Domain transformation using semi-supervised CycleGAN for improving performance of classifying thyroid tissue images.

PURPOSE: A large number of research has been conducted on the classification of medical images using deep learning. The thyroid tissue images can be also classified by cancer types. Deep learning requires a large amount of data, but every medical institution cannot collect sufficient number of data for deep learning. In that case, we can consider a case where a classifier trained at a certain medical institution that has a sufficient number of data is reused at other institutions. However, when using data from multiple institutions, it is necessary to unify the feature distribution because the feature of the data differs due to differences in data acquisition conditions. METHODS: To unify the feature distribution, the data from Institution T are transformed to have the closer distribution to that from Institution S by applying a domain transformation using semi-supervised CycleGAN. The proposed method enhances CycleGAN considering the feature distribution of classes for making appropriate domain transformation for classification. In addition, to address the problem of imbalanced data with different numbers of data for each cancer type, several methods dealing with imbalanced data are applied to semi-supervised CycleGAN. RESULTS: The experimental results showed that the classification performance was enhanced when the dataset from Institution S was used as training data and the testing dataset from Institution T was classified after applying domain transformation. In addition, focal loss contributed to improving the mean F1 score the best as a method that addresses the class imbalance. CONCLUSION: The proposed method achieved the domain transformation of thyroid tissue images between two domains, where it retained the important features related to the classes across domains and showed the best F1 score with significant differences compared with other methods. In addition, the proposed method was further enhanced by addressing the class imbalance of the dataset.

Improved artificial intelligence discrimination of minor histological populations by supplementing with color-adjusted images.

Despite the dedicated research of artificial intelligence (AI) for pathological images, the construction of AI applicable to histopathological tissue subtypes, is limited by insufficient dataset collection owing to disease infrequency. Here, we present a solution involving the addition of supplemental tissue array (TA) images that are adjusted to the tonality of the main data using a cycle-consistent generative adversarial network (CycleGAN) to the training data for rare tissue types. F1 scores of rare tissue types that constitute < 1.2% of the training data were significantly increased by improving recall values after adding color-adjusted TA images constituting < 0.65% of total training patches. The detector also enabled the equivalent discrimination of clinical images from two distinct hospitals and the capability was more increased following color-correction of test data before AI identification (F1 score from 45.2 ± 27.1 to 77.1 ± 10.3, p < 0.01). These methods also classified intraoperative frozen sections, while excessive supplementation paradoxically decreased F1 scores. These results identify strategies for building an AI that preserves the imbalance between training data with large differences in actual disease frequencies, which is important for constructing AI for practical histopathological classification.

The presence of an intron relieves gene repression caused by promoter-proximal four-bp specific sequences in yeast.

Introns can enhance gene expression in eukaryotic cells in a process called intron-mediated enhancement (IME). The levels of enhancement are affected not only by the intron sequence but also by coding sequences (CDSs). However, the parts of CDSs responsible for mediating IME have not yet been identified. In this study, we identified an IME-mediating sequence by analyzing three pairs of IME-sensitive and -insensitive CDSs in Saccharomyces cerevisiae. Expression of the CDSs yCLuc, yRoGLU1, and KmBGA1 was enhanced by the presence of an intron (i.e., they were IME sensitive), but the expression of each corresponding codon-changed CDS, which encoded the identical amino acid sequence, was not enhanced (i.e., they were IME insensitive). Interestingly, the IME-insensitive CDSs showed higher expression levels that were like intron-enhanced expression of IME-sensitive CDSs, suggesting that expression of IME-sensitive CDSs was repressed. A four-nucleotide sequence (TCTT) located in the promoter-proximal position of either the untranslated or coding region was found to be responsible for repression in IME-sensitive CDSs, and repression caused by the TCTT sequence was relieved by the presence of an intron. Further, it was found that the expression of intron-containing yeast-native genes, UBC4 and MPT5, was repressed by TCTT in the CDS but relieved by the introns. These results indicate that TCTT sequences in promoter-proximal positions repress gene expression and that introns play a role in relieving gene repression caused by sequences such as TCTT.

Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease.

Contracting COPD reduces a patient's physical activity and restricts everyday activities (physical activity disorder). However, the fundamental cause of physical activity disorder has not been found. In addition, costly and specialized equipment is required to accurately examine the disorder; hence, it is not regularly assessed in normal clinical practice. In this study, we constructed a machine learning model to predict physical activity using test items collected during the normal care of COPD patients. In detail, we first applied three types of data preprocessing methods (zero-padding, multiple imputation by chained equations (MICE), and k-nearest neighbor (kNN)) to complement missing values in the dataset. Then, we constructed several types of neural networks to predict physical activity. Finally, permutation importance was calculated to identify the importance of the test items for prediction. Multifactorial analysis using machine learning, including blood, lung function, walking, and chest imaging tests, was the unique point of this research. From the experimental results, it was found that the missing value processing using MICE contributed to the best prediction accuracy (73.00%) compared to that using zero-padding (68.44%) or kNN (71.52%), and showed better accuracy than XGBoost (66.12%) with a significant difference (p < 0.05). For patients with severe physical activity reduction (total exercise < 1.5), a high sensitivity (89.36%) was obtained. The permutation importance showed that "sex, the number of cigarettes, age, and the whole body phase angle (nutritional status)" were the most important items for this prediction. Furthermore, we found that a smaller number of test items could be used in ordinary clinical practice for the screening of physical activity disorder.

Segmentation of Lung Nodules on CT Images Using a Nested Three-Dimensional Fully Connected Convolutional Network.

In computer-aided diagnosis systems for lung cancer, segmentation of lung nodules is important for analyzing image features of lung nodules on computed tomography (CT) images and distinguishing malignant nodules from benign ones. However, it is difficult to accurately and robustly segment lung nodules attached to the chest wall or with ground-glass opacities using conventional image processing methods. Therefore, this study aimed to develop a method for robust and accurate three-dimensional (3D) segmentation of lung nodule regions using deep learning. In this study, a nested 3D fully connected convolutional network with residual unit structures was proposed, and designed a new loss function. Compared with annotated images obtained under the guidance of a radiologist, the Dice similarity coefficient (DS) and intersection over union (IoU) were 0.845 ± 0.008 and 0.738 ± 0.011, respectively, for 332 lung nodules (lung adenocarcinoma) obtained from 332 patients. On the other hand, for 3D U-Net and 3D SegNet, the DS was 0.822 ± 0.009 and 0.786 ± 0.011, respectively, and the IoU was 0.711 ± 0.011 and 0.660 ± 0.012, respectively. These results indicate that the proposed method is significantly superior to well-known deep learning models. Moreover, we compared the results obtained from the proposed method with those obtained from conventional image processing methods, watersheds, and graph cuts. The DS and IoU results for the watershed method were 0.628 ± 0.027 and 0.494 ± 0.025, respectively, and those for the graph cut method were 0.566 ± 0.025 and 0.414 ± 0.021, respectively. These results indicate that the proposed method is significantly superior to conventional image processing methods. The proposed method may be useful for accurate and robust segmentation of lung nodules to assist radiologists in the diagnosis of lung nodules such as lung adenocarcinoma on CT images.

Semi-supervised CycleGAN for domain transformation of chest CT images and its application to opacity classification of diffuse lung diseases.

PURPOSE: The performance of deep learning may fluctuate depending on the imaging devices and settings. Although domain transformation such as CycleGAN for normalizing images is useful, CycleGAN does not use information on the disease classes. Therefore, we propose a semi-supervised CycleGAN with an additional classification loss to transform images suitable for the diagnosis. The method is evaluated by opacity classification of chest CT. METHODS: (1) CT images taken at two hospitals (source and target domains) are used. (2) A classifier is trained on the target domain. (3) Class labels are given to a small number of source domain images for semi-supervised learning. (4) The source domain images are transformed to the target domain. (5) A classification loss of the transformed images with class labels is calculated. RESULTS: The proposed method showed an F-measure of 0.727 in the domain transformation from hospital A to B, and 0.745 in that from hospital B to A, where significant differences are between the proposed method and the other three methods. CONCLUSIONS: The proposed method not only transforms the appearance of the images but also retains the features being important to classify opacities, and shows the best precision, recall, and F-measure.

Deep Learning for Pulmonary Image Analysis: Classification, Detection, and Segmentation.

Image-based computer-aided diagnosis (CAD) algorithms by the use of convolutional neural network (CNN) which do not require the image-feature extractor are powerful compared with conventional feature-based CAD algorithms which require the image-feature extractor for classification of lung abnormalities. Moreover, computer-aided detection and segmentation algorithms by the use of CNN are useful for analysis of lung abnormalities. Deep learning will improve the performance of CAD systems dramatically. Therefore, they will change the roles of radiologists in the near future. In this article, we introduce development and evaluation of such image-based CAD algorithms for various kinds of lung abnormalities such as lung nodules and diffuse lung diseases.

Unsupervised class labeling of diffuse lung diseases using frequent attribute patterns.

PURPOSE: For realizing computer-aided diagnosis (CAD) of computed tomography (CT) images, many pattern recognition methods have been applied to automatic classification of normal and abnormal opacities; however, for the learning of accurate classifier, a large number of images with correct labels are necessary. It is a very time-consuming and impractical task for radiologists to give correct labels for a large number of CT images. In this paper, to solve the above problem and realize an unsupervised class labeling mechanism without using correct labels, a new clustering algorithm for diffuse lung diseases using frequent attribute patterns is proposed. METHODS: A large number of frequently appeared patterns of opacities are extracted by a data mining algorithm named genetic network programming (GNP), and the extracted patterns are automatically distributed to several clusters using genetic algorithm (GA). In this paper, lung CT images are used to make clusters of normal and diffuse lung diseases. RESULTS: After executing the pattern extraction by GNP, 1,148 frequent attribute patterns were extracted; then, GA was executed to make clusters. This paper deals with making clusters of normal and five kinds of abnormal opacities (i.e., six-class problem), and then, the proposed method without using correct class labels in the training showed 47.7 % clustering accuracy. CONCLUSION: It is clarified that the proposed method can make clusters without using correct labels and has the potential to apply to CAD, reducing the time cost for labeling CT images.

A graph-based evolutionary algorithm: Genetic Network Programming (GNP) and its extension using reinforcement learning.

This paper proposes a graph-based evolutionary algorithm called Genetic Network Programming (GNP). Our goal is to develop GNP, which can deal with dynamic environments efficiently and effectively, based on the distinguished expression ability of the graph (network) structure. The characteristics of GNP are as follows. 1) GNP programs are composed of a number of nodes which execute simple judgment/processing, and these nodes are connected by directed links to each other. 2) The graph structure enables GNP to re-use nodes, thus the structure can be very compact. 3) The node transition of GNP is executed according to its node connections without any terminal nodes, thus the past history of the node transition affects the current node to be used and this characteristic works as an implicit memory function. These structural characteristics are useful for dealing with dynamic environments. Furthermore, we propose an extended algorithm, "GNP with Reinforcement Learning (GNPRL)" which combines evolution and reinforcement learning in order to create effective graph structures and obtain better results in dynamic environments. In this paper, we applied GNP to the problem of determining agents' behavior to evaluate its effectiveness. Tileworld was used as the simulation environment. The results show some advantages for GNP over conventional methods.

Propagation and control of stochastic signals through universal learning networks.

The way of propagating and control of stochastic signals through Universal Learning Networks (ULNs) and its applications are proposed. ULNs have been already developed to form a superset of neural networks and have been applied as a universal framework for modeling and control of non-linear large-scale complex systems. However, the ULNs cannot deal with stochastic variables. Deterministic signals can be propagated through a ULN, but the ULN does not provide any stochastic characteristics of the signals propagating through it. The proposed method named Probabilistic Universal Learning Networks (PrULNs) can process stochastic variables and can train network parameters so that the signals behave with the pre-specified stochastic properties. As examples of applications of the proposed method, control and identification of non-linear dynamic systems with noises are studied, and it is shown that the method are useful for dealing with the control and identification of the non-linear stochastic systems contaminated with noises.