FedTKD: A Trustworthy Heterogeneous Federated Learning Based on Adaptive Knowledge Distillation.

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based on its environment, making it difficult to perform federated learning in a heterogeneous model environment. Some knowledge distillation methods address the problem of heterogeneous model fusion to some extent. However, these methods assume that each client is trustworthy. Some clients may produce malicious or low-quality knowledge, making it difficult to aggregate trustworthy knowledge in a heterogeneous environment. To address these challenges, we propose a trustworthy heterogeneous federated learning framework (FedTKD) to achieve client identification and trustworthy knowledge fusion. Firstly, we propose a malicious client identification method based on client logit features, which can exclude malicious information in fusing global logit. Then, we propose a selectivity knowledge fusion method to achieve high-quality global logit computation. Additionally, we propose an adaptive knowledge distillation method to improve the accuracy of knowledge transfer from the server side to the client side. Finally, we design different attack and data distribution scenarios to validate our method. The experiment shows that our method outperforms the baseline methods, showing stable performance in all attack scenarios and achieving an accuracy improvement of 2% to 3% in different data distributions.

Spatiotemporal variations of magnetic susceptibility in the deep gray matter nuclei from 1 month to 6 years: A quantitative susceptibility mapping study.

BACKGROUND: Quantitative susceptibility mapping (QSM) is emerging as a technique that quantifies the paramagnetic nonheme iron in brain tissue. Brain iron quantification during early development provides insights into the underlying mechanism of brain maturation. PURPOSE: To quantify the spatiotemporal variations of brain iron-related magnetic susceptibility in deep gray matter nuclei during early development by using QSM. STUDY TYPE: Retrospective. SUBJECTS: Eighty-seven infants and children aged 1 month to 6 years. FIELD STRENGTH/SEQUENCE: Enhanced T2 *-weighted angiography using a 3D gradient-echo sequence at 3.0T. ASSESSMENT: QSM was calculated by modified sophisticated harmonic artifact reduction for phase data and sparse linear equations and sparse least squares-based algorithm. Means of susceptibility in deep gray matter nuclei (caudate nucleus, putamen, globus pallidus, thalamus) relative to that in splenium of corpus callosum were measured. STATISTICAL TESTS: Relationships of mean susceptibility with age and referenced iron concentration were tested by Pearson correlation. Differences of mean susceptibility between the selected nuclei in each age group were compared by one-way analysis of variance (ANOVA) and Fisher's Linear Significant Difference (LSD) test. RESULTS: Positive correlations of susceptibility with both referenced iron concentration and age were found (P < 0.0001); particularly, globus pallidus showed the highest correlation with age (correlation coefficient, 0.882; slope, 1.203; P < 0.001) and greatest susceptibility (P < 0.05) among the selected nuclei. DATA CONCLUSION: QSM allows the feasible quantification of iron deposition in deep gray matter nuclei in infants and young children, which exhibited gradual accumulation at different speeds. The fastest and highest iron accumulation was observed in the globus pallidus with increasing age during early development. LEVEL OF EVIDENCE: 4 Technical Efficacy:Stage 2 J. Magn. Reson. Imaging 2018.

TDCPP protects cardiomyocytes from H2O2-induced injuries via activating PI3K/Akt/GSK3ß signaling pathway.

Tris (1, 3-dichloro-2-propyl) phosphate (TDCPP) is a major type of organophosphorus flame retardants, and long-term exposure to TDCPP to normal cells or tissues under physiological conditions can induce toxic effects. But how TDCPP leads to the adverse effects is not yet clear, and the effect of TDCPP under pathological conditions such as reactive oxygen species assault is not well understood. The present study aimed to explore the potential effect of TDCPP against H2O2-induced oxidative stress in H9c2 cardiomyoblasts and rat neonatal cardiomyocytes. We found that H2O2-treatment decreased cell viability and increased lactate dehydrogenase and malondialdehyde generation of H9c2 cells. However, TDCPP could alleviate these effects. TDCPP alleviated Ca2+-overload caused by H2O2 through decreasing store-operated calcium entry. More importantly, TDCPP remarkably decreased H2O2-induced dephosphorylation of Akt and GSK3ß, and through this pathway TDCPP mitigated the H2O2-induced apoptosis and detrimental autophagy. Collectively, via mitigating Ca2+-overload and activating the Akt/GSK3ß signaling pathway, TDCPP may have a role in protecting cardiomyocytes from oxidative stress.

A Literature Review: Geometric Methods and Their Applications in Human-Related Analysis.

Geometric features, such as the topological and manifold properties, are utilized to extract geometric properties. Geometric methods that exploit the applications of geometrics, e.g., geometric features, are widely used in computer graphics and computer vision problems. This review presents a literature review on geometric concepts, geometric methods, and their applications in human-related analysis, e.g., human shape analysis, human pose analysis, and human action analysis. This review proposes to categorize geometric methods based on the scope of the geometric properties that are extracted: object-oriented geometric methods, feature-oriented geometric methods, and routine-based geometric methods. Considering the broad applications of deep learning methods, this review also studies geometric deep learning, which has recently become a popular topic of research. Validation datasets are collected, and method performances are collected and compared. Finally, research trends and possible research topics are discussed.

Morphological analysis of blood vessels near lung tumors using 3-D quantitative CT.

BACKGROUND: Improved visualization of lung cancer-associated vessels is vital. OBJECTIVE: To evaluate the efficacy of 3-D quantitative CT in lung cancer-associated pulmonary vessel assessment. METHODS: Vascular CT changes were assessed visually and using FACT-Digital lung TM software (n = 162 patients, 178 controls). The total number of pulmonary vessels (TNV) and mean lumen area of pulmonary vessels (MAV) vertical to cross-sections of fifth/sixth-generation bronchioles were measured. RESULTS: Visual investigation revealed fewer ipsilateral pulmonary vascular abnormalities in lung cancer (151/162) than did quantitative CT (162/162), and required more time (3.2±1.5 vs. 2.5±1.3 min) (P < 0.05). CT measurements revealed that the TNV vertical to the fifth-generation bronchial cross-section of the ipsilateral, contralateral, and control groups was 14.58±4.75, 9.58±3.74, and 10.22±4.07 and the MAV in these groups was 99.70±26.20, 58.76±29.29, and 57.76±18.32, respectively. The TNV vertical to the sixth-generation bronchial cross-section of the ipsilateral, contralateral, and control groups was 16.64±5.14, 11.59±4.06, and 11.75±4.16 and the MAV was 110.22±31.47, 67.62±30.41, and 60.24±16.18, respectively. The TNV and MAV in ipsilateral lung cancer tissues exceeded those in the contralateral side and control group tissues (P < 0.001). CONCLUSIONS: Automated 3-D quantitative CT could successfully characterize pulmonary vessels and their lung cancer-associated changes.

Application of automated bronchial 3D-CT measurement in pulmonary contusion complicated with acute respiratory distress syndrome.

BACKGROUNDQuantitative measurement of bronchial morphological changes in pulmonary contusion with acute respiratory distress syndrome (ARDS) has important clinical implications.OBJECTIVETo investigate the morphological changes in bronchus before and after treatment in patients with pulmonary contusion combined with ARDS using an automated bronchial three-dimensional computed tomography (3D-CT) measurement method.METHODSThe study involves a dataset of CT images of 62 patients diagnosed with pulmonary contusion combined with ARDS. The volume of pulmonary contusion lesions was calculated as a percentage of the total lung volume using the automated 3D-CT method. The bronchial luminal cross-sectional area, wall cross-sectional area, the maximum and average wall thickness, the maximum and average luminal densities, intraluminal and extraluminal diameters, and circumferences of generations 2-4 bronchi before and after treatment were measured. Furthermore, the corresponding differences were analyzed statistically.RESULTSThe luminal cross-sectional area, wall cross-sectional area, intraluminal and extraluminal diameters, and circumferences of generations 2-4 bronchi were all significantly lower before treatment than after treatment (P < 0.05). However, the maximum and average wall thicknesses were both significantly higher before treatment than after treatment (P < 0.05). No significant difference was found in the maximum and average luminal densities before and after treatment (P > 0.05). The percentage of the pulmonary contusion lesion volume to the total lung volume correlated positively with the thoracic trauma severity score (r = 0.74, P < 0.01).CONCLUSIONSQuantitative bronchial CT image analysis enables to detect and assess bronchial morphological changes in patients diagnosed with pulmonary contusion combined with ARDS.

Social Image Captioning: Exploring Visual Attention and User Attention.

Image captioning with a natural language has been an emerging trend. However, the social image, associated with a set of user-contributed tags, has been rarely investigated for a similar task. The user-contributed tags, which could reflect the user attention, have been neglected in conventional image captioning. Most existing image captioning models cannot be applied directly to social image captioning. In this work, a dual attention model is proposed for social image captioning by combining the visual attention and user attention simultaneously.Visual attention is used to compress a large mount of salient visual information, while user attention is applied to adjust the description of the social images with user-contributed tags. Experiments conducted on the Microsoft (MS) COCO dataset demonstrate the superiority of the proposed method of dual attention.

Emotion Recognition from Chinese Speech for Smart Affective Services Using a Combination of SVM and DBN.

Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed.

Healthcare4VideoStorm: Making Smart Decisions Based on Storm Metrics.

Storm-based stream processing is widely used for real-time large-scale distributed processing. Knowing the run-time status and ensuring performance is critical to providing expected dependability for some applications, e.g., continuous video processing for security surveillance. The existing scheduling strategies' granularity is too coarse to have good performance, and mainly considers network resources without computing resources while scheduling. In this paper, we propose Healthcare4Storm, a framework that finds Storm insights based on Storm metrics to gain knowledge from the health status of an application, finally ending up with smart scheduling decisions. It takes into account both network and computing resources and conducts scheduling at a fine-grained level using tuples instead of topologies. The comprehensive evaluation shows that the proposed framework has good performance and can improve the dependability of the Storm-based applications.

Updating the Species Diversity of Pestalotioid Fungi: Four New Species of Neopestalotiopsis and Pestalotiopsis.

Pestalotioid fungi are associated with a wide variety of plants around the world as pathogens, endophytes, and saprobes. In this study, diseased leaves and branches of plants were collected from Guizhou and Sichuan in China. Here, the fungal isolates were identified based on a phylogenetic analysis of the internal transcribed spacer region (ITS), the translation elongation factor 1-alpha (tef1-α) and the beta-tubulin (tub2) of ribosomal DNA, and the morphological characteristics. Ten Neopestalotiopsis isolates and two Pestalotiopsis isolates were obtained, and these isolates were further confirmed as four novel species (N. acericola, N. cercidicola, N. phoenicis, and P. guiyangensis) and one known species, N. concentrica.

Case Report: A case of third-degree atrioventricular block associated with primary cardiac lymphoma.

Background: Primary cardiac lymphoma is an extremely rare malignant lymphoma, with clinical manifestations related to its location. We reported the diagnosis and treatment of primary cardiac lymphoma in a patient presented with atrioventricular block. Case presentation: A 64 year-old man was admitted to our hospital because of symptoms of a tired heart and shortness of breath. The initial electrocardiogram revealed a third-degree atrioventricular block. Computed tomography scan showed an irregularly shaped right heart, irregular clusters, and relatively weakly enhanced areas in the right auricle, atrium, and ventricle. The local boundary between the lesion, pericardium, and left atrium was unclear, and the ventricular septum was irregular and thickened. Multiple irregular gray neoplasms with less smooth surfaces were observed, with a maximum diameter of approximately 7 cm. Pathological findings confirmed a non-germinal center B cell subtype of diffuse large B-cell lymphoma. After surgical resection of the tumor and implantation of a permanent pacemaker, the symptoms of the patient were significantly improved, allowing subsequent chemotherapy. Conclusion: Surgical resection and placement of a permanent pacemaker were effective treatments for a patient with primary cardiac lymphoma presented with atrioventricular block.

Wearable sensor-based quantitative gait analysis in Parkinson's disease patients with different motor subtypes.

Gait impairments are among the most common and disabling symptoms of Parkinson's disease and worsen as the disease progresses. Early detection and diagnosis of subtype-specific gait deficits, as well as progression monitoring, can help to implement effective and preventive personalized treatment for PD patients. Yet, the gait features have not been fully studied in PD and its motor subtypes. To characterize comprehensive and objective gait alterations and to identify the potential gait biomarkers for early diagnosis, subtype differentiation, and disease severity monitoring. We analyzed gait parameters related to upper/lower limbs, trunk and lumbar, and postural transitions from 24 tremor-dominant (TD) and 20 postural instability gait difficulty (PIGD) dominant PD patients who were in early stage and 39 matched healthy controls (HC) during the Timed Up and Go test using wearable sensors. Results show: (1) Both TD and PIGD groups showed restricted backswing range in bilateral lower extremities and more affected side (MAS) arm, reduced trunk and lumbar rotation range in the coronal plane, and low turning efficiency. The receiver operating characteristic (ROC) analysis revealed these objective gait features had high discriminative value in distinguishing both PD subtypes from the HC with the area under the curve (AUC) values of 0.7~0.9 (p < 0.01). (2) Subtle but measurable gait differences existed between TD and PIGD patients before the onset of clinically apparent gait impairment. (3) Specific gait parameters were significantly associated with disease severity in TD and PIGD subtypes. Objective gait biomarkers based on wearable sensors may facilitate timely and personalized gait treatments in PD subtypes through early diagnosis, subtype differentiation, and disease severity monitoring.

Vulvar Hidradenoma Papilliferum.

Aim: This study examines the clinical and pathological characteristics, immune profile, histological occurrence, diagnosis, and differential diagnosis of vulvar hidradenoma papilliferum. Methods: An analysis was conducted on clinical data, histological patterns, and immunohistochemical findings from 45 cases of vulvar hidradenoma papilliferum, and relevant published articles were reviewed. Simultaneously, high-risk HPV typing was performed on these 45 cases. Results: The 45 cases of vulvar hidradenoma papilliferum displayed tumor sizes ranging from 0.3 to 2.0 cm and were observed to be pink or red in appearance. Vacuolated cytoplasm, large abnormal nuclei, distinct nucleoli, and scattered eosinophilic luminal secretions were observed in the glands. Positive staining for CK7 and progesterone receptor (PR) with focal mammaglobin and GCDFP-15 expression was found through immunohistochemistry. CK20 staining was noted as negative. Conclusion: Hidradenoma papilliferum is a rare benign tumor that originates in secretory glands. The diagnosis of this condition is aided by gross and immunohistochemical results, and differentiation from other conditions is necessary.

Relationships Between Rapid Eye Movement Sleep Behavior Disorder and Parkinson's Disease: Indication from Gut Microbiota Alterations.

Rapid eye movement sleep behavior disorder (RBD) has a close relationship with Parkinson's disease (PD) and was even regarded as the most reliable hallmark of prodromal PD. RBD might have similar changes in gut dysbiosis to PD, but the relationship between RBD and PD in gut microbial alterations is rarely studied. In this study, we aim to investigate whether there were consistent changes between RBD and PD in gut microbiota, and found some specific biomarkers in RBD that might indicate phenoconversion to PD. Alpha-diversity showed no remarkable difference and beta-diversity showed significant differences based on the unweighted (R = 0.035, P = 0.037) and weighted (R = 0.0045, P = 0.008) UniFrac analysis among idiopathic RBD (iRBD), PD with RBD, PD without RBD and normal controls (NC). Enterotype distribution indicated iRBD, PD with RBD and PD without RBD were Ruminococcus-dominant while NC were Bacteroides-dominant. 7 genera (4 increased: Aerococcus, Eubacterium, Gordonibacter and Stenotrophomonas, 3 decreased: Butyricicoccus, Faecalibacterium and Haemophilus) were consistently changed in iRBD and PD with RBD. Among them, 4 genera (Aerococcus, Eubacterium, Butyricicoccus, Faecalibacterium) remained distinctive in the comparison between PD with RBD and PD without RBD. Through clinical correlation analysis, Butyricicoccus and Faecalibacterium were found negatively correlated with the severity of RBD (RBD-HK). Functional analysis showed iRBD had similarly increased staurosporine biosynthesis to PD with RBD. Our study indicates that RBD had similar gut microbial changes to PD. Decreased Butyricicoccus and Faecalibacterium might be potential hallmarks of phenoconversion of RBD to PD.

Coevolution of furA-Regulated Hyper-Inflammation and Mycobacterial Resistance to Oxidative Killing through Adaptation to Hydrogen Peroxide.

Mycobacterium tuberculosis (Mtb) is highly resistant to host oxidative killing. We hypothesized that the evolutionary adaptation of M. smegmatis to hydrogen peroxide (H2O2) would endow the nonpathogenic Mycobacterium persistent in a host. In the study, we screened a highly H2O2-resistant strain (mc2114) via evolutionary H2O2 adaptation in vitro. The MIC of mc2114 to H2O2 is 320 times that of wild-type mc2155. Mouse infection experiments showed that mc2114, similar to Mtb, was persistent in the lungs and caused high lethality in mice with restricted responses of NOX2, ROS, IFN-γ, decreased macrophage apoptosis, and overexpressed inflammatory cytokines in the lungs. Whole-genome sequencing analysis revealed that mc2114 harbored 29 single nucleotide polymorphisms in multiple genes; one of them was on the furA gene that caused FurA deficiency-mediated overexpression of KatG, a catalase-peroxidase to detoxify ROS. Complementation of mc2114 with a wild-type furA gene reversed lethality and hyper-inflammatory response in mice with rescued overexpression of KatG and inflammatory cytokines, whereas NOX2, ROS, IFN-γ, and macrophage apoptosis remained reduced. The results indicate that although FurA regulates KatG expression, it does not contribute significantly to the restriction of ROS response. Instead, FurA deficiency is responsible for the detrimental pulmonary inflammation that contributes to the severity of the infection, a previously nonrecognized function of FurA in mycobacterial pathogenesis. The study also indicates that mycobacterial resistance to oxidative burst results from complex mechanisms involving adaptive genetic changes in multiple genes. IMPORTANCE Mycobacterium tuberculosis (Mtb) causes human tuberculosis (TB), which has killed more people in human history than any other microorganism. However, the mechanisms underlying Mtb pathogenesis and related genes have not yet been fully elucidated, which impedes the development of effective strategies for containing and eradicating TB. In the study, we generated a mutant of M. smegmatis (mc2114) with multiple mutations by an adaptive evolutionary screen with H2O2. One of the mutations in furA caused a deficiency of FurA, which mediated severe inflammatory lung injury and higher lethality in mice by overexpression of inflammatory cytokines. Our results indicate that FurA-regulated pulmonary inflammation plays a critical role in mycobacterial pathogenesis in addition to the known downregulation of NOX2, ROS, IFN-γ responses, and macrophage apoptosis. Further analysis of the mutations in mc2114 would identify more genes related to the increased pathogenicity and help in devising new strategies for containing and eradicating TB.

Differentiating malignant and benign pleural effusion in patients with lung cancer: an 18F-FDG PET/CT retrospectively study.

Rationale: To explore the clinical role of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in differentiating malignant pleural effusion (MPE) from benign pleural effusion (BPE) in patients with lung cancer. Methods: Over a 8-year period, we retrospectively reviewed PET/CT data of lung cancer patients with pleural effusion, with 237 participants enrolled for analysis. The nature of pleural effusion was confirmed using pleural cytology or biopsy. MPE versus BPE comparison and multiple regression analysis were performed. Receiver operating characteristic (ROC) curve analysis was used for evaluating the diagnostic performance. Results: Of the 237 participants, 170 had MPEs and 67 had BPEs. Compared with BPEs, MPEs had higher pleural SUVmax and thicker pleura and were more common among non-small cell lung cancers, peripheral tumors, and women (p < 0.05). BPEs had larger and higher 18F-FDG uptake thoracic lymph nodes and more complications of pneumonia (p < 0.05) than MPEs. Multiple regression analysis was used to identify the pleural SUVmax (odds ratio, OR = 38.8), sex (OR = 0.033), and mediastinal lymphoid node size (OR = 0.86) as independent risk factors for MPEs. The sensitivity, specificity, and area under the ROC curve (AUC) in the combined ROC curve analysis by using the three factors were 95.3%, 95.5%, and 0.989, respectively. Conclusion: 18F-FDG PET/CT integrated imaging is an effective non-invasive method for differential diagnosis of MPE in patients with lung cancer. Pleural SUVmax combined with thoracic lymph nodes and sex has high diagnostic value.

DFML: Dynamic Federated Meta-Learning for Rare Disease Prediction.

Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. Hospitals are usually reluctant to share patient information for data fusion due to the sensitivity of medical data. These challenges make it difficult for traditional AI models to extract rare disease features for disease prediction. In this paper, we propose a Dynamic Federated Meta-Learning (DFML) approach to improve rare disease prediction. We design an Inaccuracy-Focused Meta-Learning (IFML) approach that dynamically adjusts the attention to different tasks according to the accuracy of base learners. Additionally, a dynamic weight-based fusion strategy is proposed to further improve federated learning, which dynamically selects clients based on the accuracy of each local model. Experiments on two public datasets show that our approach outperforms the original federated meta-learning algorithm in accuracy and speed with as few as five shots. The average prediction accuracy of the proposed model is improved by 13.28% compared with each hospital's local model.

The impact of global warming on the signature virulence gene, thermolabile hemolysin, of Vibrio parahaemolyticus.

IMPORTANCE: In this study, Vibrio parahaemolyticus strains were collected from a large number of aquatic products globally and found that temperature has an impact on the virulence of these bacteria. As global temperatures rise, mutations in a gene marker called thermolabile hemolysin (tlh) also increase. This suggests that environmental isolates adapt to the warming environment and become more pathogenic. The findings can help in developing tools to analyze and monitor these bacteria as well as assess any link between climate change and vibrio-associated diseases, which could be used for forecasting outbreaks associated with them.

A Novel Deep Learning Model for Medical Report Generation by Inter-Intra Information Calibration.

Automatic generation of medical reports can provide diagnostic assistance to doctors and reduce their workload. To improve the quality of the generated medical reports, injecting auxiliary information through knowledge graphs or templates into the model is widely adopted in previous methods. However, they suffer from two problems: 1) The injected external information is limited in amount and difficult to adequately meet the information needs of medical report generation in content. 2) The injected external information increases the complexity of model and is hard to be reasonably integrated into the generation process of medical reports. Therefore, we propose an Information Calibrated Transformer (ICT) to address the above issues. First, we design a Precursor-information Enhancement Module (PEM), which can effectively extract numerous inter-intra report features from the datasets as the auxiliary information without external injection. And the auxiliary information can be dynamically updated with the training process. Secondly, a combination mode, which consists of PEM and our proposed Information Calibration Attention Module (ICA), is designed and embedded into ICT. In this method, the auxiliary information extracted from PEM is flexibly injected into ICT and the increment of model parameters is small. The comprehensive evaluations validate that the ICT is not only superior to previous methods in the X-Ray datasets, IU-X-Ray and MIMIC-CXR, but also successfully be extended to a CT COVID-19 dataset COV-CTR.

Gefitinib improves severe bronchorrhea and prolongs the survival of a patient with lung invasive mucinous adenocarcinoma: A case report.

BACKGROUND: Lung invasive mucinous adenocarcinoma (LIMA), formerly referred to as mucinous bronchioloalveolar carcinoma, is a rare disease that usually presents as bilateral lung infiltration, is unsuitable for surgery and radiotherapy, and shows poor response to conventional chemotherapy. CASE SUMMARY: We report a 56-year-old Chinese man with a history of smoking and epidermal growth factor receptor mutation-positivity who was initially misdiagnosed as severe pneumonia, but was ultimately diagnosed as a case of invasive mucinous adenocarcinoma of the lung by computed tomography -guided percutaneous lung biopsy. Bronchorrhea and dyspnea were improved within 24 h after initiation of gefitinib therapy and the radiographic signs of bilateral lung consolidation showed visible improvement within 30 d. After more than 11 months of treatment, there is no evidence of recurrence or severe adverse events. CONCLUSION: Although the precise mechanism of the antitumor effects of gefitinib are not clear, our experience indicates an important role of the drug in LIMA and provides a reference for the diagnosis and treatment of this disease.