Objective
To identify the feasibility of using a deep convolutional neural network (DCNN) for the detection and localization of hip fractures on plain frontal pelvic radiographs (PXRs).
Summary of background data
Hip fracture is a leading worldwide health problem for the elderly. A missed diagnosis of hip fracture on radiography leads to a dismal prognosis. The application of a DCNN to PXRs can potentially improve the accuracy and efficiency of hip fracture diagnosis.
Methods
A DCNN was pretrained using 25,505 limb radiographs between January 2012 and December 2017. It was retrained using 3605 PXRs between August 2008 and December 2016. The accuracy, sensitivity, false-negative rate, and area under the receiver operating characteristic curve (AUC) were evaluated on 100 independent PXRs acquired during 2017. The authors also used the visualization algorithm gradient-weighted class activation mapping (Grad-CAM) to confirm the validity of the model.
Results
The algorithm achieved an accuracy of 91%, a sensitivity of 98%, a false-negative rate of 2%, and an AUC of 0.98 for identifying hip fractures. The visualization algorithm showed an accuracy of 95.9% for lesion identification.
Conclusions
A DCNN not only detected hip fractures on PXRs with a low false-negative rate but also had high accuracy for localizing fracture lesions. The DCNN might be an efficient and economical model to help clinicians make a diagnosis without interrupting the current clinical pathway.
Key Points
•
Automated detection of hip fractures on frontal pelvic radiographs may facilitate emergent screening and evaluation efforts for primary physicians.
• Good visualization of the fracture site by Grad-CAM enables the rapid integration of this tool into the current medical system.
• The feasibility and efficiency of utilizing a deep neural network have been confirmed for the screening of hip fractures
.
Aims
In this study, we examine the clinicopathological and molecular features of gastric cancer (GC) with SMARCA4 alterations.
Methods and results
We screened SMARCA4 alterations using immunohistochemistry on 1199 surgically resected GCs with information on Epstein–Barr virus (EBV), microsatellite instability (MSI) and other SWI/SNF subunits. SMARCA4, SMARCA2 and ARID1A mutations were investigated by targeted sequencing. The clinicopathological significance was determined by statistical analysis. Twenty‐seven cases (2%) with altered SMARCA4 expression were identified, exhibiting completely lost (six), reduced (nine) or heterogeneous (12) patterns. Frequent concomitant alterations of other SWI/SNF subunits were noted with an unusual discordant spatial heterogeneity. In comparison with SMARCA4‐retained GCs, SMARCA4‐lost GCs were observed more frequently in the non‐EBV/MSI subgroup (five of six) and reduced or heterogeneous SMARCA4 expression mainly occurred in EBV‐ or MSI‐associated cases (six of nine and six of 12, respectively; P < 0.001). Histologically, SMARCA4‐altered GC, irrespective of expression pattern, demonstrated divergent histomorphology, spanning tubular, poorly cohesive or mixed, neuroendocrine to solid and undifferentiated carcinoma, with a predilection to the latter two (P < 0.001). De‐differentiation‐like transition and rhabdoid features were noted in a minority of cases. For overall survival, altered SMARCA4 expression was an unfavourable prognostic factor in stage III, EBV‐associated GC and non‐EBV/MSI intestinal subtype (P ≤ 0.001). SMARCA4 or ARID1A mutations were detected mainly in SMARCA4‐lost or reduced GC, respectively.
Conclusions
SMARCA4‐altered GCs are rare and have intratumoral heterogeneity, histomorphological diversity, conditional prognostic significance and various genetic drivers. SMARCA4‐lost GC may represent a genuine SMARCA4‐deficient neoplasm, but most SMARCA4‐reduced/heterogeneous cases are secondary to ARID1A collapse or associated with different genotypes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.