Citations

Abstract Respiratory bronchiolitis-associated interstitial lung disease (RB-ILD) and alveolar macrophage pneumonia (AMP) are two rare but closely related conditions within the spectrum of smoking-related interstitial pneumonias. Both share characteristic histopathologic features, including the accumulation of pigmented alveolar macrophages alongside varying degrees of interstitial inflammation and fibrosis. RB-ILD is typically a localized, bronchiolocentric process often found in smokers, whereas AMP represents a more diffuse and clinically significant disease that may arise not only from tobacco smoke but also from other causes such as occupational exposures, autoimmune diseases, and drug reactions. This review highlights the clinical presentation, imaging findings, histopathology, and treatment of both entities, emphasizing their overlapping features as well as key distinctions. We further discuss the pathogenic mechanisms driven by cigarette smoke—including oxidative stress, immune activation, and fibrosis—that underlie these diseases. A clear understanding of the similarities and differences between RB-ILD and AMP is essential for accurate diagnosis, effective management, and prognostication, particularly in patients with a history of smoking and diffuse parenchymal lung involvement.

Abstract Background Photon‐counting‐detector (PCD) CT systems offer ultra‐high spatial resolution, yet the visual spatial resolution on clinical images often constrained by large pixel size, yielding resolutions below system capabilities. While reducing pixel size and using sharp kernels enhance visual spatial resolution, it increases noise, compromising image quality. Purpose To investigate the combined effects of pixel size and reconstruction kernels on visual spatial resolution using phantom and clinical images and to develop a dedicated high‐resolution deep convolutional neural network (HR‐CNN) to better utilize the intrinsic high spatial resolution of PCD‐CT in clinical imaging. Methods The relationship between spatial resolution, reconstruction kernel, and pixel size was investigated to identify strategies for utilizing the full spatial resolution potential of PCD‐CT. To overcome the increased noise associated with high‐resolution settings, a dedicated HR‐CNN was developed to push the limit of spatial resolution in routine PCD‐CT exams. The HR‐CNN was trained using patient exams acquired with ultra‐high‐resolution (UHR) mode and reconstructed with a 150‐mm field of view (FOV), matrix size of 1024×1024 (0.15‐mm pixel size) and sharpest quantitative kernel (Qr89). The impact of FOV, kernel, and denoising on spatial resolution was studied using bar‐pattern phantoms and a pilot clinical evaluation including 5 patients with interstitial lung diseases. Two thoracic radiologists evaluated 4 different FOV/reconstruction conditions: (1) FOV‐410/Qr56‐Iterative reconstruction (IR), (2) FOV‐410/Qr89‐IR, (3) FOV‐150/Qr89‐IR, and (4) FOV‐150/Qr89‐HR‐CNN in terms of overall image quality, noise, visual spatial resolution, and overall preference. Results With a FOV of 410 mm, the Qr89 sharp kernel displayed bar‐patterns up to 14 lp/cm, not much higher than the routine lung kernel Qr56. When the FOV was reduced to 150 mm, Qr89‐IR allowed for the visualization of line pair patterns ranging from 18 to 20 lp/cm, with 20 lp/cm being moderately discernible. The application of Qr89‐HR‐CNN yielded further improvement, enabling the display of line pair patterns as high as 20–22 lp/cm. In patient cases, both radiologists consistently ranked the FOV‐150 images processed with HR‐CNN as superior across metrics including overall image quality, noise reduction, visual spatial resolution, and overall preference. The HR‐CNN reduced the noise in patients’ images by 93.0 ± 0.6% and 44.9 ± 5.3% in comparison with the original FBP and IR images, respectively. Conclusions The spatial resolution of PCD‐CT is not maximized in routine practice due to the large FOV and high noise levels at sharp kernels. The proposed HR‐CNN denoising method, along with small pixel size, may allow the high spatial resolution toward the system limit to be implemented in practice, which is beneficial in the diagnosis of many diseases, including interstitial lung disease.

Quantitative imaging is an innovative noninvasive tool for interstitial lung disease evaluation, providing objective, reproducible metrics for diagnosis, monitoring, and prognostic assessment.

Objectives: To determine the feasibility of reduced-dose chest computed tomographic angiography (CTA) with convolutional neural network (CNN) denoising for detecting pulmonary arteriovenous malformations (pAVMs) in children with hereditary hemorrhagic telangiectasia (cwHHT). Methods: Fifteen cwHHT underwent a chest CTA (ie, a controlled “study” dose). Noise was inserted to simulate a quarter dose (QD) exam. Images were reconstructed using iterative reconstruction (IR) and our self-trained CNN denoising model. For each case, 3 sets of images were created: study dose (SD)+IR, QD+IR, and QD+CNN. Two thoracic radiologists independently scored each set to assess quality, spatial resolution, artifacts, and the presence of pAVMs using 4-level ordinal scales. Quantitative assessments of image quality were performed using contrast-to-noise ratios (CNRs) with comparisons made between the experimental conditions. Results: Thirteen of the 15 patients recruited with hereditary hemorrhagic telangiectasia (mean age: 9.3±4.5 y) were positive for pAVM by transthoracic contrast echocardiography. The sensitivities using QD+CNN were 0.85 and 1.00 for readers 1 and 2, respectively. This was compared with 0.69 and 0.84 using QD+IR versus 0.85 and 0.92 for SD+IR. Inter-reader agreement for pAVM detection utilizing QD+CNN was moderate and resulted in kappa=0.59 ( P =0.012). The subjective assessments for QD+CNN were comparable to the SD technique. Regression analysis of reader scores revealed improved quality in QD+CNN versus QD+IR ( P =0.001). Similarly, the QD+CNN condition demonstrated the highest CNRs. Conclusions: Reduced-dose chest CTA with CNN denoising provides a level of sensitivity comparable to standard dose CTA and high CNRs for the detection of pAVMs in cwHHT.

The Society of Thoracic Radiology (STR) membership enthusiastically embraced the launch of its mentorship program, with peaks in participation and engagement after annual meetings and during the COVID pandemic. The program provides a valuable resource for early to mid-career thoracic radiologists, especially those lacking local resources. This report describes the program’s inception and design, and summarizes the program’s successes and challenges at 5 years, based on a 2023 mentorship survey. STR mentees, spanning early to mid-career stages, most frequently sought mentorship in career development, graduate medical education, research portfolio development, publishing, cardiac imaging, grant funding, and artificial intelligence. Mentors offered expertise in these areas, plus lung cancer screening, career development, and workplace navigation. The committee prioritized creating dyads based on mutual interest and expertise, achieving mutual top-choice match rates of 70% to 97%. Enduring dyads flourished as the program matured. At 5 years, a survey of participants was fielded. Mentees reported moderate to high program impact on scholarly activities, leadership, networking, clinical service, education, and career satisfaction. Mentors described satisfaction in their roles, highlighting networking, career satisfaction, and the opportunity to influence upcoming generations of cardiothoracic radiologists, thereby impacting the field’s future. Most participants expressed high career satisfaction. Descriptive comments further enriched findings. Survey results confirmed that strengthening dyad formation and enhancing mentoring outcomes remain pivotal. Remote mentorship, while valuable, presents challenges—personal connections and contextual familiarity, considered essential to successful mentorship relationships, are typically absent in these settings. Activities to potentially enhance the STR mentorship program are offered.

Diffuse idiopathic pulmonary neuroendocrine cell hyperplasia (DIPNECH) is a rare, but increasingly recognized entity that primarily affects middle-aged and elderly women. It is characterized by abnormal proliferation of pulmonary neuroendocrine cells (PNECs) and is considered a preinvasive lesion for carcinoid tumorlets/tumors. Sometimes, DIPNECH is accompanied by constrictive bronchiolitis which usually manifests as chronic cough and/or dyspnea, along with airflow limitation on spirometry. The telltale imaging sign of DIPNECH is the presence of multiple noncalcified pulmonary nodules and mosaic attenuation on CT. However, these clinico-radiologic features of DIPNECH are characteristic but nonspecific; thus, histopathologic confirmation is usually necessary. DIPNECH has an indolent course and only rarely leads to respiratory failure or death; progression to overt neuroendocrine tumor (carcinoid) of the lung occurs in a minority of patients. Of available therapies, somatostatin analogs and mechanistic target of rapamycin inhibitors are the most promising. In this review, we provide an update regarding the diagnosis and management of DIPNECH and describe critical gaps in our understanding of this entity, including the central terms ‘diffuse’ and ‘idiopathic.’ We also summarize the inconsistencies in definitions employed by recent studies and discuss the pitfalls of the DIPNECH definitions proposed by the World Health Organization in 2021. In this context, we propose an objective and reproducible radio-pathologic case definition intended for implementation in the research realm and seeks to enhance homogeneity across cohorts. Furthermore, we discuss aspects of PNECs biology which suggest that PNEC hyperplasia may contribute to the pathogenesis of phenotypes of lung disease aside from constrictive bronchiolitis and carcinoid tumorlets/tumors. Finally, we steer attention to some of the most pressing and impactful research questions awaiting to be unraveled.