Heterogeneous Images Research Articles

Reappraising imaging features of pancreatic acinar cystic transformation: be aware of differential diagnoses.

Imaging features of pancreatic acinar cystic transformation (ACT) have been published. We aimed to describe the clinical and radiological characteristics of patients with a presumed pancreatic ACT diagnosis, reappraising the value of these published imaging criteria. Single-center retrospective study (2003-2021) of consecutive patients with a presumed diagnosis of ACT as suggested by the local expert multidisciplinary case review board. Patients without available imaging (CT or MRI) for review were excluded. Patients were classified into "certain" ACT (if ≥ 2 imaging criteria and no differential diagnosis) or "uncertain" ACT (if ≥ 1 imaging criteria and suggested differential diagnoses). Sixty-four patients (35 males, [55%]) were included. ACT was considered "certain" for 34 patients (53%) and "uncertain" for 30 patients (47%). The number of ACT criteria did not differ between groups, with 91.2% of patients with ≥ 3 ACT imaging criteria in the "certain" group vs 93.3% in the "uncertain" group (p = 0.88). In the "uncertain" group, the main suggested differentials were branch-duct intraductal papillary mucinous neoplasm (18/30 patients, 60%), calcifying chronic pancreatitis (8/30 patients, 27%), both (three patients, 10%) and serous cystadenoma (one patient, 3%). Calcifications were significantly more frequent in the "uncertain" group (89% vs 63% in the "certain" group, p = 0.02). Published ACT imaging criteria are frequently associated with features suggesting differential diagnoses. They appear insufficient to reach a final diagnosis in a subset of patients. ACT displays a heterogeneous morphological imaging presentation challenging the non-invasive diagnostic work-up. Physicians' and radiologists' awareness of this entity is important to better understand its natural history and improve non-invasive diagnostic criteria. The criteria to help diagnose ACT are frequently associated with features suggestive of differentials. The main alternatives suggested when ACT diagnosis was "uncertain" were branch-duct intraductal papillary mucinous neoplasm and calcifying chronic pancreatitis. Published ACT diagnostic imaging criteria can be insufficient for a definite non-invasive diagnosis.

Self-Guided Autoencoders for Unsupervised Change Detection in Heterogeneous Remote Sensing Images

Self-Guided Autoencoders for Unsupervised Change Detection in Heterogeneous Remote Sensing Images

A Simple Normalization Technique Using Window Statistics to Improve the Out-of-Distribution Generalization on Medical Images.

Since data scarcity and data heterogeneity are prevailing for medical images, well-trained Convolutional Neural Networks (CNNs) using previous normalization methods may perform poorly when deployed to a new site. However, a reliable model for real-world clinical applications should generalize well both on in-distribution (IND) and out-of-distribution (OOD) data (e.g., the new site data). In this study, we present a novel normalization technique called window normalization (WIN) to improve the model generalization on heterogeneous medical images, which offers a simple yet effective alternative to existing normalization methods. Specifically, WIN perturbs the normalizing statistics with the local statistics computed within a window. This feature-level augmentation technique regularizes the models well and improves their OOD generalization significantly. Leveraging its advantage, we propose a novel self-distillation method called WIN-WIN. WIN-WIN can be easily implemented with two forward passes and a consistency constraint, serving as a simple extension to existing methods. Extensive experimental results on various tasks (6 tasks) and datasets (24 datasets) demonstrate the generality and effectiveness of our methods.

A multi-branch dual attention segmentation network for epiphyte drone images

Acquiring images of epiphytes growing on trees using Unmanned Aerial Vehicles (UAVs) enables botanists to efficiently collect data on these important plant species. Despite the advantages offered by UAVs, challenges such as complex backgrounds, uneven lighting inside the tree canopy, and accessibility issues hinder the acquisition of quality images, resulting in acquiring images datasets of heterogenous quality. AI/Deep Learning algorithms can be used to segment target plants in these images for selecting sampling locations. Existing DL models require large volume of data for training, and they tend to prioritize local features over global ones, impacting segmentation accuracy, particularly on smaller, heterogeneous quality image datasets. To overcome these limitations, we propose a multi-branch dual attention segmentation network designed to effectively handle small datasets with heterogeneous quality. The proposed network incorporates dedicated branches for extracting both global and local features, utilizing spatial and channel attention mechanisms to focus on important regions. Through a fusion process and a decoder with crossed fusion technique, this network effectively combines and enhances features from multiple branches, resulting in improved segmentation performance. Output obtained from the trained model demonstrated major improvements in predicting the boundary regions and class labels, even in close-range, low-light, and zoomed/cropped images. The average Intersection over Union (IoU) scores of the trained model was 5% higher for images acquired close range, 48% higher for images in low-light conditions, and 68% higher for zoomed/cropped images when compared to those obtained from TransUnet, a state-of-the-art vision transformer model trained on epiphyte dataset. The proposed network can be used for segmenting epiphytes in images of heterogeneous quality as well as identifying targets in images acquired in domains such as agriculture and forestry.

Self-Paced Multi-Scale Joint Feature Mapper for Multi-Objective Change Detection in Heterogeneous Images

Self-Paced Multi-Scale Joint Feature Mapper for Multi-Objective Change Detection in Heterogeneous Images

RadioGWAS links radiome to genome to discover driver genes with somatic mutations for heterogeneous tumor image phenotype in pancreatic cancer

Addressing the significant level of variability exhibited by pancreatic cancer necessitates the adoption of a systems biology approach that integrates molecular data, biological properties of the tumors, medical images, and clinical features of the patients. In this study, a comprehensive multi-omics methodology was employed to examine a distinctive collection of patient dataset containing rapid autopsy tumor and normal tissue samples as well as longitudinal imaging with a focus on pancreatic cancer. By performing a whole exome sequencing analysis on tumor and normal tissues to identify somatic gene variants and a radiomic feature analysis to tumor CT images, the genome-wide association approach established a connection between pancreatic cancer driver genes and relevant radiomic features, enabling a thorough and quantitative assessment of the heterogeneity of pancreatic tumors. The significant association between sets of genes and radiomic features revealed the involvement of genes in shaping tumor morphological heterogeneity. Some results of the association established a connection between the molecular level mechanism and their outcomes at the level of tumor structural heterogeneity. Because tumor structure and tumor structural heterogeneity are related to the patients’ overall survival, patients who had pancreatic cancer driver gene mutations with an association to a certain radiomic feature have been observed to experience worse survival rates than cases without these somatic mutations. Furthermore, the association analysis has revealed potential gene mutations and radiomic feature candidates that warrant further investigation in future research endeavors.

Fluorescence Lifetime Imaging of Lipid Heterogeneity in the Inner Mitochondrial Membrane with a Super‐photostable Environment‐Sensitive Probe

AbstractThe inner mitochondrial membrane (IMM) undergoes dynamic morphological changes, which are crucial for the maintenance of mitochondrial functions as well as cell survival. As the dynamics of the membrane are governed by its lipid components, a fluorescent probe that can sense spatiotemporal alterations in the lipid properties of the IMM over long periods of time is required to understand mitochondrial physiological functions in detail. Herein, we report a red‐emissive IMM‐labeling reagent with excellent photostability and sensitivity to its environment, which enables the visualization of the IMM ultrastructure using super‐resolution microscopy as well as of the lipid heterogeneity based on the fluorescence lifetime at the single mitochondrion level. Combining the probe and fluorescence lifetime imaging microscopy (FLIM) showed that peroxidation of unsaturated lipids in the IMM by reactive oxygen species caused an increase in the membrane order, which took place prior to mitochondrial swelling.

Fluorescence Lifetime Imaging of Lipid Heterogeneity in the Inner Mitochondrial Membrane with a Super-photostable Environment-Sensitive Probe.

The inner mitochondrial membrane (IMM) undergoes dynamic morphological changes, which are crucial for the maintenance of mitochondrial functions as well as cell survival. As the dynamics of the membrane are governed by its lipid components, a fluorescent probe that can sense spatiotemporal alterations in the lipid properties of the IMM over long periods of time is required to understand mitochondrial physiological functions in detail. Herein, we report a red-emissive IMM-labeling reagent with excellent photostability and sensitivity to its environment, which enables the visualization of the IMM ultrastructure using super-resolution microscopy as well as of the lipid heterogeneity based on the fluorescence lifetime at the single mitochondrion level. Combining the probe and fluorescence lifetime imaging microscopy (FLIM) showed that peroxidation of unsaturated lipids in the IMM by reactive oxygen species caused an increase in the membrane order, which took place prior to mitochondrial swelling.

BarlowTwins-CXR: enhancing chest X-ray abnormality localization in heterogeneous data with cross-domain self-supervised learning.

Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, particularly in detecting abnormalities, by developing a self-supervised learning strategy called "BarlwoTwins-CXR". We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation. Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples. BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions.

An open flame and smoke detection dataset for deep learning in remote sensing based fire detection

ABSTRACT The early warning of fires is pivotal for preventing substantial economic losses and ecological damage. However, the enhancement of fire model generalization performance still faces challenges due to limitations in existing fire datasets, such as image quantity and heterogeneity. Taking the advantage of rapid advancements in remote sensing technology and artificial intelligence, we introduce the Flame And Smoke Detection Dataset (FASDD), a pioneering collection comprising over 120,000 heterogeneous images covering various fire scenarios, aiming to promote the evolution of fire detection models. FASDD serves as a challenging benchmark for object detection tasks and features three sub-datasets: FASDD_CV, FASDD_UAV, and FASDD_RS. These sub-datasets comprise cross-domain images from ground-based, airborne, and spaceborne sensors, respectively. Extensive experiments using advanced Swin Transformer models demonstrate satisfactory fire detection performance, with mAP scores of 84.9%, 89.7%, and 74.0% on the respective sub-datasets. Notably, the application case in wildfire localization highlights the proficiency of FASDD_RS models for monitoring and tracking forest fires. Trained on FASDD_RS, FASDD_UAV, and FASDD_CV, deep learning models can be individually deployed on edge devices including satellites, drones, and terrestrial sensors, thus empowering collaborative fire warning within the space-air-ground integrated observation network. Additionally, a standardized procedure for data preparation, data procedure, and quality assurance is established, providing off-the-shelf annotations with four common configurations to facilitate machine learning model training. FASDD stands as a pivotal benchmark, providing valuable resources for training and evaluating deep learning fire detection models, especially Large Vision Models (LVM). It holds the potential to accelerate research progress in urban firefighting or forest fire detection, providing vital security measures for early fire warning and emergency response tasks.

Harmonizing three-dimensional MRI using pseudo-warping field guided GAN

In pursuit of cultivating automated models for magnetic resonance imaging (MRI) to aid in diagnostics, an escalating demand for extensive, multisite, and heterogeneous brain imaging datasets has emerged. This potentially introduces biased outcomes when directly applied for subsequent analysis. Researchers have endeavored to address this issue by pursuing the harmonization of MRIs. However, most existing image-based harmonization methods for MRI are tailored for 2D slices, which may introduce inter-slice variations when they are combined into a 3D volume. In this study, we aim to resolve inconsistencies between slices by introducing a pseudo-warping field. This field is created randomly and utilized to transform a slice into an artificially warped subsequent slice. The objective of this pseudo-warping field is to ensure that generators can consistently harmonize adjacent slices to another domain, without being affected by the varying content present in different slices. Furthermore, we construct unsupervised spatial and recycle loss to enhance the spatial accuracy and slice-wise consistency across the 3D images. The results demonstrate that our model effectively mitigates inter-slice variations and successfully preserves the anatomical details of the images during the harmonization process. Compared to generative harmonization models that employ 3D operators, our model exhibits greater computational efficiency and flexibility.

18F]AlF-NOTA-PCP2: a novel PET/CT tracer for enhanced PD-L1 heterogeneity imaging and comparative analysis with [18F]AlF-NOTA-WL12 in glioblastoma xenografts.

The unsatisfactory efficacy of PD-L1 antibodies in glioblastoma (GBM) is largely due to the temporal and spatial heterogeneity of PD-L1 expression. Molecular imaging can enhance understanding of the tumor immune microenvironment and guide immunotherapy. However, highly sensitive imaging agents capable of effectively visualizing PD-L1 heterogeneity are limited. This study introduces a novel PET tracer, offering improved imaging of PD-L1 heterogeneity in GBM xenografts, with a comparative analysis to [18F]AlF-NOTA-WL12. [18F]AlF-NOTA-PCP2 was synthesized with high purity and its affinity for PD-L1 was characterized using surface plasmon resonance (SPR) and cell binding assays. Its specificity for PD-L1 was evaluated both in vitro using various cell lines and in vivo with GBM xenograft models in NOD/SCID mice. PET/CT imaging was conducted to evaluate the tracer's biodistribution, pharmacokinetics, and ability to quantify tumoral spatial heterogeneity of PD-L1 expression. A focused comparative analysis between [18F]AlF-NOTA-PCP2 and [18F]AlF-NOTA-WL12 was conducted, examining binding affinity, biodistribution, pharmacokinetics, and imaging effectiveness in GBM xenografts. Additionally, human radiation dosimetry estimates compared the safety profiles of both tracers. [18F]AlF-NOTA-PCP2 demonstrated high radiochemical purity (> 95%) and a strong affinity for PD-L1, comparable to [18F]AlF-NOTA-WL12. In vitro and in vivo studies confirmed its specificity for PD-L1, with increased uptake in PD-L1 expressing cells and tumors. Toxicological profiles indicated no significant abnormalities in serum biochemical indicators or major organ tissues. MicroPET/CT imaging showed [18F]AlF-NOTA-PCP2's effectiveness in visualizing PD-L1 expression levels and spatial heterogeneity in GBM xenografts. Comparative studies revealed [18F]AlF-NOTA-PCP2's improved pharmacokinetic properties, including higher tumor-to-blood ratios and lower nonspecific liver uptake, as well as reduced radiation exposure compared to [18F]AlF-NOTA-WL12. [18F]AlF-NOTA-PCP2 distinguishes itself as an exceptionally sensitive PET/CT tracer, adept at non-invasively and accurately quantifying PD-L1 expression and its spatial heterogeneity in tumors, especially in GBM. Its favorable pharmacokinetic properties, safety profile, and high affinity for PD-L1 highlight its potential for enhancing the precision of cancer immunotherapy and guiding individualized treatment strategies. While promising, its clinical translation, especially in brain imaging, necessitates further validation in clinical trials.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor.

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

Fourier Finite Difference Migration Based Heterogeneous Photoacoustic Imaging in Irregular Layered Media

Fourier Finite Difference Migration Based Heterogeneous Photoacoustic Imaging in Irregular Layered Media

Gradient Weakly Sensitive Multi-Source Sensor Image Registration Method

Aiming at the nonlinear radiometric differences between multi-source sensor images and coherent spot noise and other factors that lead to alignment difficulties, the registration method of gradient weakly sensitive multi-source sensor images is proposed, which does not need to extract the image gradient in the whole process and has rotational invariance. In the feature point detection stage, the maximum moment map is obtained by using the phase consistency transform to replace the gradient edge map for chunked Harris feature point detection, thus increasing the number of repeated feature points in the heterogeneous image. To have rotational invariance of the subsequent descriptors, a method to determine the main phase angle is proposed. The phase angle of the region near the feature point is counted, and the parabolic interpolation method is used to estimate the more accurate main phase angle under the determined interval. In the feature description stage, the Log-Gabor convolution sequence is used to construct the index map with the maximum phase amplitude, the heterogeneous image is converted to an isomorphic image, and the isomorphic image of the region around the feature point is rotated by using the main phase angle, which is in turn used to construct the feature vector with the feature point as the center by the quadratic interpolation method. In the feature matching stage, feature matching is performed by using the sum of squares of Euclidean distances as a similarity metric. Finally, after qualitative and quantitative experiments of six groups of five pairs of different multi-source sensor image alignment correct matching rates, root mean square errors, and the number of correctly matched points statistics, this algorithm is verified to have the advantage of robust accuracy compared with the current algorithms.

Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition

Illumination variation has been a long-term challenge in real-world facial expression recognition (FER). Under uncontrolled or non-visible light conditions, near-infrared (NIR) can provide a simple and alternative solution to obtain high-quality images and supplement the geometric and texture details that are missing in the visible (VIS) domain. Due to the lack of large-scale NIR facial expression datasets, directly extending VIS FER methods to the NIR spectrum may be ineffective. Additionally, previous heterogeneous image synthesis methods are restricted by low controllability without prior task knowledge. To tackle these issues, we present the first approach, called for NIR-FER Stochastic Differential Equations (NFER-SDE), that transforms face expression appearance between heterogeneous modalities to the overfitting problem on small-scale NIR data. NFER-SDE can take the whole VIS source image as input and, together with domain-specific knowledge, guide the preservation of modality-invariant information in the high-frequency content of the image. Extensive experiments and ablation studies show that NFER-SDE significantly improves the performance of NIR FER and achieves state-of-the-art results on the only two available NIR FER datasets, Oulu-CASIA and Large-HFE.

AI-Based Measurement of Lumbar Spinal Stenosis on MRI: External Evaluation of a Fully Automated Model.

The aim of this study was to clinically validate a fully automated AI model for magnetic resonance imaging (MRI)-based quantifications of lumbar spinal canal stenosis. This retrospective study included lumbar spine MRI of 100 consecutive clinical patients (56 ± 17 years; 43 females, 57 males) performed on clinical 1.5 (51 examinations) and 3 T MRI scanners (49 examinations) with heterogeneous clinical imaging protocols. The AI model performed segmentations of the thecal sac on axial T2-weighted sequences. Based on these segmentations, the anteroposterior (AP) and mediolateral (ML) distance, and the area of the thecal sac were measured in a fully automated manner. For comparison, 2 fellowship-trained musculoskeletal radiologists performed the same segmentations and measurements independently. Statistics included 1-sample t tests, the intraclass correlation coefficient (ICC), Bland-Altman plots, and Dice coefficients. A P value of <0.05 was considered statistically significant. The average measurements of the AI model, reader 1, and reader 2 were 194 ± 72 mm 2 , 181 ± 71 mm 2 , and 179 ± 70 mm 2 for thecal sac area, 13 ± 3.3 mm, 12.6 ± 3.3 mm, and 12.6 ± 3.2 mm for AP distance, and 19.5 ± 3.9 mm, 20 ± 4.3 mm, and 19.4 ± 4 mm for ML distance, respectively. Significant differences existed for all pairwise comparisons, besides reader 1 versus AI model for the ML distance and reader 1 versus reader 2 for the AP distance ( P = 0.1 and P = 0.21, respectively). The pairwise mean absolute errors among reader 1, reader 2, and the AI model ranged from 0.59 mm and 0.75 mm for the AP distance, from 1.16 mm to 1.37 mm for the ML distance, and from 7.9 mm 2 to 15.54 mm 2 for the thecal sac area. Pairwise ICCs among reader 1, reader 2, and the AI model ranged from 0.91 and 0.94 for the AP distance and from 0.86 to 0.9 for the ML distance without significant differences. For the thecal sac area, the pairwise ICC between both readers and the AI model of 0.97 each was slightly, but significantly lower than the ICC between reader 1 and reader 2 of 0.99. Similarly, the Dice coefficient and Hausdorff distance between both readers and the AI model were significantly lower than the values between reader 1 and reader 2, overall ranging from 0.93 to 0.95 for the Dice coefficients and 1.1 to 1.44 for the Hausdorff distances. The investigated AI model is reliable for assessing the AP and the ML thecal sac diameters with human level accuracies. The small differences for measurement and segmentation of the thecal sac area between the AI model and the radiologists are likely within a clinically acceptable range.

Salt-and-pepper Noise Reduction for Medical Images Based on Image Fusion.

During the collection process, the prostate capsule is prone to introduce salt and pepper noise due to gastrointestinal peristalsis, which will affect the precision of subsequent object detection. A cascade optimization scheme for image denoising based on image fusion was proposed to improve the peak signal-to-noise ratio(PSNR) and contour protection performance of heterogeneous medical images after image denoising. Anisotropic diffusion fusion (ADF) was used to decompose the images denoised by adaptive median filter, non-local adaptive median filter and artificial neural network to generate the base layer and detail layer, which were fused by weighted average and Karhunen-Loeve Transform respectively. Finally, the image was reconstructed by linear superposition. Compared with the traditional denoising method, the image denoised by this method has a higher PSNR while maintaining the image edge contour. Using the denoised dataset for object detection, the detection precision of the obtained model is higher.

The role of susceptibility-weighted imaging & contrast-enhanced MRI in the diagnosis of primary CNS vasculitis: a large case series.

Primary CNS Vasculitis (PCNSV) is a rare, diverse, and polymorphic CNS blood vessel inflammatory condition. Due to its rarity, clinical variability, heterogeneous imaging results, and lack of definitive laboratory markers, PCNSV diagnosis is challenging. This retrospective cohort analysis identified patients with histological diagnosis of PCNSV. Demographic data, clinical presentation, neuroimaging studies, and histopathologic findings were recorded. We enrolled 56 patients with a positive biopsy of CNS vasculitis. Most patients had cerebral hemisphere or brainstem symptoms. Most brain MRI lesions were bilateral, diffuse discrete to confluent white matter lesions. Frontal lobe lesions predominated, followed by inferior cerebellar lesions. Susceptibility-weighted imaging (SWI) hemorrhages in 96.4% (54/56) of patients, either solitary microhemorrhages or a combination of micro and macrohemorrhages. Contrast-enhanced T1-WIs revealed parenchymal enhancement in 96.3% (52/54 patients). The most prevalent pattern of enhancement observed was dot-linear (87%), followed by nodular (61.1%), perivascular (25.9%), and patchy (16.7%). Venulitis was found in 19 of 20 individuals in cerebral DSA. Hemorrhages in SWI and dot-linear enhancement pattern should be incorporated as MINOR diagnostic criteria to diagnose PCNSV accurately within an appropriate clinical context. Microhemorrhages in SWI and venulitis in DSA, should be regarded as a potential marker for PCNSV.

Edge-Bound Change Detection in Multisource Remote Sensing Images

Detecting changes in multisource heterogeneous images is a great challenge for unsupervised change detection methods. Image-translation-based methods, which transform two images to be homogeneous for comparison, have become a mainstream approach. However, most of them primarily rely on information from unchanged regions, resulting in networks that cannot fully capture the connection between two heterogeneous representations. Moreover, the lack of a priori information and sufficient training data makes the training vulnerable to the interference of changed pixels. In this paper, we propose an edge-oriented generative adversarial network (EO-GAN) for change detection that indirectly translates images using edge information, which serves as a core and stable link between heterogeneous representations. The EO-GAN is composed of an edge extraction network and a reconstructive network. During the training process, we ensure that the edges extracted from heterogeneous images are as similar as possible through supplemented data based on superpixel segmentation. Experimental results on both heterogeneous and homogeneous datasets demonstrate the effectiveness of our proposed method.