With the advent of deep learning algorithms, fully automated radiological image analysis is within reach. In spine imaging, several atlas- and shape-based as well as deep learning segmentation algorithms have been proposed, allowing for subsequent automated analysis of morphology and pathology. The first “Large Scale Vertebrae Segmentation Challenge” (VerSe 2019) showed that these perform well on normal anatomy, but fail in variants not frequently present in the training dataset. Building on that experience, we report on the largely increased VerSe 2020 dataset and results from the second iteration of the VerSe challenge (MICCAI 2020, Lima, Peru). VerSe 2020 comprises annotated spine computed tomography (CT) images from 300 subjects with 4142 fully visualized and annotated vertebrae, collected across multiple centres from four different scanner manufacturers, enriched with cases that exhibit anatomical variants such as enumeration abnormalities (n = 77) and transitional vertebrae (n = 161). Metadata includes vertebral labelling information, voxel-level segmentation masks obtained with a human-machine hybrid algorithm and anatomical ratings, to enable the development and benchmarking of robust and accurate segmentation algorithms.

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and are typically constrained to binary counterfactuals. In contrast, we propose a novel method that operates directly on the latent space of a generative model, specifically a Diffusion Autoencoder (DAE). This approach offers inherent interpretability by enabling the generation of CEs and the continuous visualization of the model’s internal representation across decision boundaries. Our method leverages the DAE’s ability to encode images into a semantically rich latent space in an unsupervised manner, eliminating the need for labeled data or separate feature extraction models. We show that these latent representations are helpful for medical condition classification and the ordinal regression of severity pathologies, such as vertebral compression fractures (VCF) and diabetic retinopathy (DR). Beyond binary CEs, our method supports the visualization of ordinal CEs using a linear model, providing deeper insights into the model’s decision-making process and enhancing interpretability. Experiments across various medical imaging datasets demonstrate the method’s advantages in interpretability and versatility. The linear manifold of the DAE’s latent space allows for meaningful interpolation and manipulation, making it a powerful tool for exploring medical image properties. Our code is available at https://github.com/matanat/dae_counterfactual

Background: Most artificial intelligence (AI) systems are restricted to solving a pre-defined task, thus limiting their generalizability to unselected datasets. Anomaly detection relieves this shortfall by flagging all pathologies as deviations from a learned norm. Here, we investigate whether diagnostic accuracy and reporting times can be improved by an anomaly detection tool for head computed tomography (CT), tailored to provide patient-level triage and voxel-based highlighting of pathologies. Methods: Four neuroradiologists with 1–10 years of experience each investigated a set of 80 routinely acquired head CTs containing 40 normal scans and 40 scans with common pathologies. In a random order, scans were investigated with and without AI-predictions. A 4-week wash-out period between runs was included to prevent a reminiscence effect. Performance metrics for identifying pathologies, reporting times, and subjectively assessed diagnostic confidence were determined for both runs. Results: AI-support significantly increased the share of correctly classified scans (normal/pathological) from 309/320 scans to 317/320 scans (p = 0.0045), with a corresponding sensitivity, specificity, negative- and positive- predictive value of 100%, 98.1%, 98.2% and 100%, respectively. Further, reporting was significantly accelerated with AI-support, as evidenced by the 15.7% reduction in reporting times (65.1 ± 8.9 s vs. 54.9 ± 7.1 s; p < 0.0001). Diagnostic confidence was similar in both runs. Conclusion: Our study shows that AI-based triage of CTs can improve the diagnostic accuracy and accelerate reporting for experienced and inexperienced radiologists alike. Through ad hoc identification of normal CTs, anomaly detection promises to guide clinicians towards scans requiring urgent attention.

Background: Cocaine use disorder (CUD) is a global health issue with severe behavioral and cognitive sequelae. While previous evidence suggests a variety of structural and age-related brain changes in CUD, the impact on both, cortical thickness and brain age measures remains unclear.Methods: Derived from a publicly available data set (SUDMEX_CONN), 74 CUD patients and 62 matched healthy controls underwent brain MRI and behavioral-clinical assessment. We determined cortical thickness by surface-based morphometry using CAT12 and Brain Age Gap Estimate (BrainAGE) via relevance vector regression. Associations between structural brain changes and behavioral-clinical variables of patients with CUD were investigated by correlation analyses.Results: We found significantly lower cortical thickness in bilateral prefrontal cortices, posterior cingulate cortices, and the temporoparietal junction and significantly increased BrainAGE in patients with CUD [mean (SD) = 1.97 (±3.53)] compared to healthy controls (p < 0.001, Cohen’s d = 0.58). Increased BrainAGE was associated with longer cocaine abuse duration.Conclusion: Results demonstrate structural brain abnormalities in CUD, particularly lower cortical thickness in association cortices and dose-dependent, increased brain age.

Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate between benign and malignant vertebral fractures. Materials and Methods CT scans acquired in patients with benign or malignant vertebral fractures from June 2005 to December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic and radiologic information. An internal test set was randomly selected, and an external test set was obtained from an additional hospital. Models used a three-dimensional U-Net encoder-classifier architecture and applied data augmentation during training. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared with that of two residents and one fellowship-trained radiologist using the DeLong test. Results The training set included 381 patients (mean age, 69.9 years ± 11.4 [SD]; 193 male) with 1307 vertebrae (378 benign fractures, 447 malignant fractures, 482 malignant lesions). Internal and external test sets included 86 (mean age, 66.9 years ± 12; 45 male) and 65 (mean age, 68.8 years ± 12.5; 39 female) patients, respectively. The better-performing model of two training approaches achieved AUCs of 0.85 (95% CI: 0.77, 0.92) in the internal and 0.75 (95% CI: 0.64, 0.85) in the external test sets. Including an uncertainty category further improved performance to AUCs of 0.91 (95% CI: 0.83, 0.97) in the internal test set and 0.76 (95% CI: 0.64, 0.88) in the external test set. The AUC values of residents were lower than that of the best-performing model in the internal test set (AUC, 0.69 [95% CI: 0.59, 0.78] and 0.71 [95% CI: 0.61, 0.80]) and external test set (AUC, 0.70 [95% CI: 0.58, 0.80] and 0.71 [95% CI: 0.60, 0.82]), with significant differences only for the internal test set (P < .001). The AUCs of the fellowship-trained radiologist were similar to those of the best-performing model (internal test set, 0.86 [95% CI: 0.78, 0.93; P = .39]; external test set, 0.71 [95% CI: 0.60, 0.82; P = .46]). Conclusion Developed models showed a high discriminatory power to differentiate between benign and malignant vertebral fractures, surpassing or matching the performance of radiology residents and matching that of a fellowship-trained radiologist. © RSNA, 2024 See also the editorial by Booz and D'Angelo in this issue.

Despite substantial neuroscience research in the last decade revealing the claustrum's prominent role in mammalian forebrain organization, as evidenced by its extraordinarily widespread connectivity pattern, claustrum studies in humans are rare. This is particularly true for studies focusing on claustrum connections. Two primary reasons may account for this situation: First, the intricate anatomy of the human claustrum located between the external and extreme capsule hinders straightforward and reliable structural delineation. In addition, the few studies that used diffusion‐weighted‐imaging (DWI)‐based tractography could not clarify whether in vivo tractography consistently and reliably identifies claustrum connections in humans across different subjects, cohorts, imaging methods, and connectivity metrics. To address these issues, we combined a recently developed deep‐learning‐based claustrum segmentation tool with DWI‐based tractography in two large adult cohorts: 81 healthy young adults from the human connectome project and 81 further healthy young participants from the Bavarian longitudinal study. Tracts between the claustrum and 13 cortical and 9 subcortical regions were reconstructed in each subject using probabilistic tractography. Probabilistic group average maps and different connectivity metrics were generated to assess the claustrum's connectivity profile as well as consistency and replicability of tractography. We found, across individuals, cohorts, DWI‐protocols, and measures, consistent and replicable cortical and subcortical ipsi‐ and contralateral claustrum connections. This result demonstrates robust in vivo tractography of claustrum connections in humans, providing a base for further examinations of claustrum connectivity in health and disease.