To develop CT-based machine learning radiomics models used for the diagnosis of dysthyroid optic neuropathy (DON). This is a retrospective study included 57 patients (114 orbits) diagnosed with thyroid-associated ophthalmopathy (TAO) at the Beijing Tongren Hospital between December 2019 and June 2023. CT scans, medical history, examination results, and clinical data of the participants were collected. DON was diagnosed based on clinical manifestations and examinations. The DON orbits and non-DON orbits were then divided into a training set and a test set at a ratio of approximately 7:3. The 3D slicer software was used to identify the volumes of interest (VOI). Radiomics features were extracted using the Pyradiomics and selected by t-test and least absolute shrinkage and selection operator (LASSO) regression algorithm with 10-fold cross-validation. Machine-learning models, including random forest (RF) model, support vector machine (SVM) model, and logistic regression (LR) model were built and validated by receiver operating characteristic (ROC) curves, area under the curves (AUC) and confusion matrix-related data. The net benefit of the models is shown by the decision curve analysis (DCA). We extracted 107 features from the imaging data, representing various image information of the optic nerve and surrounding orbital tissues. Using the LASSO method, we identified the five most informative features. The AUC ranged from 0.77 to 0.80 in the training set and the AUC of the RF, SVM and LR models based on the features were 0.86, 0.80 and 0.83 in the test set, respectively. The DeLong test showed there was no significant difference between the three models (RF model vs SVM model: <i>p</i> = .92; RF model vs LR model: <i>p</i> = .94; SVM model vs LR model: <i>p</i> = .98) and the models showed optimal clinical efficacy in DCA. The CT-based machine learning radiomics analysis exhibited excellent ability to diagnose DON and may enhance diagnostic convenience.

Multi-modality medical image fusion (MMIF) technology utilizes the complementarity of different modalities to provide more comprehensive diagnostic insights for clinical practice. Existing deep learning-based methods often focus on extracting the primary information from individual modalities while ignoring the correlation of information distribution across different modalities, which leads to insufficient fusion of image details and color information. To address this problem, a diffusion-driven MMIF method is proposed to leverage the information distribution relationship among multi-modality images in the latent space. To better preserve the complementary information from different modalities, a local and global network (LAGN) is suggested. Additionally, a loss strategy is designed to establish robust constraints among diffusion-generated images, original images, and fused images. This strategy supervises the training process and prevents information loss in fused images. The experimental results demonstrate that the proposed method surpasses state-of-the-art image fusion methods in terms of unsupervised metrics on three datasets: MRI/CT, MRI/PET, and MRI/SPECT images. The proposed method successfully captures rich details and color information. Furthermore, 16 doctors and medical students were invited to evaluate the effectiveness of our method in assisting clinical diagnosis and treatment.

Commonly used MR image quality (IQ) metrics have poor concordance with radiologist-perceived diagnostic IQ. Here, we develop and explore deep feature distances (DFDs)-distances computed in a lower-dimensional feature space encoded by a convolutional neural network (CNN)-as improved perceptual IQ metrics for MR image reconstruction. We further explore the impact of distribution shifts between images in the DFD CNN encoder training data and the IQ metric evaluation. We compare commonly used IQ metrics (PSNR and SSIM) to two "out-of-domain" DFDs with encoders trained on natural images, an "in-domain" DFD trained on MR images alone, and two domain-adjacent DFDs trained on large medical imaging datasets. We additionally compare these with several state-of-the-art but less commonly reported IQ metrics, visual information fidelity (VIF), noise quality metric (NQM), and the high-frequency error norm (HFEN). IQ metric performance is assessed via correlations with five expert radiologist reader scores of perceived diagnostic IQ of various accelerated MR image reconstructions. We characterize the behavior of these IQ metrics under common distortions expected during image acquisition, including their sensitivity to acquisition noise. All DFDs and HFEN correlate more strongly with radiologist-perceived diagnostic IQ than SSIM, PSNR, and other state-of-the-art metrics, with correlations being comparable to radiologist inter-reader variability. Surprisingly, out-of-domain DFDs perform comparably to in-domain and domain-adjacent DFDs. A suite of IQ metrics, including DFDs and HFEN, should be used alongside commonly-reported IQ metrics for a more holistic evaluation of MR image reconstruction perceptual quality. We also observe that general vision encoders are capable of assessing visual IQ even for MR images.

Positron Emission Tomography (PET) is a powerful molecular imaging tool that visualizes radiotracer distribution to reveal physiological processes. Recent advances in total-body PET have enabled low-dose, CT-free imaging; however, accurate organ segmentation using PET-only data remains challenging. This study develops and validates a deep learning model for multi-organ PET segmentation across varied imaging conditions and tracers, addressing critical needs for fully PET-based quantitative analysis. This retrospective study employed a 3D deep learning-based model for automated multi-organ segmentation on PET images acquired under diverse conditions, including low-dose and non-attenuation-corrected scans. Using a dataset of 798 patients from multiple centers with varied tracers, model robustness and generalizability were evaluated via multi-center and cross-tracer tests. Ground-truth labels for 23 organs were generated from CT images, and segmentation accuracy was assessed using the Dice similarity coefficient (DSC). In the multi-center dataset from four different institutions, our model achieved average DSC values of 0.834, 0.825, 0.819, and 0.816 across varying dose reduction factors and correction conditions for FDG PET images. In the cross-tracer dataset, the model reached average DSC values of 0.737, 0.573, 0.830, 0.661, and 0.708 for DOTATATE, FAPI, FDG, Grazytracer, and PSMA, respectively. The proposed model demonstrated effective, fully PET-based multi-organ segmentation across a range of imaging conditions, centers, and tracers, achieving high robustness and generalizability. These findings underscore the model's potential to enhance clinical diagnostic workflows by supporting ultra-low dose PET imaging. Not applicable. This is a retrospective study based on collected data, which has been approved by the Research Ethics Committee of Ruijin Hospital affiliated to Shanghai Jiao Tong University School of Medicine.

Quantitative analysis of PET images in brain PET/CT relies on MRI-derived regions of interest (ROIs). However, the pairs of PET/CT and MR images are not always available, and their alignment is challenging if their acquisition times differ considerably. To address these problems, this study proposes a deep learning framework for translating CT of PET/CT to synthetic MR images (MR_SYN) and performing automated quantitative regional analysis using MR_SYN-derived segmentation. In this retrospective study, 139 subjects who underwent brain [¹⁸F]FBB PET/CT and T1-weighted MRI were included. A U-Net-like model was trained to translate CT images to MR_SYN; subsequently, a separate model was trained to segment MR_SYN into 95 regions. Regional and composite standardised uptake value ratio (SUVr) was calculated in [¹⁸F]FBB PET images using the acquired ROIs. For evaluation of MR_SYN, quantitative measurements including structural similarity index measure (SSIM) were employed, while for MR_SYN-based segmentation evaluation, Dice similarity coefficient (DSC) was calculated. Wilcoxon signed-rank test was performed for SUVrs computed using MR_SYN and ground-truth MR (MR_GT). Compared to MR_GT, the mean SSIM of MR_SYN was 0.974 ± 0.005. The MR_SYN-based segmentation achieved a mean DSC of 0.733 across 95 regions. No statistical significance (P > 0.05) was found for SUVr between the ROIs from MR_SYN and those from MR_GT, excluding the precuneus. We demonstrated a deep learning framework for automated regional brain analysis in PET/CT with MR_SYN. Our proposed framework can benefit patients who have difficulties in performing an MRI scan.

Left ventricular ejection fraction (LVEF) is a critical indicator of cardiac function, aiding in the assessment of heart conditions. Accurate segmentation of the left ventricle (LV) is essential for LVEF calculation. However, current methods are often limited by small datasets and exhibit poor generalization. While leveraging large models can address this issue, many fail to capture multi-scale information and introduce additional burdens on users to generate prompts. To overcome these challenges, we propose LV-SAM, a model based on the large model SAM-Med2D, for accurate LV segmentation. It comprises three key components: an image encoder with a multi-scale adapter (MSAd), a multimodal prompt encoder (MPE), and a multi-scale decoder (MSD). The MSAd extracts multi-scale information at the encoder level and fine-tunes the model, while the MSD employs skip connections to effectively utilize multi-scale information at the decoder level. Additionally, we introduce an automated pipeline for generating self-extracted dense prompts and use a large language model to generate text prompts, reducing the user burden. The MPE processes these prompts, further enhancing model performance. Evaluations on the CAMUS dataset show that LV-SAM outperforms existing SOAT methods in LV segmentation, achieving the lowest MAE of 5.016 in LVEF estimation.

With developments in computer science and technology, great progress has been made in three-dimensional (3D) ultrasound. Recently, ultrasound-based 3D bone modelling has attracted much attention, and its accuracy has been studied for the femur, tibia, and spine. The use of ultrasound allows data for bone surface to be acquired non-invasively and without radiation. Freehand 3D ultrasound of the bone surface can be roughly divided into two steps: segmentation of the bone surface from two-dimensional (2D) ultrasound images and 3D reconstruction of the bone surface using the segmented images. The aim of this study was to develop an automatic algorithm to segment the midface bone surface from 2D ultrasound images based on deep learning methods. Six deep learning networks were trained (nnU-Net, U-Net, ConvNeXt, Mask2Former, SegFormer, and DDRNet). The performance of the algorithms was compared with that of the ground truth and evaluated by Dice coefficient (DC), intersection over union (IoU), 95th percentile Hausdorff distance (HD95), average symmetric surface distance (ASSD), precision, recall, and time. nnU-Net yielded the highest DC of 89.3% ± 13.6% and the lowest ASSD of 0.11 ± 0.40 mm. This study showed that nnU-Net can automatically and effectively segment the midfacial bone surface from 2D ultrasound images.

In clinical work, there are difficulties in distinguishing pulmonary contusion(PC) from bacterial pneumonia(BP) on CT images by the naked eye alone when the history of trauma is unknown. Artificial intelligence is widely used in medical imaging, but its diagnostic performance for pulmonary contusion is unclear. In this study, artificial intelligence was used for the first time to identify lung contusion and bacterial pneumonia, and its diagnostic performance was compared with that of manual. In this retrospective study, 2179 patients between April 2016 and July 2022 from two hospitals were collected and divided into a training set, an internal validation set, an external validation set. PC and BP were automatically recognized, segmented using VB-net and radiomics features were automatically extracted. Four machine learning algorithms including Decision Trees, Logistic Regression, Random Forests and Support Vector Machines(SVM) were using to built the models. De-long test was used to compare the performance among models. The best performing model and four radiologists diagnosed the external validation set, and compare the diagnostic efficacy of human and artificial intelligence. VB-net automatically detected and segmented PC and BP. Among the four machine learning models we've built, De-long test showed that SVM model had the best performance, with AUC, accuracy, sensitivity, and specificity of 0.998 (95% CI: 0.995-1), 0.980, 0.979, 0.982 in the training set, 0.891 (95% CI: 0.854-0.928), 0.979, 0.750, 0.860 in the internal validation set, 0.885 (95% CI: 0.850-0.920), 0.903, 0.976, 0.794 in the external validation set. The diagnostic ability of the SVM model was superior to that of human (P < 0.05). Our VB-net automatically recognizes and segments PC and BP in chest CT images. SVM model based on radiomics features can quickly and accurately differentiate between them with higher accuracy than experienced radiologist.

To evaluate a deep learning-based time-of-flight (DLToF) model trained to enhance the image quality of non-ToF PET images for different tracers, reconstructed using BSREM algorithm, towards ToF images. A 3D residual U-NET model was trained using 8 different tracers (FDG: 75% and non-FDG: 25%) from 11 sites from US, Europe and Asia. A total of 309 training and 33 validation datasets scanned on GE Discovery MI (DMI) ToF scanners were used for development of DLToF models of three strengths: low (L), medium (M) and high (H). The training and validation pairs consisted of target ToF and input non-ToF BSREM reconstructions using site-preferred regularisation parameters (beta values). The contrast and noise properties of each model were defined by adjusting the beta value of target ToF images. A total of 60 DMI datasets, consisting of a set of 4 tracers (¹⁸F-FDG, ¹⁸F-PSMA, ⁶⁸Ga-PSMA, ⁶⁸Ga-DOTATATE) and 15 exams each, were collected for testing and quantitative analysis of the models based on standardized uptake value (SUV) in regions of interest (ROI) placed in lesions, lungs and liver. Each dataset includes 5 image series: ToF and non-ToF BSREM and three DLToF images. The image series (300 in total) were blind scored on a 5-point Likert score by 4 readers based on lesion detectability, diagnostic confidence, and image noise/quality. In lesion SUV_max quantification with respect to ToF BSREM, DLToF-H achieved the best results among the three models by reducing the non-ToF BSREM errors from -39% to -6% for ¹⁸F-FDG (38 lesions); from -42% to -7% for ¹⁸F-PSMA (35 lesions); from -34% to -4% for ⁶⁸Ga-PSMA (23 lesions) and from -34% to -12% for ⁶⁸Ga-DOTATATE (32 lesions). Quantification results in liver and lung also showed ToF-like performance of DLToF models. Clinical reader resulted showed that DLToF-H results in an improved lesion detectability on average for all four radiotracers whereas DLToF-L achieved the highest scores for image quality (noise level). The results of DLToF-M however showed that this model results in the best trade-off between lesion detection and noise level and hence achieved the highest score for diagnostic confidence on average for all radiotracers. This study demonstrated that the DLToF models are suitable for both FDG and non-FDG tracers and could be utilized for digital BGO PET/CT scanners to provide an image quality and lesion detectability comparable and close to ToF.

Artificial Intelligence models based on medical (imaging) data are increasingly developed. However, the imaging software on which the original data is generated is frequently updated. The impact of updated imaging software on the performance of AI models is unclear. We aimed to develop machine learning models using shear wave elastography (SWE) data to identify malignant breast lesions and to test the models' generalizability by validating them on external data generated by both the original updated software versions. We developed and validated different machine learning models (GLM, MARS, XGBoost, SVM) using multicenter, international SWE data (NCT02638935) using tenfold cross-validation. Findings were compared to the histopathologic evaluation of the biopsy specimen or 2-year follow-up. The outcome measure was the area under the curve (AUROC). We included 1288 cases in the development set using the original imaging software and 385 cases in the validation set using both, original and updated software. In the external validation set, the GLM and XGBoost models showed better performance with the updated software data compared to the original software data (AUROC 0.941 vs. 0.902, p < 0.001 and 0.934 vs. 0.872, p < 0.001). The MARS model showed worse performance with the updated software data (0.847 vs. 0.894, p = 0.045). SVM was not calibrated. In this multicenter study using SWE data, some machine learning models demonstrated great potential to bridge the gap between original software and updated software, whereas others exhibited weak generalizability.