Accurate quantification of the extent of bronchial damage across various airway levels in chronic obstructive pulmonary disease (COPD) remains a challenge. In this study, artificial intelligence (AI) was employed to develop an airway segmentation model to investigate the morphological changes of the central and peripheral airways in COPD patients and the effects of these airway changes on pulmonary function classification and acute COPD exacerbations. Clinical data from a total of 340 patients with COPD and 73 healthy volunteers were collected and compiled. An AI-driven airway segmentation model was constructed using Convolutional Neural Regressor (CNR) and Airway Transfer Network (ATN) algorithms. The efficacy of the model was evaluated through support vector machine (SVM) and random forest regression approaches. The area under the receiver operating characteristic (ROC) curve (AUC) of the SVM in evaluating the COPD airway segmentation model was 0.96, with a sensitivity of 97% and a specificity of 92%, however, the AUC value of the SVM was 0.81 when it was replaced the healthy group by non-COPD outpatients. Compared with the healthy group, the grade and the total number of airway segmentation were decreased and the diameters of the right main bronchus and bilateral lobar bronchi of patients with COPD were smaller and the airway walls were thinner (all P < 0.01). However, the diameters of the subsegmental and small airway bronchi were increased, and airway walls were thickened, and the arc lengths were shorter ( all P < 0.01), especially in patients with severe COPD (all P < 0.05). Correlation and regression analysis showed that FEV1%pre was positively correlated with the diameters and airway wall thickness of the main and lobar airway, and the arc lengths of small airway bronchi (all P < 0.05). Airway wall thickness of the subsegment and small airway were found to have the greatest impact on the frequency of COPD exacerbations. Artificial intelligence lung CT airway segmentation model is a non-invasive quantitative tool for measuring chronic obstructive pulmonary disease. The main changes in COPD patients are that the central airway diameter becomes narrower and the thickness becomes thinner. The arc length of the peripheral airway becomes shorter, and the diameter and airway wall thickness become larger, which is more obvious in severe patients. Pulmonary function classification and small and medium airway dysfunction are also affected by the diameter, thickness and arc length of large and small airways. Small airway remodeling is more significant in acute exacerbations of COPD.

The Radiological Society of North America has actively promoted artificial intelligence (AI) challenges since 2017. Algorithms emerging from the recent RSNA 2022 Cervical Spine Fracture Detection Challenge demonstrated state-of-the-art performance in the competition's data set, surpassing results from prior publications. However, their performance in real-world clinical practice is not known. As an initial step toward the goal of assessing feasibility of these models in clinical practice, we conducted a generalizability test by using one of the leading algorithms of the competition. The deep learning algorithm was selected due to its performance, portability, and ease of use, and installed locally. One hundred examinations (50 consecutive cervical spine CT scans with at least 1 fracture present and 50 consecutive negative CT scans) from a level 1 trauma center not represented in the competition data set were processed at 6.4 seconds per examination. Ground truth was established based on the radiology report with retrospective confirmation of positive fracture cases. Sensitivity, specificity, F1 score, and area under the curve were calculated. The external validation data set comprised older patients in comparison to the competition set (53.5 ± 21.8 years versus 58 ± 22.0, respectively; <i>P</i> < .05). Sensitivity and specificity were 86% and 70% in the external validation group and 85% and 94% in the competition group, respectively. Fractures misclassified by the convolutional neural networks frequently had features of advanced degenerative disease, subtle nondisplaced fractures not easily identified on the axial plane, and malalignment. The model performed with a similar sensitivity on the test and external data set, suggesting that such a tool could be potentially generalizable as a triage tool in the emergency setting. Discordant factors such as age-associated comorbidities may affect accuracy and specificity of AI models when used in certain populations. Further research should be encouraged to help elucidate the potential contributions and pitfalls of these algorithms in supporting clinical care.

To construct two machine learning radiomics (MLR) for invasive adenocarcinoma (IVA) prediction using normal-spatial-resolution (NSR) and high-spatial-resolution (HSR) training cohorts, and to validate models (model-NSR and -HSR) in another test cohort while comparing independent radiologists' (R1, R2) performance with and without model-HSR. In this retrospective multicenter study, all CT images were reconstructed using NSR data (512 matrix, 0.5-mm thickness) and HSR data (2048 matrix, 0.25-mm thickness). Nodules were divided into training (n = 61 non-IVA, n = 165 IVA) and test sets (n = 36 non-IVA, n = 203 IVA). Two MLR models were developed with 18 significant factors for the NSR model and 19 significant factors for the HSR model from 172 radiomics features using random forest. Area under the receiver operator characteristic curves (AUC) was analyzed using DeLong's test in the test set. Accuracy (acc), sensitivity (sen), and specificity (spc) of R1 and R2 with and without model-HSR were compared using McNemar test. 437 patients (70 ± 9 years, 203 men) had 465 nodules (n = 368, IVA). Model-HSR AUCs were significantly higher than model-NSR in training (0.839 vs. 0.723) and test sets (0.863 vs. 0.718) (p < 0.05). R1's acc (87.2%) and sen (93.1%) with model-HSR were significantly higher than without (77.0% and 79.3%) (p < 0.0001). R2's acc (83.7%) and sen (86.7%) with model-HSR might be equal or higher than without (83.7% and 85.7%, respectively), but not significant (p > 0.50). Spc of R1 (52.8%) and R2 (66.7%) with model-HSR might be lower than without (63.9% and 72.2%, respectively), but not significant (p > 0.21). HSR-based MLR model significantly increased IVA diagnostic performance compared to NSR, supporting radiologists without compromising accuracy and sensitivity. However, this benefit came at the cost of reduced specificity, potentially increasing false positives, which may lead to unnecessary examinations or overtreatment in clinical settings.

Predicting shorter life expectancy is crucial for prioritizing antifibrotic therapy in fibrotic lung diseases, where progression varies widely, from stability to rapid deterioration. This heterogeneity complicates treatment decisions, emphasizing the need for reliable baseline measures. This study focuses on leveraging artificial intelligence model to address heterogeneity in disease outcomes, focusing on mortality as the ultimate measure of disease trajectory. This retrospective study included 1744 anonymised patients who underwent high-resolution CT scanning. The AI model, SABRE (Smart Airway Biomarker Recognition Engine), was developed using data from patients with various lung diseases (n=460, including lung cancer, pneumonia, emphysema, and fibrosis). Then, 1284 high-resolution CT scans with evidence of diffuse FLD from the Australian IPF Registry and OSIC were used for clinical analyses. Airway branches were categorized and quantified by anatomic structures and volumes, followed by multivariable analysis to explore the associations between these categories and patients' progression and mortality, adjusting for disease severity or traditional measurements. Cox regression identified SABRE-based variables as independent predictors of mortality and progression, even adjusting for disease severity (fibrosis extent, traction bronchiectasis extent, and ILD extent), traditional measures (FVC%, DLCO%, and CPI), and previously reported deep learning algorithms for fibrosis quantification and morphological analysis. Combining SABRE with DLCO significantly improved prognosis utility, yielding an AUC of 0.852 at the first year and a C-index of 0.752. SABRE-based variables capture prognostic signals beyond that provided by traditional measurements, disease severity scores, and established AI-based methods, reflecting the progressiveness and pathogenesis of the disease.

This study aimed to develop an interpretable 3-year disease-free survival risk prediction tool to stratify patients with stage II colorectal cancer (CRC) by integrating CT images and clinicopathological factors. A total of 769 patients with pathologically confirmed stage II CRC and disease-free survival (DFS) follow-up information were recruited from three medical centers and divided into training (n = 442), test (n = 190), and validation cohorts (n = 137). CT-based tumor radiomics features were extracted, selected, and used to calculate a Radscore. A combined model was developed using artificial neural network (ANN) algorithm, by integrating the Radscore with significant clinicoradiological factors to classify patients into high- and low-risk groups. Model performance was assessed using the area under the curve (AUC), and feature contributions were qualified using the Shapley additive explanation (SHAP) algorithm. Kaplan-Meier survival analysis revealed the prognostic stratification value of the risk groups. Fourteen radiomics features and five clinicoradiological factors were selected to construct the radiomics and clinicoradiological models, respectively. The combined model demonstrated optimal performance, with AUCs of 0.811 and 0.846 in the test and validation cohorts, respectively. Kaplan-Meier curves confirmed effective patient stratification (p < 0.001) in both test and validation cohorts. A high Radscore, rough intestinal outer edge, and advanced age were identified as key prognostic risk factors using the SHAP. The combined model effectively stratified patients with stage II CRC into different prognostic risk groups, aiding clinical decision-making. Integrating CT images with clinicopathological information can facilitate the identification of patients with stage II CRC who are most likely to benefit from adjuvant chemotherapy. The effectiveness of adjuvant chemotherapy for stage II colorectal cancer remains debated. A combined model successfully identified high-risk stage II colorectal cancer patients. Shapley additive explanations enhance the interpretability of the model's predictions.

This study aimed to develop and assess an advanced Attention-Based Residual U-Net (ResUNet) model for accurately segmenting different types of brain hemorrhages from CT images. The goal was to overcome the limitations of manual segmentation and current automated methods regarding precision and generalizability. A dataset of 1,347 patient CT scans was collected retrospectively, covering six types of hemorrhages: subarachnoid hemorrhage (SAH, 231 cases), subdural hematoma (SDH, 198 cases), epidural hematoma (EDH, 236 cases), cerebral contusion (CC, 230 cases), intraventricular hemorrhage (IVH, 188 cases), and intracerebral hemorrhage (ICH, 264 cases). The dataset was divided into 80% for training using a 10-fold cross-validation approach and 20% for testing. All CT scans were standardized to a common anatomical space, and intensity normalization was applied for uniformity. The ResUNet model included attention mechanisms to enhance focus on important features and residual connections to support stable learning and efficient gradient flow. Model performance was assessed using the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and directed Hausdorff distance (dHD). The ResUNet model showed excellent performance during both training and testing. On training data, the model achieved DSC scores of 95 ± 1.2 for SAH, 94 ± 1.4 for SDH, 93 ± 1.5 for EDH, 91 ± 1.4 for CC, 89 ± 1.6 for IVH, and 93 ± 2.4 for ICH. IoU values ranged from 88 to 93, with dHD between 2.1- and 2.7-mm. Testing results confirmed strong generalization, with DSC scores of 93 for SAH, 93 for SDH, 92 for EDH, 90 for CC, 88 for IVH, and 92 for ICH. IoU values were also high, indicating precise segmentation and minimal boundary errors. The ResUNet model outperformed standard U-Net variants, achieving higher multi-label segmentation accuracy. This makes it a valuable tool for clinical applications that require fast and reliable brain hemorrhage analysis. Future research could investigate semi-supervised techniques and 3D segmentation to further enhance clinical use. Not applicable.

BackgroundConvolutional neural networks (CNNs) have emerged to reduce clinical resources and standardize auto-contouring of organs-at-risk (OARs). Although CNNs perform adequately for most patients, understanding when the CNN might fail is critical for effective and safe clinical deployment. However, the limitations of CNNs are poorly understood because of their black-box nature. Explainable artificial intelligence (XAI) can expose CNNs inner mechanisms for classification. Here, we investigate the inner mechanisms of CNNs for segmentation and explore a novel, computational approach to a-priori flag potentially insufficient parotid gland (PG) contours. MethodsFirst, 3D UNets were trained in three PG segmentation situations using (1) synthetic cases; (2) 1925 clinical computed tomography (CT) scans with typical and (3) more consistent contours curated through a previously validated auto-curation step. Then, we generated attribution maps for seven XAI methods, and qualitatively assessed them for congruency between simulated and clinical contours, and how much XAI agreed with expert reasoning. To objectify observations, we explored persistent homology intensity filtrations to capture essential topological characteristics of XAI attributions. Principal component (PC) eigenvalues of Euler characteristic profiles were correlated with spatial agreement (Dice-Sorensen similarity coefficient; DSC). Evaluation was done using sensitivity, specificity and the area under receiver operating characteristic (AUROC) curve on an external AAPM dataset, where as proof-of-principle, we regard the lowest 15% DSC as insufficient. ResultsPatternNet attributions (PNet-A) focused on soft-tissue structures, whereas guided backpropagation (GBP) highlighted both soft-tissue and high-density structures (e.g. mandible bone), which was congruent with synthetic situations. Both methods typically had higher/denser activations in better auto-contoured medial and anterior lobes. Curated models produced "cleaner" gradient class-activation mapping (GCAM) attributions. Quantitative analysis showed that PC{lambda}1 of guided GCAMs (GGCAM) Euler characteristic (EC) profile had good predictive value (sensitivity>0.85, specificity>0.9) of DSC for AAPM cases, with AUROC=0.66, 0.74, 0.94, 0.83 for GBP, GCAM, GGCAM and PNet-A. For for {lambda}1<-1.8e3 of GGCAMs EC-profile, 87% of cases were insufficient. ConclusionsGBP and PNet-A qualitatively agreed most with expert reasoning on directly (structure borders) and indirectly (proxies used for identifying structure borders) important features for PG segmentation. Additionally, this work investigated as proof-of-principle how topological data analysis could possibly be used for quantitative XAI signal analysis to a-priori mark potentially inadequate CNN-segmentations, using only features from inside the predicted PG. This work used PG as a well-understood segmentation paradigm and may extend to target volumes and other organs-at-risk.

Radiation-induced xerostomia is a common sequela in patients who undergo head and neck radiation therapy. This study aims to develop a three-dimensional deep learning model to predict xerostomia by fusing data from the gross tumor volume primary (GTVp) channel and parotid glands (PGs) channel. Retrospective data were collected from 180 head and neck cancer patients. Xerostomia was defined as xerostomia of grade ≥ 2 occurring in the 6th month of radiation therapy. The dataset was split into 137 cases (58.4% xerostomia, 41.6% non-xerostomia) for training and 43 (55.8% xerostomia, 44.2% non-xerostomia) for testing. XeroNet was composed of GNet, PNet, and a Naive Bayes decision fusion layer. GNet processed data from the GTVp channel (CT, dose distributions corresponding and the GTVp contours). PNet processed data from the PGs channel (CT, dose distributions and the PGs contours). The Naive Bayes decision fusion layer was used to integrate the results from GNet and PNet. Model performance was evaluated using accuracy, F-score, sensitivity, specificity, and area under the receiver operator characteristic curve (AUC). The proposed model achieved promising prediction results. The accuracy, AUC, F-score, sensitivity and specificity were 0.779, 0.858, 0.797, 0.777, and 0.782, respectively. Features extracted from the CT and dose distributions in the GTVp and PGs regions were used to construct machine learning models. However, the performance of these models was inferior to our method. Compared with recent studies on xerostomia prediction, our method also showed better performance. The proposed model could effectively extract features from the GTVp and PGs channels, achieving good performance in xerostomia prediction.

High-resolution CT (HR-CT) cannot image trabecular bone due to insufficient spatial resolution. Ultra-high-resolution CT may be a valuable alternative. We aimed to describe the accuracy of Canon Medical HR, super-high-resolution (SHR), and ultra-high-resolution (UHR)-CT in measuring trabecular bone microarchitectural parameters using micro-CT as a reference. Sixteen cadaveric distal tibial epiphyses were enrolled in this pre-clinical study. Images were acquired with HR-CT (i.e., 0.5 mm slice thickness/512² matrix) and SHR-CT (i.e., 0.25 mm slice thickness and 1024² matrix) with and without deep learning reconstruction (DLR) and UHR-CT (i.e., 0.25 mm slice thickness/2048² matrix) without DLR. Trabecular bone parameters were compared. Trabecular thickness was closest with UHR-CT but remained 1.37 times that of micro-CT (P < 0.001). With SHR-CT without and with DLR, it was 1.75 and 1.79 times that of micro-CT, respectively (P < 0.001), and 3.58 and 3.68 times that of micro-CT with HR-CT without and with DLR, respectively (P < 0.001). Trabecular separation was 0.7 times that of micro-CT with UHR-CT (P < 0.001), 0.93 and 0.94 times that of micro-CT with SHR-CT without and with DLR (P = 0.36 and 0.79, respectively), and 1.52 and 1.36 times that of micro-CT with HR-CT without and with DLR (P < 0.001). Bone volume/total volume was overestimated (i.e., 1.66 to 1.92 times that of micro-CT) by all techniques (P < 0.001). However, HR-CT values were superior to UHR-CT values (P = 0.03 and 0.01, without and with DLR, respectively). UHR and SHR-CT were the closest techniques to micro-CT and surpassed HR-CT.

Artificial intelligence and large language models (LLMs)-particularly GPT-4 and GPT-4o-have demonstrated high correct-answer rates in medical examinations. GPT-4o has enhanced diagnostic capabilities, advanced image processing, and updated knowledge. Japanese surgeons face critical challenges, including a declining workforce, regional health care disparities, and work-hour-related challenges. Nonetheless, although LLMs could be beneficial in surgical education, no studies have yet assessed GPT-4o's surgical knowledge or its performance in the field of surgery. This study aims to evaluate the potential of GPT-4 and GPT-4o in surgical education by using them to take the Japan Surgical Board Examination (JSBE), which includes both textual questions and medical images-such as surgical and computed tomography scans-to comprehensively assess their surgical knowledge. We used 297 multiple-choice questions from the 2021-2023 JSBEs. The questions were in Japanese, and 104 of them included images. First, the GPT-4 and GPT-4o responses to only the textual questions were collected via OpenAI's application programming interface to evaluate their correct-answer rate. Subsequently, the correct-answer rate of their responses to questions that included images was assessed by inputting both text and images. The overall correct-answer rates of GPT-4o and GPT-4 for the text-only questions were 78% (231/297) and 55% (163/297), respectively, with GPT-4o outperforming GPT-4 by 23% (P=<.01). By contrast, there was no significant improvement in the correct-answer rate for questions that included images compared with the results for the text-only questions. GPT-4o outperformed GPT-4 on the JSBE. However, the results of the LLMs were lower than those of the examinees. Despite the capabilities of LLMs, image recognition remains a challenge for them, and their clinical application requires caution owing to the potential inaccuracy of their results.