RATIONALE AND OBJECTIVES:Radiology residency often fails to account for individual differences between residents or provide sufficient exposure to diverse pathologies. We sought to evaluate whether artificial intelligence (AI)-enabled "Precision Education" can accurately identify and address individual radiology resident pathology exposure gaps through supplemental personalized teaching cases. MATERIALS AND METHODS:A curriculum outlined types and frequencies of important pathologies (IPs) residents should encounter during postgraduate years 2 through 4 (PGY-2 through PGY-4). Daily resident "live" clinical reports were analyzed by ChatGPT-4o prompts to detect IPs encountered. Each resident's live cases were then supplemented with curated anonymized teaching cases, with priority given to IPs encountered below curriculum-defined target thresholds to date. Volumes and IP exposure were compared between pre- (2022-2023) and postintervention (2024-2025) academic years. RESULTS:ChatGPT-4o demonstrated over 91% precision and recall in accurately identifying IPs. Unique IPs encountered by residents significantly increased postintervention from median 75-107 to 93.5-144 in abdominal, 43.5-70 to 73-99 in musculoskeletal, 32.5-38 to 64.5-79 in neuro-, 39.5-49 to 82-96.5 in pediatric, and 42.5-56 to 49.3-85.3 in thoracic imaging (all p < 0.05). Residents met significantly more curriculum-defined targets postintervention, increasing from a median 54-64 to 78.5-131.5 in abdominal, 21-49 to 51.5-75.5 in musculoskeletal, 3.5-9 to 21-38 in neuro-, 13.5-21 to 51.5-72 in pediatric, and 12.5-33 to 23-58 in thoracic imaging (all p < 0.05). Median live case interpretations were not significantly reduced by the intervention, aside from PGY-3 abdominal imaging cases (p = 0.0489). CONCLUSION:Personalized AI-enabled Precision Education accurately identified resident pathology exposure gaps, enhanced exposure to IPs, and maintained clinical training opportunities.

There is a body‐wide network of interstitial spaces that includes three components: a large‐scale fascial network made up of fluid‐filled spaces containing collagens and other extracellular matrix components like hyaluronic acid (HA), the peri‐vascular/capillary interstitium, and intercellular interstitial spaces. Staining for HA within the colon, skin, and liver has demonstrated spatial continuity of the fascial interstitium across tissue layers and between organs, while continuity of HA staining between perineurial and adventitial sheathes beyond organ boundaries confirmed that they also participate in this body‐wide network. We asked whether the pulmonary interstitium comprises a continuous organ‐wide network that also connects to the body‐wide interstitium via routes along nerves and the vasculature. We studied archival lung lobectomy specimens containing normal tissues inclusive of all lung anatomical units from six females and three males (mean age 53+/− 16.5 years). For comparison, we also studied normal mouse lung. Multiplex immunohistochemical cocktails were used to identify: (1) HA, CD34, and vimentin – highlighting interstitium; (2) HA, CD34, and podoplanin (D2‐40) – highlighting relationships between the interstitium, vasculature, and lymphatics. Sizes of extracellular APP were measured. Tissues from nine patients (six females, three males, mean age 53+/− 16.5 years) were studied. HA staining was continuous throughout the five major anatomic compartments of the lung: alveolar walls, subpleural connective tissue, centrilobular peribronchovascular compartment, interlobular septal compartment, and axial peribronchovascular of the hilum, with similar findings in murine lung tissue. Continuity with interstitial spaces of the perineurium and adventitia was confirmed. The distribution of APP corresponded to known routes of lymphatic drainage, superficial and deep. APP within perineurium and perivascular adventitia further demonstrated continuity between intra‐ and extrapulmonary interstitium. To conclude, all segments of the lung interstitium are connected and are linked along nerves and the vascular tree to a body‐wide communication network. These findings have significant implications for understanding lung physiology and pathobiology, suggesting routes of passage for inflammatory cells and mediators, malignant cells, and infectious agents. Interstitial spaces may be important in microbiome signaling within and beyond the lung and may be a component of the lung–brain axis.

Surgical approaches to lung cancer resection are rapidly evolving, particularly for early-stage lung cancer. Advances in chest CT technology and increasing use of CT in patient care have led to detection of smaller nodules, many with ground-glass attenuation that do not require lobectomy for resection. Lung-sparing and minimally invasive techniques have been shown to result in improved patient outcomes compared with those of traditional open thoracotomy and are noninferior in terms of cancer recurrence. As more patients undergo these surgeries, it is important for radiologists to be aware of useful information for surgeons before the operation. It is helpful for radiologists to understand the indications for lung-sparing surgery and have a basic understanding of the techniques involved in video-assisted and robotic thoracic operations. Identification of the location and morphology of the tumor, as well as the pulmonary vasculature that feeds and drains the segment of lung containing the tumor is important. Also, the presence of emphysema, pulmonary fibrosis, and incomplete fissures is useful information. In addition, chest imaging is also progressing, with improvements in multiplanar reformations and three-dimensional imaging allowing for more detailed and accurate image-based localization of tumors and visualization of anatomy. Nodule localization for surgery plays an even larger role given the limited ability to palpate nodules during surgery with minimally invasive surgery approaches. Methods can involve imaging and in vivo localization, with transthoracic and bronchoscopic methods used to label a nodule. Finally, radiologists should be aware of postoperative complications and their imaging characteristics, such as suture line granulomas and bronchopleural fistulas. Supplemental material is available for this article. ©RSNA, 2025.

SSNs, including both pGGNs and PSNs, may relate to inflammatory or neoplastic etiologies. When persistence is established on follow-up imaging studies, SSNs are likely to be adenocarcinoma spectrum lesions. Developing or progressing solid components within SSNs are associated with invasive adenocarcinoma and other aggressive features, usually with good radiologic-pathologic correlation. Awareness of nodule features and growth that affect management and potential pitfalls that can occur is helpful. Various guidelines have been published, including by the Fleischner Society, which serve as useful guides for SSN management.

This international multisociety consensus statement, developed by 21 thoracic radiologists and reviewed by four pulmonology experts, aims to standardize chest CT indications, acquisition, and reporting of post–COVID-19 residual CT lung abnormalities.

Photon -counting CT (PCCT) is an emerging advanced CT technology that differs from conventional CT in its ability to directly convert incident x-ray photon energies into electrical signals. The detector design also permits substantial improvements in spatial resolution and radiation dose efficiency and allows for concurrent high -pitch and high -temporal -resolution multienergy imaging. This review summarizes (a) key differences in PCCT image acquisition and image reconstruction compared with conventional CT; (b) early evidence for the clinical benefit of PCCT for high -spatial -resolution diagnostic tasks in thoracic imaging, such as assessment of airway and parenchymal diseases, as well as benefits of high -pitch and multienergy scanning; (c) anticipated radiation dose reduction, depending on the diagnostic task, and increased utility for routine low -dose thoracic CT imaging; (d) adaptations for thoracic imaging in children; (e) potential for further quantitation of thoracic diseases; and (f) limitations and trade-offs. Moreover, important points for conducting and interpreting clinical studies examining the benefit of PCCT relative to conventional CT and integration of PCCT systems into multivendor, multispecialty radiology practices are discussed. (c) RSNA, 2024 Supplemental material is available for this article.

Imaging plays a major role in the care of the intensive care unit (ICU) patients. An understanding of the monitoring devices is essential for the interpretation of imaging studies. An awareness of their expected locations aids in identifying complications in a timely manner. This review describes the imaging of ICU monitoring and support catheters, tubes, and pulmonary and cardiac devices, some more commonly encountered and others that have been introduced into clinical patient care more recently. Special focus will be placed on chest radiography and potential pitfalls encountered.

Imaging plays a major role in the care of the intensive care unit (ICU) patients. An understanding of the monitoring devices is essential for the interpretation of imaging studies. An awareness of their expected locations aids in identifying complications in a timely manner. This review describes the imaging of ICU monitoring and support catheters, tubes, and pulmonary and cardiac devices, some more commonly encountered and others that have been introduced into clinical patient care more recently. Special focus will be placed on chest radiography and potential pitfalls encountered.

A strong understanding of radiation techniques, including CRT and SBRT, and the expected posttherapy imaging manifestations enables more confident and accurate interpretations of surveillance CT imaging studies in patients with prior RT. Knowledge of common complications and corresponding CT imaging appearances, particularly tumor recurrence and infection, leads to more accurate diagnoses, timely treatment, and avoidance of pitfalls in interpretation.

Distinguishing post-COVID-19 residual abnormalities from interstitial lung abnormalities (ILA) on CT can be challenging if clinical information is limited. This study aimed to evaluate the diagnostic performance of radiologists in distinguishing post-COVID-19 residual abnormalities from ILA. This multi-reader, multi-case study included 60 age- and sex-matched subjects with chest CT scans. There were 40 cases of ILA (20 fibrotic and 20 non-fibrotic) and 20 cases of post-COVID-19 residual abnormalities. Fifteen radiologists from multiple nations with varying levels of experience independently rated suspicion scores on a 5-point scale to distinguish post-COVID-19 residual abnormalities from fibrotic ILA or non-fibrotic ILA. Interobserver agreement was assessed using the weighted κ value, and the scores of individual readers were compared with the consensus of all readers. Receiver operating characteristic curve analysis was conducted to evaluate the diagnostic performance of suspicion scores for distinguishing post-COVID-19 residual abnormalities from ILA and for differentiating post-COVID-19 residual abnormalities from both fibrotic and non-fibrotic ILA. Radiologists’ diagnostic performance for distinguishing post-COVID-19 residual abnormalities from ILA was good (area under the receiver operating characteristic curve (AUC) range, 0.67–0.92; median AUC, 0.85) with moderate agreement (κ = 0.56). The diagnostic performance for distinguishing post-COVID-19 residual abnormalities from non-fibrotic ILA was lower than that from fibrotic ILA (median AUC = 0.89 vs. AUC = 0.80, p = 0.003). Radiologists demonstrated good diagnostic performance and moderate agreement in distinguishing post-COVID-19 residual abnormalities from ILA, but careful attention is needed to avoid misdiagnosing them as non-fibrotic ILA. Question How good are radiologists at differentiating interstitial lung abnormalities (ILA) from changes related to COVID-19 infection? Findings Radiologists had a median AUC of 0.85 in distinguishing post-COVID-19 abnormalities from ILA with moderate agreement (κ = 0.56). Clinical relevance Radiologists showed good diagnostic performance and moderate agreement in distinguishing post-COVID-19 residual abnormalities from ILA; nonetheless, caution is needed in distinguishing residual abnormalities from non-fibrotic ILA.

OBJECTIVES:To evaluate the clinical significance of low-field MRI lung opacity severity. METHODS:Retrospective cross-sectional analysis of post-acute Covid-19 patients imaged with low-field MRI from 9/2020 through 9/2022, and within 1 month of pulmonary function tests (PFTs), 6-min walk test (6mWT), and symptom inventory (SI), and/or within 3 months of St. George Respiratory Questionnaire (SGRQ) was performed. Univariate and correlative analyses were performed with Wilcoxon, Chi-square, and Spearman tests. The association between disease and demographic factors and MR opacity severity, PFTs, 6mWT, SI, and SGRQ, and association between MR opacity severity with functional and patient-reported outcomes (PROs), was evaluated with mixed model analysis of variance, covariance and generalized estimating equations. Two-sided 5 % significance level was used, with Bonferroni multiple comparison correction. RESULTS:81 MRI exams in 62 post-acute Covid-19 patients (median age 57, IQR 41-64; 25 women) were included. Exams were a median of 8 months from initial illness. Univariate analysis showed lung opacity severity was associated with decreased %DLCO (ρ = -0.55, P = .0125), and lung opacity severity quartile was associated with decreased %DLCO, predicted TLC, FVC, and increased FEV1/FVC. Multivariable analysis adjusting for sex, initial disease severity, and interval from Covid-19 diagnosis showed MR lung opacity severity was associated with decreased %DLCO (P < .001). Lung opacity severity was not associated with PROs. CONCLUSION:Low-field MRI lung opacity severity correlated with decreased %DLCO in post-acute Covid-19 patients, but was not associated with PROs.

Purpose To determine the performance of volumetric dual energy low kV and iodine radiomic features for the differentiation of intrathoracic lymph node histopathology, and influence of contrast protocol. Materials and methods Intrathoracic lymph nodes with histopathologic correlation (neoplastic, granulomatous sarcoid, benign) within 90 days of DECT chest imaging were volumetrically segmented. 1691 volumetric radiomic features were extracted from iodine maps and low-kV images, totaling 3382 features. Univariate analysis was performed using 2-sample t-test and filtered for false discoveries. Multivariable analysis was used to compute AUCs for lymph node classification tasks. Results 129 lymph nodes from 72 individuals (mean age 61 ± 15 years) were included, 52 neoplastic, 51 benign, and 26 granulomatous-sarcoid. Among all contrast enhanced DECT protocol exams (routine, PE and CTA), univariable analysis demonstrated no significant differences in iodine and low kV features between neoplastic and non-neoplastic lymph nodes; in the subset of neoplastic versus benign lymph nodes with routine DECT protocol, 199 features differed (p = .01- < 0.05).Multivariable analysis using both iodine and low kV features yielded AUCs >0.8 for differentiating neoplastic from non-neoplastic lymph nodes (AUC 0.86), including subsets of neoplastic from granulomatous (AUC 0.86) and neoplastic from benign (AUC 0.9) lymph nodes, among all contrast protocols. Conclusions Volumetric DECT radiomic features demonstrate strong collective performance in differentiation of neoplastic from non-neoplastic intrathoracic lymph nodes, and are influenced by contrast protocol.

PURPOSE:Apical pleuroparenchymal scarring (APPS) is commonly seen on chest computed tomography (CT), though the imaging and clinical features, to the best of our knowledge, have never been studied. The purpose was to understand APPS's typical morphologic appearance and associated clinical features. PATIENTS AND METHODS:A random generator selected 1000 adult patients from all 21516 chest CTs performed at urban outpatient centers from January 1, 2016 to December 31, 2016. Patients with obscuring apical diseases were excluded to eliminate confounding factors. After exclusions, 780 patients (median age: 64 y; interquartile range: 56 to 72 y; 55% males) were included for analysis. Two radiologists evaluated the lung apices of each CT for the extent of abnormality in the axial plane (mild: <5 mm, moderate: 5 to 10 mm, severe: >10 mm), craniocaudal plane (extension halfway to the aortic arch, more than halfway, vs below the arch), the predominant pattern (nodular vs reticular and symmetry), and progression. Cohen kappa coefficient was used to assess radiologists' agreement in scoring. Ordinal logistic regression was used to determine associations of clinical and imaging variables with APPS. RESULTS:APPS was present on 65% (507/780) of chest CTs (54% mild axial; 80% mild craniocaudal). The predominant pattern was nodular and symmetric. Greater age, female sex, lower body mass index, greater height, and white race were associated with more extensive APPS. APPS was not found to be associated with lung cancer in this cohort. CONCLUSION:Classifying APPS by the extent of disease in the axial or craniocaudal planes, in addition to the predominant pattern, enabled statistically significant associations to be determined, which may aid in understanding the pathophysiology of apical scarring and potential associated risks.

TOPIC IMPORTANCE: Chest CT imaging holds a major role in the diagnosis of lung diseases, many of which affect the peribronchovascular region. Identification and categorization of peribronchovascular abnormalities on CT imaging can assist in formulating a differential diagnosis and directing further diagnostic evaluation. REVIEW FINDINGS: The peribronchovascular region of the lung encompasses the pulmonary arteries, airways, and lung interstitium. Understanding disease processes associated with structures of the peribronchovascular region and their appearances on CT imaging aids in prompt diagnosis. This article reviews current knowledge in anatomic and pathologic features of the lung interstitium composed of intercommunicating prelymphatic spaces, lymphatics, collagen bundles, lymph nodes, and bronchial arteries; diffuse lung diseases that present in a peribronchovascular distribution; and an approach to classifying diseases according to patterns of imaging presentations. Lung peribronchovascular diseases can appear on CT imaging as diffuse thickening, fibrosis, masses or masslike consolidation, ground-glass or air space consolidation, and cysts, acknowledging that some diseases may have multiple presentations. SUMMARY: A category approach to peribronchovascular diseases on CT imaging can be integrated with clinical features as part of a multidisciplinary approach for disease diagnosis.

Radiation therapy is part of a multimodality treatment approach to lung cancer. The radiologist must be aware of both the expected and the unexpected imaging findings of the post–radiation therapy patient, including the time course for development of post– radiation therapy pneumonitis and fibrosis. In this review, a brief discussion of radiation therapy techniques and indications is presented, followed by an image-heavy differential diagnostic approach. The review focuses on computed tomography imaging examples to help distinguish normal postradiation pneumonitis and fibrosis from alternative complications, such as infection, local recurrence, or radiation-induced malignancy.

PURPOSE:The purpose of this study was to identify differences in imaging features between patients with confirmed right middle lobe (RML) torsion compared to those suspected yet without torsion. MATERIALS AND METHODS:This retrospective study entailing a search of radiology reports from April 1, 2014, to April 15, 2021, resulted in 52 patients with suspected yet without lobar torsion and 4 with confirmed torsion, supplemented by 2 additional cases before the search period for a total of 6 confirmed cases. Four thoracic radiologists (1 an adjudicator) evaluated chest radiographs and computed tomography (CT) examinations, and Fisher exact and Mann-Whitney tests were used to identify any significant differences in imaging features ( P <0.05). RESULTS:A reversed halo sign was more frequent for all readers ( P= 0.001) in confirmed RML torsion than patients without torsion (83.3% vs. 0% for 3 readers, one the adjudicator). The CT coronal bronchial angle between RML bronchus and bronchus intermedius was larger ( P= 0.035) in torsion (121.28 degrees) than nontorsion cases (98.26 degrees). Patients with torsion had a higher percentage of ground-glass opacity in the affected lobe ( P= 0.031). A convex fissure towards the adjacent lobe on CT ( P= 0.009) and increased lobe volume on CT ( P= 0.001) occurred more often in confirmed torsion. CONCLUSION:A reversed halo sign, larger CT coronal bronchial angle, greater proportion of ground-glass opacity, fissural convexity, and larger lobe volume on CT may aid in early recognition of the rare yet highly significant diagnosis of lobar torsion.

Incidental pulmonary nodules are common. Although the majority are benign, most are indeterminate for malignancy when first encountered making their management challenging. CT remains the primary imaging modality to first characterize and follow-up incidental lung nodules. This document reviews available literature on various imaging modalities and summarizes management of indeterminate pulmonary nodules detected incidentally. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Purpose To assess deep learning denoised (DLD) computed tomography (CT) chest images at various low doses by both quantitative and qualitative perceptual image analysis. Methods Simulated noise was inserted into sinogram data from 32 chest CTs acquired at 100 mAs, generating anatomically registered images at 40, 20, 10, and 5 mAs. A DLD model was developed, with 23 scans selected for training, 5 for validation, and 4 for test. Quantitative analysis of perceptual image quality was assessed with Structural SIMilarity Index (SSIM) and Fréchet Inception Distance (FID). Four thoracic radiologists graded overall diagnostic image quality, image artifact, visibility of small structures, and lesion conspicuity. Noise-simulated and denoised image series were evaluated in comparison with one another, and in comparison with standard 100 mAs acquisition at the 4 mAs levels. Statistical tests were conducted at the 2-sided 5% significance level, with multiple comparison correction. Results At the same mAs levels, SSIM and FID between noise-simulated and reconstructed DLD images indicated that images were closer to a perfect match with increasing mAs (closer to 1 for SSIM, and 0 for FID). In comparing noise-simulated and DLD images to standard-dose 100-mAs images, DLD improved SSIM and FID. Deep learning denoising improved SSIM of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in SSIM from 0.91 to 0.94, 0.87 to 0.93, 0.67 to 0.87, and 0.54 to 0.84, respectively. Deep learning denoising improved FID of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in FID from 20 to 13, 46 to 21, 104 to 41, and 148 to 69, respectively. Qualitative image analysis showed no significant difference in lesion conspicuity between DLD images at any mAs in comparison with 100-mAs images. Deep learning denoising images at 10 and 5 mAs were rated lower for overall diagnostic image quality (P < 0.001), and at 5 mAs lower for overall image artifact and visibility of small structures (P = 0.002), in comparison with 100 mAs. Conclusions Deep learning denoising resulted in quantitative improvements in image quality. Qualitative assessment demonstrated DLD images at or less than 10 mAs to be rated inferior to standard-dose images.