SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion.

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation.Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask.Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47).Significance.The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

MCAFNet: multiscale cross-layer attention fusion network for honeycomb lung lesion segmentation.

Accurate segmentation of honeycomb lung lesions from lung CT images plays a crucial role in the diagnosis and treatment of various lung diseases. However, the availability of algorithms for automatic segmentation of honeycomb lung lesions remains limited. In this study, we propose a novel multi-scale cross-layer attention fusion network (MCAFNet) specifically designed for the segmentation of honeycomb lung lesions, taking into account their shape specificity and similarity to surrounding vascular shadows. The MCAFNet incorporates several key modules to enhance the segmentation performance. Firstly, a multiscale aggregation (MIA) module is introduced in the input part to preserve spatial information during downsampling. Secondly, a cross-layer attention fusion (CAF) module is proposed to capture multiscale features by integrating channel information and spatial information from different layers of the feature maps. Lastly, a bidirectional attention gate (BAG) module is constructed within the skip connection to enhance the model's ability to filter out background information and focus on the segmentation target. Experimental results demonstrate the effectiveness of the proposed MCAFNet. On the honeycomb lung segmentation dataset, the network achieves an Intersection over Union (IoU) of 0.895, mean IoU (mIoU) of 0.921, and mean Dice coefficient (mDice) of 0.949, outperforming existing medical image segmentation algorithms. Furthermore, experiments conducted on additional datasets confirm the generalizability and robustness of the proposed model. The contribution of this study lies in the development of the MCAFNet, which addresses the lack of automated segmentation algorithms for honeycomb lung lesions. The proposed network demonstrates superior performance in accurately segmenting honeycomb lung lesions, thereby facilitating the diagnosis and treatment of lung diseases. This work contributes to the existing literature by presenting a novel approach that effectively combines multi-scale features and attention mechanisms for lung lesion segmentation. The code is available at https://github.com/Oran9er/MCAFNet .

Uncertainty-guided cross learning via CNN and transformer for semi-supervised honeycomb lung lesion segmentation.

Objective. Deep learning networks such as convolutional neural networks (CNN) and Transformer have shown excellent performance on the task of medical image segmentation, however, the usual problem with medical images is the lack of large-scale, high-quality pixel-level annotations, which is a very time-consuming and laborious task, and its further leads to compromised the performance of medical image segmentation under limited annotation conditions.Approach. In this paper, we propose a new semi-supervised learning method, uncertainty-guided cross learning, which uses a limited number of annotated samples along with a large number of unlabeled images to train the network. Specifically, we use two networks with different learning paradigms, CNN and Transformer, for cross learning, and use the prediction of one of them as a pseudo label to supervise the other, so that they can learn from each other, fully extract the local and global features of the images, and combine explicit and implicit consistency regularization constraints with pseudo label methods. On the other hand, we use epistemic uncertainty as a guiding message to encourage the model to learn high-certainty pixel information in high-confidence regions, and minimize the impact of erroneous pseudo labels on the overall learning process to improve the performance of semi-supervised segmentation methods.Main results. We conducted honeycomb lung lesion segmentation experiments using a honeycomb lung CT image dataset, and designed several sets of comparison experiments and ablation experiments to validate the effectiveness of our method. The final experimental results show that the Dice coefficient of our proposed method reaches 88.49% on the test set, and our method achieves state-of-the-art performance in honeycomb lung lesion segmentation compared to other semi-supervised learning methods.Significance. Our proposed method can effectively improve the accuracy of segmentation of honeycomb lung lesions, which provides an important reference for physicians in the diagnosis and treatment of this disease.

Honeycomb lung is a major risk factor for preoperative radiological tumor size underestimation in patients with primary lung cancer.

Background: Lung cancer frequently occurs in lungs with background idiopathic interstitial pneumonias (IIPs). Limited resection is often selected to treat lung cancer in patients with IIPs in whom respiratory function is already compromised. However, accurate surgical margins are essential for curative resection; underestimating these margins is a risk for residual lung cancer after surgery. We aimed to investigate the findings of lung fields adjacent to cancer segments affect the estimation of tumor size on computed tomography compared with the pathological specimen. Methods: This analytical observational study retrospectively investigated 896 patients with lung cancer operated on at Fujita Health University from January 2015 to June 2020. The definition of underestimation was a ≥10 mm difference between the radiological and pathological maximum sizes of the tumor. Results: The lung tumors were in 15 honeycomb, 30 reticulated, 207 emphysematous, and 628 normal lungs. The ratio of underestimation in honeycomb lungs was 33.3% compared to 7.4% without honeycombing (P=0.004). Multivariate analysis showed that honeycombing was a significant risk factor for tumor size underestimation. A Bland-Altman plot represented wide 95% limits of agreement, -40.8 to 70.2 mm, between the pathological and radiological maximum tumor sizes in honeycomb lungs.

Honeycomb-like structures in sarcoidosis pathologically showing granulomas in walls of clustered bronchioles.

In the clinical setting, it is often difficult to judge whether honeycomb-like structures represent progression of fibrosis in pulmonary sarcoidosis or a complication by interstitial pneumonitis. This report described a valuable case in which pathology of video-assisted thoracoscopic surgery specimens collected from the lungs with honeycomb-like structures that were continuous with the dilated bronchioles on chest computed tomography (CT) showed granulomas in the membranous bronchiole walls, thereby demonstrating that the honeycomb-like structures were lung lesions of sarcoidosis. Pathological features of these structures on chest CT included cystic changes attributable to incorporation of peripheral alveoli into dilated bronchioles in lobules: these findings in lung sarcoidosis were different from those corresponding to honeycomb lung in idiopathic pulmonary fibrosis/usual interstitial pneumonia. Radiological and pathological findings showed the possibility that progressive clustering of dilated bronchi and bronchioles causes cystic changes, resulting in the formation of honeycomb-like structures as fibrosis progresses in sarcoidosis with lung involvement.

Recognition of honeycomb lung in CT images based on improved MobileNet model.

PURPOSE: The research is to improve the efficiency and accuracy of recognition of honeycomb lung in CT images. METHODS: Deep learning methods are used to achieve automatic recognition of honeycomb lung in CT images, however, are time consuming and less accurate due to the large amount of structural parameters. In this paper, a novel recognition method based on MobileNetV1 network, multiscale feature fusion method (MSFF), and dilated convolution is explored to deal with honeycomb lung in CT image classification. Firstly, the dilated convolution with different dilated rate is used to extract features to obtain receptive fields of different sizes, and then fuse the features of different scales at multiscale feature fusion block is used to solve the problem of feature loss and incomplete feature extraction. After that, by using linear activation functions (Sigmoid) instead of nonlinear activation functions (ReLu) in the improved deep separable convolution blocks to retain the feature information of each channel. Finally, by reducing the number of improved deep separable blocks to reduce the computation and resource consumption of the model. RESULTS: The experimental results show that improved MobileNet model has the best performance and the potential for recognition of honeycomb lung image datasets, which includes 6318 images. By comparing with 4 traditional models (SVM, RF, decision tree, and KNN) and 11 deep learning models (LeNet-5, AlexNet, VGG-16, GoogleNet, ResNet18, DenseNet121, SENet18, InceptionV3, InceptionV4, Xception, and MobileNetV1), our model achieved the performance with an accuracy of 99.52%, a sensitivity of 99.35%, and a specificity of 99.89%. CONCLUSION: Improved MobileNet model is designed for the automatic recognition and classification of honeycomb lung in CT images. Through experiments comparative analysis of other models of machine learning and deep learning, it is proved that the proposed improved MobileNet method has the best recognition accuracy with fewer the model parameters and less the calculation time.

Honeycomb lung-like structures resulting from clustering of traction bronchiectasis distally in sarcoidosis.

Gene expression profiles of patients with progressive sarcoidosis, most of whom had evidence of fibrosis on imaging, have been reported to be similar to those of patients with inflammatory hypersensitivity pneumonitis, while expression profiles in progressive sarcoidosis did not resemble those of idiopathic pulmonary fibrosis. However, it is not known whether specific parenchymal features discerned on computed tomography (CT) imaging can predict development of fibrosis in pulmonary fibrosis. We herein describe a rare case of pulmonary sarcoidosis with honeycomb lung-like structures developing as a result of concentration of traction bronchiectasis distally, predominantly in both lower lung fields, which developed through shrinkage of consolidations comprising a "central-peripheral band" detected in a woman in her 60s, with non-caseating epithelioid granuloma. To our knowledge, this is the first case demonstrating the distinctive morphology and developmental process of honeycomb lung-like structures in fibrotic pulmonary sarcoidosis.

Computed Tomography Images of Fibrotic Pulmonary Sarcoidosis Leading to Chronic Respiratory Failure.

BACKGROUND: There is currently no consensus on the morphology of severe fibrotic pulmonary sarcoidosis, and we examined computed tomography (CT) findings and progression. METHODS: We analyzed findings in 10 consecutive patients (three men, seven women) with pulmonary sarcoidosis requiring oxygen therapy for chronic respiratory failure, who were extracted from >2500 sarcoidosis patients (three hospitals, 2000-2018). Patients with comorbidities causing chronic respiratory failure were excluded. RESULTS: Predominant findings were consolidations along the bronchovascular bundles comprising 'central-peripheral band', traction bronchiectasis, peripheral cysts/bullae, and upper lobe shrinkage. Traction bronchiectasis arose from opacities comprising 'central-peripheral band'. Clustering of traction bronchiectasis at the distal side formed honeycomb lung-like structures in three patients. Upper lobe shrinkage progressed in seven patients together with progression of consolidations, 'central-peripheral band', traction bronchiectasis clusters, and cysts, while patients without shrinkage included two patients with severe multiple cysts without traction bronchiectasis. Restrictive ventilatory impairment developed in most patients. Pulmonary hypertension (PH) was detected radiologically in five patients, and chronic progressive pulmonary aspergillosis (CPPA) in four patients. CONCLUSIONS: During progression, consolidations comprising 'central-peripheral band' progressed together with traction bronchiectasis clusters and peripheral cysts, resulting in upper lobe shrinkage. This may lead to respiratory failure with possible complications such as PH and CPPA.

Two Cases of Microscopic Polyangiitis with Honeycomb Lung / 결핵

Microscopic polyangiitis is a systemic small-vessel vasculitis that is associated primarily with necrotizing glomerulonephritis and pulmonary capillaritis. A recurrent and diffuse alveolar hemorrhage due to pulmonary capi llaritis is the main clinical manifestation of lung involvement. Recently, an interstitial lung disease that mimics idiopathic pulmonary fibrosis was reported to be rarely associated with microscopic polyangiitis. Here we report two patients with microscopic polyangiitis who showed a honeycomb lung at the time of the initial diagnosis with a brief review of relevant literature.