An interpretable multi-task system for clinically applicable COVID-19 diagnosis using CXR.

BACKGROUND: With the emergence of continuously mutating variants of coronavirus, it is urgent to develop a deep learning model for automatic COVID-19 diagnosis at early stages from chest X-ray images. Since laboratory testing is time-consuming and requires trained laboratory personal, diagnosis using chest X-ray (CXR) is a befitting option. OBJECTIVE: In this study, we proposed an interpretable multi-task system for automatic lung detection and COVID-19 screening in chest X-rays to find an alternate method of testing which are reliable, fast and easily accessible, and able to generate interpretable predictions that are strongly correlated with radiological findings. METHODS: The proposed system consists of image preprocessing and an unsupervised machine learning (UML) algorithm for lung region detection, as well as a truncated CNN model based on deep transfer learning (DTL) to classify chest X-rays into three classes of COVID-19, pneumonia, and normal. The Grad-CAM technique was applied to create class-specific heatmap images in order to establish trust in the medical AI system. RESULTS: Experiments were performed with 15,884 frontal CXR images to show that the proposed system achieves an accuracy of 91.94% in a test dataset with 2,680 images including a sensitivity of 94.48% on COVID-19 cases, a specificity of 88.46% on normal cases, and a precision of 88.01% on pneumonia cases. Our system also produced state-of-the-art outcomes with a sensitivity of 97.40% on public test data and 88.23% on a previously unseen clinical data (1,000 cases) for binary classification of COVID-19-positive and COVID-19-negative films. CONCLUSION: Our automatic computerized evaluation for grading lung infections exhibited sensitivity comparable to that of radiologist interpretation in clinical applicability. Therefore, the proposed solution can be used as one element of patient evaluation along with gold-standard clinical and laboratory testing.

Silicon substrate as a novel cell culture device for myoblast cells.

BACKGROUND: Tissue and organ regeneration via transplantation of cell bodies in-situ has become an interesting strategy in regenerative medicine. Developments of cell carriers to systematically deliver cell bodies in the damage site have fall shorten on effectively meet this purpose due to inappropriate release control. Thus, there is still need of novel substrate to achieve targeted cell delivery with appropriate vehicles. In the present study, silicon based photovoltaic (PV) devices are used as a cell culturing substrate for the expansion of myoblast mouse cell (C2C12 cells) that offers an atmosphere for regular cell growth in vitro. The adherence, viability and proliferation of the cells on the silicon surface were examined by direct cell counting and fluorescence microscopy. RESULTS: It was found that on the silicon surface, cells proliferated over 7 days showing normal morphology, and expressed their biological activities. Cell culture on silicon substrate reveals their attachment and proliferation over the surface of the PV device. After first day of culture, cell viability was 88% and cell survival remained above 86% as compared to the seeding day after the seventh day. Furthermore, the DAPI staining revealed that the initially scattered cells were able to eventually build a cellular monolayer on top of the silicon substrate. CONCLUSIONS: This study explored the biological applications of silicon based PV devices, demonstrating its biocompatibility properties and found useful for culture of cells on porous 2-D surface. The incorporation of silicon substrate has been efficaciously revealed as a potential cell carrier or vehicle in cell growth technology, allowing for their use in cell based gene therapy, tissue engineering, and therapeutic angiogenesis.

Machine-Learning-Enabled Diagnostics with Improved Visualization of Disease Lesions in Chest X-ray Images.

The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network's determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map. To fill this research gap, we first propose a VGG-16-architecture-based deep learning approach in combination with image enhancement, segmentation-based region of interest (ROI) cropping, and data augmentation steps to enhance classification accuracy. Later, a multi-layer Gradient CAM (ML-Grad-CAM) algorithm is integrated to generate a class-specific saliency map for improved visualization in CXR images. We also define and calculate a Severity Assessment Index (SAI) from the saliency map to quantitatively measure infection severity. The trained model achieved an accuracy score of 96.44% for the three-class CXR classification task, i.e., COVID-19, pneumonia, and normal (healthy patients), outperforming many existing techniques in the literature. The saliency maps generated from the proposed ML-GRAD-CAM algorithm are compared with the original Gran-CAM algorithm.

Multi-modal learning for inpatient length of stay prediction.

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS. To address the challenge, this study aims to establish a novel data-fusion model, termed as DF-Mdl, to integrate heterogeneous clinical data for predicting the LoS of inpatients between hospital discharge and admission. Multi-modal data such as demographic data, clinical notes, laboratory test results, and medical images are utilized in our proposed methodology with individual "basic" sub-models separately applied to each different data modality. Specifically, a convolutional neural network (CNN) model, which we termed CRXMDL, is designed for chest X-ray (CXR) image data, two long short-term memory networks are used to extract features from long text data, and a novel attention-embedded 1D convolutional neural network is developed to extract useful information from numerical data. Finally, these basic models are integrated to form a new data-fusion model (DF-Mdl) for inpatient LoS prediction. The proposed method attains the best R2 and EVAR values of 0.6039 and 0.6042 among competitors for the LoS prediction on the Medical Information Mart for Intensive Care (MIMIC)-IV test dataset. Empirical evidence suggests better performance compared with other state-of-the-art (SOTA) methods, which demonstrates the effectiveness and feasibility of the proposed approach.

Time-to-event modeling for hospital length of stay prediction for COVID-19 patients.

Providing timely patient care while maintaining optimal resource utilization is one of the central operational challenges hospitals have been facing throughout the pandemic. Hospital length of stay (LOS) is an important indicator of hospital efficiency, quality of patient care, and operational resilience. Numerous researchers have developed regression or classification models to predict LOS. However, conventional models suffer from the lack of capability to make use of typically censored clinical data. We propose to use time-to-event modeling techniques, also known as survival analysis, to predict the LOS for patients based on individualized information collected from multiple sources. The performance of six proposed survival models is evaluated and compared based on clinical data from COVID-19 patients.

Fast and fully-automated detection and segmentation of pulmonary nodules in thoracic CT scans using deep convolutional neural networks.

Deep learning techniques have been extensively used in computerized pulmonary nodule analysis in recent years. Many reported studies still utilized hybrid methods for diagnosis, in which convolutional neural networks (CNNs) are used only as one part of the pipeline, and the whole system still needs either traditional image processing modules or human intervention to obtain final results. In this paper, we introduced a fast and fully-automated end-to-end system that can efficiently segment precise lung nodule contours from raw thoracic CT scans. Our proposed system has four major modules: candidate nodule detection with Faster regional-CNN (R-CNN), candidate merging, false positive (FP) reduction with CNN, and nodule segmentation with customized fully convolutional neural network (FCN). The entire system has no human interaction or database specific design. The average runtime is about 16 s per scan on a standard workstation. The nodule detection accuracy is 91.4% and 94.6% with an average of 1 and 4 false positives (FPs) per scan. The average dice coefficient of nodule segmentation compared to the groundtruth is 0.793.

A new near-term breast cancer risk prediction scheme based on the quantitative analysis of ipsilateral view mammograms.

PURPOSE: To help improve efficacy of screening mammography and eventually establish an optimal personalized screening paradigm, this study aimed to develop and test a new near-term breast cancer risk prediction scheme based on the quantitative analysis of ipsilateral view of the negative screening mammograms. METHODS: The dataset includes digital mammograms acquired from 392 women with two sequential full-field digital mammography examinations. All the first ("prior") sets of mammograms were interpreted as negative during the original reading. In the sequential ("current") screening, 202 were proved positive and 190 remained negative/benign. For each pair of the "prior" ipsilateral mammograms, we adaptively fused the image features computed from two views. Using four different types of image features, we built four elastic net support vector machine (EnSVM) based classifiers. Then, the initial prediction scores form the 4 EnSVMs were combined to build a final artificial neural network (ANN) classifier that produces the final risk prediction score. The performance of the new scheme was evaluated by using a 10-fold cross-validation method and an assessment index of the area under the receiver operating characteristic curve (AUC). RESULTS: A total number of 466 features were initially extracted from each pair of ipsilateral mammograms. Among them, 51 were selected to build the EnSVM based prediction scheme. The AUC = 0.737 ±â€¯0.052 was yielded using the new scheme. Applying an optimal operating threshold, the prediction sensitivity was 60.4% (122 of 202) and the specificity was 79.0% (150 of 190). CONCLUSION: The study results showed moderately high positive association between computed risk scores using the "prior" negative mammograms and the actual outcome of the image-detectable breast cancers in the next subsequent screening examinations. The study also demonstrated that quantitative analysis of the ipsilateral views of the mammograms enabled to provide useful information in predicting near-term breast cancer risk.

Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data.

In this study we developed a graph based semi-supervised learning (SSL) scheme using deep convolutional neural network (CNN) for breast cancer diagnosis. CNN usually needs a large amount of labeled data for training and fine tuning the parameters, and our proposed scheme only requires a small portion of labeled data in training set. Four modules were included in the diagnosis system: data weighing, feature selection, dividing co-training data labeling, and CNN. 3158 region of interests (ROIs) with each containing a mass extracted from 1874 pairs of mammogram images were used for this study. Among them 100 ROIs were treated as labeled data while the rest were treated as unlabeled. The area under the curve (AUC) observed in our study was 0.8818, and the accuracy of CNN is 0.8243 using the mixed labeled and unlabeled data.

Computerized breast cancer analysis system using three stage semi-supervised learning method.

BACKGROUND AND OBJECTIVE: A large number of labeled medical image data is usually a requirement to train a well-performed computer-aided detection (CAD) system. But the process of data labeling is time consuming, and potential ethical and logistical problems may also present complications. As a result, incorporating unlabeled data into CAD system can be a feasible way to combat these obstacles. METHODS: In this study we developed a three stage semi-supervised learning (SSL) scheme that combines a small amount of labeled data and larger amount of unlabeled data. The scheme was modified on our existing CAD system using the following three stages: data weighing, feature selection, and newly proposed dividing co-training data labeling algorithm. Global density asymmetry features were incorporated to the feature pool to reduce the false positive rate. Area under the curve (AUC) and accuracy were computed using 10 fold cross validation method to evaluate the performance of our CAD system. The image dataset includes mammograms from 400 women who underwent routine screening examinations, and each pair contains either two cranio-caudal (CC) or two mediolateral-oblique (MLO) view mammograms from the right and the left breasts. From these mammograms 512 regions were extracted and used in this study, and among them 90 regions were treated as labeled while the rest were treated as unlabeled. RESULTS: Using our proposed scheme, the highest AUC observed in our research was 0.841, which included the 90 labeled data and all the unlabeled data. It was 7.4% higher than using labeled data only. With the increasing amount of labeled data, AUC difference between using mixed data and using labeled data only reached its peak when the amount of labeled data was around 60. CONCLUSIONS: This study demonstrated that our proposed three stage semi-supervised learning can improve the CAD performance by incorporating unlabeled data. Using unlabeled data is promising in computerized cancer research and may have a significant impact for future CAD system applications.

Rough set based rule induction in decision making using credible classification and preference from medical application perspective.

This paper presents a new heuristic algorithm for reduct selection based on credible index in the rough set theory (RST) applications. This algorithm is efficient and effective in selecting the decision rules particularly the problem to be solved in a large scale. This algorithm is capable to derive the rules with multi-outcomes and identify the most significant features simultaneously, which is unique and useful in solving predictive medical problems. The end results of the proposed approach are a set of decision rules that illustrates the causes for solitary pulmonary nodule and results of the long term treatment.

Photovoltaic surfaces enable clonal myoblastic cell release using visible light as external stimulation.

Many new biomedical approaches to treating disease require the supply of cells delivered to an injured or diseased organ either individually, collectively as aggregates or sheets, or encapsulated with a scaffold. The collection of cells is accomplished by using enzymatic digestion witch suffer from the need to remove the enzymes after digestion. In addition, enzymatic methods are not applicable for all cells, cell aggregates, cell sheets or 3D structures. The objective of this study was to investigate the release of cultured cells from silicon based Photovoltaic (PV) surfaces using a light source as external stimulation. C2C12 myoblasts were cultured on the negative surface of a PV device and upon confluence they were exposed to light. The amount of released cells was quantified as a function light exposure. It was found that light exposure at 25,000 lux for one hour caused equivalent cell release from the PV surface than trypsination. The released cells are viable and can be re-cultured if needed. This mechanism may offer an alternative method to release excitable cells without using an enzymatic agent. This may be important for cell therapy if larger cell structures such as sheets need to be collected.

Using multiscale texture and density features for near-term breast cancer risk analysis.

PURPOSE: To help improve efficacy of screening mammography by eventually establishing a new optimal personalized screening paradigm, the authors investigated the potential of using the quantitative multiscale texture and density feature analysis of digital mammograms to predict near-term breast cancer risk. METHODS: The authors' dataset includes digital mammograms acquired from 340 women. Among them, 141 were positive and 199 were negative/benign cases. The negative digital mammograms acquired from the "prior" screening examinations were used in the study. Based on the intensity value distributions, five subregions at different scales were extracted from each mammogram. Five groups of features, including density and texture features, were developed and calculated on every one of the subregions. Sequential forward floating selection was used to search for the effective combinations. Using the selected features, a support vector machine (SVM) was optimized using a tenfold validation method to predict the risk of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) was used as the performance assessment index. RESULTS: From a total number of 765 features computed from multiscale subregions, an optimal feature set of 12 features was selected. Applying this feature set, a SVM classifier yielded performance of AUC = 0.729 ± 0.021. The positive predictive value was 0.657 (92 of 140) and the negative predictive value was 0.755 (151 of 200). CONCLUSIONS: The study results demonstrated a moderately high positive association between risk prediction scores generated by the quantitative multiscale mammographic image feature analysis and the actual risk of a woman having an image-detectable breast cancer in the next subsequent examinations.