Hasil untuk "Pediatrics"

Salma J. Ahmed, Emad A. Mohammed, Azam Asilian Bidgoli

Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand dataset shift, or intervene in a principled manner. We introduce Med-SegLens, a model-diffing framework that decomposes segmentation model activations into interpretable latent features using sparse autoencoders trained on SegFormer and U-Net. Through cross-architecture and cross-dataset latent alignment across healthy, adult, pediatric, and sub-Saharan African glioma cohorts, we identify a stable backbone of shared representations, while dataset shift is driven by differential reliance on population-specific latents. We show that these latents act as causal bottlenecks for segmentation failures, and that targeted latent-level interventions can correct errors and improve cross-dataset adaption without retraining, recovering performance in 70% of failure cases and improving Dice score from 39.4% to 74.2%. Our results demonstrate that latent-level model diffing provides a practical and mechanistic tool for diagnosing failures and mitigating dataset shift in segmentation models.

Sathish Krishna Anumula, Vetrivelan Tamilmani, Aniruddha Arjun Singh et al.

Pneumonia has been one of the major causes of morbidities and mortality in the world and the prevalence of this disease is disproportionately high among the pediatric and elderly populations especially in resources trained areas Fast and precise diagnosis is a prerequisite for successful clinical intervention but due to inter observer variation fatigue among experts and a shortage of qualified radiologists traditional approaches that rely on manual interpretation of chest radiographs are frequently constrained To address these problems this paper introduces a unified automated diagnostic model using a custom Convolutional Neural Network CNN that can recognize pneumonia in chest Xray images with high precision and at minimal computational expense In contrast like other generic transfer learning based models which often possess redundant parameters the offered architecture uses a tailor made depth wise separable convolutional design which is optimized towards textural characteristics of grayscale medical images Contrast Limited Adaptive Histogram Equalization CLAHE and geometric augmentation are two significant preprocessing techniques used to ensure that the system does not experience class imbalance and is more likely to generalize The system is tested using a dataset of 5863 anterior posterior chest Xrays.

Alif Munim, Adibvafa Fallahpour, Teodora Szasz et al.

Foundation models for echocardiography often struggle to disentangle anatomical signal from the stochastic speckle and acquisition artifacts inherent to ultrasound. We present EchoJEPA, a foundation model trained on 18 million echocardiograms across 300K patients, representing the largest pretraining corpus for this modality to date. By leveraging a latent predictive objective, EchoJEPA learns robust anatomical representations that ignore speckle noise. We validate this using a novel multi-view probing framework with frozen backbones, where EchoJEPA outperforms leading baselines by approximately 20% in left ventricular ejection fraction (LVEF) estimation and 17% in right ventricular systolic pressure (RVSP) estimation. The model also exhibits remarkable sample efficiency, reaching 79% view classification accuracy with only 1% of labeled data versus 42% for the best baseline trained on 100%. Crucially, EchoJEPA demonstrates superior generalization, degrading by only 2% under physics-informed acoustic perturbations compared to 17% for competitors. Most remarkably, its zero-shot performance on pediatric patients surpasses fully fine-tuned baselines, establishing latent prediction as a superior paradigm for robust, generalizable medical AI.

Yan Hu, Mingdao Gong, Zhongxi Qiu et al.

Retinal image registration is vital for diagnostic therapeutic applications within the field of ophthalmology. Existing public datasets, focusing on adult retinal pathologies with high-quality images, have limited number of image pairs and neglect clinical challenges. To address this gap, we introduce COph100, a novel and challenging dataset known as the Comprehensive Ophthalmology Retinal Image Registration dataset for infants with a wide range of image quality issues constituting the public "RIDIRP" database. COph100 consists of 100 eyes, each with 2 to 9 examination sessions, amounting to a total of 491 image pairs carefully selected from the publicly available dataset. We manually labeled the corresponding ground truth image points and provided automatic vessel segmentation masks for each image. We have assessed COph100 in terms of image quality and registration outcomes using state-of-the-art algorithms. This resource enables a robust comparison of retinal registration methodologies and aids in the analysis of disease progression in infants, thereby deepening our understanding of pediatric ophthalmic conditions.

Omer Abid, Gholamreza Rafiee

Medulloblastoma is a malignant pediatric brain cancer, and the discovery of molecular subgroups is enabling personalized treatment strategies. In 2019, a consensus identified eight novel subtypes within Groups 3 and 4, each displaying heterogeneous characteristics. Classifiers are essential for translating these findings into clinical practice by supporting clinical trials, personalized therapy development and application, and patient monitoring. This study presents a DNA methylation-based, cross-platform machine learning classifier capable of distinguishing these subtypes on both HM450 and EPIC methylation array samples. Across two independent test sets, the model achieved weighted F1 = 0.95 and balanced accuracy = 0.957, consistent across platforms. As the first cross-platform solution, it provides backward compatibility while extending applicability to a newer platform, also enhancing accessibility. It also has the potential to become the first publicly available classifier for these subtypes once deployed through a web application, as planned in the future. This work overall takes steps in the direction of advancing precision medicine and improving clinical outcomes for patients within the majority prevalence medulloblastoma subgroups, groups 3 and 4.

Marco Aruta, Ciro Listone, Giuseppe Murano et al.

Leukemia diagnosis and monitoring rely increasingly on high-throughput image data, yet conventional clustering methods lack the flexibility to accommodate evolving cellular patterns and quantify uncertainty in real time. We introduce Adaptive and Dynamic Neuro-Fuzzy Clustering, a novel streaming-capable framework that combines Convolutional Neural Network-based feature extraction with an online fuzzy clustering engine. ADNF initializes soft partitions via Fuzzy C-Means, then continuously updates micro-cluster centers, densities, and fuzziness parameters using a Fuzzy Temporal Index (FTI) that measures entropy evolution. A topology refinement stage performs density-weighted merging and entropy-guided splitting to guard against over- and under-segmentation. On the C-NMC leukemia microscopy dataset, our tool achieves a silhouette score of 0.51, demonstrating superior cohesion and separation over static baselines. The method's adaptive uncertainty modeling and label-free operation hold immediate potential for integration within the INFANT pediatric oncology network, enabling scalable, up-to-date support for personalized leukemia management.

Misaal Khan, Mayank Vatsa, Kuldeep Singh et al.

Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener, a retrieval-augmented, multi-pose graph attention network that combines CLIP-based visual embeddings, class-boosted knowledge retrieval, and context awareness to enable robust malnutrition detection and anthropometric prediction from children's images, simultaneously addressing generalizability and class imbalance. In a clinical study, doctors rated it 4.3/5 for accuracy and 4.6/5 for efficiency, confirming its deployment readiness in low-resource settings. Trained and tested on 2,141 children from AnthroVision and additionally evaluated on diverse cross-continent populations, including ARAN and an in-house collected CampusPose dataset, it achieves 0.79 recall, 0.82 AUC, and significantly lower anthropometric RMSEs, demonstrating reliable measurement in unconstrained pediatric settings. Cross-dataset results show up to 25% recall gain and up to 3.5 cm RMSE reduction using demographically matched knowledge bases. NutriScreener offers a scalable and accurate solution for early malnutrition detection in low-resource environments.

Md Abdul Baset Sarker, Art Nguyen, Sigmond Kukla et al.

This paper introduces a novel AI vision-enabled pediatric prosthetic hand designed to assist children aged 10-12 with upper limb disabilities. The prosthesis features an anthropomorphic appearance, multi-articulating functionality, and a lightweight design that mimics a natural hand, making it both accessible and affordable for low-income families. Using 3D printing technology and integrating advanced machine vision, sensing, and embedded computing, the prosthetic hand offers a low-cost, customizable solution that addresses the limitations of current myoelectric prostheses. A micro camera is interfaced with a low-power FPGA for real-time object detection and assists with precise grasping. The onboard DL-based object detection and grasp classification models achieved accuracies of 96% and 100% respectively. In the force prediction, the mean absolute error was found to be 0.018. The features of the proposed prosthetic hand can thus be summarized as: a) a wrist-mounted micro camera for artificial sensing, enabling a wide range of hand-based tasks; b) real-time object detection and distance estimation for precise grasping; and c) ultra-low-power operation that delivers high performance within constrained power and resource limits.

Duncan Stothers, Ben Stothers, Emily Schaeffer et al.

We study an ultrasound-first, radiation-preserving policy for developmental dysplasia of the hip (DDH) that requests a radiograph only when needed. We (i) pretrain modality-specific encoders (ResNet-18) with SimSiam on a large unlabelled registry (37186 ultrasound; 19546 radiographs), (ii) freeze the backbones and fit small, measurement-faithful heads on DDH-relevant landmarks and measurements, (iii) calibrate a one-sided conformal deferral rule on ultrasound predictions that provides finite sample marginal coverage guarantees under exchangeability, using a held-out calibration set. Ultrasound heads predict Graf alpha, beta, and femoral head coverage; X-ray heads predict acetabular index (AI), center-edge (CE) angle and IHDI grade. On our held out labeled evaluation set, ultrasound measurement error is modest (e.g., alpha MAE ~= 9.7 degrees, coverage MAE ~= 14.0%), while radiographic probes achieve AI and CE MAEs of ~= 7.6 degrees and ~= 8.9 degrees, respectively. The calibrated US-only policy is explored across rule families (alpha-only; alpha OR coverage; alpha AND coverage), conformal miscoverage levels, and per-utility trade-offs using decision-curve analysis. Conservative settings yield high coverage with near-zero US-only rates; permissive settings (e.g., alpha OR coverage at larger deltas) achieve non-zero US-only throughput with expected coverage tradeoffs. The result is a simple, reproducible pipeline that turns limited labels into interpretable measurements and tunable selective imaging curves suitable for clinical handoff and future external validation.

Woretaw Sisay Zewdu, Mulugeta Molla Zeleke, Yared Andargie Ferede et al.

IntroductionDespite the fact that antiretroviral therapy (ART) has reduced HIV/AIDS-related morbidity and mortality, pediatrics treatment failure remains a global concern. As a result, this study set out prudently to determine the prevalence of virologic failure and its predictors among children and adolescents on a Dolutegravir (DTG)-based antiretroviral regimen.MethodsA hospital-based retrospective cross-sectional study was conducted on children and adolescents on ART at Debre Tabor Comprehensive Specialized Hospital in Northwest Ethiopia from February-2017 to September-2023. Study participants were selected purposively. Data was collected using a semi-structured questionnaire and a data abstraction tool. Bivariate and multivariate logistic regression analyses were fitted to determine the linked factors. A p-value less than 0.05 was deemed to indicate a statistically significant association.ResultsAmong the 359 children and adolescents included in this study, 38 (10.58%) had developed virological failure. The odds of virological failure among children and adolescents were found to be increased by the age of the child <10 years (AOR = 4.41; 95% CI: 2.60–7.47), the care taker being a guardian or neighbor of patient (AOR = 2.03; 95% CI: 1.15–4.73), both parents passing away (AOR = 1.29; 95% CI: 0.12–2.68), CD4 counts ≤200 cells/µL (AOR = 4.3; 95% CI: 1.32–5.9), being infected with OIs (AOR = 2.03; 95% CI: 1.38–3.55), poor adherence status (AOR = 1.37: 95% CI: 1.12–3.11), adverse drug reaction (AOR = 1.75: 95% CI: 1.02–4.97), and anemic (AOR = 1.70: 95% CI: 1.03–5.15.04).ConclusionDespite potent DTG-based ARTs being introduced, virologic failure remains a concern in the study area. Special consideration should be directed towards children under the age of 10 years who are in the care of a guardian or neighbors, have lost both parents, are infected with opportunistic infections, have a poor adherence status, are experiencing adverse drug reactions, and anemic.

Chengxian Yang, Kewei Li, Bo Xiang

BackgroundAlthough gastrointestinal stromal tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract, they are rare in children, particularly those located on the duodenum. Here, we present an interesting pediatric case involving a 13-year-old boy who experienced gastrointestinal hemorrhage, he was misdiagnosed with a tumor located on the major duodenal papilla and was ultimately confirmed to be duodenal GISTs.Case presentationA 13-year-old boy presented to a local hospital with fatigue and melena. Gastroscopy suggested a tumor located at the major duodenal papilla, and the patient was referred to our hospital for surgical evaluation. Upon further investigation and surgical exploration, the diagnosis was revised to a duodenal GIST with surface ulceration and active bleeding. The ulcer's morphology and location mimicked the appearance of the major duodenal papilla, leading to the initial diagnostic error.ConclusionsDuodenal GISTs in pediatric patients often present asymptomatically but can manifest with severe complications such as fatal gastrointestinal bleeding. The tumor's morphology and location can obscure the major papilla, complicating preoperative diagnosis and influencing surgical decision-making. Comprehensive preoperative evaluation and careful intraoperative exploration are critical for accurate diagnosis and optimal management.

Sunyoung Jung, Yoonseok Choi, Mohammed A. Al-masni et al.

Motion artifacts caused by prolonged acquisition time are a significant challenge in Magnetic Resonance Imaging (MRI), hindering accurate tissue segmentation. These artifacts appear as blurred images that mimic tissue-like appearances, making segmentation difficult. This study proposes a novel deep learning framework that demonstrates superior performance in both motion correction and robust brain tissue segmentation in the presence of artifacts. The core concept lies in a complementary process: a disentanglement learning network progressively removes artifacts, leading to cleaner images and consequently, more accurate segmentation by a jointly trained motion estimation and segmentation network. This network generates three outputs: a motioncorrected image, a motion deformation map that identifies artifact-affected regions, and a brain tissue segmentation mask. This deformation serves as a guidance mechanism for the disentanglement process, aiding the model in recovering lost information or removing artificial structures introduced by the artifacts. Extensive in-vivo experiments on pediatric motion data demonstrate that our proposed framework outperforms state-of-the-art methods in segmenting motion-corrupted MRI scans.

Saige Rutherford, Thomas Wolfers, Charlotte Fraza et al.

Reference classes in healthcare establish healthy norms, such as pediatric growth charts of height and weight, and are used to chart deviations from these norms which represent potential clinical risk. How the demographics of the reference class influence clinical interpretation of deviations is unknown. Using normative modeling, a method for building reference classes, we evaluate the fairness (racial bias) in reference models of structural brain images that are widely used in psychiatry and neurology. We test whether including race in the model creates fairer models. We predict self-reported race using the deviation scores from three different reference class normative models, to better understand bias in an integrated, multivariate sense. Across all of these tasks, we uncover racial disparities that are not easily addressed with existing data or commonly used modeling techniques. Our work suggests that deviations from the norm could be due to demographic mismatch with the reference class, and assigning clinical meaning to these deviations should be done with caution. Our approach also suggests that acquiring more representative samples is an urgent research priority.

Dalila Failli, Maria Francesca Marino, Francesca Martella

In the context of network data, bipartite networks are of particular interest, as they provide a useful description of systems representing relationships between sending and receiving nodes. In this framework, we extend the Mixture of Latent Trait Analyzers (MLTA) to perform a joint clustering of sending and receiving nodes, as in the biclustering framework. In detail, sending nodes are partitioned into clusters (called components) via a finite mixture of latent trait models. In each component, receiving nodes are partitioned into clusters (called segments) by adopting a flexible and parsimonious specification of the linear predictor. Dependence between receiving nodes is modeled via a multidimensional latent trait, as in the original MLTA specification. The proposal also allows for the inclusion of concomitant variables in the latent layer of the model, with the aim of understanding how they influence component formation. To estimate model parameters, an EM-type algorithm based on a Gauss-Hermite approximation of intractable integrals is proposed. A simulation study is conducted to test the performance of the model in terms of clustering and parameters' recovery. The proposed model is applied to a bipartite network on pediatric patients possibly affected by appendicitis with the objective of identifying groups of patients (sending nodes) being similar with respect to subsets of clinical conditions (receiving nodes).

Charles W. Stube, Alexander S. Ljungberg, Jason A. Borton et al.

Introduction: There are several options for receiving acute care besides emergency departments (ED), such as primary care physician (PCP) offices, urgent care centers (UCC), and telehealth services. It is unknown whether these alternative modes of care have decreased the number of ED visits for patients or whether they are considered before visiting the ED. A comprehensive study considering all potential methods of care is needed to address the evolving landscape of healthcare. Our goal was to identify any factors or barriers that may have influenced a patient’s choice to visit the ED as opposed to a UCC, PCP, another local ED, or use telehealth services. Methods: We surveyed ED patients between three hospital sites in the greater Buffalo, NY, area. The survey consisted of questions regarding the patients’ reasons and rationale for choosing the ED over the alternative care options. The study also involved a health record review of the patients’ diagnoses, tests/procedures, consults, and final disposition after completion of the survey. Results: Of the 590 patients consented and surveyed, 152 (25.7%) considered seeking care at a UCC, 18 (3.1%) considered telehealth services, and 146 (24.7%) attempted to contact their PCP. On the recommendation of their PCP, patients presented to the ED 110 (20.7%) times and on the recommendation of the clinician at the UCC 54 (9.2%) times. Patients’ perceived seriousness of their condition was the most common reason for their selected mode of transport to the ED and reason for choosing the ED as opposed to alternative care sites (PCP, UCC, telehealth). Based on criteria for an avoidable ED visit, 83 (14.1%) ED patients met these criteria. Conclusion: Individuals prioritize the perceived severity of their condition when deciding where to seek emergency care. While some considered alternatives (PCP, UCC, telehealth services), uncertainties about their condition and recommendations from other clinicians led many to opt for ED care. Our findings suggest a potential gap in understanding the severity of symptoms and determining the most suitable place to seek medical care for these particular conditions.

Kelly Counts, Sue Lasiter

Introduction: Healthcare advances have contributed to patients living longer with chronic illnesses and diseases with uncertain trajectories impacting quality of life (QOL). Palliative care (PC) is no longer only for dying oncology patients as many healthcare practitioners have adopted the PC concept in diverse care settings and the timing of PC implementation remains ambiguous. There is a need to develop an operational definition of early palliative care (EPC) by clarifying the phenomenon and bridging concepts with empirical data to develop and test possible interventions before integrating EPC into emergency care (EC). Methods: Norris’ concept clarification method was used as the philosophical framework to define, analyze, and clarify EPC. An electronic search of literature from 2000-2024, using CINAHL, PubMed, APA PsychINFO, and Psychology and Behavioral Sciences Collection databases and search terms "early palliative care" AND "emergency care" NOT "animals", and NOT "pediatrics" were screened for eligible articles. Results: Of the 826 articles identified; 22 articles were retained for review. Attributes included timing, palliative, and EC; antecedents included symptom burden, access to care, and cognitive awareness; consequences included QOL and resource utilization; an empirical referent used to screen patients is the highly accurate surprise question "Would I be surprised if this patient died within a year?" Conclusion: Clarifying the concept of EPC leading to an operational definition will advance the development of interventions that support the implementation of EPC in ED clinical practice.

Harris Papadopoulos, George Anastassopoulos

Vesicoureteral Reflux (VUR) is a pediatric disorder in which urine flows backwards from the bladder to the upper urinary tract. Its detection is of great importance as it increases the risk of a Urinary Tract Infection, which can then lead to a kidney infection since bacteria may have direct access to the kidneys. Unfortunately the detection of VUR requires a rather painful medical examination, called voiding cysteourethrogram (VCUG), that exposes the child to radiation. In an effort to avoid the exposure to radiation required by VCUG some recent studies examined the use of machine learning techniques for the detection of VUR based on data that can be obtained without exposing the child to radiation. This work takes one step further by proposing an approach that provides lower and upper bounds for the conditional probability of a given child having VUR. The important property of these bounds is that they are guaranteed (up to statistical fluctuations) to contain well-calibrated probabilities with the only requirement that observations are independent and identically distributed (i.i.d.). Therefore they are much more informative and reliable than the plain yes/no answers provided by other techniques.

Robin Klein, Erin D. Snyder, Jennifer Koch et al.

Abstract Introduction Evidence suggests gender disparities in medical education assessment, including differences in ratings of competency and narrative comments provided in resident performance assessments. This study explores how gender manifests within the content of qualitative assessments (i.e., narrative comments or performance feedback) of resident performance. Methods Qualitative content analysis was used to explore gender-based differences in narrative comments included in faculty assessments of resident performance during inpatient medicine rotations at six Internal Medicine residency programs, 2016–2017. A blinded, multi-analyst approach was employed to identify themes across comments. Patterns in themes with resident gender and post-graduate year (PGY) were explored, focusing on PGY2 and PGY3 when residents are serving in the team leader role. Results Data included 3,383 evaluations with narrative comments of 385 men (55.2%) and 313 women residents (44.8%). There were thematic differences in narrative comments received by men and women residents and how these themes manifested within comments changed with training time. Compared to men, comments about women had a persistent relationship-orientation and emphasized confidence over training including as interns and in PGY2 and PGY3, when serving as team leader. The relationship-orientation was characterized not only by the residents’ communal attributes but also their interpersonal and communication skills, including efforts supporting others and establishing the tone for the team. Comments about women residents often highlighted confidence, including recommendations around behaviors that convey confidence in decision-making and team leadership. Discussion There were gender-based thematic differences in qualitative assessments. Comments about women resident team leaders highlight relationship building skills and urge confidence and actions that convey confidence as team leader. Persistent attention to communal skills suggests gendered expectations for women resident team leaders and a lost opportunity for well-rounded feedback to the disadvantage of women residents. These findings may inform interventions to promote equitable assessment, such as providing feedback across the competencies.

A.O. Mezentsev, D.E. Petrenko, D.O. Demchenko

Передня мобілізація хребта є ефективним методом етапної корекції грудного ідіопатичного сколіозу з кутом Cobb 80-100º. Впровадження в клінічну практику сучасних транспедикулярних імплантатів та остеотомій заднього опірного комплексу зменшило частоту її використання, але збільшило кількість неврологічних ускладнень. Мета - порівняти результати використання передньої мобілізації в поєднанні із заднім коригувальним спондилодезом та тільки заднього коригувального спондилодезу в пацієнтів із ригідним грудним ідіопатичним сколіозом. Матеріали та методи. Проведено ретроспективний порівняльний аналіз результатів хірургічного лікування 167 хворих на грудний ідіопатичний сколіоз із кутом Cobb 80-100º. Пацієнтів поділено на дві групи: 1-ша група - 83 особи (середній вік - 13,7 року), яким виконували передню мобілізацію викривлення та задній коригувальний спондилодез, 2-га група - 84 особи (середній вік - 14,7 року), яким виконували задній коригувальний спондилодез та остеотомію Ponte на 3-5 рівнях. Результати. Середній показник кута Cobb грудного викривлення до хірургічного лікування у 1-й групі становив 87,1º (±1,96), у 2-й групі - 83,8º (±2,85); після хірургічного лікування - відповідно 32,2º (±2,24), або 63% корекції, і 44,2º (±3,22), або 47% корекції. Загальна середня тривалість хірургічних втручань у 1-й групі дорівнювала 410 хв (140 хв+270 хв), у 2-й групі - 320 хв. Інтраопераційна крововтрата складала відповідно 890 мл і 900 мл. Середній обʼєм гемотрансфузії становив відповідно 650 мл і 672 мл. Середній час перебування на стаціонарному лікуванні був відповідно 15,6 доби і 8,6 доби. Висновки. Порівняно із заднім коригувальним спондилодезом, застосування двоетапного лікування, яке включає в себе передню мобілізацію викривлення та задній коригувальний спондилолез за хірургічної корекції ригідних сколіотичних деформацій хребта, дає змогу збільшити інтраопераційну корекцію основного викривлення на 17%. Дослідження виконано відповідно до принципів Гельсінської декларації. Протокол дослідження ухвалено Локальним етичним комітетом усіх зазначених у роботі установ. На проведення досліджень отримано інформовану згоду пацієнтів. Автори заявляють про відсутність конфлікту інтересів.

Yu Fu, Shunjie Dong, Yi Liao et al.

18F-fluorodeoxyglucose (18F-FDG) Positron Emission Tomography (PET) imaging usually needs a full-dose radioactive tracer to obtain satisfactory diagnostic results, which raises concerns about the potential health risks of radiation exposure, especially for pediatric patients. Reconstructing the low-dose PET (L-PET) images to the high-quality full-dose PET (F-PET) ones is an effective way that both reduces the radiation exposure and remains diagnostic accuracy. In this paper, we propose a resource-efficient deep learning framework for L-PET reconstruction and analysis, referred to as transGAN-SDAM, to generate F-PET from corresponding L-PET, and quantify the standard uptake value ratios (SUVRs) of these generated F-PET at whole brain. The transGAN-SDAM consists of two modules: a transformer-encoded Generative Adversarial Network (transGAN) and a Spatial Deformable Aggregation Module (SDAM). The transGAN generates higher quality F-PET images, and then the SDAM integrates the spatial information of a sequence of generated F-PET slices to synthesize whole-brain F-PET images. Experimental results demonstrate the superiority and rationality of our approach.