Accurate and fully automated pancreas segmentation is critical for advancing imaging biomarkers in early pancreatic cancer detection and for biomarker discovery in endocrine and exocrine pancreatic diseases. We developed and evaluated a deep learning (DL)-based convolutional neural network (CNN) for automated pancreas segmentation using the largest single-institution dataset to date (n = 3031 CTs). Ground truth segmentations were performed by radiologists, which were used to train a 3D nnU-Net model through five-fold cross-validation, generating an ensemble of top-performing models. To assess generalizability, the model was externally validated on the multi-institutional AbdomenCT-1K dataset (n = 585), for which volumetric segmentations were newly generated by expert radiologists and will be made publicly available. In the test subset (n = 452), the CNN achieved a mean Dice Similarity Coefficient (DSC) of 0.94 (SD 0.05), demonstrating high spatial concordance with radiologist-annotated volumes (Concordance Correlation Coefficient [CCC]: 0.95). On the AbdomenCT-1K dataset, the model achieved a DSC of 0.96 (SD 0.04) and a CCC of 0.98, confirming its robustness across diverse imaging conditions. The proposed DL model establishes new performance benchmarks for fully automated pancreas segmentation, offering a scalable and generalizable solution for large-scale imaging biomarker research and clinical translation.

Retinal diseases recognition is still a challenging task. Many deep learning classification methods and their modifications have been developed for medical imaging. Recently, Vision Transformers (ViT) have been applied for classification of retinal diseases with great success. Therefore, in this study a novel method was proposed, the Residual Self-Attention Vision Transformer (RS-A ViT), for automatic detection of acquired vitelliform lesions (AVL), macular drusen as well as distinguishing them from healthy cases. The Residual Self-Attention module instead of Self-Attention was applied in order to improve model's performance. The new tool outperforms the classical deep learning methods, like EfficientNet, InceptionV3, ResNet50 and VGG16. The RS-A ViT method also exceeds the ViT algorithm, reaching 96.62%. For the purpose of this research a new dataset was created that combines AVL data gathered from two research centers and drusen as well as normal cases from the OCT dataset. The augmentation methods were applied in order to enlarge the samples. The Grad-CAM interpretability method indicated that this model analyses the appropriate areas in optical coherence tomography images in order to detect retinal diseases. The results proved that the presented RS-A ViT model has a great potential in classification retinal disorders with high accuracy and thus may be applied as a supportive tool for ophthalmologists.

Radiation pneumonia (RP) is the most common side effect of chest radiotherapy, and can affect patients' quality of life. This study aimed to establish a combined model of radiomics, dosiomics, deep learning (DL) based on simulated location CT and dosimetry images combining with clinical parameters to improve the predictive ability of ≥ 2 grade RP (RP2) in patients with non-small cell lung cancer (NSCLC). This study retrospectively collected 245 patients with NSCLC who received radiotherapy from three hospitals. 162 patients from Hospital I were randomly divided into training cohort and internal validation cohort according to 7:3. 83 patients from two other hospitals served as an external validation cohort. Multivariate analysis was used to screen independent clinical predictors and establish clinical model (CM). The radiomic and dosiomics (RD) features and DL features were extracted from simulated location CT and dosimetry images based on the region of interest (ROI) of total lung-PTV (TL-PTV). The features screened by the t-test and least absolute shrinkage and selection operator (LASSO) were used to construct the RD and DL model, and RD-score and DL-score were calculated. RD-score, DL-score and independent clinical features were combined to establish deep learning radiomics and dosiomics nomogram (DLRDN). The model performance was evaluated by area under the curve (AUC). Three clinical factors, including V20, V30, and mean lung dose (MLD), were used to establish the CM. 7 RD features including 4 radiomics features and 3 dosiomics features were selected to establish RD model. 10 DL features were selected to establish DL model. Among the different models, DLRDN showed the best predictions, with the AUCs of 0.891 (0.826-0.957), 0.825 (0.693-0.957), and 0.801 (0.698-0.904) in the training cohort, internal validation cohort and external validation cohort, respectively. DCA showed that DLRDN had a higher overall net benefit than other models. The calibration curve showed that the predicted value of DLRDN was in good agreement with the actual value. Overall, radiomics, dosiomics, and DL features based on simulated location CT and dosimetry images have the potential to help predict RP2. The combination of multi-dimensional data produced the optimal predictive model, which could provide guidance for clinicians.

Identifying patients suitable for conversion therapy through early non-invasive screening is crucial for tailoring treatment in advanced gastric cancer (AGC). This study aimed to develop and validate a deep learning method, utilizing preoperative computed tomography (CT) images, to predict the response to conversion therapy in AGC patients. This retrospective study involved 140 patients. We utilized Progressive Distill (PD) methodology to construct a deep learning model for predicting clinical response to conversion therapy based on preoperative CT images. Patients in the training set (n = 112) and in the test set (n = 28) were sourced from The First Affiliated Hospital of Wenzhou Medical University between September 2017 and November 2023. Our PD models' performance was compared with baseline models and those utilizing Knowledge Distillation (KD), with evaluation metrics including accuracy, sensitivity, specificity, receiver operating characteristic curves, areas under the receiver operating characteristic curve (AUCs), and heat maps. The PD model exhibited the best performance, demonstrating robust discrimination of clinical response to conversion therapy with an AUC of 0.99 and accuracy of 99.11% in the training set, and 0.87 AUC and 85.71% accuracy in the test set. Sensitivity and specificity were 97.44% and 100% respectively in the training set, 85.71% and 85.71% each in the test set, suggesting absence of discernible bias. The deep learning model of PD method accurately predicts clinical response to conversion therapy in AGC patients. Further investigation is warranted to assess its clinical utility alongside clinicopathological parameters.

Deep learning models are increasingly being implemented for automated medical image analysis to inform patient care. Most models, however, lack uncertainty information, without which the reliability of model outputs cannot be ensured. Several uncertainty quantification (UQ) methods exist to capture model uncertainty. Yet, it is not clear which method is optimal for a given task. The purpose of this work was to investigate several commonly used UQ methods for the critical yet understudied task of metastatic lesion segmentation on whole body PET/CT. 
Approach:
59 whole body 68Ga-DOTATATE PET/CT images of patients undergoing theranostic treatment of metastatic neuroendocrine tumors were used in this work. A 3D U-Net was trained for lesion segmentation following five-fold cross validation. Uncertainty measures derived from four UQ methods-probability entropy, Monte Carlo dropout, deep ensembles, and test time augmentation-were investigated. Each uncertainty measure was assessed across four quantitative evaluations: (1) its ability to detect artificially degraded image data at low, medium, and high degradation magnitudes; (2) to detect false-positive (FP) predicted regions; (3) to recover false-negative (FN) predicted regions; and (3) to establish correlations with model biomarker extraction and segmentation performance metrics. 
Results: Test time augmentation and probability entropy respectively achieved the highest and lowest degraded image detection at low (AUC=0.54 vs. 0.68), medium (AUC=0.70 vs. 0.82), and high (AUC=0.83 vs. 0.90) degradation magnitudes. For detecting FPs, all UQ methods achieve strong performance, with AUC values ranging narrowly between 0.77 and 0.81. FN region recovery performance was strongest for test time augmentation and weakest for probability entropy. Performance for the correlation analysis was mixed, where the strongest performance was achieved by test time augmentation for SUVtotal capture (ρ=0.57) and segmentation Dice coefficient (ρ=0.72), by Monte Carlo dropout for SUVmean capture (ρ=0.35), and by probability entropy for segmentation cross entropy (ρ=0.96).
Significance: Overall, test time augmentation demonstrated superior uncertainty quantification performance and is recommended for use in metastatic lesion segmentation task. It also offers the advantage of being post hoc and computationally efficient. In contrast, probability entropy performed the worst, highlighting the need for advanced UQ approaches for this task.&#xD.

To evaluate the impact of fluid volume fluctuations quantified with artificial intelligence in optical coherence tomography scans during the maintenance phase and visual outcomes at 12 and 24 months in a real-world, multicentre, national cohort of treatment-naïve neovascular age-related macular degeneration (nAMD) eyes. Demographics, visual acuity (VA) and number of injections were collected using the Fight Retinal Blindness tool. Intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), total fluid (TF) and central subfield thickness (CST) were quantified using the RetinAI Discovery tool. Fluctuations were defined as the SD of within-eye quantified values, and eyes were distributed according to SD quartiles for each biomarker. A total of 452 naïve nAMD eyes were included. Eyes with highest (Q4) versus lowest (Q1) fluid fluctuations showed significantly worse VA change (months 3-12) in IRF -3.91 versus 3.50 letters, PED -4.66 versus 3.29, TF -2.07 versus 2.97 and CST -1.85 versus 2.96 (all p<0.05), but not for SRF 0.66 versus 0.93 (p=0.91). Similar VA outcomes were observed at month 24 for PED -8.41 versus 4.98 (p<0.05), TF -7.38 versus 1.89 (p=0.07) and CST -10.58 versus 3.60 (p<0.05). The median number of injections (months 3-24) was significantly higher in Q4 versus Q1 eyes in IRF 9 versus 8, SRF 10 versus 8 and TF 10 versus 8 (all p<0.05). This multicentre study reports a negative effect in VA outcomes of fluid volume fluctuations during the maintenance phase in specific fluid compartments, suggesting that anatomical and functional treatment response patterns may be fluid-specific.

Artificial intelligence (AI) can be applied in multiple subspecialties in craniomaxillofacial (CMF) surgeries. This article overviews AI fundamentals focusing on classification, object detection, and segmentation-core tasks used in CMF applications. The article then explores the development and integration of AI in dentoalveolar surgery, implantology, traumatology, oncology, craniofacial surgery, and orthognathic and feminization surgery. It highlights AI-driven advancements in diagnosis, pre-operative planning, intra-operative assistance, post-operative management, and outcome prediction. Finally, the challenges in AI adoption are discussed, including data limitations, algorithm validation, and clinical integration.

To investigate lung changes in patients with polymyositis/dermatomyositis-associated interstitial lung disease (PM/DM-ILD) using quantitative CT and to construct a diagnostic model to evaluate the application of quantitative CT and machine learning in diagnosing PM/DM-ILD. Chest CT images from 348 PM/DM individuals were quantitatively analyzed to obtain the lung volume (LV), mean lung density (MLD), and intrapulmonary vascular volume (IPVV) of the whole lung and each lung lobe. The percentage of high attenuation area (HAA %) was determined using the lung density histogram. Patients hospitalized from 2016 to 2021 were used as the training set (n=258), and from 2022 to 2023 were used as the temporal test set (n=90). Seven classification models were established, and their performance was evaluated through ROC analysis, decision curve analysis, calibration, and precision-recall curve. The optimal model was selected and interpreted with Python's SHAP model interpretation package. Compared to the non-ILD group, the mean lung density and percentage of high attenuation area in the whole lung and each lung lobe were significantly increased, and the lung volume and intrapulmonary vessel volume were significantly decreased in the ILD group. The Random Forest (RF) model demonstrated superior performance with the test set area under the curve of 0.843 (95% CI: 0.821-0.865), accuracy of 0.778, sensitivity of 0.784, and specificity of 0.750. Quantitative CT serves as an objective and precise method to assess pulmonary changes in PM/DM-ILD patients. The RF model based on CT quantitative parameters displayed strong diagnostic efficiency in identifying ILD, offering a new and convenient approach for evaluating and diagnosing PM/DM-ILD patients.

The automatic diagnosis of chest diseases is a popular and challenging task. Most current methods are based on convolutional neural networks (CNNs), which focus on local features while neglecting global features. Recently, self-attention mechanisms have been introduced into the field of computer vision, demonstrating superior performance. Therefore, this paper proposes an effective model, CheX-DS, for classifying long-tail multi-label data in the medical field of chest X-rays. The model is based on the excellent CNN model DenseNet for medical imaging and the newly popular Swin Transformer model, utilizing ensemble deep learning techniques to combine the two models and leverage the advantages of both CNNs and Transformers. The loss function of CheX-DS combines weighted binary cross-entropy loss with asymmetric loss, effectively addressing the issue of data imbalance. The NIH ChestX-ray14 dataset is selected to evaluate the model's effectiveness. The model outperforms previous studies with an excellent average AUC score of 83.76\%, demonstrating its superior performance.

Foundation models, pretrained on extensive datasets, have significantly advanced machine learning by providing robust and transferable embeddings applicable to various domains, including medical imaging diagnostics. This study evaluates the utility of embeddings derived from both general-purpose and medical domain-specific foundation models for training lightweight adapter models in multi-class radiography classification, focusing specifically on tube placement assessment. A dataset comprising 8842 radiographs classified into seven distinct categories was employed to extract embeddings using six foundation models: DenseNet121, BiomedCLIP, Med-Flamingo, MedImageInsight, Rad-DINO, and CXR-Foundation. Adapter models were subsequently trained using classical machine learning algorithms. Among these combinations, MedImageInsight embeddings paired with an support vector machine adapter yielded the highest mean area under the curve (mAUC) at 93.8%, followed closely by Rad-DINO (91.1%) and CXR-Foundation (89.0%). In comparison, BiomedCLIP and DenseNet121 exhibited moderate performance with mAUC scores of 83.0% and 81.8%, respectively, whereas Med-Flamingo delivered the lowest performance at 75.1%. Notably, most adapter models demonstrated computational efficiency, achieving training within one minute and inference within seconds on CPU, underscoring their practicality for clinical applications. Furthermore, fairness analyses on adapters trained on MedImageInsight-derived embeddings indicated minimal disparities, with gender differences in performance within 2% and standard deviations across age groups not exceeding 3%. These findings confirm that foundation model embeddings-especially those from MedImageInsight-facilitate accurate, computationally efficient, and equitable diagnostic classification using lightweight adapters for radiographic image analysis.