Chatbot dialogic reading boosts comprehension for Chinese kindergarteners with higher language skills.

Dialogic reading promotes early language and literacy development, but high-quality interactions may be inaccessible to disadvantaged children. This study examined whether a chatbot could deliver dialogic reading support comparable to a human partner for Chinese kindergarteners. Using a 2 × 2 factorial design, 148 children (83 girls; Mage = 70.07 months, SD = 7.64) from less resourced families in Beijing, China, were randomly assigned to one of four conditions: dialogic or non-dialogic reading techniques with either a chatbot or human partner. The chatbot provided comparable dialogic support to the human partner, enhancing story comprehension and word learning. Critically, the chatbot's effect on story comprehension was moderated by children's language proficiency rather than age or reading ability. This demonstrates that chatbots can facilitate dialogic reading and highlights the importance of considering children's language skills when implementing chatbot dialogic interventions.

Deep learning based on ultrasound to differentiate pathologically proven atypical and typical medullary thyroid carcinoma from follicular thyroid adenoma.

OBJECTIVES: To investigate the feasibility and value of deep learning based on grayscale ultrasonography in the differentiation of pathologically proven atypical and typical medullary thyroid carcinoma (MTC) from follicular thyroid adenoma (FTA). METHODS: The preoperative 770 ultrasound images consisted of 354 MTCs (66% were typical MTCs with a high suspicion sonographic pattern, 34% were atypical MTCs with a suspicion pattern of intermediate or less) and 416 FTAs. All images were delineated manually by a senior sonographer to achieve the regions of interest. Two deep neural networks of ResNet-34 and ResNet-18 were performed on the training set (n = 690). The test data set (n = 80) was subsequently evaluated by the two models and two sonographers, their diagnostic performances and misdiagnosis lesions were compared and analyzed. RESULTS: The ResNet-34 model shows higher diagnostic ability than the junior sonographer with an area under the receiver operating curve of 0.992 (95% CI: 0.840-0.970)versus 0.754 (95% CI:0.645-0.843). Moreover, 12 of 16 atypical MTCs were successfully identified by the ResNet-34, which is significantly better than the senior and junior sonographer, suggesting that these patients could benefit from timely serological examination and surgical strategy at an earlier stage. CONCLUSION: Deep learning to differentiate MTC from FTA on grayscale ultrasound may be a useful diagnostic support tool, especially in atypical MTC and FTA. Moreover, the computing time of deep learning is short, which will help to incorporate it into real-time ultrasound diagnosis.

Application of artificial intelligence in preoperative imaging of hepatocellular carcinoma: Current status and future perspectives.

Hepatocellular carcinoma (HCC) is the most common primary malignant liver tumor in China. Preoperative diagnosis of HCC is challenging because of atypical imaging manifestations and the diversity of focal liver lesions. Artificial intelligence (AI), such as machine learning (ML) and deep learning, has recently gained attention for its capability to reveal quantitative information on images. Currently, AI is used throughout the entire radiomics process and plays a critical role in multiple fields of medicine. This review summarizes the applications of AI in various aspects of preoperative imaging of HCC, including segmentation, differential diagnosis, prediction of histopathology, early detection of recurrence after curative treatment, and evaluation of treatment response. We also review the limitations of previous studies and discuss future directions for diagnostic imaging of HCC.

Conventional Machine Learning versus Deep Learning for Magnification Dependent Histopathological Breast Cancer Image Classification: A Comparative Study with Visual Explanation.

Breast cancer is a serious threat to women. Many machine learning-based computer-aided diagnosis (CAD) methods have been proposed for the early diagnosis of breast cancer based on histopathological images. Even though many such classification methods achieved high accuracy, many of them lack the explanation of the classification process. In this paper, we compare the performance of conventional machine learning (CML) against deep learning (DL)-based methods. We also provide a visual interpretation for the task of classifying breast cancer in histopathological images. For CML-based methods, we extract a set of handcrafted features using three feature extractors and fuse them to get image representation that would act as an input to train five classical classifiers. For DL-based methods, we adopt the transfer learning approach to the well-known VGG-19 deep learning architecture, where its pre-trained version on the large scale ImageNet, is block-wise fine-tuned on histopathological images. The evaluation of the proposed methods is carried out on the publicly available BreaKHis dataset for the magnification dependent classification of benign and malignant breast cancer and their eight sub-classes, and a further validation on KIMIA Path960, a magnification-free histopathological dataset with 20 image classes, is also performed. After providing the classification results of CML and DL methods, and to better explain the difference in the classification performance, we visualize the learned features. For the DL-based method, we intuitively visualize the areas of interest of the best fine-tuned deep neural networks using attention maps to explain the decision-making process and improve the clinical interpretability of the proposed models. The visual explanation can inherently improve the pathologist's trust in automated DL methods as a credible and trustworthy support tool for breast cancer diagnosis. The achieved results show that DL methods outperform CML approaches where we reached an accuracy between 94.05% and 98.13% for the binary classification and between 76.77% and 88.95% for the eight-class classification, while for DL approaches, the accuracies range from 85.65% to 89.32% for the binary classification and from 63.55% to 69.69% for the eight-class classification.

Integrating Lung Parenchyma Segmentation and Nodule Detection With Deep Multi-Task Learning.

Lung parenchyma segmentation is valuable for improving the performance of lung nodule detection in computed tomography (CT) images. Traditionally, the two tasks are performed separately. This paper proposes a deep multi-task learning (MTL) approach to integrate these tasks for better lung nodule detection. Three new ideas lead to our proposed approach. First, lung parenchyma segmentation is used as the attention module and is combined with nodule detection in a single deep network. Second, lung nodule detection is performed in an anchor-free manner by dividing it into two subtasks, nodule center identification and nodule size regression. Third, a novel pyramid dilated convolution block (PDCB) is proposed to utilize the advantage of dilated convolution and tackle its gridding problem for better lung parenchyma segmentation. Based on these ideas, we design our end-to-end deep network architecture and corresponding MTL method to achieve lung parenchyma segmentation and nodule detection simultaneously. We evaluate the proposed approach on the commonly used Lung Nodule Analysis 2016 (LUNA16) dataset. The experimental results show the value of our contributions and demonstrate that our approach can yield significant improvements compared with state-of-the-art counterparts.

Automatic Segmentation of the Prostate on MR Images based on Anatomy and Deep Learning.

Accurate segmentation of the prostate has many applications in the detection, diagnosis and treatment of prostate cancer. Automatic segmentation can be a challenging task because of the inhomogeneous intensity distributions on MR images. In this paper, we propose an automatic segmentation method for the prostate on MR images based on anatomy. We use the 3D U-Net guided by anatomy knowledge, including the location and shape prior knowledge of the prostate on MR images, to constrain the segmentation of the gland. The proposed method has been evaluated on the public dataset PROMISE2012. Experimental results show that the proposed method achieves a mean Dice similarity coefficient of 91.6% as compared to the manual segmentation. The experimental results indicate that the proposed method based on anatomy knowledge can achieve satisfactory segmentation performance for prostate MRI.

Computer-aided Classification of Lung Nodules on CT Images with Expert Knowledge.

Accurate classification of pulmonary nodules in the CT images is critical for early detection of lung cancer as well as the assessment of the effect from COVID-19. In this paper, we propose a computer-aided classification method for lung nodules using expert knowledge. We use a decoupling metric learning model to describe the deep characteristics of the nodules and then calculate the similarity between the current nodule and the nodules in the database. By analyzing the returned nodules with the diagnosis information, we obtain the expert knowledge of similar nodules, based on which we make the decision of the current nodule. The proposed method has been evaluated on the benchmark LIDC-IDRI dataset and achieved an accuracy of 95.7% and AUC of 0.9901. The proposed classification method can have a variety of applications in lung cancer detection, diagnosis and therapy.

A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.

Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.

A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases.

The common CT imaging signs of lung diseases (CISLs) which frequently appear in lung CT images are widely used in the diagnosis of lung diseases. Computer-aided diagnosis (CAD) based on the CISLs can improve radiologists' performance in the diagnosis of lung diseases. Since similarity measure is important for CAD, we propose a multi-level method to measure the similarity between the CISLs. The CISLs are characterized in the low-level visual scale, mid-level attribute scale, and high-level semantic scale, for a rich representation. The similarity at multiple levels is calculated and combined in a weighted sum form as the final similarity. The proposed multi-level similarity method is capable of computing the level-specific similarity and optimal cross-level complementary similarity. The effectiveness of the proposed similarity measure method is evaluated on a dataset of 511 lung CT images from clinical patients for CISLs retrieval. It can achieve about 80% precision and take only 3.6 ms for the retrieval process. The extensive comparative evaluations on the same datasets are conducted to validate the advantages on retrieval performance of our multi-level similarity measure over the single-level measure and the two-level similarity methods. The proposed method can have wide applications in radiology and decision support. Graphical abstract.

Automatic recognition of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNNs.

Ground-glass opacity (GGO) is a common CT imaging sign on high-resolution CT, which means the lesion is more likely to be malignant compared to common solid lung nodules. The automatic recognition of GGO CT imaging signs is of great importance for early diagnosis and possible cure of lung cancers. The present GGO recognition methods employ traditional low-level features and system performance improves slowly. Considering the high-performance of CNN model in computer vision field, we proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling is performed on multi-views and multi-receptive fields, which reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has the ability to obtain the optimal fine-tuning model. Multi-CNN models fusion strategy obtains better performance than any single trained model. We evaluated our method on the GGO nodule samples in publicly available LIDC-IDRI dataset of chest CT scans. The experimental results show that our method yields excellent results with 96.64% sensitivity, 71.43% specificity, and 0.83 F1 score. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images. Graphical abstract We proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has ability to obtain the optimal fine-tuning model. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images.

Empirical Driven Automatic Detection of Lobulation Imaging Signs in Lung CT.

Computer-aided detection (CAD) of lobulation can help radiologists to diagnose/detect lung diseases easily and accurately. Compared to CAD of nodule and other lung lesions, CAD of lobulation remained an unexplored problem due to very complex and varying nature of lobulation. Thus, many state-of-the-art methods could not detect successfully. Hence, we revisited classical methods with the capability of extracting undulated characteristics and designed a sliding window based framework for lobulation detection in this paper. Under the designed framework, we investigated three categories of lobulation classification algorithms: template matching, feature based classifier, and bending energy. The resultant detection algorithms were evaluated through experiments on LISS database. The experimental results show that the algorithm based on combination of global context feature and BOF encoding has best overall performance, resulting in F1 score of 0.1009. Furthermore, bending energy method is shown to be appropriate for reducing false positives. We performed bending energy method following the LIOP-LBP mixture feature, the average positive detection per image was reduced from 30 to 22, and F1 score increased to 0.0643 from 0.0599. To the best of our knowledge this is the first kind of work for direct lobulation detection and first application of bending energy to any kind of lobulation work.

A new method of content based medical image retrieval and its applications to CT imaging sign retrieval.

This paper proposes a new method of content based medical image retrieval through considering fused, context-sensitive similarity. Firstly, we fuse the semantic and visual similarities between the query image and each image in the database as their pairwise similarities. Then, we construct a weighted graph whose nodes represent the images and edges measure their pairwise similarities. By using the shortest path algorithm over the weighted graph, we obtain a new similarity measure, context-sensitive similarity measure, between the query image and each database image to complete the retrieval process. Actually, we use the fused pairwise similarity to narrow down the semantic gap for obtaining a more accurate pairwise similarity measure, and spread it on the intrinsic data manifold to achieve the context-sensitive similarity for a better retrieval performance. The proposed method has been evaluated on the retrieval of the Common CT Imaging Signs of Lung Diseases (CISLs) and achieved not only better retrieval results but also the satisfactory computation efficiency.

Learning with distribution of optimized features for recognizing common CT imaging signs of lung diseases.

Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients. CISLs play important roles in the diagnosis of lung diseases. This paper proposes a novel learning method, namely learning with distribution of optimized feature (DOF), to effectively recognize the characteristics of CISLs. We improve the classification performance by learning the optimized features under different distributions. Specifically, we adopt the minimum spanning tree algorithm to capture the relationship between features and discriminant ability of features for selecting the most important features. To overcome the problem of various distributions in one CISL, we propose a hierarchical learning method. First, we use an unsupervised learning method to cluster samples into groups based on their distribution. Second, in each group, we use a supervised learning method to train a model based on their categories of CISLs. Finally, we obtain multiple classification decisions from multiple trained models and use majority voting to achieve the final decision. The proposed approach has been implemented on a set of 511 samples captured from human lung CT images and achieves a classification accuracy of 91.96%. The proposed DOF method is effective and can provide a useful tool for computer-aided diagnosis of lung diseases on CT images.

Combining Population and Patient-Specific Characteristics for Prostate Segmentation on 3D CT Images.

Prostate segmentation on CT images is a challenging task. In this paper, we explore the population and patient-specific characteristics for the segmentation of the prostate on CT images. Because population learning does not consider the inter-patient variations and because patient-specific learning may not perform well for different patients, we are combining the population and patient-specific information to improve segmentation performance. Specifically, we train a population model based on the population data and train a patient-specific model based on the manual segmentation on three slice of the new patient. We compute the similarity between the two models to explore the influence of applicable population knowledge on the specific patient. By combining the patient-specific knowledge with the influence, we can capture the population and patient-specific characteristics to calculate the probability of a pixel belonging to the prostate. Finally, we smooth the prostate surface according to the prostate-density value of the pixels in the distance transform image. We conducted the leave-one-out validation experiments on a set of CT volumes from 15 patients. Manual segmentation results from a radiologist serve as the gold standard for the evaluation. Experimental results show that our method achieved an average DSC of 85.1% as compared to the manual segmentation gold standard. This method outperformed the population learning method and the patient-specific learning approach alone. The CT segmentation method can have various applications in prostate cancer diagnosis and therapy.

Random Walk Based Segmentation for the Prostate on 3D Transrectal Ultrasound Images.

This paper proposes a new semi-automatic segmentation method for the prostate on 3D transrectal ultrasound images (TRUS) by combining the region and classification information. We use a random walk algorithm to express the region information efficiently and flexibly because it can avoid segmentation leakage and shrinking bias. We further use the decision tree as the classifier to distinguish the prostate from the non-prostate tissue because of its fast speed and superior performance, especially for a binary classification problem. Our segmentation algorithm is initialized with the user roughly marking the prostate and non-prostate points on the mid-gland slice which are fitted into an ellipse for obtaining more points. Based on these fitted seed points, we run the random walk algorithm to segment the prostate on the mid-gland slice. The segmented contour and the information from the decision tree classification are combined to determine the initial seed points for the other slices. The random walk algorithm is then used to segment the prostate on the adjacent slice. We propagate the process until all slices are segmented. The segmentation method was tested in 32 3D transrectal ultrasound images. Manual segmentation by a radiologist serves as the gold standard for the validation. The experimental results show that the proposed method achieved a Dice similarity coefficient of 91.37±0.05%. The segmentation method can be applied to 3D ultrasound-guided prostate biopsy and other applications.

A new classifier fusion method based on historical and on-line classification reliability for recognizing common CT imaging signs of lung diseases.

Common CT imaging signs of lung diseases (CISL) play important roles in the diagnosis of lung diseases. This paper proposes a new method of multiple classifier fusion to recognize the CISLs, which is based on the confusion matrices of the classifiers and the classification confidence values outputted by the classifiers. The confusion matrix reflects the historical reliability of decision-making of a classifier, while the difference between the classification confidence values reflects the on-line reliability of its decision-making. The two factors are merged to determine the weights of the classifiers' classification confidence values. Then the classifiers are fused in a weighted-sum form to make the final decision. We apply the proposed classifier fusion method to combine five types of classifiers for CISL recognition, including support vector machine (SVM), back-propagation neural network (BPNN), Naïve Bayes (NB), k-nearest neighbor (k-NN) and decision tree (DT). In the experiments on lung CT images, our method not only brought stable improvements of recognition performance, compared with single classifiers, but also outperformed two well-known methods of classifier fusion, AdaBoost and Bagging. These results show that the proposed method is effective and promising.

The LISS--a public database of common imaging signs of lung diseases for computer-aided detection and diagnosis research and medical education.

Lung computed tomography (CT) imaging signs play important roles in the diagnosis of lung diseases. In this paper, we review the significance of CT imaging signs in disease diagnosis and determine the inclusion criterion of CT scans and CT imaging signs of our database. We develop the software of abnormal regions annotation and design the storage scheme of CT images and annotation data. Then, we present a publicly available database of lung CT imaging signs, called LISS for short, which contains 271 CT scans and 677 abnormal regions in them. The 677 abnormal regions are divided into nine categories of common CT imaging signs of lung disease (CISLs). The ground truth of these CISLs regions and the corresponding categories are provided. Furthermore, to make the database publicly available, all private data in CT scans are eliminated or replaced with provisioned values. The main characteristic of our LISS database is that it is developed from a new perspective of CT imaging signs of lung diseases instead of commonly considered lung nodules. Thus, it is promising to apply to computer-aided detection and diagnosis research and medical education.

Recognizing common CT imaging signs of lung diseases through a new feature selection method based on Fisher criterion and genetic optimization.

Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients and play important roles in the diagnosis of lung diseases. This paper proposes a new feature selection method based on FIsher criterion and genetic optimization, called FIG for short, to tackle the CISL recognition problem. In our FIG feature selection method, the Fisher criterion is applied to evaluate feature subsets, based on which a genetic optimization algorithm is developed to find out an optimal feature subset from the candidate features. We use the FIG method to select the features for the CISL recognition from various types of features, including bag-of-visual-words based on the histogram of oriented gradients, the wavelet transform-based features, the local binary pattern, and the CT value histogram. Then, the selected features cooperate with each of five commonly used classifiers including support vector machine (SVM), Bagging (Bag), Naïve Bayes (NB), k -nearest neighbor (k-NN), and AdaBoost (Ada) to classify the regions of interests (ROIs) in lung CT images into the CISL categories. In order to evaluate the proposed feature selection method and CISL recognition approach, we conducted the fivefold cross-validation experiments on a set of 511 ROIs captured from real lung CT images. For all the considered classifiers, our FIG method brought the better recognition performance than not only the full set of original features but also any single type of features. We further compared our FIG method with the feature selection method based on classification accuracy rate and genetic optimization (ARG). The advantages on computation effectiveness and efficiency of FIG over ARG are shown through experiments.