Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.
X-Rays ; Algorithms ; Diagnosis, Computer-Assisted ; Thorax/diagnostic imaging* ; Lung/diagnostic imaging* ; Image Processing, Computer-Assisted

OBJECTIVE: To investigate the correlation between glenohumeral joint congruence and stability in recurrent shoulder dislocations. METHODS: Eighty-nine patients (89 sides) with recurrent shoulder dislocation admitted between June 2022 and June 2023 and met the selection criteria were included as study subjects. There were 36 males and 53 females with an average age of 44 years (range, 20-79 years). There were 40 cases of left shoulder and 49 cases of right shoulder. The shoulder joints dislocated 2-6 times, with an average of 3 times. The three-dimensional models of the humeral head and scapular glenoid were reconstructed using Mimics 20.0 software based on CT scanning images. The glenoid track (GT), inclusion index, chimerism index, fit index, and Hill-Sachs interval (HSI) were measured, and the degree of on/off track was judged (K value, the difference between HSI and GT). Multiple linear regression was used to analyze the correlation between the degree of on/off track (K value) and inclusion index, chimerism index, and fit index. RESULTS: Multiple linear regression analysis showed that the K value had no correlation with the inclusion index ( P>0.05), and was positively correlated with the chimerism index and the fit index ( P<0.05). Regression equation was K=-24.898+35.982×inclusion index+8.280×fit index, R ²=0.084. CONCLUSION Humeral head and scapular glenoid bony area and curvature are associated with shoulder joint stability in recurrent shoulder dislocations. Increased humeral head bony area, decreased scapular glenoid bony area, increased humeral head curvature, and decreased scapular glenoid curvature are risk factors for glenohumeral joint stability.
Female ; Male ; Humans ; Adult ; Shoulder Joint/diagnostic imaging* ; Shoulder Dislocation/diagnostic imaging* ; Joint Dislocations ; Scapula/diagnostic imaging* ; Thorax

Lung cancer is the malignant tumor with the highest morbidity and mortality in China. Non-small cell lung cancer (NSCLC) is the main pathological subtype of lung cancer. On April 13, 2023, the National Comprehensive Cancer Network (NCCN) released the third edition of the 2023 NCCN Oncology Clinical Practice Guidelines: Non-small Cell Lung Cancer, which reflects the latest advances in international lung cancer research. This article will interpret the main updated contents of the new edition of the guidelines, and compare it with the third edition of the NCCN guidelines in 2022, so as to provide references about the diagnosis and treatment of NSCLC for clinical medical personnel in China.
.
Humans ; Carcinoma, Non-Small-Cell Lung ; China ; Lung Neoplasms ; Thorax

Objective: To explore the efficacy and safety of endoscopic diaphragm incision in pediatric congenital duodenal diaphragm. Methods: Eight children with duodenal diaphragm treated by endoscopic diaphragm incision in the Department of Gastroenterology of Guangzhou Women and Children's Medical Center from October 2019 to May 2022 were enrolled in this study. Their clinical data including general conditions, clinical manifestations, laboratory and imaging examinations, endoscopic procedures and outcomes were retrospectively analyzed. Results: Among the 8 children, 4 were males and 4 females. The diagnosis was confirmed at the age of 6-20 months; the age of onset was 0-12 months and the course of disease was 6-18 months. The main clinical manifestations were recurrent non-biliary vomiting, abdominal distension and malnutrition. One case complicated with refractory hyponatremia was first diagnosed with atypical congenital adrenal hyperplasia in the endocrinology department. After treatment with hydrocortisone, the blood sodium returned to normal, but vomiting was recurrent. One patient underwent laparoscopic rhomboid duodenal anastomosis in another hospital but had recurred vomiting after the operation, who was diagnosed with double duodenal diaphragm under endoscope. No other malformations were found in all the 8 cases. The duodenal diaphragm was located in the descending part of the duodenum, and the duodenal papilla was located below the diaphragm in all the 8 cases. Three cases had the diaphragm dilated by balloon to explore the diaphragm opening range before diaphragm incision; the other 5 had diaphragm incision performed after probing the diaphragm opening with guide wire. All the 8 cases were successfully treated by endoscopic incision of duodenal diaphragm, with the operation time of 12-30 minutes. There were no complications such as intestinal perforation, active bleeding or duodenal papilla injury. At one month of follow-up, their weight increased by 0.4-1.5 kg, with an increase of 5%-20%. Within the postoperative follow-up period of 2-20 months, all the 8 children had duodenal obstruction relieved, without vomiting or abdominal distension, and all resumed normal feeding. Gastroscopy reviewed at 2-3 months after the operation in 3 cases found no deformation of the duodenal bulbar cavity, and the mucosa of the incision was smooth, with a duodenal diameter of 6-7 mm. Conclusion: Endoscopic diaphragm incision is safe, effective and less invasive in pediatric congenital duodenal diaphragm, with favorable clinical applicability.
Male ; Child ; Female ; Humans ; Infant ; Infant, Newborn ; Retrospective Studies ; Thorax ; Endoscopy ; Physical Examination ; Adrenal Hyperplasia, Congenital

Non-rigid registration plays an important role in medical image analysis. U-Net has been proven to be a hot research topic in medical image analysis and is widely used in medical image registration. However, existing registration models based on U-Net and its variants lack sufficient learning ability when dealing with complex deformations, and do not fully utilize multi-scale contextual information, resulting insufficient registration accuracy. To address this issue, a non-rigid registration algorithm for X-ray images based on deformable convolution and multi-scale feature focusing module was proposed. First, it used residual deformable convolution to replace the standard convolution of the original U-Net to enhance the expression ability of registration network for image geometric deformations. Then, stride convolution was used to replace the pooling operation of the downsampling operation to alleviate feature loss caused by continuous pooling. In addition, a multi-scale feature focusing module was introduced to the bridging layer in the encoding and decoding structure to improve the network model's ability of integrating global contextual information. Theoretical analysis and experimental results both showed that the proposed registration algorithm could focus on multi-scale contextual information, handle medical images with complex deformations, and improve the registration accuracy. It is suitable for non-rigid registration of chest X-ray images.
Algorithms ; Learning ; Thorax

Diaphragm excursion,diaphragm thickness,and diaphragmatic thickening fraction are three indicators for evaluating the two hemidiaphragms by ultrasound.Diaphragm ultrasound has been widely applied in clinical practice including anesthesia management.It can help to diagnose postoperative residual curarisation and identify patients at a high risk of suffering from postoperative pulmonary complications.It can serve to recognize patients with diaphragm paralysis due to surgical or anesthetic factors as early as possible.Moreover,diaphragm ultrasound plays a role in preoperative pulmonary function assessment for special sufferers with chronic obstructive pulmonary disease,adolescent idiopathic scoliosis,or neuromuscular disease.Apart from these,diaphragm ultrasound can give anesthesiologists and colleagues in intensive care unit an important clue for extubation and weaning from mechanical ventilation of patients.
Adolescent ; Humans ; Diaphragm/diagnostic imaging* ; Prospective Studies ; Ultrasonography ; Thorax ; Postoperative Complications ; Anesthesia

T cell immunoreceptor with immunoglobulin and immunoreceptor tyrosine-based inhibition motif domain (TIGIT) is a newly discovered immune checkpoint molecule, mainly expressed on the surface of T cells and natural killer (NK) cells. By binding to cluster of differentiation 155 (CD155) and other ligands, it inhibits T cell and NK cell-mediated immune responses and affects the tumor microenvironment. Multiple preclinical studies have demonstrated that the TIGIT/CD155 pathway plays a role in a variety of solid and hematological tumors. Clinical trials investigating TIGIT inhibitors alone or in combination with programmed cell death 1 (PD-1)/programmed cell death ligand 1 (PD-L1) inhibitors for lung cancer are currently underway.
.
Humans ; Lung Neoplasms/drug therapy* ; Immunotherapy ; Thorax ; Immunologic Factors ; Receptors, Immunologic ; Tumor Microenvironment

Percutaneous pulmonary puncture guided by computed tomography (CT) is one of the most effective tools for obtaining lung tissue and diagnosing lung cancer. Path planning is an important procedure to avoid puncture complications and reduce patient pain and puncture mortality. In this work, a path planning method for lung puncture is proposed based on multi-level constraints. A digital model of the chest is firstly established using patient's CT image. A Fibonacci lattice sampling is secondly conducted on an ideal sphere centered on the tumor lesion in order to obtain a set of candidate paths. Finally, by considering clinical puncture guidelines, an optimal path can be obtained by a proposed multi-level constraint strategy, which is combined with oriented bounding box tree (OBBTree) algorithm and Pareto optimization algorithm. Results of simulation experiments demonstrated the effectiveness of the proposed method, which has good performance for avoiding physical and physiological barriers. Hence, the method could be used as an aid for physicians to select the puncture path.
Humans ; Lung/diagnostic imaging* ; Lung Neoplasms/diagnostic imaging* ; Punctures ; Thorax ; Tomography, X-Ray Computed

BACKGROUND: Body mass-independent parameters might be more appropriate for assessing cardiometabolic abnormalities than weight-dependent indices in Asians who have relatively high visceral adiposity but low body fat. Dual-energy X-ray absorptiometry (DXA)-measured trunk-to-peripheral fat ratio is one such body mass-independent index. However, there are no reports on relationships between DXA-measured regional fat ratio and cardiometabolic risk factors targeting elderly Asian men. METHODS: We analyzed cross-sectional data of 597 elderly men who participated in the baseline survey of the Fujiwara-kyo Osteoporosis Risk in Men (FORMEN) study, a community-based single-center prospective cohort study conducted in Japan. Whole-body fat and regional fat were measured with a DXA scanner. Trunk-to-appendicular fat ratio (TAR) was calculated as trunk fat divided by appendicular fat (sum of arm and leg fat), and trunk-to-leg fat ratio (TLR) as trunk fat divided by leg fat. RESULTS: Both TAR and TLR in the group of men who used ≥ 1 medication for hypertension, dyslipidemia, or diabetes ("user group"; N = 347) were significantly larger than those who did not use such medication ("non-user group"; N = 250) (P < 0.05). After adjusting for potential confounding factors including whole-body fat, both TAR and TLR were significantly associated with low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, triglyceride, fasting serum insulin, and the insulin resistance index in the non-user group and non-overweight men in the non-user group (N = 199). CONCLUSION The trunk-to-peripheral fat ratio was associated with cardiometabolic risk factors independently of whole-body fat mass. Parameters of the fat ratio may be useful for assessing cardiometabolic risk factors, particularly in underweight to normal-weight populations.
Absorptiometry, Photon ; Adiposity/physiology* ; Aged ; Aged, 80 and over ; Biomarkers/metabolism* ; Cardiometabolic Risk Factors ; Cross-Sectional Studies ; Humans ; Intra-Abdominal Fat/diagnostic imaging* ; Japan ; Male ; Osteoporosis/etiology* ; Prospective Studies ; Risk Assessment ; Risk Factors ; Thorax/diagnostic imaging*

Humans ; Neck/surgery* ; Orbit/injuries* ; Thorax ; Wounds, Penetrating