The verification of chest X-ray images involves several checkpoints, including orientation and reversal. To address the challenges of manual verification, this study developed an artificial intelligence (AI)-based system using a deep convolutional neural network (DCNN) to automatically verify the consistency between the imaging direction and examination orders. The system classified the chest X-ray images into four categories: anteroposterior (AP), posteroanterior (PA), flipped AP, and flipped PA. To evaluate the impact of internal and external datasets on the classification accuracy, the DCNN was trained using multiple publicly available chest X-ray datasets and tested on both internal and external data. The results demonstrated that the DCNN accurately classified the imaging directions and detected image reversal. However, the classification accuracy was strongly influenced by the training dataset. When trained exclusively on NIH data, the network achieved an accuracy of 98.9% on the same dataset; however, this reduced to 87.8% when evaluated with PADChest data. When trained on a mixed dataset, the accuracy improved to 96.4%; however, it decreased to 76.0% when tested on an external COVID-CXNet dataset. Further, using Grad-CAM, we visualized the decision-making process of the network, highlighting the areas of influence, such as the cardiac silhouette and arm positioning, depending on the imaging direction. Thus, this study demonstrated the potential of AI in assisting in automating the verification of imaging direction and positioning in chest X-rays. However, the network must be fine-tuned to local data characteristics to achieve optimal performance.

To create and validate a machine learning (ML)-based model for predicting the adverse perinatal outcome (APO) in foetal growth restriction (FGR) at diagnosis. A retrospective study. Multi-centre in China. Pregnancies affected by FGR. We enrolled singleton foetuses with a perinatal diagnosis of FGR who were admitted between January 2021 and November 2023. A total of 361 pregnancies from Beijing Obstetrics and Gynecology Hospital were used as the training set and the internal test set. In comparison, data from 50 pregnancies from Haidian Maternal and Child Health Hospital were used as the external test set. Feature screening was performed using the random forest (RF), the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression (LR). Subsequently, six ML methods, including Stacking, were used to construct models to predict the APO of FGR. Model's performance was evaluated through indicators such as the area under the receiver operating characteristic curve (AUROC). The Shapley Additive Explanation analysis was used to rank each model feature and explain the final model. Mean ± SD gestational age at diagnosis was 32.3 ± 4.8 weeks in the absent APO group and 27.3 ± 3.7 in the present APO group. Women enrolled in the present APO group had a higher rate of hypertension related to pregnancy (74.8% vs. 18.8%, p < 0.001). Among 17 candidate predictors (including maternal characteristics, maternal comorbidities, obstetric characteristics and ultrasound parameters), the integration of RF, LASSO and LR methodologies identified maternal body mass index, hypertension, gestational age at diagnosis of FGR, estimated foetal weight (EFW) z score, EFW growth velocity and abnormal umbilical artery Doppler (defined as a pulsatility index above the 95th percentile or instances of absent/reversed diastolic flow) as significant predictors. The Stacking model demonstrated a good performance in both the internal test set [AUROC: 0.861, 95% confidence interval (CI), 0.838-0.896] and the external test set [AUROC: 0.906, 95% CI, 0.875-0.947]. The calibration curve showed high agreement between the predicted and observed risks. The Hosmer-Lemeshow test for the internal and external test sets was p = 0.387 and p = 0.825, respectively. The ML algorithm for APO, which integrates maternal clinical factors and ultrasound parameters, demonstrates good predictive value for APO in FGR at diagnosis. This suggested that ML techniques may be a valid approach for the early detection of high-risk APO in FGR pregnancies.

We propose a self-supervised feature learning assisted reconstruction (SSFL-Recon) framework for MRI reconstruction to address the limitation of existing supervised learning methods. Although recent deep learning-based methods have shown promising performance in MRI reconstruction, most require fully-sampled images for supervised learning, which is challenging in practice considering long acquisition times under respiratory or organ motion. Moreover, nearly all fully-sampled datasets are obtained from conventional reconstruction of mildly accelerated datasets, thus potentially biasing the achievable performance. The numerous undersampled datasets with different accelerations in clinical practice, hence, remain underutilized. To address these issues, we first train a self-supervised feature extractor on undersampled images to learn sampling-insensitive features. The pre-learned features are subsequently embedded in the self-supervised reconstruction network to assist in removing artifacts. Experiments were conducted retrospectively on an in-house 2D cardiac Cine dataset, including 91 cardiovascular patients and 38 healthy subjects. The results demonstrate that the proposed SSFL-Recon framework outperforms existing self-supervised MRI reconstruction methods and even exhibits comparable or better performance to supervised learning up to 16× retrospective undersampling. The feature learning strategy can effectively extract global representations, which have proven beneficial in removing artifacts and increasing generalization ability during reconstruction.

Low-quality pseudo labels pose a significant obstacle in semi-supervised medical image segmentation (SSMIS), impeding consistency learning on unlabeled data. Leveraging vision-language model (VLM) holds promise in ameliorating pseudo label quality by employing textual prompts to delineate segmentation regions, but it faces the challenge of cross-modal alignment uncertainty due to multiple correspondences (multiple images/texts tend to correspond to one text/image). Existing VLMs address this challenge by modeling semantics as distributions but such distributions lead to semantic degradation. To address these problems, we propose Alignment-Multiplicity Aware Vision-Language Model (AMVLM), a new VLM pre-training paradigm with two novel similarity metric strategies. (i) Cross-modal Similarity Supervision (CSS) proposes a probability distribution transformer to supervise similarity scores across fine-granularity semantics through measuring cross-modal distribution disparities, thus learning cross-modal multiple alignments. (ii) Intra-modal Contrastive Learning (ICL) takes into account the similarity metric of coarse-fine granularity information within each modality to encourage cross-modal semantic consistency. Furthermore, using the pretrained AMVLM, we propose a pioneering text-guided SSMIS network to compensate for the quality deficiencies of pseudo-labels. This network incorporates a text mask generator to produce multimodal supervision information, enhancing pseudo label quality and the model's consistency learning. Extensive experimentation validates the efficacy of our AMVLM-driven SSMIS, showcasing superior performance across four publicly available datasets. The code will be available at: https://github.com/QingtaoPan/AMVLM.

Quantifying biological parameters of interest through dynamic positron emission tomography (PET) requires an arterial input function (AIF) conventionally obtained from arterial blood samples. The AIF can also be non-invasively estimated from blood pools in PET images, often identified using co-registered MRI images. Deploying methods without blood sampling or the use of MRI generally requires total body PET systems with a long axial field-of-view (LAFOV) that includes a large cardiovascular blood pool. However, the number of such systems in clinical use is currently much smaller than that of short axial field-of-view (SAFOV) scanners. We propose a data-driven approach for AIF estimation for SAFOV PET scanners, which is non-invasive and does not require MRI or blood sampling using brain PET scans. The proposed method was validated using dynamic ¹⁸F-fluorodeoxyglucose [¹⁸F]FDG total body PET data from 10 subjects. A variational inference-based machine learning approach was employed to correct for peak activity. The prior was estimated using a probabilistic vascular MRI atlas, registered to each subject's PET image to identify cerebral arteries in the brain. The estimated AIF using brain PET images (IDIF-Brain) was compared to that obtained using data from the descending aorta of the heart (IDIF-DA). Kinetic rate constants (K₁, k₂, k₃) and net radiotracer influx (K_i) for both cases were computed and compared. Qualitatively, the shape of IDIF-Brain matched that of IDIF-DA, capturing information on both the peak and tail of the AIF. The area under the curve (AUC) of IDIF-Brain and IDIF-DA were similar, with an average relative error of 9%. The mean Pearson correlations between kinetic parameters (K₁, k₂, k₃) estimated with IDIF-DA and IDIF-Brain for each voxel were between 0.92 and 0.99 in all subjects, and for K_i, it was above 0.97. This study introduces a new approach for AIF estimation in dynamic PET using brain PET images, a probabilistic vascular atlas, and machine learning techniques. The findings demonstrate the feasibility of non-invasive and subject-specific AIF estimation for SAFOV scanners.

Artificial Intelligence (AI) is increasingly being integrated into the field of musculoskeletal (MSK) radiology, from research methods to routine clinical practice. Within the field of fracture detection, AI is allowing for precision and speed previously unimaginable. Yet, AI's decision-making processes are sometimes wrought with deficiencies, undermining trust, hindering accountability, and compromising diagnostic precision. To make AI a trusted ally for radiologists, we recommend incorporating clinical history, rationalizing AI decisions by explainable AI (XAI) techniques, increasing the variety and scale of training data to approach the complexity of a clinical situation, and active interactions between clinicians and developers. By bridging these gaps, the true potential of AI can be unlocked, enhancing patient outcomes and fundamentally transforming radiology through a harmonious integration of human expertise and intelligent technology. In this article, we aim to examine the factors contributing to AI inaccuracies and offer recommendations to address these challenges-benefiting both radiologists and developers striving to improve future algorithms.

<b>Background and purpose:</b> This study focuses on an objective evaluation of a novel reconstruction algorithm-Deep Learning Image Reconstruction (DLIR)-ability to improve image quality and reduce radiation dose compared to the established standard of Adaptive Statistical Iterative Reconstruction-V (ASIR-V), in unenhanced head computed tomography (CT). <b>Materials and methods:</b> A retrospective analysis of 163 consecutive unenhanced head CTs was conducted. Image quality assessment was computed on the objective parameters of Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), derived from 5 regions of interest (ROI). The evaluation of DLIR dose reduction abilities was based on the analysis of the PACS derived parameters of dose length product and computed tomography dose index volume (CTDIvol). <b>Results:</b> Following the application of rigorous criteria, the study comprised 35 patients. Significant image quality improvement was achieved with the implementation of DLIR, as evidenced by up to a 145% and 160% increase in SNR in supra- and infratentorial regions, respectively. CNR measurements further confirmed the superiority of DLIR over ASIR-V, with an increase of 171.5% in the supratentorial region and a 59.3% increase in the infratentorial region. Despite the signal improvement and noise reduction DLIR facilitated radiation dose reduction of up to 44% in CTDIvol. <b>Conclusion:</b> Implementation of DLIR in head CT scans enables significant image quality improvement and dose reduction abilities compared to standard ASIR-V. However, the dose reduction feature was proven insufficient to counteract the lack of gantry angulation in wide-detector scanners.

Background and objectiveCOVID-19 is considered as the biggest global health disaster in the 21st century, and it has a huge impact on the world.MethodsThis paper publishes a publicly available dataset of CT images of multiple types of pneumonia (COVID-19CT+). Specifically, the dataset contains 409,619 CT images of 1333 patients, with subset-A containing 312 community-acquired pneumonia cases and subset-B containing 1021 COVID-19 cases. In order to demonstrate that there are differences in the methods used to classify COVID-19CT+ images across time, we selected 13 classical machine learning classifiers and 5 deep learning classifiers to test the image classification task.ResultsIn this study, two sets of experiments are conducted using traditional machine learning and deep learning methods, the first set of experiments is the classification of COVID-19 in Subset-B versus COVID-19 white lung disease, and the second set of experiments is the classification of community-acquired pneumonia in Subset-A versus COVID-19 in Subset-B, demonstrating that the different periods of the methods differed on COVID-19CT+. On the first set of experiments, the accuracy of traditional machine learning reaches a maximum of 97.3% and a minimum of only 62.6%. Deep learning algorithms reaches a maximum of 97.9% and a minimum of 85.7%. On the second set of experiments, traditional machine learning reaches a high of 94.6% accuracy and a low of 56.8%. The deep learning algorithm reaches a high of 91.9% and a low of 86.3%.ConclusionsThe COVID-19CT+ in this study covers a large number of CT images of patients with COVID-19 and community-acquired pneumonia and is one of the largest datasets available. We expect that this dataset will attract more researchers to participate in exploring new automated diagnostic algorithms to contribute to the improvement of the diagnostic accuracy and efficiency of COVID-19.

Trauma-induced rib fractures are common injuries. The gold standard for diagnosing rib fractures is computed tomography (CT), but the sensitivity in the acute setting is low, and interpreting CT slices is labor-intensive. This has led to the development of new diagnostic approaches leveraging deep learning (DL) models. This systematic review and pooled analysis aimed to compare the performance of DL models in the detection, segmentation, and classification of rib fractures based on CT scans. A literature search was performed using various databases for studies describing DL models detecting, segmenting, or classifying rib fractures from CT data. Reported performance metrics included sensitivity, false-positive rate, F1-score, precision, accuracy, and mean average precision. A meta-analysis was performed on the sensitivity scores to compare the DL models with clinicians. Of the 323 identified records, 25 were included. Twenty-one studies reported on detection, four on segmentation, and 10 on classification. Twenty studies had adequate data for meta-analysis. The gold standard labels were provided by clinicians who were radiologists and orthopedic surgeons. For detecting rib fractures, DL models had a higher sensitivity (86.7%; 95% CI: 82.6%-90.2%) than clinicians (75.4%; 95% CI: 68.1%-82.1%). In classification, the sensitivity of DL models for displaced rib fractures (97.3%; 95% CI: 95.6%-98.5%) was significantly better than that of clinicians (88.2%; 95% CI: 84.8%-91.3%). DL models for rib fracture detection and classification achieved promising results. With better sensitivities than clinicians for detecting and classifying displaced rib fractures, the future should focus on implementing DL models in daily clinics. Level III-systematic review and pooled analysis.

This study is aimed to clarify the effectiveness of the image-rotation technique and zooming augmentation to improve the accuracy of the deep learning (DL)-based dose conversion from pencil beam (PB) to Monte Carlo (MC) in proton beam therapy (PBT). We adapted 85 patients with head and neck cancers. The patient dataset was randomly divided into 101 plans (334 beams) for training/validation and 11 plans (34 beams) for testing. Further, we trained a DL model that inputs a computed tomography (CT) image and the PB dose in a single-proton field and outputs the MC dose, applying the image-rotation technique and zooming augmentation. We evaluated the DL-based dose conversion accuracy in a single-proton field. The average γ-passing rates (a criterion of 3%/3 mm) were 80.6 ± 6.6% for the PB dose, 87.6 ± 6.0% for the baseline model, 92.1 ± 4.7% for the image-rotation model, and 93.0 ± 5.2% for the data-augmentation model, respectively. Moreover, the average range differences for R90 were - 1.5 ± 3.6% in the PB dose, 0.2 ± 2.3% in the baseline model, -0.5 ± 1.2% in the image-rotation model, and - 0.5 ± 1.1% in the data-augmentation model, respectively. The doses as well as ranges were improved by the image-rotation technique and zooming augmentation. The image-rotation technique and zooming augmentation greatly improved the DL-based dose conversion accuracy from the PB to the MC. These techniques can be powerful tools for improving the DL-based dose calculation accuracy in PBT.