RESUMO
Accurate skin lesion segmentation from dermoscopic images is of great importance for skin cancer diagnosis. However, automatic segmentation of melanoma remains a challenging task because it is difficult to incorporate useful texture representations into the learning process. Texture representations are not only related to the local structural information learned by CNN, but also include the global statistical texture information of the input image. In this paper, we propose a transFormer network (SkinFormer) that efficiently extracts and fuses statistical texture representation for Skin lesion segmentation. Specifically, to quantify the statistical texture of input features, a Kurtosis-guided Statistical Counting Operator is designed. We propose Statistical Texture Fusion Transformer and Statistical Texture Enhance Transformer with the help of Kurtosis-guided Statistical Counting Operator by utilizing the transformer's global attention mechanism. The former fuses structural texture information and statistical texture information, and the latter enhances the statistical texture of multi-scale features. Extensive experiments on three publicly available skin lesion datasets validate that our SkinFormer outperforms other SOAT methods, and our method achieves 93.2% Dice score on ISIC 2018. It can be easy to extend SkinFormer to segment 3D images in the future. Our code is available at https://github.com/Rongtao-Xu/SkinFormer.
RESUMO
PURPOSE: The purpose of this study is to investigate whether gene mutations can lead to the growth of malignant pulmonary nodules. METHODS: Retrospective analysis was conducted on patients with pulmonary nodules at Hebei Provincial People's Hospital, collecting basic clinical information such as gender, age, BMI, and hematological indicators. According to the inclusion and exclusion criteria, 85 patients with malignant pulmonary nodules were selected for screening, and gene mutation testing was performed on all patient tissues to explore the relationship between gene mutations and the growth of malignant pulmonary nodules. RESULTS: There is a correlation between KRAS and TP53 gene mutations and the growth of pulmonary nodules (P < 0.05), while there is a correlation between KRAS and TP53 gene mutations and the growth of pulmonary nodules in the subgroup of invasive malignant pulmonary nodules (P < 0.05). CONCLUSION: Mutations in the TP53 gene can lead to the growth of malignant pulmonary nodules and are correlated with the degree of invasion of malignant pulmonary nodules.
Assuntos
Neoplasias Pulmonares , Mutação , Proteínas Proto-Oncogênicas p21(ras) , Proteína Supressora de Tumor p53 , Humanos , Masculino , Feminino , Estudos Retrospectivos , Pessoa de Meia-Idade , Proteínas Proto-Oncogênicas p21(ras)/genética , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patologia , Proteína Supressora de Tumor p53/genética , Idoso , Nódulos Pulmonares Múltiplos/genética , Nódulos Pulmonares Múltiplos/diagnóstico por imagem , Nódulos Pulmonares Múltiplos/patologia , Adulto , Análise Mutacional de DNA , Genes p53/genéticaRESUMO
Therapeutic HPV vaccines that induce potent HPV-specific cellular immunity and eliminate pre-existing infections remain elusive. Among various candidates under development, those based on DNA constructs are considered promising because of their safety profile, stability, and efficacy. However, the use of electroporation (EP) as a main delivery method for such vaccines is notorious for adverse effects like pain and potentially irreversible muscle damage. Moreover, the requirement for specialized equipment adds to the complexity and cost of clinical applications. As an alternative to EP, lipid nanoparticles (LNPs) that are already commercially available for delivering mRNA and siRNA vaccines are likely to be feasible. Here, we have compared three intramuscular delivery systems in a preclinical setting. In terms of HPV-specific cellular immune responses, mice receiving therapeutic HPV DNA vaccines encapsulated with LNP demonstrated superior outcomes when compared to EP administration, while the naked plasmid vaccine showed negligible responses, as expected. In addition, SM-102 LNP M exhibited the most promising results in delivering candidate DNA vaccines. Thus, LNP proves to be a feasible delivery method in vivo, offering improved immunogenicity over traditional approaches.
RESUMO
Current clinical guidelines limit surgical intervention to patients with cT1-2N0M0 small cell lung cancer (SCLC). Our objective was to reassess the role of surgery in SCLC management, and explore novel prognostic indicators for surgically resected SCLC. We reviewed all patients diagnosed with SCLC from January 2011 to April 2021 in our institution. Survival analysis was conducted using the Kaplan-Meier method, and independent prognostic factors were assessed through the Cox proportional hazard model. In addition, immunohistochemistry (IHC) staining was performed to evaluate the predictive value of selected indicators in the prognosis of surgically resected SCLC patients. In the study, 177 SCLC patients undergoing surgical resection were ultimately included. Both univariate and multivariate Cox analysis revealed that incomplete postoperative adjuvant therapy emerged as an independent risk factor for adverse prognosis (p < 0.001, HR 2.96). Survival analysis revealed significantly superior survival among pN0-1 patients compared to pN2 patients (p < 0.0001). No significant difference in postoperative survival was observed between pN1 and pN0 patients (p = 0.062). Patients with postoperative stable disease (SD) exhibited lower levels of tumor inflammatory cells (TIC) (p = 0.0047) and IFN-γ expression in both area and intensity (p < 0.0001 and 0.0091, respectively) compared to those with postoperative progressive disease (PD). Conversely, patients with postoperative SD showed elevated levels of stromal inflammatory cells (SIC) (p = 0.0453) and increased counts of CD3+ and CD8+ cells (p = 0.0262 and 0.0330, respectively). Survival analysis indicated that high levels of SIC, along with low levels of IFN-γ+ cell area within tumor tissue, may correlate positively with improved prognosis in surgically resected SCLC (p = 0.017 and 0.012, respectively). In conclusion, the present study revealed that the patients with pT1-2N1M0 staging were a potential subgroup of SCLC patients who may benefit from surgery. Complete postoperative adjuvant therapy remains an independent factor promoting a better prognosis for SCLC patients undergoing surgical resection. Moreover, CD3, CD8, IFN-γ, TIC, and SIC may serve as potential indicators for predicting the prognosis of surgically resected SCLC.
Assuntos
Complexo CD3 , Imuno-Histoquímica , Interferon gama , Neoplasias Pulmonares , Carcinoma de Pequenas Células do Pulmão , Humanos , Masculino , Feminino , Estudos Retrospectivos , Pessoa de Meia-Idade , Prognóstico , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/cirurgia , Neoplasias Pulmonares/mortalidade , Interferon gama/metabolismo , Idoso , Carcinoma de Pequenas Células do Pulmão/cirurgia , Carcinoma de Pequenas Células do Pulmão/patologia , Carcinoma de Pequenas Células do Pulmão/mortalidade , Carcinoma de Pequenas Células do Pulmão/metabolismo , Complexo CD3/metabolismo , Antígenos CD8/metabolismo , Antígenos CD8/análise , Adulto , Biomarcadores Tumorais/análise , Análise de Sobrevida , Idoso de 80 Anos ou mais , Estimativa de Kaplan-Meier , Células Estromais/patologia , Células Estromais/metabolismoRESUMO
PURPOSE: To construct the comfort status scale for patients with lung cancer after thoracoscopic surgery. DESIGN: Delphi method inquiry to 15 clinical and nursing experts. METHODS: On the basis of the comfort status scale and the subjective experience and objective symptoms of patients with lung cancer after thoracoscopic surgery, the relevant literature was consulted, semistructured interviews and group discussions were conducted, the pool of items of the postoperative comfort status scale for patients with lung cancer was initially formed, and the postoperative comfort status scale for patients with lung cancer was finally established. FINDINGS: The positive coefficient of experts was 100%, the coefficient of authority was 0.92 and 0.93, and the Kendal's W was 0.257 and 0.298, the degree of coordination of expert opinions was statistically significant (P < .05). Finally, a total of 28 items in four dimensions were formed to assess the postoperative comfort status of patients with lung cancer after thoracoscopic surgery. CONCLUSIONS: The Delphi method-based comfort status scale for patients with lung cancer after thoracoscopic surgery is scientific and reliable, and can provide a quantitative basis for the evaluation of the comfort status of patients after lung cancer thoracoscopic surgery, to further provide individual comfort care measures.
Assuntos
Neoplasias Pulmonares , Pneumonectomia , Complicações Pós-Operatórias , Humanos , Neoplasias Pulmonares/cirurgia , Masculino , Complicações Pós-Operatórias/etiologia , Pneumonectomia/efeitos adversos , Aspergilose Pulmonar/cirurgia , Aspergilose Pulmonar/etiologia , Aspergilose/etiologia , Aspergilose/diagnóstico , Pessoa de Meia-Idade , Idoso , Fatores de Tempo , Antifúngicos/uso terapêutico , Antifúngicos/administração & dosagemAssuntos
Doença de Crohn , Ustekinumab , Vasculite Leucocitoclástica Cutânea , Humanos , Doença de Crohn/tratamento farmacológico , Doença de Crohn/complicações , Masculino , Ustekinumab/efeitos adversos , Ustekinumab/uso terapêutico , Vasculite Leucocitoclástica Cutânea/induzido quimicamente , Vasculite Leucocitoclástica Cutânea/patologia , AdultoRESUMO
Immune cell therapy as a revolutionary treatment modality, significantly transformed cancer care. It is a specialized form of immunotherapy that utilizes living immune cells as therapeutic reagents for the treatment of cancer. Unlike traditional drugs, cell therapies are considered "living drugs," and these products are currently customized and require advanced manufacturing techniques. Although chimeric antigen receptor (CAR)-T cell therapies have received tremendous attention in the industry regarding the treatment of hematologic malignancies, their effectiveness in treating solid tumors is often restricted, leading to the emergence of alternative immune cell therapies. Tumor-infiltrating lymphocytes (TIL) cell therapy, cytokine-induced killer (CIK) cell therapy, dendritic cell (DC) vaccines, and DC/CIK cell therapy are designed to use the body's natural defense mechanisms to target and eliminate cancer cells, and usually have fewer side effects or risks. On the other hand, cell therapies, such as chimeric antigen receptor-T (CAR-T) cell, T cell receptor (TCR)-T, chimeric antigen receptor-natural killer (CAR-NK), or CAR-macrophages (CAR-M) typically utilize either autologous stem cells, allogeneic or xenogeneic cells, or genetically modified cells, which require higher levels of manipulation and are considered high risk. These high-risk cell therapies typically hold special characteristics in tumor targeting and signal transduction, triggering new anti-tumor immune responses. Recently, significant advances have been achieved in both basic and clinical researches on anti-tumor mechanisms, cell therapy product designs, and technological innovations. With swift technological integration and a high innovation landscape, key future development directions have emerged. To meet the demands of cell therapy technological advancements in treating cancer, we comprehensively and systematically investigate the technological innovation and clinical progress of immune cell therapies in this study. Based on the therapeutic mechanisms and methodological features of immune cell therapies, we analyzed the main technical advantages and clinical transformation risks associated with these therapies. We also analyzed and forecasted the application prospects, providing references for relevant enterprises with the necessary information to make informed decisions regarding their R&D direction selection.
Assuntos
Neoplasias Hematológicas , Neoplasias , Receptores de Antígenos Quiméricos , Humanos , Neoplasias/terapia , Imunoterapia , Terapia Baseada em Transplante de Células e TecidosRESUMO
Intravascular large B-cell lymphoma (IVLBCL) is an aggressive extranodal large B-cell lymphoma, cocurrence in the same organ with other malignancies is very rare, especially in the lung. Here, we report a rare case of lung adenocarcinoma with IVLBCL. The patient was admitted to the hospital due to diarrhea associated with fever and cough. A computed tomography (CT) scan of the chest showed an irregular patchy high-density shadow in the upper lobe of the right lung with ground-glass opacity at the margin. After admission, the patient was given anti-infection treatment, but still had intermittent low fever (up to 37.5 °C). The pathological diagnosis of percutaneous lung biopsy (PLB) was lepidic-predominant adenocarcinoma with local infiltration, which was proved to be invasive nonmucinous adenocarcinoma of the lung with IVLBCL after surgery. This paper analyzed the clinicopathological characteristics and reviewed the relevant literature to improve the knowledge of clinicians and pathologists and avoid missed diagnosis or misdiagnosis.â©.
Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Neoplasias Pulmonares , Linfoma Difuso de Grandes Células B , Humanos , Neoplasias Pulmonares/diagnóstico , Neoplasias Pulmonares/diagnóstico por imagem , Linfoma Difuso de Grandes Células B/diagnóstico , Linfoma Difuso de Grandes Células B/diagnóstico por imagem , Pulmão/patologia , Adenocarcinoma/diagnóstico , Adenocarcinoma/diagnóstico por imagemRESUMO
BACKGROUND: The conventional method of heparin and protamine management during cardiopulmonary bypass (CPB) is based on total body weight which fails to account for the heterogeneous response to heparin in each patient. On the other hand, the literature is inconclusive on whether individualized anticoagulation management based on real-time blood heparin concentration improves post-CBP outcomes. METHODS: We searched databases of Medline, Excerpta Medica dataBASE (EMBASE), PubMed, Cumulative Index to Nursing and Allied Health Literature (CINHL), and Google Scholar, recruiting randomized controlled trials (RCTs) and prospective studies comparing the outcomes of dosing heparin and/or protamine based on measured heparin concentration versus patient's total body weight for CPB. Random effects meta-analyses and meta-regression were conducted to compare the outcome profiles. Primary endpoints include postoperative blood loss and the correlation with heparin and protamine doses, the reversal protamine and loading heparin dose ratio; secondary endpoints included postoperative platelet counts, antithrombin III, fibrinogen levels, activated prothrombin time (aPTT), incidences of heparin rebound, and re-exploration of chest wound for bleeding. RESULTS: Twenty-six studies, including 22 RCTs and four prospective cohort studies involving 3,810 patients, were included. Compared to body weight-based dosing, patients of individualized, heparin concentration-based group had significantly lower postoperative blood loss (mean difference (MD)=49.51 mL, 95% confidence interval (CI): 5.33-93.71), lower protamine-to-heparin dosing ratio (MD=-0.20, 95% CI: -0.32 ~ -0.12), and higher early postoperative platelet counts (MD=8.83, 95% CI: 2.07-15.59). The total heparin doses and protamine reversal were identified as predictors of postoperative blood loss by meta-regression. CONCLUSIONS: There was a significant correlation between the doses of heparin and protamine with postoperative blood loss; therefore, précised dosing of both could be critical for reducing bleeding and transfusion requirements. Data from the enrolled studies indicated that compared to conventional weight-based dosing, individualized, blood concentration-based heparin and protamine dosing may have outcome benefits reducing postoperative blood loss. The dosing calculation of heparin based on the assumption of a one-compartment pharmacokinetic/pharmacodynamic (PK/PD) model and linear relationship between the calculated dose and blood heparin concentration may be inaccurate. With the recent advancement of the technologies of machine learning, individualized, precision management of anticoagulation for CPB may be possible in the near future.
RESUMO
Albumin-bilirubin (ALBI) grade was first described in 2015 as an indicator of liver dysfunction in patients with hepatocellular carcinoma. ALBI grade has been reported to have prognostic value in several malignancies including non-small cell lung cancer (NSCLC). The present study aimed to explore the prognostic impact of ALBI grade in patients with small cell lung cancer (SCLC). It retrospectively analyzed 135 patients with SCLC treated at Hebei General Hospital between April 2015 and August 2021. Patients were divided into two groups according to the cutoff point of ALBI grade determined by the receiver operating characteristic (ROC) curve: Group 1 with pre-treatment ALBI grade ≤-2.55 for an improved hepatic reserve and group 2 with ALBI grade >-2.55. Kaplan-Meier and Cox regression analysis were performed to assess the potential prognostic factors associated with progression free survival (PFS) and overall survival (OS). Propensity score matching (PSM) was applied to eliminate the influence of confounding factors. PFS and OS (P<0.001) were significantly improved in group 1 compared with in group 2. Multivariate analysis revealed that sex (P=0.024), surgery (P=0.050), lactate dehydrogenase (LDH; P=0.038), chemotherapy (P=0.038) and ALBI grade (P=0.028) are independent risk factors for PFS and that surgery (P=0.013), LDH (P=0.039), chemotherapy (P=0.009) and ALBI grade (P=0.013) are independent risk factors for OS. After PSM, ALBI grade is an independent prognostic factor of PFS (P=0.039) and OS (P=0.007). It was concluded that ALBI grade was an independent prognostic factor in SCLC.
RESUMO
Postanesthesia paradoxical vocal cord motion disorder (PVCMD) is often benign. However, if not recognized, PVCMD can lead to unnecessary treatments. Our patient had 3 different surgeries over a period of 20 months. The first episode of PVCMD occurred after a shoulder surgery, and the patient was reintubated. PVCMD was correctly diagnosed and treated successfully with reassurance after an ulnar nerve decompression. The third episode of PVCMD occurred after a cervical fusion surgery. Prevertebral edema from surgery further compromised the airways. Our case demonstrates the challenges of identifying and managing perioperative PVCMD, especially when surgical complications confound the airway management.
Assuntos
Fusão Vertebral , Prega Vocal , Humanos , Prega Vocal/cirurgia , Manuseio das Vias Aéreas , Descompressão Cirúrgica/efeitos adversos , Fusão Vertebral/efeitos adversos , Complicações Pós-Operatórias/etiologiaRESUMO
Background: The timing and incidence of recurrent bone metastasis (BM) after radical gastrectomy in patients with gastric cancer (GC) as well as the survival of these patients were not fully understood. The aim of this study was to analyze the data of an observational GC cohort and identify patients who underwent curative gastrectomy and had recurrent BM to describe and clarify the pattern and profile of BM evolution after surgery. Methods: Data were retrieved from a hospital-based GC cohort, and patients who underwent upfront radical gastrectomy were selected. The time points of specific organ metastatic events were recorded, and the person-year incidence rate of metastatic events was calculated. The latency period of BM events after gastrectomy was measured and compared with that of the other two most common metastatic events, liver metastasis (LM) and distant lymph node metastasis (LNM), using analysis of variance. Propensity score matching and subgroup analysis were used for sensitivity analysis. Results: A total of 1324 GC cases underwent radical gastrectomy between January 2011 and December 2021. Of these, 67 BM, 218 LM, and 248 LNM occurred before the last follow-up. The incidence of BM events was 1.7/100 person-years, which was approximately 3-fold lower than that of LM and distant LNM events (5.5 and 6.3 per 100 person-years, respectively). BM events had a significantly longer latency (median time, 16.5 months) than LM and LNM events (11.1 and 12.0 months, respectively). Recurrent BM led to a worse prognosis (median survival, 4.5 months) than those of LM and LNM events (median survival, 7.7 and 7.1 months, respectively). However, no difference in overall survival after gastrectomy was observed among the groups. Conclusions: Compared with other common metastatic events, BM in GC after gastrectomy is a late-onset event indicating poor survival. Trial registration: No. ChiCTR1800019978; http://www.chictr.org.cn/.
RESUMO
BACKGROUND: There is currently a shortage of effective diagnostic tools that are used for identifying long-term survival among non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor (EGFR) mutations. This research utilized the development of a prognostic model to assist clinicians in forecasting the survival over 24 months. METHODS: In Phase III and IV those patients who were diagnosed with EGFR mutation from January 2018 to June 2022 were enrolled into the lung cancer group of Thoracic Surgery Department of Hebei Provincial People's Hospital. Long-run survival was stated as survival for 24 months after being diagnosed. A multivariate prognostic pattern was constructed by means of internal validation and binary logistic regression by bootstrapping. One nomogram was created with a view to boosting the explanation and applicability of the pattern. RESULTS: A total of 603 patients with EGFR mutation were registered. Elements linked to the whole survival beyond 24 months were age (OR 6.15); female (OR 1.79); functional status (ECOG 0-1) (OR 5.26); Exon 20 insertion mutation deletion (OR 2.08); No central nervous system metastasis (OR 2.66), targeted therapy (OR 0.43); Immunotherapy (OR 0.24). The model has good internal validation. CONCLUSION: Seven pretreatment clinicopathological variables predicted survival over 24 months. That pattern owns a great discriminative capability. It is hypothesized that this pattern is capable of assisting in selecting the optimal treatment sequence for NSCLC patients with EGFR mutations.
Assuntos
Carcinoma Pulmonar de Células não Pequenas , Receptores ErbB , Neoplasias Pulmonares , Mutação , Nomogramas , Humanos , Carcinoma Pulmonar de Células não Pequenas/genética , Carcinoma Pulmonar de Células não Pequenas/patologia , Carcinoma Pulmonar de Células não Pequenas/mortalidade , Carcinoma Pulmonar de Células não Pequenas/diagnóstico , Feminino , Receptores ErbB/genética , Masculino , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/mortalidade , Neoplasias Pulmonares/diagnóstico , Prognóstico , Pessoa de Meia-Idade , Idoso , Taxa de Sobrevida , Adulto , SeguimentosRESUMO
Potato is one of the most important crops worldwide, to feed a fast-growing population. In addition to providing energy, fiber, vitamins, and minerals, potato storage proteins are considered as one of the most valuable sources of non-animal proteins due to their high essential amino acid (EAA) index. However, low tuber protein content and limited knowledge about potato storage proteins restrict their widespread utilization in the food industry. Here, we report a proof-of-concept study, using deep learning-based protein design tools, to characterize the biological and chemical characteristics of patatins, the major potato storage proteins. This knowledge was then employed to design multiple cysteines on the patatin surface to build polymers linked by disulfide bonds, which significantly improved viscidity and nutrient of potato flour dough. Our study shows that deep learning-based protein design strategies are efficient to characterize and to create novel proteins for future food sources.
Assuntos
Aprendizado Profundo , Solanum tuberosum , Solanum tuberosum/química , Proteínas de Plantas/metabolismo , Tubérculos/química , Carboidratos/análiseRESUMO
Butylphthalide, a prescription medicine recognized for its efficacy in treating ischemic strokes approved by the State Food and Drug Administration of China in 2005, is sourced from the traditional botanical remedy Ligusticum chuanxiong. While chemical synthesis offers a viable route, limitations in the production of isomeric variants with compromised bioactivity necessitate alternative strategies. Addressing this issue, biosynthesis offers a promising solution. However, the intricate in vivo pathway for butylphthalide biosynthesis remains elusive. In this study, we examined the distribution of butylphthalide across various tissues of L. chuanxiong and found a significant accumulation in the rhizome. By searching transcriptome data from different tissues of L. chuanxiong, we identified four rhizome-specific genes annotated as 2-oxoglutarate-dependent dioxygenase (2-OGDs) that emerged as promising candidates involved in butylphthalide biosynthesis. Among them, LcSAO1 demonstrates the ability to catalyze the desaturation of senkyunolide A at the C-4 and C-5 positions, yielding the production of butylphthalide. Experimental validation through transient expression assays in Nicotiana benthamiana corroborates this transformative enzymatic activity. Notably, phylogenetic analysis of LcSAO1 revealed that it belongs to the DOXB clade, which typically encompasses genes with hydroxylation activity, rather than desaturation. Further structure modelling and site-directed mutagenesis highlighted the critical roles of three amino acid residues, T98, S176, and T178, in substrate binding and enzyme activity. By unraveling the intricacies of the senkyunolide A desaturase, the penultimate step in the butylphthalide biosynthesis cascade, our findings illuminate novel avenues for advancing synthetic biology research in the realm of medicinal natural products.
Assuntos
Medicamentos de Ervas Chinesas , Ligusticum , Ligusticum/química , Filogenia , Medicamentos de Ervas Chinesas/química , Rizoma/químicaRESUMO
OBJECTIVE: Despite the vital role of blood perfusion in tumor progression, in patients with persistent pulmonary nodule with ground-glass opacity (GGO) is still unclear. This study aims to investigate the relationship between tumor blood vessel and the growth of persistent malignant pulmonary nodules with ground-glass opacity (GGO). METHODS: We collected 116 cases with persistent malignant pulmonary nodules, including 62 patients as stable versus 54 patients in the growth group, from 2017 to 2021. Three statistical methods of logistic regression model, Kaplan-Meier analysis regression analysis were used to explore the potential risk factors for growth of malignant pulmonary nodules with GGO. RESULTS: Multivariate variables logistic regression analysis and Kaplan-Meier analysis identified that tumor blood vessel diameter (p = 0.013) was an significant risk factor in the growth of nodules and Cut-off value of tumor blood vessel diameter was 0.9 mm with its specificity 82.3% and sensitivity 66.7%.While in subgroup analysis, for the GGO CTR < 0.5[C(the maximum diameter of consolidation in tumor)/T(the maximum diameter of the whole tumor including GGO) ratio], tumor blood vessel diameter (p = 0.027) was important during the growing processes of nodules. CONCLUSIONS: The tumor blood vessel diameter of GGO lesion was closely associated with the growth of malignant pulmonary nodules. The results of this study would provide evidence for effective follow-up strategies for pulmonary nodule screening.
Assuntos
Neoplasias Pulmonares , Nódulos Pulmonares Múltiplos , Humanos , Neoplasias Pulmonares/cirurgia , Imageamento Tridimensional , Nódulos Pulmonares Múltiplos/cirurgia , Fatores de Risco , Tomografia Computadorizada por Raios XRESUMO
Accurate lung lesion segmentation from computed tomography (CT) images is crucial to the analysis and diagnosis of lung diseases, such as COVID-19 and lung cancer. However, the smallness and variety of lung nodules and the lack of high-quality labeling make the accurate lung nodule segmentation difficult. To address these issues, we first introduce a novel segmentation mask named "soft mask", which has richer and more accurate edge details description and better visualization, and develop a universal automatic soft mask annotation pipeline to deal with different datasets correspondingly. Then, a novel network with detailed representation transfer and soft mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results. Our DSNet contains a special detailed representation transfer module (DRTM) for reconstructing the detailed representation to alleviate the small size of lung nodules images and an adversarial training framework with soft mask for further improving the accuracy of segmentation. Extensive experiments validate that our DSNet outperforms other state-of-the-art methods for accurate lung nodule segmentation, and has strong generalization ability in other accurate medical segmentation tasks with competitive results. Besides, we provide a new challenging lung nodules segmentation dataset for further studies (https://drive.google.com/file/d/15NNkvDTb_0Ku0IoPsNMHezJR TH1Oi1wm/view?usp=sharing).