Medical images like MR scans often show domain shifts across imaging sites due to scanner and protocol differences, which degrade machine learning performance in tasks such as disease classification. Domain harmonization is thus a critical research focus. Recent approaches encode brain images x into a low-dimensional latent space z, then disentangle it into zu(domain-invariant) and zd(domain-specific), achieving strong results. However, these methods often lack interpretability—an essential requirement in medical applications—leaving practical issues unresolved. We propose Pseudo-Linear-Style Encoder Adversarial Domain Adaptation (PL-SE-ADA), a general framework for domain harmonization and interpretable representation learning that preserves disease-relevant information in brain MR images. PL-SE-ADA includes two encoders fEand fSEto extract zuand zd, a decoder to reconstruct the image fD, and a domain predictor gD. Beyond adversarial training between the encoder and domain predictor, the model learns to reconstruct the input image x by summing reconstructions from zuand zd, ensuring both harmonization and informativeness. Compared to prior methods, PL-SE-ADA achieves equal or better performance in image reconstruction, disease classification, and domain recognition. It also enables visualization of both domain-independent brain features and domain-specific components, offering high interpretability across the entire framework.

Plant disease classification from leaf images is often hindered by domain shift and a lack of interpretability. We propose a multimodal framework that integrates visual features with structured semantic information through image-specific alignment. Using LongCLIP (ViT-B/16), our system extracts image embeddings and aligns them with natural language descriptions derived from a self-curated, CLIP-compatible leaf feature dictionary. This dictionary includes 16 botanical categories that capture traits such as leaf margin, venation pattern, texture, and lesion color. CLIP-based similarity scoring selects the most relevant features from each category, which are then synthesized into modular natural language descriptions and converted into binary semantic vectors. These vectors are fused with image embeddings in a dual-encoder architecture, enhancing both classification performance and interpretability. Our method outperforms image-only base-lines across four crop datasets—tomato, cucumber, eggplant, and strawberry—achieving average macro-F1 improvements of +10.89 points on validation and +12.52 points on test data. The approach generalizes effectively to unseen farms, linking predictions to biologically meaningful features and providing a modular, extensible framework for explainable AI in plant health monitoring and beyond.

Numerous studies have shown the effectiveness of machine learning in plant disease classification. However, large-scale studies reveal significant performance drops on images from unseen environments due to insufficient data diversity relative to the variability in disease symptoms. Although various techniques including domain adaptation have been proposed, there still remain many struggles under substantial domain shifts. To address this, we propose ROI-mixup and neighborhood alignment (RMNA), an unsupervised domain adaptation method based on transductive learning, where the unlabeled target-domain (test-domain) data is fully accessible during training. Specifically, the proposed ROI-mixup reduces background interference by blending ROI and non-ROI tokens from source and target images, enhancing the extraction of key plant disease features. The neighborhood alignment leverages feature similarity and nearest-neighbor relationships to refine feature-space alignment, improving intra-class consistency and interclass separability. Across four crop-specific datasets, RMNA achieved up to a 4.99% accuracy improvement (67.14% → 72.13%) and increased the F1-score by 7.00% (73.00% → 80.00%), surpassing the state-of-the-art conditional adversarial domain adaptation (CDAN) model.

Various deep learning-based systems have been proposed for accurate and convenient plant disease diagnosis, achieving impressive performance. However, recent studies show that these systems often fail to maintain diagnostic accuracy on images captured under different conditions from the training environment—an essential criterion for model robustness. Many deep learning methods have shown high accuracy in plant disease diagnosis. However, they often struggle to generalize to images taken in conditions that differ from the training setting. This drop in performance stems from the subtle variability of disease symptoms and domain gaps—differences in image context and environment. The root cause is the limited diversity of training data relative to task complexity, making even advanced models vulnerable in unseen domains. To tackle this challenge, we propose a simple yet highly adaptable learning framework called Target-Aware Metric Learning with Prioritized Sampling (TMPS), grounded in metric learning. TMPS operates under the assumption of access to a limited number of labeled samples from the target (deployment) domain and leverages these samples effectively to improve diagnostic robustness. We assess TMPS on a large-scale automated plant disease diagnostic task using a dataset comprising 223,073 leaf images sourced from 23 agricultural fields, spanning 21 diseases and healthy instances across three crop species. By incorporating just 10 target domain samples per disease into training, TMPS surpasses models trained using the same combined source and target samples, and those fine-tuned with these target samples after pre-training on source data. It achieves average macro F1 score improvements of 7.3 and 3.6 points, respectively, and a remarkable 18.7 and 17.1 point improvement over the baseline and conventional metric learning.

Rapid advancements in artificial intelligence (AI) have made it crucial to integrate moral reasoning into AI systems. However, existing models and datasets often overlook regional and cultural differences. To address this shortcoming, we have expanded the JCommonsenseMorality (JCM) dataset, the only publicly available dataset focused on Japanese morality. The Extended JCM (eJCM) has grown from the original 13,975 sentences to 31,184 sentences using our proposed sentence expansion method called Masked Token and Label Enhancement (MTLE). MTLE selectively masks important parts of sentences related to moral judgment and replaces them with alternative expressions generated by a large language model (LLM), while re-assigning appropriate labels. The model trained using our eJCM achieved an F1 score of 0.857, higher than the scores for the original JCM (0.837), ChatGPT one-shot classification (0.841), and data augmented using AugGPT, a state-of-the-art augmentation method (0.850). Specifically, in complex moral reasoning tasks unique to Japanese culture, the model trained with eJCM showed a significant improvement in performance (increasing from 0.681 to 0.756) and achieved a performance close to that of GPT-4 Turbo (0.787). These results demonstrate the validity of the eJCM dataset and the importance of developing models and datasets that consider the cultural context.

Recommendation algorithms automatically suggest news articles based on past behavioral logs. There has been reported cases of mental health problems caused by continuous consumption of negative articles, besides recommendation algorithms has a problem of over-recommendation which may induce continuous consumption of negative articles. Although research on the relationship between negative news article consumption and mental health has been conducted via small-scale user interviews, large-scale behavioral research on user engagement with recommended news articles has not been carried out. Therefore, we comprehensively investigated how the emotional polarity of articles affects each indicator of user attention by assigning emotional labels to news articles using crowdsourcing and analyzing about 1 million user behavior logs that viewed these articles. To the best of our knowledge, this is one of the first publicly available studies to analyze the impact of negative articles on users' news consumption behavior on an online news platform. The findings indicated that negative articles, irrespective of their category, were more likely to be clicked on, were read for longer durations, and had lower bounce rates. Furthermore, users showed greater interest in negative news related to entertainment and sports. These findings can be used as a first step for news platforms to build safer recommendation algorithms that consider the psychological impact on users.

To make content-based image retrieval (CBIR) technology for magnetic resonance (MR) images of the brain practical and useful for diagnosis and research, it is important to obtain low-dimensional representations that embody pathological attributes. However, recent evidence suggests that variations in domains resulting from differences in imaging equipment and protocols at each imaging facility can overshadow pathological attributes. In this study, we propose a novel approach known as multidecoder adversarial domain adaptation (MD-ADA) to obtain low-dimensional representations of brain MR images that preserve pathological features while mitigating domain differences. This method combines adversarial domain adaptation techniques with convolutional autoencoders that have distinct decoders for each domain and employs adversarial learning to prevent domain discrimination from the produced low-dimensional representations. Experimental evaluations on two datasets, ADNI and PPMI, comprising 4,168 brain images demonstrate that the proposed MD-ADA significantly reduces domain differences between datasets without compromising the recoverability of brain images or the accuracy of disease classification.

It is often difficult to correctly infer a writer's emotion from text exchanged online, and differences in recognition between writers and readers can be problematic. In this paper, we propose a new framework for detecting sentences that create differences in emotion recognition between the writer and the reader and for detecting the kinds of expressions that cause such differences. The proposed framework consists of a bidirectional encoder representations from transformers (BERT)-based detector that detects sentences causing differences in emotion recognition and an analysis that acquires expressions that characteristically appear in such sentences. The detector, based on a Japanese SNS-document dataset with emotion labels annotated by both the writer and three readers of the social networking service (SNS) documents, detected "hidden-anger sentences" with AUC = 0.772; these sentences gave rise to differences in the recognition of anger. Because SNS documents contain many sentences whose meaning is extremely difficult to interpret, by analyzing the sentences detected by this detector, we obtained several expressions that appear characteristically in hidden-anger sentences. The detected sentences and expressions do not convey anger explicitly, and it is difficult to infer the writer's anger, but if the implicit anger is pointed out, it becomes possible to guess why the writer is angry. Put into practical use, this framework would likely have the ability to mitigate problems based on misunderstandings.

Content-based image retrieval (CBIR) systems are an emerging technology that supports reading and interpreting medical images. Since 3D brain MR images are high dimensional, dimensionality reduction is necessary for CBIR using machine learning techniques. In addition, for a reliable CBIR system, each dimension in the resulting low-dimensional representation must be associated with a neurologically interpretable region. We propose a localized variational autoencoder (Loc-VAE) that provides neuroanatomically interpretable low-dimensional representation from 3D brain MR images for clinical CBIR. Loc-VAE is based on $\beta-$VAE with the additional constraint that each dimension of the low-dimensional representation corresponds to a local region of the brain. The proposed Loc-VAE is capable of acquiring representation that preserves disease features and is highly localized, even under high-dimensional compression ratios (4096:1). The low-dimensional representation obtained by Loc-VAE improved the locality measure of each dimension by 4.61 points compared to naive $\beta-$VAE, while maintaining comparable brain reconstruction capability and information about the diagnosis of Alzheimer’ s disease.

Many applications for the automated diagnosis of plant disease have been developed based on the success of deep learning techniques. However, these applications often suffer from overfitting, and the diagnostic performance is drastically decreased when used on test data sets from new environments. In this article, we propose LeafGAN, a novel image-to-image translation system with own attention mechanism. LeafGAN generates a wide variety of diseased images via transformation from healthy images, as a data augmentation tool for improving the performance of plant disease diagnosis. Due to its own attention mechanism, our model can transform only relevant areas from images with a variety of backgrounds, thus enriching the versatility of the training images. Experiments with five-class cucumber disease classification show that data augmentation with vanilla CycleGAN cannot help to improve the generalization, i.e., disease diagnostic performance increased by only 0.7% from the baseline. In contrast, LeafGAN boosted the diagnostic performance by 7.4%. We also visually confirmed that the generated images by our LeafGAN were much better quality and more convincing than those generated by vanilla CycleGAN. The code is available publicly athttps://github.com/IyatomiLab/LeafGAN.Note to PractitionersAutomated plant disease diagnosis systems play an important role in the agricultural automation field. Building a practical image-based automatic plant diagnosis system requires collecting a wide variety of disease images with reliable label information. However, it is quite labor-intensive. Conventional systems have reported relatively high diagnosis performance, but most of their scores were largely biased due to the “latent similarity” between training and test images, and their true diagnosis capabilities were much lower than claimed. To address this issue, we propose LeafGAN, which generates countless diverse and high-quality training images; it works as an efficient data augmentation for the diagnosis classifier. Such generated images can be used as useful resources for improving the performance of the cucumber disease diagnosis systems.

Although image-based melanoma diagnosis has achieved a sufficient level of numerical accuracy, providing objective evidence is essential to enhance the explainability and reliability of this approach. The collection of label information based on quantitative clinical indicators is very expensive, meaning that the amount of labeled data available is limited. In this paper, we propose an effective method for predicting explainable melanoma indicators defined by a 7-point checklist in a situation where only a limited number of labeled data are available. Our proposal effectively utilizes virtual adversarial training as a semi-supervised learning framework with multi-task learning. This approach gives favorable performance for only a very limited number of expensive labeled data. The proposed method improves the final accuracy of melanoma diagnosis calculated based on these predicted indices by 7.5% (making it equivalent to expert dermatologists), based on 9,124 unlabeled images with diagnosis information added to the 226 base labeled training images.

X-ray examinations are a common choice in mass screenings for gastric cancer. Compared to endoscopy and other common modalities, X-ray examinations have the significant advantage that they can be performed not only by radiologists but also by radiology technicians. However, the diagnosis of gastric X-ray images is very difficult and it has been reported that the diagnostic accuracy of these images is only 85.5%. In this study, we propose a practical diagnosis support system for gastric X-ray images. An important component of our system is the proposed on-line data augmentation strategy named stochastic gastric image augmentation (sGAIA), which stochastically generates various enhanced images of gastric folds in X-ray images. The proposed sGAIA improves the detection performance of the malignant region by 6.9% in F1-score and our system demonstrates promising screening performance for gastric cancer (recall of 92.3% with a precision of 32.4%) from X-ray images in a clinical setting based on Faster R-CNN with ResNetl01 networks.

Increasing numbers of MRI brain scans, improvements in image resolution, and advancements in MRI acquisition technology are causing significant increases in the demand for and burden on radiologists' efforts in terms of reading and interpreting brain MRIs. Content-based image retrieval (CBIR) is an emerging technology for reducing this burden by supporting the reading of medical images. High dimensionality is a major challenge in developing a CBIR system that is applicable for 3D brain MRIs. In this study, we propose a system called disease-oriented data concentration with metric learning (DDCML). In DDCML, we introduce deep metric learning to a 3D convolutional autoencoder (CAE). Our proposed DDCML scheme achieves a high dimensional compression rate (4096:1) while preserving the disease-related anatomical features that are important for medical image classification. The low-dimensional representation obtained by DDCML improved the clustering performance by 29.1% compared to plain 3D-CAE in terms of discriminating Alzheimer's disease patients from healthy subjects, and successfully reproduced the relationships of the severity of disease categories that were not included in the training.

In image-based plant diagnosis, clues related to diagnosis are often unclear, and the other factors such as image backgrounds often have a significant impact on the final decision. As a result, overfitting due to latent similarities in the dataset often occurs, and the diagnostic performance on real unseen data (e,g. images from other farms) is usually dropped significantly. However, this problem has not been sufficiently explored, since many systems have shown excellent diagnostic performance due to the bias caused by the similarities in the dataset. In this study, we investigate this problem with experiments using more than 50,000 images of cucumber leaves, and propose an anti-overfitting pretreatment (AOP) for realizing practical image-based plant diagnosis systems. The AOP detects the area of interest (leaf, fruit etc.) and performs brightness calibration as a preprocessing step. The experimental results demonstrate that our AOP can improve the accuracy of diagnosis for unknown test images from different farms by 12.2% in a practical setting.

Practical automated detection and diagnosis of plant disease from wide-angle images (i.e. in-field images containing multiple leaves using a fixed-position camera) is a very important application for large-scale farm management, in view of the need to ensure global food security. However, developing automated systems for disease diagnosis is often difficult, because labeling a reliable wide-angle disease dataset from actual field images is very laborious. In addition, the potential similarities between the training and test data lead to a serious problem of model overfitting. In this paper, we investigate changes in performance when applying disease diagnosis systems to different scenarios involving wide-angle cucumber test data captured on real farms, and propose an effective diagnostic strategy. We show that leading object recognition techniques such as SSD and Faster R-CNN achieve excellent end-to-end disease diagnostic performance only for a test dataset that is collected from the same population as the training dataset (with F1-score of 81.5% - 84.1% for diagnosed cases of disease), but their performance markedly deteriorates for a completely different test dataset (with F1-score of 4.4 - 6.2%). In contrast, our proposed two-stage systems using independent leaf detection and leaf diagnosis stages attain a promising disease diagnostic performance that is more than six times higher than end-to-end systems (with F1-score of 33.4 - 38.9%) on an unseen target dataset. We also confirm the efficiency of our proposal based on visual assessment, concluding that a two-stage model is a suitable and reasonable choice for practical applications.

Accurately predicting conversions in advertisements is generally a challenging task, because such conversions do not occur frequently. In this paper, we propose a new framework to support creating high-performing ad creatives, including the accurate prediction of ad creative text conversions before delivering to the consumer. The proposed framework includes three key ideas: multi-task learning, conditional attention, and attention highlighting. Multi-task learning is an idea for improving the prediction accuracy of conversion, which predicts clicks and conversions simultaneously, to solve the difficulty of data imbalance. Furthermore, conditional attention focuses attention of each ad creative with the consideration of its genre and target gender, thus improving conversion prediction accuracy. Attention highlighting visualizes important words and/or phrases based on conditional attention. We evaluated the proposed framework with actual delivery history data (14,000 creatives displayed more than a certain number of times from Gunosy Inc.), and confirmed that these ideas improve the prediction performance of conversions, and visualize noteworthy words according to the creatives' attributes.

Languages such as Chinese and Japanese have a significantly large number (several thousands) of alphabets as compared to other languages, and each of their sentences consists of several concatenated words with wide varieties of inflected forms; thus appropriate word segmentation is quite difficult. Therefore, recently proposed sophisticated language-processing methods designed for languages such as English cannot be applied. In this paper, we address those issues and propose a new and efficient document classification technique for such languages. The proposed method is characterized into a new “image-based character embedding” method and character-level convolutional neural networks method with “wildcard training.” The first method encodes each character based on its pictorial structures and preserves them. Further, the second method treats some of the input characters as wildcards in the classification stage and functions as efficient data augmentation. We confirmed that our proposed method showed superior performance when compared conventional methods for Japanese document classification problems.

In this paper, we propose a simple and effective preprocessing method for melanoma classification by considering cytological properties of melanomas, in particular the alignment of the major axis of the tumor in the same direction. We evaluate our method with a set of 1,760 dermoscopic images (329 of melanomas and 1,431 of nevi) and a simple convolutional neural network (CNN) classifier with five-fold cross validation. The proposed tumor alignment method improves the classification performance by 5.8% in terms of the area under the ROC curve (AUC). In addition, it proves to be 2.1% better in term of AUC when compared with the same configured CNN trained using images that are nine times larger. Our results also show that considering the intrinsic features of the classification target is important even when the classifier has a capability to obtain effective features automatically through its learning process.

Accurate plant diagnosis requires experts' knowledge but is usually expensive and time consuming. Therefore, it has become necessary to design an accurate, easy, and low-cost automated diagnostic system for plant diseases. In this paper, we propose a new practical plant-disease detection system. We use 7,520 cucumber leaf images comprising images of healthy leaves and those infected by almost all types of viral diseases. The leaves were photographed on site under only one requirement, that is, each image must contain a leaf roughly at its center, thus providing them with a large variety of appearances (i.e., parameters including distance, angle, background, and lighting condition were not uniform). Although half of the images used in this experiment were taken in bad conditions, our classification system based on convolutional neural networks attained an average of 82.3% accuracy under the 4-fold cross validation strategy.

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In many cases, the lesion can be roughly separated from the background skin using a thresholding method applied to the blue channel. However, no single thresholding method appears to be robust enough to successfully handle a wide variety of dermoscopic images. In this paper, we present an automated method for detecting lesion borders in dermoscopy images using a fusion of several thresholding methods. Experiments on a difficult set of 90 images demonstrate that the proposed method achieves both fast and accurate results when compared to six state-of-the-art methods.

Accurate color information in dermoscopy images is very important for melanoma diagnosis since inappropriate white balance or brightness in the images adversely affects the diagnostic performance. In this paper, we present an automated color normalization method for dermoscopy images of skin lesions. We develop color normalization filters based on a total of 319 images which normalize color of images using the HSV color system. We determined that the color characteristics of the peripheral part of the tumors significantly influence the color normalization and confirmed that the developed normalization filter achieved satisfactory normalization performance as evaluated by a cross-validation test.

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is typically the first step in this analysis yet is often limited by the quality of the images to be analyzed. In this paper, we present an effective method to enhance the contrast in dermoscopy images. Given an input RGB image, we determine the optimal weights to convert it to grayscale by maximizing a histogram bimodality measure. Experiments on a large set of images demonstrate that this adaptive optimization scheme increases the contrast between the lesion and the background skin, and leads to a more accurate separation of the two regions using Otsu's thresholding method.

Accurate extraction of lesion borders is a crucial step in analysing dermoscopic skin lesion images. In this paper we present an effective approach to extracting lesion areas by combining an iterative segmentation algorithm with a preprocessing step that enhances colour information and image contrast. Following the pre-processing, analysis of the image background is conducted by iterative measurements based on median and standard deviation of non-lesion pixels, which in turn facilitates automatic and recurring noise reduction and enhancement. The algorithm does not depend on the use of rigid threshold values as an optimal thresholding algorithm is used to determine the optimal threshold iteratively. Extensive experimental evaluation is carried out on a dataset of 90 dermoscopy images with known ground truths obtained from three expert dermatologists. The results show that our approach is capable of providing good segmentation performance and that the colour enhancement step is indeed crucial as demonstrated by comparison with results obtained from the original RGB images.

A new system of knowledge extraction and recognition from scenery images is proposed in this paper. The system can extract different levels of knowledge automatically using Fuzzy Inference Neural Network (FINN). The proposed system consists of several Knowledge Extraction Networks (KENs). Each one is composed of FINN, and it can extract fuzzy if-then rules automatically. The KEN has an input-output (I/O) layer and two different-sized rule layers. The I/O layer includes the input part and the output part. The input part receives information on a pixel such as the position, the Intensity, the Hue and the Saturation. The output part receives the label of the corresponding pixel such as sky, mountains and woods, etc. The larger rule layer extracts detailed knowledge and it uses for the image recognition. On the other hand, the smaller rule layer extracts global knowledge which can correct contradiction of detailed knowledge and can remove trivial knowledge. It can be seen that the proposed system can recognize the image almost correctly by computer experiments. Knowledge is obtained by integrating rules from each KEN and then translating them into linguistic form. The extracted knowledge is quite natural.