Search Results (432)

Catamenial pneumothorax is a rare form of recurrent spontaneous pneumothorax occurring in women in temporal association with the menstrual cycle, most commonly within 72 h before or after the onset of menstruation, and is frequently encountered as part of thoracic endometriosis syndrome. Thoracic endometriosis represents an extrapelvic manifestation of endometriosis in which ectopic endometrial tissue may involve the pleura, diaphragm, lung parenchyma, or airways, leading to cyclic pleuropulmonary symptoms. The clinical spectrum includes catamenial pneumothorax, catamenial hemothorax, catamenial hemoptysis, and pulmonary endometriotic nodules. This narrative review critically analyzes the diagnostic challenges and limitations of imaging modalities in thoracic endometriosis, with particular emphasis on diagnostic delay, radiological pitfalls, and the discrepancy between morphological detection and etiological confirmation. Chest radiography and computed tomography are useful for documenting acute thoracic events, whereas magnetic resonance imaging may provide additional tissue characterization in selected cases, particularly when hemorrhagic or diaphragmatic lesions are suspected. However, imaging findings are often nonspecific, temporally variable, and insufficient to establish the diagnosis when interpreted in isolation. Recognition of thoracic endometriosis therefore requires correlation of imaging findings with menstrual cyclicity, gynecological history, clinical phenotype, and, when indicated, surgical and histopathological assessment. The available evidence remains limited by retrospective designs, small case series, inconsistent diagnostic criteria, and lack of validated thoracic-specific imaging pathways. Accordingly, an integrated clinical–radiological–surgical approach should be regarded as a pragmatic diagnostic framework rather than a validated algorithm. Such an approach may improve clinical suspicion, reduce diagnostic delay, and support more appropriate multidisciplinary management of this underrecognized condition. Full article

Tumor localization during pulmonary surgery has become increasingly challenging with the earlier detection of smaller and smaller lung nodules. Concomitantly, minimally invasive surgical (MIS) techniques have been increasingly adopted within the field of thoracic surgical oncology. Surgeons face growing challenges not only with locating these small tumors, but also with immediate margin assessment, reduced tactile feedback, and nodal assessment. Intraoperative molecular imaging (IMI) has emerged as a promising adjunct to address these challenges by enabling real-time visualization of malignant tissue during pulmonary resection. In its current form, IMI integrates systemically administered, tumor-targeting near-infrared fluorophores with fluorescence-capable imaging platforms to enhance intraoperative decision-making. Early clinical experiences in thoracic surgery suggest particular utility in the localization of small or nonpalpable pulmonary nodules and for improved margin assessment during MIS. Despite encouraging preliminary data, widespread adoption of IMI remains limited by biologic variability in target expression, optical depth constraints, false-positive fluorescence in inflammatory tissue, and challenges in workflow integration. Applications for nodal evaluation, staging, and longer-term oncologic outcome improvement remain investigational. Addressing these multifaceted barriers will be essential for the translation of IMI from a promising, experimental adjunct to a more broadly implementable surgical technology. This work summarizes the current state of IMI in thoracic surgical oncology, highlighting key translational studies, established and emerging clinical applications, and critical limitations within the current landscape. The authors also outline future directions for the field, including quantitative fluorescence interpretation, standardized reporting, and outcomes-driven clinical trials evaluating margin adequacy, recurrence, staging impact, and cost-effectiveness to support widespread evidence-based implementation. Full article

A 51-year-old woman was admitted with a malodorous ulceration covering the whole area of both breasts, without visible breast contour or remnants of breast tissue. After excision of a skin nodule an invasive ductal carcinoma was diagnosed; grade-2, hormone receptor (HR)-positive, HER2-negative, Ki-67 at 25%. Computed tomography of the thorax and abdomen showed pulmonary and osseous metastases. Six cycles of systemic chemotherapy with epirubicin and cyclophosphamide at three-week intervals were administered, followed by endocrine therapy with letrozole. Almost four years later, palbociclib became available and it was added to the patient’s treatment. Loco-regional and distant disease control was achieved attaining maximum response at 11 months after initial diagnosis and since then the patient remains progression-free with good quality of life for more than eight years. This is to the best of our knowledge an extreme case of primary metastatic ulcerative breast cancer with complete local tissue destruction and markedly prolonged progression-free survival. As this is a single-case clinical observation, any conclusions have limited generalizability. Given the rarity of primary metastatic ulcerative breast cancer there are no specific evidence-based treatment guidelines available and published studies have high heterogeneity and low level of evidence, necessitating multidisciplinary approach on a case-by-case basis. Full article

Background: Lung cancer is the second most common cause of cancer with high mortality, thereby emphasizing the importance of early detection. However, the rate of new lung cancer diagnosis has remained relatively unchanged. Despite the advancements in navigational bronchoscopy, the diagnostic yield of pulmonary nodules, particularly posterior nodules, is often limited by CT-to-body divergence. Our study aims to evaluate the feasibility and safety of prone positioning during navigational bronchoscopy and its impact on the diagnostic yield of posterior pulmonary nodules. Methods: Retrospective cohort study of nine patients who underwent Ion robotic navigational bronchoscopy in prone position and 237 patients in supine position. The study period was July 2024 to December 2024 for the prone cohort and July 2020 to September 2024 for the supine cohort. Results: In the supine cohort, the diagnostic yield was 93.3%, including a malignant yield of 62.3%, and the post-operative complication rates were 1.5% for pneumothorax, 3.5% for bronchopulmonary hemorrhage, and 1.9% for respiratory failure. In the prone cohort, the diagnostic yield was 77.8% and a malignant yield of 85.7%, and the postoperative complication rates were 0% for pneumothorax, bronchopulmonary hemorrhage, and respiratory failure. Conclusions: CT-to-body divergence is a major obstacle in the diagnostic work-up of pulmonary nodules, of which a major contributor is atelectasis. Our study demonstrates that prone positioning combined with a strict anesthesia protocol is both a feasible and safe approach in the diagnostic work-up of pulmonary nodules. Full article

Background/Objectives: Pleura-based pulmonary nodules in soft-tissue sarcoma (STS) patients remain diagnostically challenging, and entity-specific contrast-enhanced ultrasound (CEUS) data are scarce. We aimed to characterize CEUS perfusion patterns of pleura-based STS pulmonary metastases in a pilot cohort. Methods: We investigated a single-center retrospective cohort at a tertiary STS referral center (Dec 2024–Dec 2025). Of 51 consecutive STS patients with suspected pulmonary metastases screened, 32 lacked pleural contact and 6 were excluded for logistical reasons; the remaining 13 underwent standardized CEUS of a pleura-contacting lesion (≥5 mm) visible on B-mode lung ultrasound (B-LUS), with 1 excluded on biopsy (anaplastic lymphoma). The reference standard combined histology, therapy-related size reduction of the index lesion, and/or documented distant metastatic STS. Two readers rated all examinations independently, with adjudication by a third senior reader. Wilson 95% confidence intervals (CIs) and Cohen’s κ were computed. Results: In the 12 analyzed patients (mean age 58.8 ± 17.8 years; 7 male), the index lesion was histologically confirmed in 4 (33.3%). On CEUS, bronchial-arterial (BA) enhancement predominated (10/12; 83.3%, 95% CI 55.2–95.3%) and pulmonary-arterial timing occurred in 2/12 (16.7%). Marked enhancement was present in 9/12 (75.0%), homogeneous in 8/12 (66.7%), and rapid washout (<120 s) in all lesions (12/12; 100%, 95% CI 75.8–100%). Inter-reader agreement was substantial to almost perfect for the diagnostically relevant CEUS perfusion variables (enhancement κ = 0.75; EE κ = 0.80; HE κ = 0.82) and moderate for the descriptive shape variable (Form κ = 0.47). Conclusions: In this selected pilot cohort, pleura-based STS lung metastases most commonly showed BA-dominant enhancement with universal rapid washout. The findings are hypothesis-generating and require validation in larger, prospective multicenter cohorts. Full article

Thin-slice high-resolution computed tomography (CT) has improved the detection of small pulmonary nodules, increasing the demand for minimally invasive diagnostic and therapeutic resection. While lobectomy with lymph node dissection remains the standard surgical approach for many patients with resectable non-small cell lung cancer, accumulating evidence supports sublobar resection for selected small, peripheral, and ground-glass-dominant lesions when sufficient margins are achievable. In thoracoscopic and robotic surgery, localization of nodules ≤10 mm or lesions located >5 mm from the pleural surface can be challenging, and failure to identify the target may lead to conversion, larger resection than intended, or prolonged operative time. Several localization strategies have been developed, including CT-guided percutaneous wire/coil/dye marking, bronchoscopic dye mapping, and virtual-assisted lung mapping (VAL-MAP), robotic-assisted bronchoscopic dye or fiducial localization, radiofrequency identification microtag systems (Surgical Real-Time FInger Navigation and Detection) that provide real-time depth information, and single-stage intraoperative CT-guided marking and resection in hybrid operating rooms. This review synthesizes representative evidence and published outcome ranges, and compares workflows, marker-to-lesion precision metrics, complication profiles, operational burden, and cost structures. We emphasize the practical contrast between two-stage and single-stage workflows, the access-route differences between transthoracic and transbronchial techniques, and the need to report localization-to-incision “time at risk”. We also present an expert-consensus decision algorithm aimed at facilitating tailored selection of localization strategies for modern minimally invasive thoracic surgery. Full article

Background/Objectives: Lipoid pneumonia (LP) is a rare and frequently underdiagnosed pulmonary condition with a broad spectrum of radiological manifestations that can closely mimic infectious, inflammatory, and neoplastic lung diseases. Despite its clinical relevance, no standardized imaging-based diagnostic pathway exists. For this reason, this pictorial narrative review aims to provide a structured, imaging-centred synthesis of LP, to characterise the full spectrum of high-resolution CT (HRCT) and magnetic resonance imaging (MRI) findings, and to propose a pragmatic diagnostic workflow. Methods: A systematic literature search was performed in PubMed, MEDLINE, Embase, and the Cochrane Library from January 1950 to February 2025. Search terms combined “lipoid pneumonia” with imaging-related keywords including “HRCT,” “computed tomography,” “MRI,” and “fat attenuation.” After screening 891 deduplicated records, 60 studies were included in the narrative synthesis. Eight illustrative institutional cases with imaging–pathology correlation were additionally selected to demonstrate key imaging phenotypes. Results: HRCT is the cornerstone modality, demonstrating intralesional fat attenuation (typically −30 to −150 HU) in 40–80% of cases depending on series and disease chronicity. Additional patterns include ground-glass opacity, crazy paving, centrilobular nodules, and mass-like consolidation mimicking malignancy. Fat attenuation is absent in up to 60% of cases when inflammatory exudate or fibrosis masks lipid content. MRI, particularly chemical shift imaging, serves as a problem-solving adjunct in pseudotumoral or densitometrically equivocal presentations. A pragmatic diagnostic workflow is proposed, integrating HRCT findings, exposure history, fat-sensitive MRI in selected cases, BAL cytology, and histopathological confirmation when required. Conclusions: A pattern-based radiological approach, anchored on HRCT and integrated with clinical exposure history, BAL cytology, and selective use of fat-sensitive MRI, enables accurate diagnosis of LP in most cases and can prevent unnecessary invasive procedures including surgical resection performed under suspicion of malignancy. Full article

Objectives: Whereas irreversible compression of Digital Imaging and Communications in Medicine (DICOM) files can reduce data size, research on its impact on diagnostic ability when using artificial intelligence (AI) software is limited. The objective was to determine the effect that irreversible compression has on diagnostic ability when using AI software. In addition, the effect of nodal properties on computed tomography (CT) on detection rates was examined. Methods: A total of 335 patients with pulmonary nodules were included. Chest radiographs were subjected to irreversible compression at 10:1 and 50:1 ratios. The associations between the detection rate of the AI software and factors such as location on CT, morphology, and diameter, were determined. Results: The number of positive cases identified with the AI imaging software was as follows: 188 cases (56.1%) with no compression, 184 cases (54.9%) with 10:1 compression, and 175 cases (52.2%) with 50:1 compression. There was a significant difference between the uncompressed images and the 50:1 compressed images, as well as between the 10:1 compressed images and the 50:1 compressed images (all p < 0.05). With all compression ratios, there were significant differences in the associations between the AI software’s nodule detection rate and the target nodule’s maximum diameter, minimum diameter, morphology, and overlap with multiple organs on CT (all p < 0.0001). Conclusions: The detection rate by the AI software of lung tumors on chest radiographs showed no significant difference when images were subjected to 10:1 irreversible compression; however, there was a significant decrease when subjected to 50:1 irreversible compression. Full article

Background/Objectives: Distinguishing primary lung squamous cell carcinoma (PLSCC) from metastatic head and neck squamous cell carcinoma (MHNSCC) to the lungs is challenging for pathologists, especially when patients present with a solitary lung nodule. The purpose of this study was to identify CT imaging features that differ between PLSCC from solitary MHNSCC to the lungs, using next-generation sequencing (NGS) and human papillomavirus in situ hybridization analysis as the gold reference standard. Methods: This retrospective, single-institution cross-sectional study included patients with a biopsy-proven PLSCC or solitary MHNSCC from July 2013 to May 2022, who underwent NGS or in situ hybridization, and baseline CT or PET/CT. Each scan was evaluated by at least two radiologists. Nodular, pleural, and ancillary CT features, as well as maximum standardized uptake value (SUVmax) from PET/CTs, were recorded. Associations between imaging features and pathology were examined using either the Wilcoxon rank-sum or Fisher’s exact test. Results: In total, 81 patients were included (median 66 years; 64 male); 36/81 (44%) had PLSCC and 45/81 (56%) had MHNSCC. PLSCC was associated with a larger size (median, 3.3–3.6 cm vs. 1.4–1.6 cm, p < 0.001), and the presence of post obstructive atelectasis (p = 0.002), pleural retraction (p < 0.001), pleural tags (p = 0.02), and pleural surface involvement (p = 0.02). MHNSCC presented as smaller peripheral nodules (p = 0.003) with lower SUVmax (p = 0.01). Conclusions: Several CT imaging features as well as SUVmax from PET/CT were significantly different between PLSCC and solitary MHNSCC and their potential discriminatory ability warrants evaluation in future studies. Full article

Background/Objectives: Lung cancer survival depends on early detection; however, in the Philippines, high radiologist workloads and the anatomical complexity of chest X-rays (CXRs) contribute to missed pulmonary nodules and false-negative diagnoses. This study aims to develop an enhanced deep learning model to improve nodule classification and localization sensitivity. Methods: We propose RNNet-MST, an extension of ResNet-50 that incorporates Multi-Scale Transformer blocks for global context modeling and a custom spatial attention mechanism for attention-based weak localization of disease-relevant regions. The model was trained and evaluated on the NODE21 chest X-ray dataset and compared with a baseline ResNet-50 using classification metrics, with attention maps used for weak localization analysis. Results: RNNet-MST demonstrated consistent improvements over the baseline ResNet-50 across evaluated metrics. Mean Nodule Recall improved from 88.02 ± 1.92% to 91.55 ± 1.41%, reducing false negatives. Mean Test Precision reached 90.46 ± 0.99%, and mean Nodule F1-Score improved to 90.99 ± 0.39%. On the isolated small-nodule subset, RNNet-MST achieved a 12.3% improvement in sensitivity over the baseline. Conclusions: The integration of multi-scale transformer features improved classification sensitivity, while the attention mechanism provided weak localization cues that aligned more closely with annotated nodule regions than the baseline. RNNet-MST shows potential as a diagnostic support tool, warranting further validation on larger and more diverse clinical datasets to reduce perceptual errors and facilitate early lung cancer detection in resource-constrained settings. Full article

Background: Accurate staging is vital for optimizing outcomes in pediatric rhabdomyosarcoma (RMS). While [¹⁸F]-FDG PET/CT is increasingly utilized, its specific impact on clinical management and its prognostic value compared to conventional imaging (CI) require further evaluation. Methods: In this retrospective single-center study, we reviewed 56 pediatric patients with RMS who underwent [¹⁸F]-FDG PET/CT at our center. Imaging findings were compared with CI (CT/MRI) and correlated with clinical management and survival outcomes. Results: In the total cohort (n = 56), PET/CT demonstrated high concordance with CI for nodal assessment, with an apparent sensitivity of 89.5% and specificity of 94.6%. PET/CT identified skeletal metastases in 5 patients (8.9%) and correctly characterized suspicious pulmonary nodules in one case, though it failed to detect a 0.6 cm lung nodule visualized on chest CT. Notably, PET/CT findings directly altered clinical management in 16.1% of patients (n = 9), primarily through radiotherapy adjustments, including field expansions (n = 4), field reductions (n = 3), and the initiation of previously unplanned radiotherapy (n = 2). At a median follow-up of 33.3 months, an exploratory analysis showed that patients with an SUVmax ≥3.6 had a lower 3-year EFS (57.6% vs. 71.6%; p = 0.51) and OS (60.4% vs. 71.6%; p = 0.63); neither comparison reached statistical significance. Conclusion: [¹⁸F]-FDG PET/CT is a powerful adjunct in pediatric RMS staging, particularly for nodal and skeletal evaluation. Its ability to refine radiotherapy planning in nearly one-sixth of cases underscores its clinical utility. SUVmax is not a validated prognostic or predictive biomarker in pediatric RMS; prospective, adequately powered multicenter studies, ideally incorporating volumetric PET parameters, are needed before any role in risk-stratified therapy can be defined. Full article

Lung cancer rates are the highest among cancers, making it the leading cause of death worldwide. With advances in new technologies and diverse diagnostic methods, Computer-Aided Diagnosis Systems (CADx) have improved pulmonary nodule classification with notable accuracy and speed. However, limited data availability and privacy concerns remain significant challenges, in addition to the reported rates of false negatives and false positives. This work aims to develop an approach based on collaborative feature extraction between multiple centers, thus achieving data efficiency and diversity while ensuring privacy and reducing false positives and false negatives. This work proposes a new explainable feature-based split learning approach using diverse Computed Tomography (CT) scan datasets to evaluate data diversity and privacy. It adopts a split ResNet-50 architecture on the client side for feature extraction. On the server side, a hybrid 2D-CNN combined with an attention mechanism is used for final classification and decision-making. The architecture was evaluated using two ablation studies based on ConvNeXt-Tiny and EfficientNetB0. In addition, the model was tested on two external datasets to assess its robustness and generalizability, and with Local Interpretable Model-agnostic Explanations (LIMEs) and Grad-CAM to assess trustworthiness. This proposed approach showed an accuracy and F1-score of 99.38%, with a 1.23% false negative rate and zero false positives. Moreover, when tested on totally unseen datasets, the approach achieved an accuracy and an F1-score of 99.28% on the first dataset, with 1.24% false negatives and 0% false positives. In addition, when tested on the second dataset, the results indicate an ability to generalize, with 95.74% accuracy, with false negative and false positive rates of 7.07% and 1.41%, respectively. Full article

Pulmonary nodules detected in patients with a history of malignancy are often clinically presumed to represent metastatic disease until proven otherwise. Granular cell tumor (GCT) is an uncommon, usually benign neoplasm of presumed Schwannian origin, which rarely occurs in the lung. Our aim is to emphasize the diagnostic challenges and the crucial role of histopathology in preventing overtreatment in oncology patients. Herein, we report the case of a 56-year-old woman with a previous history of papillary renal cell carcinoma diagnosed one year earlier, staged as pT1, WHO/ISUP grade 2, and treated with partial nephrectomy, with no evidence of residual disease or distant metastases at follow-up. During routine surveillance, she developed a solitary pulmonary nodule. Chest computed tomography (CT) showed a 12 mm solid nodule in the left upper lobe which was then further investigated with a positron emission tomography with 2-[¹⁸F] fluoro-2-deoxy-D-glucose [(¹⁸F)-FDG PET/CT, revealing a low glucidic uptake (SUVmax 4 and SUV mean 1.4). Endobronchial ultrasound-guided biopsy was non-diagnostic. Given the patient’s oncological history, the solid appearance on CT, and the mild FDG uptake, metastatic disease could not be excluded, and a parenchyma-sparing diagnostic wedge resection was performed. Histology showed a well-circumscribed proliferation of epithelioid cells with abundant granular eosinophilic cytoplasm and bland nuclei. Immunohistochemistry demonstrated diffuse S100 and CD68 positivity, supporting the diagnosis of primary pulmonary granular cell tumor. This case underscores the critical role of histopathological evaluation in the assessment of solitary pulmonary nodules, emphasizing that lesions identified during oncologic surveillance are not invariably indicative of malignancy. Full article

Immune checkpoint inhibitors (ICIs) have transformed oncologic care and are increasingly used as adjuvant therapy to reduce the risk of recurrence. However, this shift has introduced immune-related adverse events (irAEs) to patients who may otherwise be clinically disease-free after definitive therapy. Sarcoidosis-like reaction (SLR) is an uncommon but important irAE characterized by non-necrotizing granulomatous inflammation. In the adjuvant setting, SLR is uniquely consequential because it can closely mimic recurrent malignancy on surveillance imaging and thereby prompt unnecessary diagnostic procedures, treatment interruption, or escalation of care. This review summarizes the current evidence on ICI-associated SLR with an emphasis on adjuvant immunotherapy, where practical guidance remains limited. We integrate evidence from clinical trials, real-world cohorts, and published case series to summarize the reported incidence of SLR, proposed immunologic mechanisms, clinical and radiographic presentation, pathology, differential diagnosis, and management. Particular attention is given to the problem of distinguishing SLR from recurrence, when tissue confirmation should be prioritized, and how management should be individualized according to clinical severity and organ involvement. Common radiographic features include bilateral mediastinal and hilar lymphadenopathy and pulmonary nodules, but tissue confirmation remains the diagnostic gold standard when feasible. Many cases are low grade and may be managed conservatively. Greater recognition of ICI-associated SLR is critical to avoid misdiagnosis and unnecessary escalation of care while preserving the therapeutic benefit of adjuvant immunotherapy. Full article

Background/Objectives: Accurate detection of pulmonary nodules on chest CT is critical for lung cancer screening, yet training robust detectors remains challenging due to the high cost of reliable annotations. In this work, we present a systematic study of curriculum learning for CT-based lung nodule detection on the enhanced LUNA25 benchmark and propose a hybrid curriculum learning framework for data-efficient optimization. Methods: Our approach estimates sample difficulty by fusing clinically interpretable handcrafted factors such as nodule size and count with model-driven signals such as prediction confidence from a teacher model, and constructs a three-stage progressive training curriculum from easy to hard samples. Using YOLOv11s as a strong baseline, the proposed hybrid curriculum is compared against conventional training without curriculum learning and against single-source curricula. Results: On the held-out LUNA25 test set, hybrid curriculum learning increases ${\mathrm{mAP}}_{50}$ from 0.672 to 0.696, ${\mathrm{mAP}}_{50–95}$ from 0.369 to 0.385, recall from 0.588 to 0.634, and precision from 0.725 to 0.764. Extensive data-efficiency experiments with proportional reductions (1/2, 1/5, 1/10) and fixed training samples (5000–40,000 slices) further confirm consistent gains across limited-data regimes. Conclusions: These results demonstrate that jointly leveraging intrinsic image complexity and optimization-aware feedback provides effective sample scheduling for robust and data-efficient lung nodule detection. Full article