To assess the accuracy of three commercially available and one open-source deep learning (DL) solutions for automatic tooth segmentation in cone beam computed tomography (CBCT) images of patients with multiple dental impactions. Twenty patients (20 CBCT scans) were selected from a retrospective cohort of individuals with multiple dental impactions. For each CBCT scan, one reference segmentation and four DL segmentations of the maxillary and mandibular teeth were obtained. Reference segmentations were generated by experts using a semi-automatic process. DL segmentations were automatically generated according to the manufacturer's instructions. Quantitative and qualitative evaluations of each DL segmentation were performed by comparing it with expert-generated segmentation. The quantitative metrics used were Dice similarity coefficient (DSC) and the normalized surface distance (NSD). The patients had an average of 12 retained teeth, with 12 of them diagnosed with a rare disease. DSC values ranged from 88.5% ± 3.2% to 95.6% ± 1.2%, and NSD values ranged from 95.3% ± 2.7% to 97.4% ± 6.5%. The number of completely unsegmented teeth ranged from 1 (0.1%) to 41 (6.0%). Two solutions (Diagnocat and DentalSegmentator) outperformed the others across all tested parameters. All the tested methods showed a mean NSD of approximately 95%, proving their overall efficiency for tooth segmentation. The accuracy of the methods varied among the four tested solutions owing to the presence of impacted teeth in our CBCT scans. DL solutions are evolving rapidly, and their future performance cannot be predicted based on our results.

Since its development, virtual monoenergetic imaging (VMI) derived from dual-energy computed tomography (DECT) has been shown to be valuable in many clinical applications. However, DECT-based VMI showed increased noise at low keV levels. In this study, we proposed an unsupervised learning method to generate VMI from DECT. This means that we don't require training and labeled (i.e. high-quality VMI) data. Specifically, DECT images were fed into a deep learning (DL) based model expected to output VMI. Based on the theory that VMI obtained from image space data is a linear combination of DECT images, we used the model output (i.e. the predicted VMI) to recalculate DECT images. By minimizing the difference between the measured and recalculated DECT images, the DL-based model can be constrained itself to generate VMI from DECT images. We investigate whether the proposed DL-based method has the ability to improve the quality of VMIs. The experimental results obtained from patient data showed that the DL-based VMIs had better image quality than the conventional DECT-based VMIs. Moreover, the CT number differences between the DECT-based and DL-based VMIs were distributed within <math xmlns="http://www.w3.org/1998/Math/MathML"><mo>±</mo></math> 10 HU for bone and <math xmlns="http://www.w3.org/1998/Math/MathML"><mo>±</mo></math> 5 HU for brain, fat, and muscle. Except for bone, no statistically significant difference in CT number measurements was found between the DECT-based and DL-based VMIs (p > 0.01). Our preliminary results show that DL has the potential to unsupervisedly generate high-quality VMIs directly from DECT.

Clinical decision-making routinely demands reasoning over heterogeneous data, yet existing multimodal language models (MLLMs) remain largely vision-centric and fail to generalize across clinical specialties. To bridge this gap, we introduce QoQ-Med-7B/32B, the first open generalist clinical foundation model that jointly reasons across medical images, time-series signals, and text reports. QoQ-Med is trained with Domain-aware Relative Policy Optimization (DRPO), a novel reinforcement-learning objective that hierarchically scales normalized rewards according to domain rarity and modality difficulty, mitigating performance imbalance caused by skewed clinical data distributions. Trained on 2.61 million instruction tuning pairs spanning 9 clinical domains, we show that DRPO training boosts diagnostic performance by 43% in macro-F1 on average across all visual domains as compared to other critic-free training methods like GRPO. Furthermore, with QoQ-Med trained on intensive segmentation data, it is able to highlight salient regions related to the diagnosis, with an IoU 10x higher than open models while reaching the performance of OpenAI o4-mini. To foster reproducibility and downstream research, we release (i) the full model weights, (ii) the modular training pipeline, and (iii) all intermediate reasoning traces at https://github.com/DDVD233/QoQ_Med.

To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices. A multicentre, platform-based development study using retrospective and cross-sectional data. Data were subjected to a two-level grading system by trained graders and a retina specialist, and categorised into three types: no DME, non-centre-involved DME and centre-involved DME (CI-DME). The 3-D convolutional neural networks algorithm was used for DME classification system development. The deep learning (DL) performance was compared with the diabetic retinopathy experts. Data were collected from Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Chaozhou People's Hospital and The Second Affiliated Hospital of Shantou University Medical College from January 2010 to December 2023. 7790 volumes of 7146 eyes from 4254 patients were annotated, of which 6281 images were used as the development set and 1509 images were used as the external validation set, split based on the centres. Accuracy, F1-score, sensitivity, specificity, area under receiver operating characteristic curve (AUROC) and Cohen's kappa were calculated to evaluate the performance of the DL algorithm. In classifying DME with non-DME, our model achieved an AUROCs of 0.990 (95% CI 0.983 to 0.996) and 0.916 (95% CI 0.902 to 0.930) for hold-out testing dataset and external validation dataset, respectively. To distinguish CI-DME from non-centre-involved-DME, our model achieved AUROCs of 0.859 (95% CI 0.812 to 0.906) and 0.881 (95% CI 0.859 to 0.902), respectively. In addition, our system showed comparable performance (Cohen's κ: 0.85 and 0.75) to the retina experts (Cohen's κ: 0.58-0.92 and 0.70-0.71). Our DL system achieved high accuracy in multiclassification tasks on DME classification with 3-D OCT images, which can be applied to population-based DME screening.

With the advancement of modern medicine and the development of technologies such as MRI, CT, and cellular analysis, it has become increasingly critical for clinicians to accurately interpret various diagnostic images. However, modern medical education often faces challenges due to limited access to high-quality teaching materials, stemming from privacy concerns and a shortage of educational resources (Balogh et al., 2015). In this context, image data generated by machine learning models, particularly generative models, presents a promising solution. These models can create diverse and comparable imaging datasets without compromising patient privacy, thereby supporting modern medical education. In this study, we explore the use of convolutional neural networks (CNNs) and CycleGAN (Zhu et al., 2017) for generating synthetic medical images. The source code is available at https://github.com/mliuby/COMP4211-Project.

A diagnostic medical foundation model (MedFM) is an artificial intelligence (AI) system engineered to accurately determine diagnoses across various medical imaging modalities and specialties. To train MedFM, we created the PubMed Central Medical Images Dataset (PMCMID), the largest annotated medical image dataset to date, comprising 16,126,659 images from 3,021,780 medical publications. Using AI- and ontology-based methods, we identified 4,482,237 medical images (e.g., clinical photos, X-rays, ultrasounds) and generated comprehensive annotations. To optimize MedFMs performance and assess biases, 13,266 images were manually annotated to establish a multimodal benchmark. MedFM achieved physician-level performance in diagnosis tasks spanning radiology, dermatology, and infectious diseases without requiring specific training. Additionally, we developed the Image2Paper app, allowing clinicians to upload medical images and retrieve relevant literature. The correct diagnoses appeared within the top ten results in 88.4% and at least one relevant differential diagnosis in 93.0%. MedFM and PMCMID were made publicly available. FundingResearch reported here was partially supported by the National Cancer Institute (NCI) (R01 CA260271), the Saudi Company for Artificial Intelligence (SCAI) Authority, and the German Federal Ministry for Economic Affairs and Climate Action (BMWK) under the project DAKI-FWS (01MK21009E). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

This study aimed to evaluate the diagnostic performance of an artificial intelligence (AI)-based platform (Diagnocat) in detecting periapical radiolucencies (PARLs) in cone-beam computed tomography (CBCT) scans of molars. Specifically, we assessed Diagnocat's performance in detecting PARLs in non-root-filled molars and compared its diagnostic performance between preoperative and postoperative scans. This retrospective study analyzed preoperative and postoperative CBCT scans of 134 molars (327 roots). PARLs detected by Diagnocat were compared with assessments independently performed by two experienced endodontists, serving as the reference standard. Diagnostic performance was assessed at both tooth and root levels using sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the receiver operating characteristic curve (AUC-ROC). In preoperative scans of non-root-filled molars, Diagnocat demonstrated high sensitivity (teeth: 93.9%, roots: 86.2%), moderate specificity (teeth: 65.2%, roots: 79.9%), accuracy (teeth: 79.1%, roots: 82.6%), PPV (teeth: 71.8%, roots: 75.8%), NPV (teeth: 91.8%, roots: 88.8%), and F1 score (teeth: 81.3%, roots: 80.7%) for PARL detection. The AUC was 0.76 at the tooth level and 0.79 at the root level. Postoperative scans showed significantly lower PPV (teeth: 54.2%; roots: 46.9%) and F1 scores (teeth: 67.2%; roots: 59.2%). Diagnocat shows promise in detecting PARLs in CBCT scans of non-root-filled molars, demonstrating high sensitivity but moderate specificity, highlighting the need for human oversight to prevent overdiagnosis. However, diagnostic performance declined significantly in postoperative scans of root-filled molars. Further research is needed to optimize the platform's performance and support its integration into clinical practice. AI-based platforms such as Diagnocat can assist clinicians in detecting PARLs in CBCT scans, enhancing diagnostic efficiency and supporting decision-making. However, human expertise remains essential to minimize the risk of overdiagnosis and avoid unnecessary treatment.

We present results of the development of Dentomo artificial intelligence model based on two neural networks. The model includes a database and a knowledge base harmonized with SNOMED CT that allows processing and interpreting the results of cone beam computed tomography (CBCT) scans of the dental system, in particular, identifying and classifying teeth, identifying CT signs of pathology and previous treatments. Based on these data, artificial intelligence can draw conclusions and generate medical reports, systematize the data, and learn from the results. The diagnostic effectiveness of Dentomo was evaluated. The first results of the study have demonstrated that the model based on neural networks and artificial intelligence is a valuable tool for analyzing CBCT scans in clinical practice and optimizing the dentist workflow.

Physics-driven artificial intelligence (PD-AI) reconstruction methods have emerged as the state-of-the-art for accelerating MRI scans, enabling higher spatial and temporal resolutions. However, the high resolution of these scans generates massive data volumes, leading to challenges in transmission, storage, and real-time processing. This is particularly pronounced in functional MRI, where hundreds of volumetric acquisitions further exacerbate these demands. Edge computing with FPGAs presents a promising solution for enabling PD-AI reconstruction near the MRI sensors, reducing data transfer and storage bottlenecks. However, this requires optimization of PD-AI models for hardware efficiency through quantization and bypassing traditional FFT-based approaches, which can be a limitation due to their computational demands. In this work, we propose a novel PD-AI computational MRI approach optimized for FPGA-based edge computing devices, leveraging 8-bit complex data quantization and eliminating redundant FFT/IFFT operations. Our results show that this strategy improves computational efficiency while maintaining reconstruction quality comparable to conventional PD-AI methods, and outperforms standard clinical methods. Our approach presents an opportunity for high-resolution MRI reconstruction on resource-constrained devices, highlighting its potential for real-world deployment.

Cone-beam computed tomography (CBCT) imaging plays a crucial role in dentistry, with automatic prediction of anatomical structures on CBCT images potentially enhancing diagnostic and planning procedures. This study aims to predict anatomical structures automatically on CBCT images using a deep learning algorithm. CBCT images from 70 patients were analyzed. Anatomical structures were annotated using a regional segmentation tool within an annotation software by two dentomaxillofacial radiologists. Each volumetric dataset comprised 405 slices, with relevant anatomical structures marked in each slice. Seventy DICOM images were converted to Nifti format, with seven reserved for testing and the remaining sixty-three used for training. The training utilized nnUNetv2 with an initial learning rate of 0.01, decreasing by 0.00001 at each epoch, and was conducted for 1000 epochs. Statistical analysis included accuracy, Dice score, precision, and recall results. The segmentation model achieved an accuracy of 0.99 for nasal fossa, maxillary sinus, nasopalatine canal, mandibular canal, foramen mentale, and foramen mandible, with corresponding Dice scores of 0.85, 0.98, 0.79, 0.73, 0.78, and 0.74, respectively. Precision values ranged from 0.73 to 0.98. Maxillary sinus segmentation exhibited the highest performance, while mandibular canal segmentation showed the lowest performance. The results demonstrate high accuracy and precision across most structures, with varying Dice scores indicating the consistency of segmentation. Overall, our segmentation model exhibits robust performance in delineating anatomical features in CBCT images, promising potential applications in dental diagnostics and treatment planning.