Automatically transferring supervised targets method for segmenting lung lesion regions with CT imaging.

BACKGROUND: To present an approach that autonomously identifies and selects a self-selective optimal target for the purpose of enhancing learning efficiency to segment infected regions of the lung from chest computed tomography images. We designed a semi-supervised dual-branch framework for training, where the training set consisted of limited expert-annotated data and a large amount of coarsely annotated data that was automatically segmented based on Hu values, which were used to train both strong and weak branches. In addition, we employed the Lovasz scoring method to automatically switch the supervision target in the weak branch and select the optimal target as the supervision object for training. This method can use noisy labels for rapid localization during the early stages of training, and gradually use more accurate targets for supervised training as the training progresses. This approach can utilize a large number of samples that do not require manual annotation, and with the iterations of training, the supervised targets containing noise become closer and closer to the fine-annotated data, which significantly improves the accuracy of the final model. RESULTS: The proposed dual-branch deep learning network based on semi-supervision together with cost-effective samples achieved 83.56 ± 12.10 and 82.67 ± 8.04 on our internal and external test benchmarks measured by the mean Dice similarity coefficient (DSC). Through experimental comparison, the DSC value of the proposed algorithm was improved by 13.54% and 2.02% on the internal benchmark and 13.37% and 2.13% on the external benchmark compared with U-Net without extra sample assistance and the mean-teacher frontier algorithm, respectively. CONCLUSION: The cost-effective pseudolabeled samples assisted the training of DL models and achieved much better results compared with traditional DL models with manually labeled samples only. Furthermore, our method also achieved the best performance compared with other up-to-date dual branch structures.

Progress on diagnosis and treatment of latent tuberculosis infection.

One fourth of the global population has been infected with Mycobacterium tuberculosis, and about 5%-10% of the infected individuals with latent tuberculosis infection (LTBI) will convert to active tuberculosis (ATB). Correct diagnosis and treatment of LTBI are important in ending the tuberculosis epidemic. Current methods for diagnosing LTBI, such as tuberculin skin test (TST) and interferon-γ release assay (IGRA), have limitations. Some novel biomarkers, such as transcriptome derived host genes in peripheral blood cells, will help to distinguish LTBI from ATB. More emphasis should be placed on surveillance in high-risk groups, including patients with HIV infection, those using biological agents, organ transplant recipients and those in close contact with ATB patients. For those with LTBI, treatment should be based on the risk of progression to ATB and the potential benefit. Prophylactic LTBI regimens include isoniazid monotherapy for 6 or 9 months, rifampicin monotherapy for 4 months, weekly rifapentine plus isoniazid for 3 months (3HP regimen) and daily rifampicin plus isoniazid for 3 months (3HR regimen). The success of the one month rifapentine plus isoniazid daily regimen (1HP regimen) suggests the feasibility of an ultra-short treatment strategy although its efficacy needs further assessment. Prophylactic treatment of LTBI in close contact with MDR-TB patients is another challenge, and the regimens include new anti-tuberculosis drugs such as bedaquiline, delamanid, fluoroquinolone and their combinations, which should be carefully evaluated. This article summarizes the current status of diagnosis and treatment of LTBI and its future development direction.

Advances in diagnosis and treatment of non-tuberculous mycobacterial lung disease.

The prevalence of Non-tuberculous Mycobacterial Pulmonary Disease (NTM-PD) is increasing worldwide. The advancement in molecular diagnostic technology has greatly promoted the rapid diagnosis of NTM-PD clinically, and the pathogenic strains can be identified to the species level through molecular typing, which provides a reliable basis for treatment. In addition to the well-known PCR and mNGS methods, there are numerous alternative methods to identify NTM to the species level. The treatment of NTM-PD remains a challenging problem. Although clinical guidelines outline several treatment options for common NTM species infections, in most cases, the therapeutic outcomes of these drugs for NTM-PD often fall short of expectations. At present, the focus of research is to find more effective and more tolerable NTM-PD therapeutic drugs and regimens. In this paper, the latest diagnostic techniques, therapeutic drugs and methods, and prevention of NTM-PD are reviewed.

Cryptogenic organizing pneumonia caused by solanine: A case report.

RATIONALE: Cryptogenic organizing pneumonia (COP) is a type of pneumonia with unknown cause, presenting with symptoms like dyspnea, fever, and cough. Solanine poisoning can cause symptoms like increased heart rate, rapid breathing, sore throat, diarrhea, vomiting, and fever, but there are no known cases of it causing COP. PATIENT CONCERNS: A 43-year-old man had a dry cough, worse at night, with phlegm and chest tightness after eating sprouted potatoes. No history of surgeries or family medical issues. DIAGNOSIS: Laboratory tests and metagenomic next-generation sequencing of bronchoalveolar lavage fluid from the bilateral lower lobes did not yield a definitive pathogen. Further evaluation included testing for vasculitis-associated antibodies and rheumatologic immune markers for myositis spectra to rule out connective tissue disease-associated interstitial lung disease as the etiology of organizing pneumonia. As a result, the final diagnosis was determined to be COP. INTERVENTIONS: The patient received glucocorticoid therapy and oxygen therapy, and responded well to the treatment. OUTCOMES: On the 10th day of hospitalization, the patient was discharged with success. A follow-up chest CT conducted over a month later revealed that the lesions in both lungs had essentially resolved, with only minor residual fibrotic changes present. LESSONS: Regularly monitoring disease progression is crucial for patients with solanine poisoning who have pulmonary symptoms. Promptly conducting chest CT scans and bronchoscopy is advised to check for any infections. It is also important to rule out pneumonia related to connective tissue disease-associated interstitial lung disease and provide appropriate treatment promptly.

T-SPOT with CT image analysis based on deep learning for early differential diagnosis of nontuberculous mycobacteria pulmonary disease and pulmonary tuberculosis.

OBJECTIVES: This study aimed to establish a diagnostic algorithm combining T-SPOT with computed tomography image analysis based on deep learning (DL) for early differential diagnosis of nontuberculous mycobacteria pulmonary disease (NTM-PD) and pulmonary tuberculosis (PTB). METHODS: A total of 1049 cases were enrolled, including 467 NTM-PD and 582 PTB cases. A total of 320 cases (160 NTM-PD and 160 PTB) were randomized as the testing set and were analyzed using T-SPOT combined with the DL model. The testing cases were first divided into T-SPOT-positive and -negative groups, and the DL model was then used to separate the cases into four subgroups further. RESULTS: The precision was found to be 91.7% for the subgroup of T-SPOT-negative and DL classified as NTM-PD, and 89.8% for T-SPOT-positive and DL classified as PTB, which covered 66.9% of the total cases, compared with the accuracy rate of 80.3% of T-SPOT alone. In the other two remaining groups, where the T-SPOT prediction was inconsistent with the DL model, the accuracy was 73.0% and 52.2%, separately. CONCLUSION: Our study shows that the new diagnostic system combining T-SPOT with DL based computed tomography image analysis can greatly improve the classification precision of NTM-PD and PTB when the two methods of prediction are consistent.