To address the unmet need for a widely available examination for mortality prediction, this study developed a foundation visual artificial intelligence (VAI) to enhance mortality risk stratification using chest X-rays (CXRs). The VAI employed deep learning to extract CXR features and a Cox proportional hazard model to generate a hazard score ("CXR-risk"). We retrospectively collected CXRs from patients visited outpatient department and physical examination center. Subsequently, we reviewed mortality and morbidity outcomes from electronic medical records. The dataset consisted of 41,945, 10,492, 31,707, and 4441 patients in the training, validation, internal test, and external test sets, respectively. During the median follow-up of 3.2 (IQR, 1.2-6.1) years of both internal and external test sets, the "CXR-risk" demonstrated C-indexes of 0.859 (95% confidence interval (CI), 0.851-0.867) and 0.870 (95% CI, 0.844-0.896), respectively. Patients with high "CXR-risk," above 85th percentile, had a significantly higher risk of mortality than those with low risk, below 50th percentile. The addition of clinical and laboratory data and radiographic report further improved the predictive accuracy, resulting in C-indexes of 0.888 and 0.900. The VAI can provide accurate predictions of mortality and morbidity outcomes using just a single CXR, and it can complement other risk prediction indicators to assist physicians in assessing patient risk more effectively.

This study aims to assess the effectiveness of integrating Segment Anything Model (SAM) and its variant MedSAM into the automated mining, object detection, and segmentation (MODS) methodology for developing robust lung cancer detection and segmentation models without post hoc labeling of training images. In a retrospective analysis, 10,000 chest computed tomography scans from patients with lung cancer were mined. Line measurement annotations were converted to bounding boxes, excluding boxes < 1 cm or > 7 cm. The You Only Look Once object detection architecture was used for teacher-student learning to label unannotated lesions on the training images. Subsequently, a final tumor detection model was trained and employed with SAM and MedSAM for tumor segmentation. Model performance was assessed on a manually annotated test dataset, with additional evaluations conducted on an external lung cancer dataset before and after detection model fine-tuning. Bootstrap resampling was used to calculate 95% confidence intervals. Data mining yielded 10,789 line annotations, resulting in 5403 training boxes. The baseline detection model achieved an internal F1 score of 0.847, improving to 0.860 after self-labeling. Tumor segmentation using the final detection model attained internal Dice similarity coefficients (DSCs) of 0.842 (SAM) and 0.822 (MedSAM). After fine-tuning, external validation showed an F1 of 0.832 and DSCs of 0.802 (SAM) and 0.804 (MedSAM). Integrating foundational segmentation models into the MODS framework results in high-performing lung cancer detection and segmentation models using only mined clinical data. Both SAM and MedSAM hold promise as foundational segmentation models for radiology images.

This study aims to investigate whether global mammographic radiomic features (GMRFs) can distinguish hardest- from easiest-to-interpret normal cases for radiology trainees (RTs). Data from 137 RTs were analysed, with each interpreting seven educational self-assessment test sets comprising 60 cases (40 normal and 20 cancer). The study only examined normal cases. Difficulty scores were computed based on the percentage of readers who incorrectly classified each case, leading to their classification as hardest- or easiest-to-interpret based on whether their difficulty scores fell within and above the 75th or within and below the 25th percentile, respectively (resulted in 140 cases in total used). Fifty-nine low-density and 81 high-density cases were identified. Thirty-four GMRFs were extracted for each case. A random forest machine learning model was trained to differentiate between hardest- and easiest-to-interpret normal cases and validated using leave-one-out-cross-validation approach. The model's performance was evaluated using the area under receiver operating characteristic curve (AUC). Significant features were identified through feature importance analysis. Difference between hardest- and easiest-to-interpret cases among 34 GMRFs and in difficulty level between low- and high-density cases was tested using Kruskal-Wallis. The model achieved AUC = 0.75 with cluster prominence and range emerging as the most useful features. Fifteen GMRFs differed significantly (p < 0.05) between hardest- and easiest-to-interpret cases. Difficulty level among low- vs high-density cases did not differ significantly (p = 0.12). GMRFs can predict hardest-to-interpret normal cases for RTs, underscoring the importance of GMRFs in identifying the most difficult normal cases for RTs and facilitating customised training programmes tailored to trainees' learning needs.

Lung adenocarcinoma and squamous cell carcinoma are the two most common pathological lung cancer subtypes. Accurate diagnosis and pathological subtyping are crucial for lung cancer treatment. Solitary solid lung nodules with lobulation and spiculation signs are often indicative of lung cancer; however, in some cases, postoperative pathology finds benign solid lung nodules. It is critical to accurately identify solid lung nodules with lobulation and spiculation signs before surgery; however, traditional diagnostic imaging is prone to misdiagnosis, and studies on artificial intelligence-assisted diagnosis are few. Therefore, we introduce a volumetric SWIN Transformer-based method. It is a multi-scale, multi-task, and highly interpretable model for distinguishing between benign solid lung nodules with lobulation and spiculation signs, lung adenocarcinomas, and lung squamous cell carcinoma. The technique's effectiveness was improved by using 3-dimensional (3D) computed tomography (CT) images instead of conventional 2-dimensional (2D) images to combine as much information as possible. The model was trained using 352 of the 441 CT image sequences and validated using the rest. The experimental results showed that our model could accurately differentiate between benign lung nodules with lobulation and spiculation signs, lung adenocarcinoma, and squamous cell carcinoma. On the test set, our model achieves an accuracy of 0.9888, precision of 0.9892, recall of 0.9888, and an F1-score of 0.9888, along with a class activation mapping (CAM) visualization of the 3D model. Consequently, our method could be used as a preoperative tool to assist in diagnosing solitary solid lung nodules with lobulation and spiculation signs accurately and provide a theoretical basis for developing appropriate clinical diagnosis and treatment plans for the patients.

The parotid glands are the largest of the major salivary glands. They can harbour both benign and malignant tumours. Preoperative work-up relies on MR images and fine needle aspiration biopsy, but these diagnostic tools have low sensitivity and specificity, often leading to surgery for diagnostic purposes. The aim of this paper is (1) to develop a machine learning algorithm based on MR images characteristics to automatically classify parotid gland tumours and (2) compare its results with the diagnoses of junior and senior radiologists in order to evaluate its utility in routine practice. While automatic algorithms applied to parotid tumours classification have been developed in the past, we believe that our study is one of the first to leverage four different MRI sequences and propose a comparison with clinicians. In this study, we leverage data coming from a cohort of 134 patients treated for benign or malignant parotid tumours. Using radiomics extracted from the MR images of the gland, we train a random forest and a logistic regression to predict the corresponding histopathological subtypes. On the test set, the best results are given by the random forest: we obtain a 0.720 accuracy, a 0.860 specificity, and a 0.720 sensitivity over all histopathological subtypes, with an average AUC of 0.838. When considering the discrimination between benign and malignant tumours, the algorithm results in a 0.760 accuracy and a 0.769 AUC, both on test set. Moreover, the clinical experiment shows that our model helps to improve diagnostic abilities of junior radiologists as their sensitivity and accuracy raised by 6 % when using our proposed method. This algorithm may be useful for training of physicians. Radiomics with a machine learning algorithm may help improve discrimination between benign and malignant parotid tumours, decreasing the need for diagnostic surgery. Further studies are warranted to validate our algorithm for routine use.

Trustworthiness is crucial for artificial intelligence (AI) models in clinical settings, and a fundamental aspect of trustworthy AI is uncertainty quantification (UQ). Conformal prediction as a robust uncertainty quantification (UQ) framework has been receiving increasing attention as a valuable tool in improving model trustworthiness. An area of active research is the method of non-conformity score calculation for conformal prediction. We propose deep conformal supervision (DCS), which leverages the intermediate outputs of deep supervision for non-conformity score calculation, via weighted averaging based on the inverse of mean calibration error for each stage. We benchmarked our method on two publicly available datasets focused on medical image classification: a pneumonia chest radiography dataset and a preprocessed version of the 2019 RSNA Intracranial Hemorrhage dataset. Our method achieved mean coverage errors of 16e-4 (CI: 1e-4, 41e-4) and 5e-4 (CI: 1e-4, 10e-4) compared to baseline mean coverage errors of 28e-4 (CI: 2e-4, 64e-4) and 21e-4 (CI: 8e-4, 3e-4) on the two datasets, respectively (p < 0.001 on both datasets). Based on our findings, the baseline results of conformal prediction already exhibit small coverage errors. However, our method shows a significant improvement on coverage error, particularly noticeable in scenarios involving smaller datasets or when considering smaller acceptable error levels, which are crucial in developing UQ frameworks for healthcare AI applications.

Office-based testing, enhanced by advances in imaging technology, is routinely used in eye care to non-invasively assess ocular structure and function. This type of imaging coupled with autonomous artificial intelligence holds immense opportunity to diagnose eye diseases quickly. Despite the wide availability and use of ocular imaging, there are several factors that hinder optimization of clinical practice and patient care. While some large institutions have developed end-to-end digital workflows that utilize electronic health records, enterprise imaging archives, and dedicated diagnostic viewers, this experience has not yet made its way to smaller and independent eye clinics. Fractured interoperability practices impact patient care in all healthcare domains, including eye care where there is a scarcity of care centers, making collaboration essential among providers, specialists, and primary care who might be treating systemic conditions with profound impact on vision. The purpose of this white paper is to describe the current state of ocular imaging by focusing on the challenges related to interoperability, reporting, and clinical workflow.

The aim of this study is to investigate the role of [¹⁸F]-PSMA-1007 PET in differentiating high- and low-risk prostate cancer (PCa) through a robust radiomics ensemble model. This retrospective study included 143 PCa patients who underwent [¹⁸F]-PSMA-1007 PET/CT imaging. PCa areas were manually contoured on PET images and 1781 image biomarker standardization initiative (IBSI)-compliant radiomics features were extracted. A 30 times iterated preliminary analysis pipeline, comprising of the least absolute shrinkage and selection operator (LASSO) for feature selection and fivefold cross-validation for model optimization, was adopted to identify the most robust features to dataset variations, select candidate models for ensemble modelling, and optimize hyperparameters. Thirteen subsets of selected features, 11 generated from the preliminary analysis plus two additional subsets, the first based on the combination of robust and fine-tuning features, and the second only on fine-tuning features were used to train the model ensemble. Accuracy, area under curve (AUC), sensitivity, specificity, precision, and f-score values were calculated to provide models' performance. Friedman test, followed by post hoc tests corrected with Dunn-Sidak correction for multiple comparisons, was used to verify if statistically significant differences were found in the different ensemble models over the 30 iterations. The model ensemble trained with the combination of robust and fine-tuning features obtained the highest average accuracy (79.52%), AUC (85.75%), specificity (84.29%), precision (82.85%), and f-score (78.26%). Statistically significant differences (p < 0.05) were found for some performance metrics. These findings support the role of [¹⁸F]-PSMA-1007 PET radiomics in improving risk stratification for PCa, by reducing dependence on biopsies.

Deep learning (DL) tools developed on adult data sets may not generalize well to pediatric patients, posing potential safety risks. We evaluated the performance of TotalSegmentator, a state-of-the-art adult-trained CT organ segmentation model, on a subset of organs in a pediatric CT dataset and explored optimization strategies to improve pediatric segmentation performance. TotalSegmentator was retrospectively evaluated on abdominal CT scans from an external adult dataset (n = 300) and an external pediatric data set (n = 359). Generalizability was quantified by comparing Dice scores between adult and pediatric external data sets using Mann-Whitney U tests. Two DL optimization approaches were then evaluated: (1) 3D nnU-Net model trained on only pediatric data, and (2) an adult nnU-Net model fine-tuned on the pediatric cases. Our results show TotalSegmentator had significantly lower overall mean Dice scores on pediatric vs. adult CT scans (0.73 vs. 0.81, P < .001) demonstrating limited generalizability to pediatric CT scans. Stratified by organ, there was lower mean pediatric Dice score for four organs (P < .001, all): right and left adrenal glands (right adrenal, 0.41 [0.39-0.43] vs. 0.69 [0.66-0.71]; left adrenal, 0.35 [0.32-0.37] vs. 0.68 [0.65-0.71]); duodenum (0.47 [0.45-0.49] vs. 0.67 [0.64-0.69]); and pancreas (0.73 [0.72-0.74] vs. 0.79 [0.77-0.81]). Performance on pediatric CT scans improved by developing pediatric-specific models and fine-tuning an adult-trained model on pediatric images where both methods significantly improved segmentation accuracy over TotalSegmentator for all organs, especially for smaller anatomical structures (e.g., > 0.2 higher mean Dice for adrenal glands; P < .001).

Predicting long-term clinical outcomes based on the early DSC PWI MRI scan is valuable for prognostication, resource management, clinical trials, and patient expectations. Current methods require subjective decisions about which imaging features to assess and may require time-consuming postprocessing. This study's goal was to predict multilabel 90-day modified Rankin Scale (mRS) score in acute ischemic stroke patients by combining ensemble models and different configurations of radiomic features generated from Dynamic susceptibility contrast perfusion-weighted imaging. In Follow-up studies, a total of 70 acute ischemic stroke (AIS) patients underwent magnetic resonance imaging within 24 hours poststroke and had a follow-up scan. In the single study, 150 DSC PWI Image scans for AIS patients. The DRF are extracted from DSC-PWI Scans. Then Lasso algorithm is applied for feature selection, then new features are generated from initial and follow-up scans. Then we applied different ensemble models to classify between three classes normal outcome (0, 1 mRS score), moderate outcome (2,3,4 mRS score), and severe outcome (5,6 mRS score). ANOVA and post-hoc Tukey HSD tests confirmed significant differences in model style performance across various studies and classification techniques. Stacking models consistently on average outperformed others, achieving an Accuracy of 0.68 ± 0.15, Precision of 0.68 ± 0.17, Recall of 0.65 ± 0.14, and F1 score of 0.63 ± 0.15 in the follow-up time study. Techniques like Bo_Smote showed significantly higher recall and F1 scores, highlighting their robustness and effectiveness in handling imbalanced data. Ensemble models, particularly Bagging and Stacking, demonstrated superior performance, achieving nearly 0.93 in Accuracy, 0.95 in Precision, 0.94 in Recall, and 0.94 in F1 metrics in follow-up conditions, significantly outperforming single models. Ensemble models based on radiomics generated from combining Initial and follow-up scans can be used to predict multilabel 90-day stroke outcomes with reduced subjectivity and user burden.