Schneider, Frank

ABSTRACTBackground and ObjectiveThe diagnosis of interstitial lung diseases (ILDs) often relies on the integration of various clinical, radiological, and histopathological data. Achieving high diagnostic accuracy in ILDs, particularly for distinguishing usual interstitial pneumonia (UIP), is challenging and requires a multidisciplinary approach. Therefore, this study aimed to develop a multimodal artificial intelligence (AI) algorithm that combines computed tomography (CT) and histopathological images to improve the accuracy and consistency of UIP diagnosis.MethodsA dataset of CT and pathological images from 324 patients with ILD between 2009 and 2021 was collected. The CT component of the model was trained to identify 28 different radiological features. The pathological counterpart was developed in our previous study. A total of 114 samples were selected and used for testing the multimodal AI model. The performance of the multimodal AI was assessed through comparisons with expert pathologists and general pathologists.ResultsThe developed multimodal AI demonstrated a substantial improvement in distinguishing UIP from non‐UIP, achieving an AUC of 0.92. When applied by general pathologists, the diagnostic agreement rate improved significantly, with a post‐model κ score of 0.737 compared to 0.273 pre‐model integration. Additionally, the diagnostic consensus rate with expert pulmonary pathologists increased from κ scores of 0.278–0.53 to 0.474–0.602 post‐model integration. The model also increased diagnostic confidence among general pathologists.ConclusionCombining CT and histopathological images, the multimodal AI algorithm enhances pathologists' diagnostic accuracy, consistency, and confidence in identifying UIP, even in cases where specialised expertise is limited. image

Context.— The accurate identification of different lung adenocarcinoma histologic subtypes is important for determining prognosis but can be challenging because of overlaps in the diagnostic features, leading to considerable interobserver variability. Objective.— To provide an overview of the diagnostic agreement for lung adenocarcinoma subtypes among pathologists and to create a ground truth using the clustering approach for downstream computational applications. Design.— Three sets of lung adenocarcinoma histologic images with different evaluation levels (small patches, areas with relatively uniform histology, and whole slide images) were reviewed by 17 international expert lung pathologists and 1 pathologist in training. Each image was classified into one or several lung adenocarcinoma subtypes. Results.— Among the 4702 patches of the first set, 1742 (37%) had an overall consensus among all pathologists. The overall Fleiss κ score for the agreement of all subtypes was 0.58. Using cluster analysis, pathologists were hierarchically grouped into 2 clusters, with κ scores of 0.588 and 0.563 in clusters 1 and 2, respectively. Similar results were obtained for the second and third sets, with fair-to-moderate agreements. Patches from the first 2 sets that obtained the consensus of the 18 pathologists were retrieved to form consensus patches and were regarded as the ground truth of lung adenocarcinoma subtypes. Conclusions.— Our observations highlight discrepancies among experts when assessing lung adenocarcinoma subtypes. However, a subsequent number of consensus patches could be retrieved from each cluster, which can be used as ground truth for the downstream computational pathology applications, with minimal influence from interobserver variability.

Context. —Patients with pneumothorax occasionally require limited lung resections to control persistent air leaks. In some patients, especially smokers, histopathologic findings suggest that a ruptured bulla or bleb caused the pneumothorax. Other patients only exhibit histopathologic changes related to the physical trauma of acute, and likely occult recurrent, peripheral lung injury in the setting of “spontaneous,” or idiopathic, lung rupture. Sometimes, pneumothorax occurs secondary to an underlying localized or diffuse parenchymal lung disease. A comprehensive description of the morphologic findings that may be seen in these specimens will help the surgical pathologist distinguish patients with more common and indolent occurrences of pneumothorax from those requiring additional workup or treatment. Objective. —To develop a diagnostic approach for surgical pathologists encountering lung specimens obtained in the context of pneumothorax repair. Data Sources. —Literature review and consultation experience of the authors. Conclusions. —Two general categories of histopathologic changes can be identified: (1) nonspecific changes, reflecting the lung's acute and chronic response to localized injury, and (2) changes suggesting an underlying lung disease that may have played an etiologic role in the development of pneumothorax. The latter changes are important to recognize because they may require additional workup or treatment of clinically occult lung disease. Difficulty arises when nonspecific histopathologic changes overlap with those of an underlying lung disease. Awareness of these diagnostic challenges and pitfalls, together with clinicoradiographic correlation, is essential in these situations and will help guide the surgical pathologist toward an accurate diagnosis and the appropriate management of clinically occult disease.

Thoracic manifestations of rheumatic disease (RD) are increasingly recognized as a significant cause of morbidity and mortality worldwide. Rheumatologic underpinnings have been identified in a significant proportion of patients with interstitial lung disease. The 5 RDs most frequently associated with pleuropulmonary disease are (1) rheumatoid arthritis, (2) systemic lupus erythematosus, (3) progressive systemic sclerosis, (4) polymyositis/dermatomyositis, and (5) Sjögren syndrome. The onset of thoracic involvement in these diseases is variable. In some patients, it precedes the systemic disease or is its only manifestation. Moreover, there is a wide spectrum of clinical presentation ranging from subclinical abnormalities to acute respiratory failure. Histopathologically, the hallmark features of thoracic involvement by RD are inflammatory, targeting one or more lung compartments. The reactions range from acute to chronic, with remodeling by fibrosis being a common result. Although the inflammatory findings are often nonspecific, certain reactions or anatomic distributions may favor one RD over another, and occasionally, a distinctive histopathology may be present (eg, rheumatoid nodules). Three diagnostic dilemmas are encountered in patients with RD who develop diffuse lung disease: 1) opportunistic infection in the immunocompromised host, 2) drug toxicity related to the medications used to treat the systemic disease, and 3) manifestations of the patient's known systemic disease in lung and pleura. To confidently address the latter, the 5 major RDs are presented here, with their most common pleuropulmonary pathologic manifestations, accompanied by brief clinical and radiologic correlations.