Role of Quantitative Computed Tomographic Scan Analysis in Lung Volume Reduction for Emphysema.

Recent advances in bronchoscopic lung volume reduction (BLVR) offer new therapeutic alternatives for patients with emphysema and hyperinflation. Endobronchial valves and coils are 2 potential BLVR techniques which have been shown to improve pulmonary function and the quality of life in patients with emphysema. Current patient selection for LVR procedures relies on 3 main inclusion criteria: low attenuation area (in %), also known as emphysema score, heterogeneity score, and fissure integrity score. Volumetric analysis in combination with densitometric analysis of the affected lung lobe or segment with quantitative CT to determine emphysema severity play an important role in treatment planning and post-operative assessment. Due to the variations in lung anatomy, manual corrections are often required to ensure successful and accurate lobe segmentation for pathological and post-treatment CT scan analysis. The advanced development and utilisation of quantitative CT do not simply represent regional changes in pulmonary function but aids in analysis for better patient selection with severe emphysema who are most likely to benefit from BLVR.

Quantitative Evaluation of Lobar Pulmonary Function of Emphysema Patients with Endobronchial Coils.

BACKGROUND: Recent advances in bronchoscopic lung volume reduction offer new therapies for patients with emphysema and hyperinflation. Pulmonary lobe segmentation with quantification of lobar volumes and emphysema severity plays a pivotal role in treatment planning and post-interventional assessment. Computed tomography (CT)-derived lobar volumes could reflect more accurate regional changes in pulmonary function. OBJECTIVES: The aim of our study is to validate the reliability of an in-house CT Lung Segmentation software (LungSeg; the Hamlyn Centre, Imperial College London, UK) for lung lobar volume and emphysema quantification for chronic obstructive pulmonary disease (COPD) patients. METHODS: A total of 108 CT scans from subjects who participated in an endobronchial coil treatment trial were included. Lobar volume and emphysema quantification were performed using the LungSeg and Syngo CT Pulmo 3D package (Siemens Healthcare GmbH, Germany). The inter-user reliability of the LungSeg program was investigated. Correlation coefficients and Bland-Altman analyses were used to quantify the inter-software variability. The agreement between CT volume analysis and plethysmography analysis was also examined. RESULTS: The high intraclass correlation coefficients (mean ICC = 0.98) of the lobar volumes and emphysema indices measured by LungSeg suggest its excellent reproducibility. The LungSeg and Syngo program have good correlation (rho ≥0.94) and agreement for both lobar volume (median difference = 94 mL and LOAnp = 214.6 mL) and emphysema index (median difference ≤1.5% and LOAnp ≤2.03%) calculations. CT analysis provides a higher estimation of total lung capacity (TLCCT) than body plethysmography (TLCpleth), while there is a fair agreement on residual volume (RVCT) by LungSeg as compared with body plethysmography (RVpleth). CONCLUSIONS: CT-derived lobar volume and emphysema quantification using the LungSeg program is efficient and reliable in allowing lobar volume assessment. LungSeg has low inter-user variability and agrees better with plethysmography for COPD assessment in our study.

Deep Graph-Based Multimodal Feature Embedding for Endomicroscopy Image Retrieval.

Representation learning is a critical task for medical image analysis in computer-aided diagnosis. However, it is challenging to learn discriminative features due to the limited size of the data set and the lack of labels. In this article, we propose a deep graph-based multimodal feature embedding (DGMFE) framework for medical image retrieval with application to breast tissue classification by learning discriminative features of probe-based confocal laser endomicroscopy (pCLE). We first build a multimodality graph model based on the visual similarity between pCLE data and reference histology images. The latent similar pCLE-histology pairs are extracted by walking with the cyclic path on the graph while the dissimilar pairs are extracted based on the geodesic distance. Given the similar and dissimilar pairs, the latent feature space is discovered by reconstructing the similarity between pCLE and histology images via deep Siamese neural networks. The proposed method is evaluated on a clinical database with 700 pCLE mosaics. The accuracy of image retrieval demonstrates that DGMFE can outperform previous works on feature learning. Especially, the top-1 accuracy in an eight-class retrieval task is 0.739, thus demonstrating a 10% improvement compared to the state-of-the-art method.

Application of artificial intelligence in surgery.

Artificial intelligence (AI) is gradually changing the practice of surgery with technological advancements in imaging, navigation, and robotic intervention. In this article, we review the recent successful and influential applications of AI in surgery from preoperative planning and intraoperative guidance to its integration into surgical robots. We conclude this review by summarizing the current state, emerging trends, and major challenges in the future development of AI in surgery.

Laser-Profiled Continuum Robot with Integrated Tension Sensing for Simultaneous Shape and Tip Force Estimation.

The development of miniaturized continuum robots has a wide range of applications in minimally invasive endoluminal interventions. To navigate inside tortuous lumens without impinging on the vessel wall and causing tissue damage or the risk of perforation, it is necessary to have simultaneous shape sensing of the continuum robot and its tip contact force sensing with the surrounding environment. Miniaturization and size constraint of the device have precluded the use of conventional sensing hardware and embodiment schemes. In this study, we propose the use of optical fibers for both actuation and tension/shape/force sensing. It uses a model-based method with structural compensation, allowing direct measurement of the cable tension near the base of the manipulator without increasing the dimensions. It further structurally filters out disturbances from the flexible shaft. In addition, a model is built by considering segment differences, cable interactions/cross talks, and external forces. The proposed model-based method can simultaneously estimate the shape of the manipulator and external force applied onto the robot tip. Detailed modeling and validation results demonstrate the accuracy and reliability of the proposed method for the miniaturized continuum robot for endoluminal intervention.

Reliable Label-Efficient Learning for Biomedical Image Recognition.

The use of deep neural networks for biomedical image analysis requires a sufficient number of labeled datasets. To acquire accurate labels as the gold standard, multiple observers with specific expertise are required for both annotation and proofreading. This process can be time-consuming and labor-intensive, making high-quality, and large-annotated biomedical datasets difficult. To address this problem, we propose a deep active learning framework that enables the active selection of both informative queries and reliable experts. To measure the uncertainty of the unlabeled data, a dropout-based strategy is integrated with a similarity criterion for both data selection and random error elimination. To select the reliable labelers, we adopt an expertise estimator to learn the expertise levels of labelers via offline-testing and online consistency evaluation. The proposed method is applied to classification tasks on two types of medical images including confocal endomicroscopy images and gastrointestinal endoscopic images. The annotations are acquired from multiple labelers with diverse levels of expertise. The experiments demonstrate the efficiency and promising performance of the proposed method compared to a set of baseline methods.

Design optimization of a contact-aided continuum robot for endobronchial interventions based on anatomical constraints.

PURPOSE: A laser-profiled continuum robot (CR) with a series of interlocking joints has been developed in our center to reach deeper areas of the airways. However, it deflects with constant curvature, which thus increases the difficulty of entering specific bronchi without relying on the tissue reaction forces. This paper aims to propose an optimization framework to find the best design parameters for nonconstant curvature CRs to reach distal targets while attempting to avoid the collision with the surrounding tissue. METHODS: First, the contact-aided compliant mechanisms (CCMs) are integrated with the continuum robot to achieve the nonconstant curvature. Second, forward kinematics considering CCMs is built. Third, inverse kinematics is implemented to steer the robot tip toward the desired targets within the confined anatomy. Finally, an optimization framework is proposed to find the best robot design to reach the target with the least collision to the bronchi walls. RESULTS: Experiments are carried out to verify the feasibility of CCMs to enable the nonconstant curvature deflection, and simulations demonstrate a lower cost function value to reach a target for the nonconstant curvature optimized design with respect to the standard constant curvature robot (0.11 vs. 2.66). In addition, the higher capacity of the optimized design to complete the task is validated by interventional experiments using fluoroscopy. CONCLUSION: Results demonstrate the effectiveness of the proposed framework to find an optimized CR with nonconstant curvature to perform safer interventions to reach distal targets.

Robust camera localisation with depth reconstruction for bronchoscopic navigation.

PURPOSE: Bronchoscopy is a standard technique for airway examination, providing a minimally invasive approach for both diagnosis and treatment of pulmonary diseases. To target lesions identified pre-operatively, it is necessary to register the location of the bronchoscope to the CT bronchial model during the examination. Existing vision-based techniques rely on the registration between virtually rendered endobronchial images and videos based on image intensity or surface geometry. However, intensity-based approaches are sensitive to illumination artefacts, while gradient-based approaches are vulnerable to surface texture. METHODS: In this paper, depth information is employed in a novel way to achieve continuous and robust camera localisation. Surface shading has been used to recover depth from endobronchial images. The pose of the bronchoscopic camera is estimated by maximising the similarity between the depth recovered from a video image and that captured from a virtual camera projection of the CT model. The normalised cross-correlation and mutual information have both been used and compared for the similarity measure. RESULTS: The proposed depth-based tracking approach has been validated on both phantom and in vivo data. It outperforms the existing vision-based registration methods resulting in smaller pose estimation error of the bronchoscopic camera. It is shown that the proposed approach is more robust to illumination artefacts and surface texture and less sensitive to camera pose initialisation. CONCLUSIONS: A reliable camera localisation technique has been proposed based on depth information for bronchoscopic navigation. Qualitative and quantitative performance evaluations show the clinical value of the proposed framework.

Effects of insulin resistance on left ventricular hypertrophy in patients with CKD stage 1-3.

BACKGROUND: Left ventricular hypertrophy (LVH) existed in patients with early stage chronic kidney disease (CKD). But whether insulin resistance (IR) exists in these patients and has some definite relationship with LVH, is unknown. METHODS: Homeostatic model method was used for detecting homeostasis model assessment of insulin resistance (HOMA-IR) in 336 subjects including 286 patients with early stage CKD and 50 control subjects, and HOMA-IR and other clinical data in all subjects were obtained based on standard methods. Then, the relationship between LVH, IR and other relevant clinical data were analyzed. RESULTS: IR and LVH existed in early stage CKD patients. The prevalence of LVH in patients with IR was significantly higher than those without, and patients with LVH had a higher prevalence of IR than those without. The patients with IR or LVH had lower levels of e-GFR, hemoglobin (Hb) and total cholesterol, while higher levels of blood urea nitrogen (BUN), serum creatinine (Scr), intact parathyroid hormone (iPTH), CRP and systolic blood pressure (SBP). HOMA-IR had positive correlations with left ventricular mass index (LVMI). HOMA-IR and LVMI had positive correlations with BUN, Scr, iPTH and CRP, but negative with e-GFR and Hb. Multiple linear stepwise regression analysis showed that e-GFR, FINS, Hb and SBP enter the regression equation. Binary unconditional logistic regression analysis indicated that the main risk factors for LVH were CKD and IR (P < 0.05, respectively). CONCLUSION: Both IR and LVH existed in early stage CKD patients and were more severe with the development of CKD. IR had a significant correlation with LVH. Furthermore, decline of e-GFR, hypertension and anemia were also associated with both IR and LVH and may have some effects in the mechanism of IR on the development of LVH.