RESUMO
Purpose: The mean linear intercept (MLI) score is a common metric for quantification of injury in lung histopathology images. The automated estimation of the MLI score is a challenging task because it requires accurate segmentation of different biological components of the lung tissue. Therefore, the most widely used approaches for MLI quantification are based on manual/semi-automated assessment of lung histopathology images, which can be expensive and time-consuming. We describe a fully automated pipeline for MLI estimation, which is capable of producing results comparable to human raters. Approach: We use a convolutional neural network based on U-Net architecture to segment the diagnostically relevant tissue segments in the whole slide images (WSI) of the mouse lung tissue. The proposed method extracts multiple field-of-view (FOV) images from the tissue segments and screen the FOV images, rejecting images based on presence of certain biological structures (i.e., blood vessels and bronchi). We used color slicing and region growing for segmentation of different biological structures in each FOV image. Results: The proposed method was tested on ten WSIs from mice and compared against the scores provided by three human raters. In segmenting the relevant tissue segments, our method obtained a mean accuracy, Dice coefficient, and Hausdorff distance of 98.34%, 98.22%, and 109.68 µ m , respectively. Our proposed method yields a mean precision, recall, and F 1 -score of 93.37%, 83.47%, and 87.87%, respectively, in screening of FOV images. There was substantial agreement found between the proposed method and the manual scores (Fleiss Kappa score of 0.76). The mean difference between the calculated MLI score between the automated method and average rater's score was 2.33 ± 4.13 ( 4.25 % ± 5.67 % ). Conclusion: The proposed pipeline for automated calculation of the MLI score demonstrates high consistency and accuracy with human raters and can be a potential replacement for manual/semi-automated approaches in the field.
RESUMO
BACKGROUND: The majority of clavicle fractures are midshaft injuries, although fractures of the distal or medial fragment also occur. The aim of this study was to review the current evidence on these injuries to help inform future treatment plans. METHODS: We searched for studies comparing interventions for medial, midshaft, or distal clavicle fractures; however, we did not identify any comparative studies on medial fractures and performed a secondary search on this topic. We conducted Bayesian network meta-analyses, although this was not feasible with studies on medial fractures and we described their results qualitatively. RESULTS: For midshaft fractures, we found statistically significant improvements in function and time to radiographic union with plating, an elastic stable intramedullary nail (ESIN), and the Sonoma CRx intramedullary nail over nonoperative treatments. Both plating and an ESIN also showed significantly lower risks of nonunion and malunion relative to nonoperative methods. For distal fractures, a locking plate (LP) with or without coracoclavicular (CC) suturing yielded significantly better outcomes over K-wires with or without tension bands, CC suturing alone, an LP with a CC screw, a hook plate, and a sling. For medial fractures, plating may result in more favorable functional and union-related outcomes, although implant irritation may occur. In addition, K-wires, tension bands, and a screw with sutures demonstrated success when plating was technically not feasible in a few cases, whereas treatment with a sling may result in reduced function and a higher risk of complications relative to surgery. CONCLUSION: This study can provide guidance on the management of medial, midshaft, and distal clavicle fractures. The current evidence suggests that plating, an ESIN, and a CRx intramedullary nail are all good options for midshaft fractures; an LP with or without CC suturing should be preferred for distal fractures; and plating is also acceptable for medial fractures, provided that the patient is deemed suitable for surgery and has the adequate bone stock and sufficiently sized medial fragment necessary to implant the device. Patient preferences for certain outcomes should be considered, which may result in different treatment recommendations.