Automated radiology report generation (RRG) aims to produce detailed textual reports from clinical imaging, such as computed tomography (CT) scans, to improve the accuracy and efficiency of diagnosis and provision of management advice. RRG is complicated by two key challenges: (1) inherent complexity in extracting relevant information from imaging data under resource constraints, and (2) difficulty in objectively evaluating discrepancies between model-generated and expert-written reports. To address these challenges, we propose $\mu^2$LLM, a $\underline{\textbf{mu}}$ltiscale $\underline{\textbf{mu}}$ltimodal large language models for RRG tasks. The novel ${\mu}^2$Tokenizer, as an intermediate layer, integrates multi-modal features from the multiscale visual tokenizer and the text tokenizer, then enhances report generation quality through direct preference optimization (DPO), guided by GREEN-RedLlama. Experimental results on four large CT image-report medical datasets demonstrate that our method outperforms existing approaches, highlighting the potential of our fine-tuned $\mu^2$LLMs on limited data for RRG tasks. At the same time, for prompt engineering, we introduce a five-stage, LLM-driven pipeline that converts routine CT reports into paired visual-question-answer triples and citation-linked reasoning narratives, creating a scalable, high-quality supervisory corpus for explainable multimodal radiology LLM. All code, datasets, and models will be publicly available in our official repository. https://github.com/Siyou-Li/u2Tokenizer

As technological innovation in computers has advanced, radiologists may now diagnose brain tumors (BT) with the use of artificial intelligence (AI). In the medical field, early disease identification enables further therapies, where the use of AI systems is essential for time and money savings. The difficulties presented by various forms of Magnetic Resonance (MR) imaging for BT detection are frequently not addressed by conventional techniques. To get around frequent problems with traditional tumor detection approaches, deep learning techniques have been expanded. Thus, for BT segmentation utilizing MR images, a U-Net-based architecture combined with Attention Mechanisms has been developed in this work. Moreover, by fine-tuning essential variables, Hyperparameter Optimization (HPO) is used using the Bayesian Optimization Algorithm to strengthen the segmentation model's performance. Tumor regions are pinpointed for segmentation using Region-Adaptive Thresholding technique, and the segmentation results are validated against ground truth annotated images to assess the performance of the suggested model. Experiments are conducted using the LGG, Healthcare, and BraTS 2021 MRI brain tumor datasets. Lastly, the importance of the suggested model has been demonstrated through comparing several metrics, such as IoU, accuracy, and DICE Score, with current state-of-the-art methods. The U-Net-based method gained a higher DICE score of 0.89687 in the segmentation of MRI-BT.

Thyroid ultrasound (US) is an essential tool for detecting and characterizing thyroid nodules. In this study, we propose an innovative approach to enhance thyroid nodule assessment by integrating Doppler US images with grayscale US images through weakly supervised data augmentation networks (WSDAN). Our method reduces background noise by replacing inefficient augmentation strategies, such as random cropping, with an advanced technique guided by bounding boxes derived from Doppler US images. This targeted augmentation significantly improves model performance in both classification and localization of thyroid nodules. The training dataset comprises 1288 paired grayscale and Doppler US images, with an additional 190 pairs used for three-fold cross-validation. To evaluate the model's efficacy, we tested it on a separate set of 190 grayscale US images. Compared to five state-of-the-art models and the original WSDAN, our Enhanced WSDAN model achieved superior performance. For classification, it reached an accuracy of 91%. For localization, it achieved Dice and Jaccard indices of 75% and 87%, respectively, demonstrating its potential as a valuable clinical tool.

Accurate stratification of the activity index of Crohn's disease (CD) using computed tomography enterography (CTE) radiomics and serum markers can aid in predicting disease progression and assist physicians in personalizing therapeutic regimens for patients with CD. This retrospective study enrolled 233 patients diagnosed with CD between January 2019 and August 2024. Patients were divided into training and testing cohorts at a ratio of 7:3 and further categorized into remission, mild active phase, and moderate-severe active phase groups based on simple endoscopic score for CD (SEC-CD). Radiomics features were extracted from CTE venous images, and T-test and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection. The serum markers were selected based on the variance analysis. We also developed a random forest (RF) model for multi-class stratification of CD. The model performance was evaluated by the area under the receiver operating characteristic curve (AUC) and quantified the contribution of each feature in the dataset to CD activity via Shapley additive exPlanations (SHAP) values. Finally, we enrolled gender, radiomics scores, and serum scores to develop a nomogram model to verify the effectiveness of feature extraction. 14 non-zero coefficient radiomics features and six serum markers with significant differences (P<0.01) were ultimately selected to predict CD activity. The AUC (micro/macro) for the ensemble machine learning model combining the radiomics features and serum markers is 0.931/0.928 for three-class. The AUC for the remission phase, the mild active phase, and the moderate-severe active phase were 0.983, 0.852, and 0.917, respectively. The mean AUC for the nomogram model was 0.940. A radiomics model was developed by integrating radiomics and serum markers of CD patients, achieving enhanced consistency with SEC-CD in grade CD. This model has the potential to assist clinicians in accurate diagnosis and treatment.

Weakly supervised semantic segmentation (WSSS) methods using class labels often rely on class activation maps (CAMs) to localize objects. However, traditional CAM-based methods struggle with partial activations and imprecise object boundaries due to optimization discrepancies between classification and segmentation. Recently, the conditional diffusion model (CDM) has been used as an alternative for generating segmentation masks in WSSS, leveraging its strong image generation capabilities tailored to specific class distributions. By modifying or perturbing the condition during diffusion sampling, the related objects can be highlighted in the generated images. Yet, the saliency maps generated by CDMs are prone to noise from background alterations during reverse diffusion. To alleviate the problem, we introduce Contrastive Learning with Diffusion Features (CLDF), a novel method that uses contrastive learning to train a pixel decoder to map the diffusion features from a frozen CDM to a low-dimensional embedding space for segmentation. Specifically, we integrate gradient maps generated from CDM external classifier with CAMs to identify foreground and background pixels with fewer false positives/negatives for contrastive learning, enabling robust pixel embedding learning. Experimental results on four segmentation tasks from two public medical datasets demonstrate that our method significantly outperforms existing baselines.

This study aims to evaluate the success of artificial intelligence models developed using convolutional neural network-based algorithms on CBCT images. Labeling was done by segmentation method for 15 different conditions including caries, restorative filling material, root-canal filling material, dental implant, implant supported crown, crown, pontic, impacted tooth, supernumerary tooth, residual root, osteosclerotic area, periapical lesion, radiolucent jaw lesion, radiopaque jaw lesion, and mixed appearing jaw lesion on the data set consisting of 300 CBCT images. In model development, the Mask R-CNN architecture and ResNet 101 model were used as a transfer learning method. The success metrics of the model were calculated with the confusion matrix method. When the F1 scores of the developed models were evaluated, the most successful dental implant was found to be 1, and the lowest F1 score was found to be a mixed appearing jaw lesion. F1 scores were respectively dental implant, root canal filling material, implant supported crown, restorative filling material, radiopaque jaw lesion, crown, pontic, impacted tooth, caries, residual tooth root, radiolucent jaw lesion, osteosclerotic area, periapical lesion, supernumerary tooth, for mixed appearing jaw lesion; 1 is 0.99, 0.98, 0.98, 0.97, 0.96, 0.96, 0.95, 0.94, 0.94, 0.94, 0.90, 0.90, 0.87, and 0.8. Interpreting CBCT images is a time-consuming process and requires expertise. In the era of digital transformation, artificial intelligence-based systems that can automatically evaluate images and convert them into report format as a decision support mechanism will contribute to reducing the workload of physicians, thus increasing the time allocated to the interpretation of pathologies.

This study focuses on automating the classification of certain thoracic lung cancer stages in 3D ¹⁸FDG-PET/CT images according to the 9th Edition of the TNM Classification for Lung Cancer (2024). By leveraging advanced segmentation and classification techniques, we aim to enhance the accuracy of distinguishing between T4 (pulmonary nodules) Thoracic M0 and M1a (pulmonary nodules) stages. Precise segmentation of pulmonary lobes using the Pulmonary Toolkit enables the identification of tumor locations and additional malignant nodules, ensuring reliable differentiation between ipsilateral and contralateral spread. A modified ResNet-50 model is employed to classify the segmented regions. The performance evaluation shows that the model achieves high accuracy. The unchanged class has the best recall 93% and an excellent F1 score 91%. The M1a (pulmonary nodules) class performs well with an F1 score of 94%, though recall is slightly lower 91%. For T4 (pulmonary nodules) Thoracic M0, the model shows balanced performance with an F1 score of 87%. The overall accuracy is 87%, indicating a robust classification model.

Artificial intelligence (AI) has enabled accurate and fast plaque quantification from coronary computed tomography angiography (CCTA). However, AI detects any coronary plaque in up to 97% of patients. To avoid overdiagnosis, a plaque burden safety cut-off for future coronary events is needed. Percent atheroma volume (PAV) was quantified with AI-guided quantitative computed tomography in a blinded fashion. Safety cut-off derivation was performed in the Turku CCTA registry (Finland), and pre-defined as ≥90% sensitivity for acute coronary syndrome (ACS). External validation was performed in the Amsterdam CCTA registry (the Netherlands). In the derivation cohort, 100/2271 (4.4%) patients experienced ACS (median follow-up 6.9 years). A threshold of PAV ≥ 2.6% was derived with 90.0% sensitivity and negative predictive value (NPV) of 99.0%. In the validation cohort 27/568 (4.8%) experienced ACS (median follow-up 6.7 years) with PAV ≥ 2.6% showing 92.6% sensitivity and 99.0% NPV for ACS. In the derivation cohort, 45.2% of patients had PAV < 2.6 vs. 4.3% with PAV 0% (no plaque) (P < 0.001) (validation cohort: 34.3% PAV < 2.6 vs. 2.6% PAV 0%; P < 0.001). Patients with PAV ≥ 2.6% had higher adjusted ACS rates in the derivation [Hazard ratio (HR) 4.65, 95% confidence interval (CI) 2.33-9.28, P < 0.001] and validation cohort (HR 7.31, 95% CI 1.62-33.08, P = 0.010), respectively. This study suggests that PAV up to 2.6% quantified by AI is associated with low-ACS risk in two independent patient cohorts. This cut-off may be helpful for clinical application of AI-guided CCTA analysis, which detects any plaque in up to 96-97% of patients.

This study aimed to investigate the role of volumetric and dissemination parameters obtained from pretreatment 18-fluorodeoxyglucose PET/computed tomography (18F-FDG PET/CT) in predicting progression/relapse in patients with diffuse large B-cell lymphoma (DLBCL) with machine learning algorithms. Patients diagnosed with DLBCL histopathologically, treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone, and followed for at least 1 year were reviewed retrospectively. Quantitative parameters such as tumor volume [total metabolic tumor volume (tMTV)], tumor burden [total lesion glycolysis (tTLG)], and the longest distance between two tumor foci (Dmax) were obtained from PET images with a standard uptake value threshold of 4.0. The MTV obtained from the volume of interest with the highest volume was noted as metabolic bulk volume (MBV). By analyzing the patients' PET parameters and clinical information with machine learning algorithms, models that attempt to predict progression/recurrence over 1 year were obtained. Of the 90 patients included, 16 had progression within 1 year. Significant differences were found in tMTV, tTLG, MBV, and Dmax values between patients with and without progression. The area under curve (AUC) of the model obtained with clinical data was 0.701. While a model with an AUC of 0.871 was obtained with a random forest algorithm using PET parameters, the model obtained with the Naive Bayes algorithm including clinical data in PET parameters had an AUC of 0.838. Using quantitative parameters derived from staging PET with machine learning algorithms may enable us to detect early progression in patients with DLBCL and improve early risk stratification and guide treatment decisions in these patients.

Congenital uterine anomalies (CUAs) can lead to infertility, miscarriage, preterm birth, and an increased risk of pregnancy complications. Compared to traditional 2D ultrasound (US), 3D US can reconstruct the coronal plane, providing a clear visualization of the uterine morphology for assessing CUAs accurately. In this paper, we propose an intelligent system for simultaneous automated plane localization and CUA diagnosis. Our highlights are: 1) we develop a denoising diffusion model with local (plane) and global (volume/text) guidance, using an adaptive weighting strategy to optimize attention allocation to different conditions; 2) we introduce a reinforcement learning-based framework with unsupervised rewards to extract the key slice summary from redundant sequences, fully integrating information across multiple planes to reduce learning difficulty; 3) we provide text-driven uncertainty modeling for coarse prediction, and leverage it to adjust the classification probability for overall performance improvement. Extensive experiments on a large 3D uterine US dataset show the efficacy of our method, in terms of plane localization and CUA diagnosis. Code is available at https://github.com/yuhoo0302/CUA-US.