One of the major neuropathological consequences of traumatic brain injury (TBI) is intracranial hemorrhage (ICH), which requires swift diagnosis to avert perilous outcomes. We present a new automatic hemorrhage segmentation technique via curriculum-based semi-supervised learning. It employs a pre-trained lightweight encoder-decoder framework (MobileNetV2) on labeled and unlabeled data. The model integrates consistency regularization for improved generalization, offering steady predictions from original and augmented versions of unlabeled data. The training procedure employs curriculum learning to progressively train the model at diverse complexity levels. We utilize the PhysioNet dataset to train and evaluate the proposed approach. The performance results surpass those of supervised model with an average Dice coefficient and Jaccard index of 0.573 and 0.428, respectively. Additionally, the method achieves 87.86% accuracy in hemorrhage classification and Cohen's Kappa value of 0.81, indicating substantial agreement with ground truth.
Segmentation of the lung field is considered as the first and crucial stage in diagnosis of pulmonary diseases. In clinical practice, computer-aided systems are used to segment the lung region from chest X-ray (CXR) or CT images. The task of segmentation is challenging due to the presence of opacities or consolidation in CXR, which are typically produced by overlaps between the lung region and intense abnormalities caused by pulmonary diseases such as pneumonia, tuberculosis, or COVID-19. Recently, Convolution Neural Networks (CNNs) have been shown promising for segmentation and detection in digital images. In this paper, we propose a two-stage framework based on adapted U-Net architecture to leverage automatic lung segmentation. In the first stage, we extract CXR-patches and train a modified U-Net architecture to generate an initial segmentation of lung field. The second stage is the post-processing step, where we deploy image processing techniques to obtain a clear final segmentation. The performance of the proposed method is evaluated on a set of 138 CXR images obtained from Montgomery County’s Tuberculosis Control Program, producing an average Dice Coefficient (DC) of 94.21%, and an average Intersection-Over-Union (IoU) of 91.37%.
To automatic detect lung nodules from CT images, we designed a two stage computer aided detection (CAD) system. The first stage is graph cuts segmentation to identify and segment the nodule candidates, and the second stage is convolutional neural network for false positive reduction. The dataset contains 595 CT cases randomly selected from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) and the 305 pulmonary nodules achieved diagnosis consensus by all four experienced radiologists were our detection targets. Consider each slice as an individual sample, 2844 nodules were included in our database. The graph cuts segmentation was conducted in a two-dimension manner, 2733 lung nodule ROIs are successfully identified and segmented. With a false positive reduction by a seven-layer convolutional neural network, 2535 nodules remain detected while the false positive dropped to 31.6%. The average F-measure of segmented lung nodule tissue is 0.8501.
Based on the likelihood of malignancy, the nodules are classified into five different levels in Lung Image Database Consortium (LIDC) database. In this study, we tested the possibility of using threedimensional (3D) texture features to identify the malignancy level of each nodule. Five groups of features were implemented and tested on 172 nodules with confident malignancy levels from four radiologists. These five feature groups are: grey level co-occurrence matrix (GLCM) features, local binary pattern (LBP) features, scale-invariant feature transform (SIFT) features, steerable features, and wavelet features. Because of the high dimensionality of our proposed features, multidimensional scaling (MDS) was used for dimension reduction. RUSBoost was applied for our extracted features for classification, due to its advantages in handling imbalanced dataset. Each group of features and the final combined features were used to classify nodules highly suspicious for cancer (level 5) and moderately suspicious (level 4). The results showed that the area under the curve (AUC) and accuracy are 0.7659 and 0.8365 when using the finalized features. These features were also tested on differentiating benign and malignant cases, and the reported AUC and accuracy were 0.8901 and 0.9353.
We explore the use of a commercial thermal imaging infrared camera (7-12 micron, uncooled microbolometer array, 320 x 240 resolution) to characterize microfluidic devices with the aims of: 1) evaluating the usefulness of thermal imaging to assess various flow configurations with respect to heat transfer, and 2) developing educational laboratory projects combining rapid prototyping, thermal imaging, microfluidics, and heat transfer. We investigated concurrent and countercurrent heat exchangers, mixing streams of different temperature (cold and hot water), mixing streams yielding a heat of mixing (ethanol and water), mixing streams yielding a heat of reaction (acid-base neutralization), and freezing and heating flowing streams in channels with a Peltier module. Energy efficiency can be assessed to determine the feasibility and effectiveness of microfluidic designs. Substantial improvements in mixing and heat transfer using a magnetic stirrer are demonstrated with thermal imaging.
A novel breast cancer risk analysis approach is proposed for enhancing performance of computerized breast cancer risk analysis using bilateral mammograms. Based on the intensity of breast area, five different sub-regions were acquired from one mammogram, and bilateral features were extracted from every sub-region. Our dataset includes 180 bilateral mammograms from 180 women who underwent routine screening examinations, all interpreted as negative and not recalled by the radiologists during the original screening procedures. A computerized breast cancer risk analysis scheme using four image processing modules, including sub-region segmentation, bilateral feature extraction, feature selection, and classification was designed to detect and compute image feature asymmetry between the left and right breasts imaged on the mammograms. The highest computed area under the curve (AUC) is 0.763 ± 0.021 when applying the multiple sub-region features to our testing dataset. The positive predictive value and the negative predictive value were 0.60 and 0.73, respectively. The study demonstrates that (1) features extracted from multiple sub-regions can improve the performance of our scheme compared to using features from whole breast area only; (2) a classifier using asymmetry bilateral features can effectively predict breast cancer risk; (3) incorporating texture and morphological features with density features can boost the classification accuracy.
A novel three stage Semi-Supervised Learning (SSL) approach is proposed for improving performance of computerized breast cancer analysis with undiagnosed data. These three stages include: (1) Instance selection, which is barely used in SSL or computerized cancer analysis systems, (2) Feature selection and (3) Newly designed ‘Divide Co-training’ data labeling method. 379 suspicious early breast cancer area samples from 121 mammograms were used in our research. Our proposed ‘Divide Co-training’ method is able to generate two classifiers through split original diagnosed dataset (labeled data), and label the undiagnosed data (unlabeled data) when they reached an agreement. The highest AUC (Area Under Curve, also called Az value) using labeled data only was 0.832 and it increased to 0.889 when undiagnosed data were included. The results indicate instance selection module could eliminate untypical data or noise data and enhance the following semi-supervised data labeling performance. Based on analyzing different data sizes, it can be observed that the AUC and accuracy go higher with the increase of either diagnosed data or undiagnosed data, and reach the best improvement (ΔAUC = 0.078, ΔAccuracy = 7.6%) with 40 of labeled data and 300 of unlabeled data.
This study investigates the feasibility of remote quality control using a host of advanced automation equipment with Internet accessibility. Recent emphasis on product quality and reduction of waste stems from the dynamic, globalized and customer-driven market, which brings opportunities and threats to companies, depending on the response speed and production strategies. The current trends in industry also include a wide spread of distributed manufacturing systems, where design, production, and management facilities are geographically dispersed. This situation mandates not only the accessibility to remotely located production equipment for monitoring and control, but efficient means of responding to changing environment to counter process variations and diverse customer demands. To compete under such an environment, companies are striving to achieve 100%, sensor-based, automated inspection for zero-defect manufacturing. In this study, the Internet-based quality control scheme is referred to as "E-Quality for Manufacturing" or "EQM" for short. By its definition, EQM refers to a holistic approach to design and to embed efficient quality control functions in the context of network integrated manufacturing systems. Such system let designers located far away from the production facility to monitor, control and adjust the quality inspection processes as production design evolves.
The current trends in industry include integration of an information and knowledge base network with a manufacturing system, which coined a new term, E-Manufacturing. From the perspective of E-Manufacturing, any production equipment and its control functions do not exist alone, but become a part of the holistic operation system with distant monitoring and fault diagnostic capabilities. The key to this new paradigm is the accessibility to a remotely located system and having the means of responding to a changing environment. In this study, a new methodology in predicting a system output has been investigated by applying a data mining technique and a hybrid type II fuzzy system in CNC turning operations. The purpose was to generate a supplemental control function under the dynamic machining environment, where unforeseeable changes may occur frequently. Two different types of membership functions were developed for the fuzzy logic systems and also by combining the two types, a hybrid system was generated. Genetic algorithm was used for fuzzy adaptation in the control system. Fuzzy rules are automatically modified in the process of genetic algorithm training. The computational results showed that the hybrid system with a genetic adaptation generated a far better accuracy. The hybrid fuzzy system with genetic algorithm training demonstrated more effective prediction capability and a strong potential for the implementation into existing control functions.
In today's global world, manufacturers are facing many challenges such as product design with distributed and collaborative workflows. Complexity in collaborative product design arises from the need to synthesize different perspectives of a problem. Specifically, dependency identification of the product design process, as well as integration and sharing of computing application among the design teams that are critical for efficiency of manufacturability. Web services are considered to be the key to collaborative product design through the Internet. Web services alone are passive whereas agents can provide alerts and updates when new information becomes available. In this paper, an agent-based Web services architecture is proposed and applied to augment manufacturability. Not only the agent-based Web services architecture makes system interoperation feasible, but also increases the efficiency of the distributed collaboration.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.