Lami, Kris

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.