Many recent approaches in representation learning implicitly assume that uncorrelated views of a data point are sufficient to learn meaningful representations for various downstream tasks. In this work, we challenge this assumption and demonstrate that meaningful structure in the latent space does not emerge naturally. Instead, it must be explicitly induced. We propose a method that aligns representations from different views of the data to align complementary information without inducing false positives. Our experiments show that our proposed self-supervised learning method, Consistent View Alignment, improves performance for downstream tasks, highlighting the critical role of structured view alignment in learning effective representations. Our method achieved first and second place in the MICCAI 2025 SSL3D challenge when using a Primus vision transformer and ResEnc convolutional neural network, respectively. The code and pretrained model weights are released at https://github.com/Tenbatsu24/LatentCampus.

Image registration is a fundamental task in medical image analysis. Deformations are often closely related to the morphological characteristics of tissues, making accurate feature extraction crucial. Recent weakly supervised methods improve registration by incorporating anatomical priors such as segmentation masks or landmarks, either as inputs or in the loss function. However, such weak labels are often not readily available, limiting their practical use. Motivated by the strong representation learning ability of visual foundation models, this paper introduces SAMIR, an efficient medical image registration framework that utilizes the Segment Anything Model (SAM) to enhance feature extraction. SAM is pretrained on large-scale natural image datasets and can learn robust, general-purpose visual representations. Rather than using raw input images, we design a task-specific adaptation pipeline using SAM's image encoder to extract structure-aware feature embeddings, enabling more accurate modeling of anatomical consistency and deformation patterns. We further design a lightweight 3D head to refine features within the embedding space, adapting to local deformations in medical images. Additionally, we introduce a Hierarchical Feature Consistency Loss to guide coarse-to-fine feature matching and improve anatomical alignment. Extensive experiments demonstrate that SAMIR significantly outperforms state-of-the-art methods on benchmark datasets for both intra-subject cardiac image registration and inter-subject abdomen CT image registration, achieving performance improvements of 2.68% on ACDC and 6.44% on the abdomen dataset. The source code will be publicly available on GitHub following the acceptance of this paper.

We developed a deep learning radiomics nomogram (DLRN) using CT scans to improve clinical decision-making and risk stratification for early recurrence of hepatocellular carcinoma (HCC) after transplantation, which typically has a poor prognosis. In this two-center study, 245 HCC patients who had contrast-enhanced CT before liver transplantation were split into a training set (n = 184) and a validation set (n = 61). We extracted radiomics and deep learning features from tumor and peritumor areas on preoperative CT images. The DLRN was created by combining these features with significant clinical variables using multivariate logistic regression. Its performance was validated against four traditional risk criteria to assess its additional value. The DLRN model showed strong predictive accuracy for early HCC recurrence post-transplant, with AUCs of 0.884 and 0.829 in training and validation groups. High DLRN scores significantly increased relapse risk by 16.370 times (95% CI: 7.100-31.690; p  < 0.001). Combining DLRN with Metro-Ticket 2.0 criteria yielded the best prediction (AUC: training/validation: 0.936/0.863). The CT-based DLRN offers a non-invasive method for predicting early recurrence following liver transplantation in patients with HCC. Furthermore, it provides substantial additional predictive value with traditional prognostic scoring systems. AI-driven predictive models utilizing preoperative CT imaging enable accurate identification of early HCC recurrence risk following liver transplantation, facilitating risk-stratified surveillance protocols and optimized post-transplant management. A CT-based DLRN for predicting early HCC recurrence post-transplant was developed. The DLRN predicted recurrence with high accuracy (AUC: 0.829) and 16.370-fold increased recurrence risk. Combining DLRN with Metro-Ticket 2.0 criteria achieved optimal prediction (AUC: 0.863).

The adoption of left ventricular global longitudinal strain (LVGLS) is still restricted by variability among various vendors and observers, despite advancements from tissue Doppler to speckle tracking imaging, machine learning, and, more recently, convolutional neural network (CNN)-based segmentation strain analysis. While CNNs have enabled fully automated strain measurement, they are inherently constrained by restricted receptive fields and a lack of temporal consistency. Transformer-based networks have emerged as a powerful alternative in medical imaging, offering enhanced global attention. Among these, the Video Swin Transformer (V-SwinT) architecture, with its 3D-shifted windows and locality inductive bias, is particularly well suited for ultrasound imaging, providing temporal consistency while optimizing computational efficiency. In this study, we propose the DTHR-SegStrain model based on a V-SwinT backbone. This model incorporates contour regression and utilizes an FCN-style multiscale feature fusion. As a result, it can generate accurate and temporally consistent left ventricle (LV) contours, allowing for direct calculation of myocardial strain without the need for conversion from segmentation to contours or any additional postprocessing. Compared to EchoNet-dynamic and Unity-GLS, DTHR-SegStrain showed greater efficiency, reliability, and validity in LVGLS measurements. Furthermore, the hybridization experiments assessed the interaction between segmentation models and strain algorithms, reinforcing that consistent segmentation contours over time can simplify strain calculations and decrease measurement variability. These findings emphasize the potential of V-SwinT-based frameworks to enhance the standardization and clinical applicability of LVGLS assessments.

In 2022, the WHO conditionally recommended the use of treatment decision algorithms (TDAs) for treatment decision-making in children <10 years with presumptive tuberculosis (TB), aiming to decrease the substantial case detection gap and improve treatment access in high TB-incidence settings. WHO also called for external validation of these TDAs. Within the Decide-TB project (PACT ID: PACTR202407866544155, 23 July 2024), we aim to generate an individual-participant dataset (IPD) from prospective TB diagnostic accuracy cohorts (RaPaed-TB, UMOYA and two cohorts from TB-Speed). Using the IPD, we aim to: (1) assess the diagnostic accuracy of published TDAs using a set of consensus case definitions produced by the National Institute of Health as reference standard (confirmed and unconfirmed vs unlikely TB); (2) evaluate the added value of novel tools (including biomarkers and artificial intelligence-interpreted radiology) in the existing TDAs; (3) generate an artificial population, modelling the target population of children eligible for WHO-endorsed TDAs presenting at primary and secondary healthcare levels and assess the diagnostic accuracy of published TDAs and (4) identify clinical predictors of radiological disease severity in children from the study population of children with presumptive TB. This study will externally validate the first data-driven WHO TDAs in a large, well-characterised and diverse paediatric IPD derived from four large paediatric cohorts of children investigated for TB. The study has received ethical clearance for sharing secondary deidentified data from the ethics committees of the parent studies (RaPaed-TB, UMOYA and TB Speed) and as the aims of this study were part of the parent studies' protocols, a separate approval was not necessary. Study findings will be published in peer-reviewed journals and disseminated at local, regional and international scientific meetings and conferences. This database will serve as a catalyst for the assessment of the inclusion of novel tools and the generation of an artificial population to simulate the impact of novel diagnostic pathways for TB in children at lower levels of healthcare. TDAs have the potential to close the diagnostic gap in childhood TB. Further finetuning of the currently available algorithms will facilitate this and improve access to care.

This study aimed to develop and validate machine learning models integrating clinicoradiological and radiomic features from 2-[18 F]-fluoro-2-deoxy-D-glucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) to predict pathological high invasiveness in cT1-sized (tumor size ≤ 3 cm) non-small cell lung cancer (NSCLC). We retrospectively reviewed 1459 patients with NSCLC (633 with pathological high invasiveness and 826 with pathological non-high invasiveness) from two medical centers. Patients with cT1-sized NSCLC were included. 1145 radiomic features were extracted per modality (PET and CT) from each patient. Optimal predictors were selected to construct a radiomics score (Rad-score) for the PET/CT radiomics model. A combined model incorporating significant clinicoradiological features and the Rad-score was developed. Logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost) algorithms were used to train the combined model. Model performance was assessed the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve, and decision curve analysis (DCA). Shapley Additive Explanations (SHAP) was applied to visualize the prediction process. The radiomics model was built using 11 radiomic features, achieving AUCs of 0.851 (training), 0.859 (internal validation), and 0.829 (external validation). Among all models, the XGBoost combined model demonstrated the best predictive performance, with AUCs of 0.958, 0.919, and 0.903, respectively, along with good calibration and high net benefit. The XGBoost combined model showed strong performance in predicting pathological high invasiveness in cT1-sized NSCLC.

Deep learning has significantly advanced automatic medical diagnostics, releasing human resources from clinical pressure, yet the persistent challenge of data scarcity in this area hampers its further improvements and applications. To address this gap, we introduce a novel ensemble framework called 'Efficient Transfer and Self-supervised Learning based Ensemble Framework' (ETSEF). ETSEF leverages features from multiple pre-trained deep learning models to efficiently learn powerful representations from a limited number of data samples. To the best of our knowledge, ETSEF is the first strategy that combines two pre-training methodologies (Transfer Learning and Self-supervised Learning) with ensemble learning approaches. Various data enhancement techniques, including data augmentation, feature fusion, feature selection, and decision fusion, have also been deployed to maximise the efficiency and robustness of the ETSEF model. Five independent medical imaging tasks, including endoscopy, breast cancer detection, monkeypox detection, brain tumour detection, and glaucoma detection, were tested to demonstrate ETSEF's effectiveness and robustness. Facing limited sample numbers and challenging medical tasks, ETSEF has demonstrated its effectiveness by improving diagnostic accuracy by up to 13.3% compared to strong ensemble baseline models and up to 14.4% compared with recent state-of-the-art methods. Moreover, we emphasise the robustness and trustworthiness of the ETSEF method through various vision-explainable artificial intelligence techniques, including Grad-CAM, SHAP, and t-SNE. Compared to large-scale deep learning models, ETSEF can be flexibly deployed and maintain superior performance for challenging medical imaging tasks, demonstrating potential for application in areas lacking training data. The code is available at Github ETSEF.

This study aims to explore the potential of machine learning as a non-invasive automated tool for skin tumor differentiation. Data were included from 156 lesions, collected retrospectively from September 2021 to February 2024. Univariate and multivariate analyses of traditional clinical features were performed to establish a logistic regression model. Ultrasound-based radiomics features are extracted from grayscale images after delineating regions of interest (ROIs). Independent samples t-tests, Mann-Whitney U tests, and Least Absolute Shrinkage and Selection Operator (LASSO) regression were employed to select ultrasound-based radiomics features. Subsequently, five machine learning methods were used to construct radiomics models based on the selected features. Model performance was evaluated using receiver operating characteristic (ROC) curves and the Delong test. Age, poorly defined margins, and irregular shape were identified as independent risk factors for malignant skin tumors. The multilayer perception (MLP) model achieved the best performance, with area under the curve (AUC) values of 0.963 and 0.912, respectively. The results of DeLong's test revealed a statistically significant discrepancy in efficacy between the MLP and clinical models (Z=2.611, p=0.009). Machine learning based skin tumor models may serve as a potential non-invasive method to improve diagnostic efficiency.

This study aimed to develop a deep learning (DL) model for automatic detection and diagnosis of gouty arthritis (GA) in the first metatarsophalangeal joint (MTPJ) using ultrasound (US) images. A retrospective study included individuals who underwent first MTPJ ultrasonography between February and July 2023. A five-fold cross-validation method (training set = 4:1) was employed. A deep residual convolutional neural network (CNN) was trained, and Gradient-weighted Class Activation Mapping (Grad-CAM) was used for visualization. Different ResNet18 models with varying residual blocks (2, 3, 4, 6) were compared to select the optimal model for image classification. Diagnostic decisions were based on a threshold proportion of abnormal images, determined from the training set. A total of 2401 US images from 260 patients (149 gout, 111 control) were analyzed. The model with 3 residual blocks performed best, achieving an AUC of 0.904 (95% CI: 0.887~0.927). Visualization results aligned with radiologist opinions in 2000 images. The diagnostic model attained an accuracy of 91.1% (95% CI: 90.4%~91.8%) on the testing set, with a diagnostic threshold of 0.328.  The DL model demonstrated excellent performance in automatically detecting and diagnosing GA in the first MTPJ.

Tyrosine kinase inhibitors (TKIs) combined with immunotherapy regimens are now widely used for treating advanced hepatocellular carcinoma (HCC), but their clinical efficacy is limited to a subset of patients. Considering that the vast majority of advanced HCC patients lose the opportunity for liver resection and thus cannot provide tumor tissue samples, we leveraged the clinical and image data to construct a multimodal convolutional neural network (CNN)-Transformer model for predicting and analyzing tumor response to TKI-immunotherapy. An automatic liver tumor segmentation system, based on a two-stage 3D U-Net framework, delineates lesions by first segmenting the liver parenchyma and then precisely localizing the tumor. This approach effectively addresses the variability in clinical data and significantly reduces bias introduced by manual intervention. Thus, we developed a clinical model using only pre-treatment clinical information, a CNN model using only pre-treatment magnetic resonance imaging data, and an advanced multimodal CNN-Transformer model that fused imaging and clinical parameters using a training cohort (n = 181) and then validated them using an independent cohort (n = 30). In the validation cohort, the area under the curve (95% confidence interval) values were 0.720 (0.710-0.731), 0.695 (0.683-0.707), and 0.785 (0.760-0.810), respectively, indicating that the multimodal model significantly outperformed the single-modality baseline models across validations. Finally, single-cell sequencing with the surgical tumor specimens reveals tumor ecosystem diversity associated with treatment response, providing a preliminary biological validation for the prediction model. In summary, this multimodal model effectively integrates imaging and clinical features of HCC patients, has a superior performance in predicting tumor response to TKI-immunotherapy, and provides a reliable tool for optimizing personalized treatment strategies.