize discs and vertebra at the same time even in the existence of missing structures. The proposed system is tested and validated on a clinical lumbar spine MR image dataset containing 80 subjects of which 64 have disc- and vertebra-related diseases and abnormalities. The experiments show that our system is successful even in abnormal cases and our results are comparable to the state of the art.

Localization of the lumbar discs using machine learning and exact probabilistic inference.

We propose a novel fully automatic approach to localize the lumbar intervertebral discs in MR images with PHOG based SVM and a probabilistic graphical model. At the local level, our method assigns a score to each pixel in target image that indicates whether it is a disc center or not. At the global level, we define a chain-like graphical model that represents the lumbar intervertebral discs and we use an exact inference algorithm to localize the discs. Our main contributions are the employment of the SVM with the PHOG based descriptor which is robust against variations of the discs and a graphical model that reflects the linear nature of the vertebral column. Our inference algorithm runs in polynomial time and produces globally optimal results. The developed system is validated on a real spine MRI dataset and the final localization results are favorable compared to the results reported in the literature.