Identifying lung cancer in patients with active pulmonary tuberculosis

BAF-Net: bidirectional attention-aware fluid pyramid feature integrated multimodal fusion network for diagnosis and prognosis

Objective. To go beyond the deficiencies of the three conventional multimodal fusion strategies (i.e. input-, feature- and output-level fusion), we propose a bidirectional attention-aware fluid pyramid feature integrated fusion network (BAF-Net) with cross-modal interactions for multimodal medical image diagnosis and prognosis.Approach. BAF-Net is composed of two identical branches to preserve the unimodal features and one bidirectional attention-aware distillation stream to progressively assimilate cross-modal complements and to learn supplementary features in both bottom-up and top-down processes. Fluid pyramid connections were adopted to integrate the hierarchical features at different levels of the network, and channel-wise attention modules were exploited to mitigate cross-modal cross-level incompatibility. Furthermore, depth-wise separable convolution was introduced to fuse the cross-modal cross-level features to alleviate the increase in parameters to a great extent. The generalization abilities of BAF-Net were evaluated in terms of two clinical tasks: (1) an in-house PET-CT dataset with 174 patients for differentiation between lung cancer and pulmonary tuberculosis. (2) A public multicenter PET-CT head and neck cancer dataset with 800 patients from nine centers for overall survival prediction.Main results. On the LC-PTB dataset, improved performance was found in BAF-Net (AUC = 0.7342) compared with input-level fusion model (AUC = 0.6825;p< 0.05), feature-level fusion model (AUC = 0.6968;p= 0.0547), output-level fusion model (AUC = 0.7011;p< 0.05). On the H&N cancer dataset, BAF-Net (C-index = 0.7241) outperformed the input-, feature-, and output-level fusion model, with 2.95%, 3.77%, and 1.52% increments of C-index (p= 0.3336, 0.0479 and 0.2911, respectively). The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets.Significance. Extensive experiments on two datasets demonstrated better performance and robustness of BAF-Net than three conventional fusion strategies and PET or CT unimodal network in terms of diagnosis and prognosis.

Treatment Strategies for Non-Small-Cell Lung Cancer with Comorbid Respiratory Disease; Interstitial Pneumonia, Chronic Obstructive Pulmonary Disease, and Tuberculosis

Non-small cell lung cancer (NSCLC) patients are often complicated by other respiratory diseases, including interstitial pneumonia (IP), chronic obstructive pulmonary disease (COPD), and pulmonary tuberculosis (TB), and the management of which can be problematic. NSCLC patients with IP sometimes develop fatal acute exacerbation induced by pharmacotherapy, and the establishment of a safe treatment strategy is desirable. For advanced NSCLC with IP, carboplatin plus nanoparticle albumin-bound paclitaxel is a relatively safe and effective first-line treatment option. Although the safety of immune checkpoint inhibitors (ICIs) for these populations remains controversial, ICIs have the potential to provide long-term survival. The severity of COPD is an important prognostic factor in NSCLC patients. Although COPD complications do not necessarily limit treatment options, it is important to select drugs with fewer side effects on the heart and blood vessels as well as the lungs. Active TB is complicated by 2-5% of NSCLC cases during their disease course. Since pharmacotherapy, especially ICIs, reportedly induces the development of TB, the possibility of developing TB should always be kept in mind during NSCLC treatment. To date, there is no coherent review article on NSCLC with these pulmonary complications. This review article summarizes the current evidence and discusses future prospects for treatment strategies for NSCLC patients complicated with IP, severe COPD, and TB.

PET morphology helps distinguish solitary and solid pulmonary tuberculosis from non-small cell lung cancer

OBJECTIVE

Solitary and solid pulmonary tuberculosis (PTB) and non-small cell lung cancer (NSCLC) can present overlapping imaging features, causing diagnostic dilemmas. Hence, this study aimed to identify positron emission tomography (PET) morphological features derived from fluorine-18-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images for a better differential diagnosis.

METHODS

Clinical records and ¹⁸F-FDG PET/CT images of 175 patients confirmed with PTB and 311 patients with NSCLC were retrospectively reviewed. Parameters including patient demographics, PET-derived morphological features and metabolic parameters, and CT-derived morphological features were investigated. Logistic regression analysis was performed to assess the independent predictive factors associated with PTB.

RESULTS

PTB presented with more heterogeneous glucometabolism than NSCLC in PET imaging (50% vs 17%, P < 0.05), especially in lesions with a maximum diameter < 30 mm (39% vs. 5%, P < 0.05). NSCLC usually showed centric hypometabolism, whereas PTB more frequently presented with an eccentric metabolic pattern, mainly including piebald, half-side, lesser curvature, and greater curvature shapes. Multivariate logistic regression identified that glucometabolic heterogeneity, eccentric hypometabolism, smaller lesion size, calcification, satellite lesions, and higher CT value of the hypometabolic area were independently diagnostic factors for PTB.

CONCLUSIONS

Morphological features derived from ¹⁸F-FDG PET images helped distinguish solitary and solid PTB from NSCLC.

The Bidirectional Relationship between Pulmonary Tuberculosis and Lung Cancer

Lung cancer and pulmonary tuberculosis are two significant public health problems that continue to take millions of lives each year. They may have similar symptoms and, in some cases, are diagnosed simultaneously or may have a causal relationship. In tuberculosis disease, the chronic inflammation, different produced molecules, genomic changes, and fibrosis are believed to be important factors that may promote carcinogenesis. As a reverse reaction, the development of carcinogenesis and the treatment may induce the reactivation of latent tuberculosis infection. Moreover, the recently used checkpoint inhibitors are a debatable subject since they help treat lung cancer but may lead to the reactivation of pulmonary tuberculosis and checkpoint-induced pneumonitis. Pulmonary rehabilitation is an effective intervention in post-tuberculosis patients and lung cancer patients and should be recommended to improve outcomes in these pathologies.

A Comprehensive Study on the Correlation of Treatment, Diagnosis and Epidemiology of Tuberculosis and Lung Cancer

The correlation between tuberculosis (TB) and lung cancer (LC) in diagnosis, epidemiology, and treatment is still unclear. Based on different cohort and retrospective studies, this correlation could be justified by immune weakness because of exposure to TB which may increase the risk of LC. In this study, we tried to exhibit a prominent connection between TB and LC. The diagnosis and treatment of patients with concomitant TB and LC differ from patients with only one of the diseases. In this review, it was well clarified that the most practical diagnostic method for LC is chest tomography, biopsy, and histopathology, and for pulmonary TB sputum microscopic examination, Autofluorescence bronchoscopy (AFB), culture, and PCR. Also, immunological methods can be a good alternative for differential diagnosis. Most epidemiological studies were about concomitant TB and LC in TB-endemic areas, especially in the Middle East. The most suggested methods for definite treatment of LC are chemotherapy, radiotherapy, and surgery while for TB, a long course of anti-TB therapy can be used. Moreover, immunotherapy is considered a good treatment for lung cancer if the interferon-gamma release assay (IGRA) is negative.

The value of dual-energy spectral CT in differentiating solitary pulmonary tuberculosis and solitary lung adenocarcinoma

BACKGROUND

To explore the value of dual-energy spectral CT in distinguishing solitary pulmonary tuberculosis (SP-TB) from solitary lung adenocarcinoma (S-LUAD).

METHODS

A total of 246 patients confirmed SP-TB (n = 86) or S-LUAD (n = 160) were retrospectively included. Spectral CT parameters include CT40keV value, CT70keV value, iodine concentration (IC), water concentration (WC), effective atomic number (Zeff), and spectral curve slope (λ70keV). Data were measured during the arterial phase (AP) and venous phase (VP). Chi-square test was used to compare categorical variables, Wilcoxon rank-sum test was used to compare continuous variables, and a two-sample t-test was used to compare spectral CT parameters. ROC curves were used to calculate diagnostic efficiency.

RESULTS

There were significant differences in spectral CT quantitative parameters (including CT40keV value [all P< 0.001] , CT70keV value [all P< 0.001], λ70keV [P< 0.001, and P = 0.027], Zeff [P =0.015, and P = 0.001], and IC [P =0.002, and P = 0.028]) between the two groups during the AP and VP. However, WC (P = 0.930, and P = 0.823) was not statistically different between the two groups. The ROC curve analysis showed that the AUC in the AP and VP was 90.9% (95% CI, 0.873-0.945) and 83.4% (95% CI, 0.780-0.887), respectively. The highest diagnostic performance (AUC, 97.6%; 95% CI, 0.961-0.991) was achieved when all spectral CT parameters were combined with clinical variables.

CONCLUSION

Dual-energy spectral CT has a significant value in distinguishing SP-TB from S-LUAD.

Epidemiological Study of Risk Factors for Lung Cancer in KwaZulu-Natal, South Africa

The high incidence cancer rates are due to factors such as behavior, occupational exposures, genetics, environmental pollution and infections. The aim of this study was to identify risk factors associated with lung cancer among patients seen in the public health facilities in KwaZulu-Natal, South Africa. In this case-control study, 75 cases and 159 controls were interviewed using a structured close-ended questionnaire. Logistic regression showed a positive association between lung cancer and tobacco smoking (OR = 2.86, 95% CI: 1.21-6.77) and exposure to passive smoke (OR = 3.28, 95% CI: 1.48-7.30). When adjusted for other covariates, tobacco smoking and passive smoke were still positively associated with increased risk of lung cancer. Alcohol consumption (aORs ranging from 2.79 to 3.35) and history of lung disease (aORs ranging from 9.91 to 12.1) were statistically significantly associated with lung cancer. Our study suggests that tobacco smoke exposure is the major cause of lung cancer, and increased exposure to occupational and environmental carcinogenic substances, alcohol consumption and history of lung disease increase the risk of lung cancer. Based on our findings, policy development and planning of prevention strategies incorporating smoking legislations, occupational health and safety are essential in South Africa.

The relationship between previous pulmonary tuberculosis and risk of lung cancer in the future

Various investigations have expanded the views that tuberculosis is an important risk factor for lung cancer occurrence. Lung cancer originates from chronic inflammation and infection. It is becoming clearer that Mycobacterium tuberculosis (M.tb) in tuberculosis patients meticulously schemes multiple mechanisms to induce tumor formation and is indispensable to participate in the occurrence of lung cancer. In addition, some additional factors such as age, sex and smoking, accelerate the development of lung cancer after Mycobacterium tuberculosis infection. The clarification of these insights is fostering new diagnoses and therapeutic approaches to prevention of the patients developing from tuberculosis into lung cancer.

A review on advances in 18F-FDG PET/CT radiomics standardisation and application in lung disease management

Radiomics analysis quantifies the interpolation of multiple and invisible molecular features present in diagnostic and therapeutic images. Implementation of 18-fluorine-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) radiomics captures various disorders in non-invasive and high-throughput manner. ¹⁸F-FDG PET/CT accurately identifies the metabolic and anatomical changes during cancer progression. Therefore, the application of ¹⁸F-FDG PET/CT in the field of oncology is well established. Clinical application of ¹⁸F-FDG PET/CT radiomics in lung infection and inflammation is also an emerging field. Combination of bioinformatics approaches or textual analysis allows radiomics to extract additional information to predict cell biology at the micro-level. However, radiomics texture analysis is affected by several factors associated with image acquisition and processing. At present, researchers are working on mitigating these interrupters and developing standardised workflow for texture biomarker establishment. This review article focuses on the application of ¹⁸F-FDG PET/CT in detecting lung diseases specifically on cancer, infection and inflammation. An overview of different approaches and challenges encountered on standardisation of ¹⁸F-FDG PET/CT technique has also been highlighted. The review article provides insights about radiomics standardisation and application of ¹⁸F-FDG PET/CT in lung disease management.

Coexistence of tuberculosis and squamous cell carcinoma in the right main bronchus: A case report

BACKGROUND

Lung cancer with pulmonary tuberculosis (TB) refers to the occurrence of lesions simultaneously or sequentially in the lung(s) of the same patient, and the pathological examination and sputum TB examination diagnose them as lung cancer and TB, respectively. The occurrence of endobronchial TB (EBTB) with endobronchial tumor sequentially in the same bronchus lesion of the same patient is relatively rare.

CASE SUMMARY

A 62-year-old female patient was admitted to a local hospital on June 18, 2019 after a 3-mo history of dyspnea. She was a farmer and had no history of smoking and alcohol misuse. The patient had neither family nor work contact indicating exposure to TB. Emergency chest computed tomography (CT) examination showed that the right main bronchus was occupied and malignant tumor was possible. Histopathologic examination of a bronchial biopsy showed granulomatous inflammation with caseification and the presence of acid fast bacilli (AFB). However, after 6 mo of antitubercular treatment, repeat bronchoscopy and biopsy histological examination showed squamous cell carcinoma. The patient has started on systemic chemotherapy with carboplatin. After another two cycles of therapy, chest CT showed complete resolution of the lesions. Bronchoalveolar lavage and bronchial aspirate were negative for AFB and cancer cells.

CONCLUSION

It is not only more likely that a patient presenting with what appears to be TB will concurrently have a pulmonary malignancy than someone who does not have a TB infection, but also that it is of greater urgency to make an expedited diagnosis of the malignancy.

SARS-CoV-2 and Mycobacterium tuberculosis coinfection: A case of unusual bronchoesophageal fistula

Tuberculosis is a treatable and curable bacterial disease caused by Mycobacterium tuberculosis that most often affects the lung. Since 2018, it has become the leading cause of death from infectious diseases. Tuberculosis is a public health problem in French Guiana. The majority of reported cases are diagnosed among people coming from neighboring Latin American countries. Since March 2020, French Guiana has been affected, like the rest of the world, by the new infectious disease COVID19 linked to the SARS-CoV-2 coronavirus. We here report a case of COVID19 and pulmonary tuberculosis coinfection. COVID19 pneumonia was the mode of discovery of the tuberculosis. In the present case, the tuberculosis appeared as parenchymal and endobronchial pseudotumoral lesion, which has been complicated by a bronchoesophageal fistula. The evolution of the parenchymal, endobronchial lesion and bronchoesophageal fistula was favorable after two months of anti-tuberculosis treatment.

Associated factors of co-existent pulmonary tuberculosis and lung cancer: A case-control study

BACKGROUND

Although the incidence of co-existent pulmonary tuberculosis (PTB) and lung cancer in China is increasing, risk factors related to its development are still poorly understood. We aimed to investigate which clinical factors were associated with the odds of co-existent PTB and lung cancer (PTB-lung cancer) cases in a case-control study.

METHOD

A total of 125 PTB-lung cancer patients were enrolled by Beijing Chest Hospital as the case group between January 2012 and December 2016. Age- and sex-matched PTB-only (N = 125) and lung cancer-only (N = 125) patients were selected as the control groups. Data were collected from the medical records and computed tomography (CT) reports. The case group was further categorized into three sub-groups according to the diagnosis intervals between previous PTB and lung cancer (<1 year, 1-10 years, and > 10 years).

RESULT

Compared with both controls of PTB-only and lung cancer-only patients, the PTB-lung cancer case group had significantly higher proportions of patients with irritant cough, expectoration, hemoptysis, fever and CT features of irregular mass and pleural thickening. For PTB patients, fibrous calcification (OR, 2.193; 95%CI, 1.168-4.117) was associated with higher odds of lung cancer (P-value < .05).

CONCLUSION

Distinct clinical symptoms and CT tests may help with the early diagnosis of PTB-lung cancer cases. PTB patients with fibrous calcification may have a higher risk of lung cancer. Further multicenter prospective studies are required to validate our findings.

Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer

PURPOSE

We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images.

PROCEDURES

A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.

RESULTS

The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323).

CONCLUSION

The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.

Efficacy and safety of concurrent anti-tuberculosis treatment and chemotherapy in lung cancer patients with co-existent tuberculosis

Background

This retrospective study evaluated the safety and efficacy of concurrent anti-tuberculosis (TB) and chemotherapy treatment in patients with advanced lung cancer and active TB.

Methods

We retrospectively analyzed patients who were first diagnosed with advanced lung cancer and received first-line chemotherapy in Guangzhou Chest Hospital from 2015 to 2017. Patients were categorized into two groups (2:1): lung cancer patients without active TB (Group A), and lung cancer patients with active TB (Group B). Primary endpoints included adverse events (AEs), objective response rate (ORR), time to treatment failure, and overall survival (OS).

Results

A total of 99 patients were eligible (Group A, n=66; Group B, n=33). Grade ≥3 treatment-related AEs, primarily hematologic toxicity, occurred in 39.4% and 51.5% of patients in Groups A and B, respectively. The hypohepatia in both groups was generally at grade 1 or 2, with similar incidences (26% and 27%, respectively). After two cycles of chemotherapy, the ORR was 42.4% and 33.3% in Group A and B, respectively (P=0.383). The median time to treatment failure (TTF) was 7.0 and 5.6 months for Groups A and B, respectively (P=0.175). The median OS was 17.0 and 14.0 months for Groups A and B, respectively (P=0.312). After 3 months of anti-TB treatment, all patients achieved sputum acid-fast bacilli (AFB) smear conversion and absorption on imaging, and the end of follow-up observed no recurrence.

Conclusions

Concurrent anti-TB and chemotherapy treatment did not increase hematological toxicity or hypohepatia in lung cancer patients with pulmonary TB.

Co-existence of well-differentiated fetal adenocarcinoma of the lung with tuberculosis in a young female: A rare case report

RATIONALE

Fetal adenocarcinoma of the lung (FLAC) with fetal lung-like morphology is a rare entity of pulmonary adenocarcinoma. Well-differentiated fetal adenocarcinoma (WDFA) belongs to its the low-grade form, which possesses a relatively favorable prognosis. Tuberculosis (TB) is an aggressive infectious disease that has been ranked as one of the top 10 causes of death worldwide. There may be a connection between the 2 and attention should be paid to the differential diagnosis.

PATIENT CONCERNS

A 28-year-old non-smoking female was admitted with signs of hemoptysis, and she had been coughing up phlegm for 5 years. The patient was previously diagnosed with TB in another hospital, and underwent an anti-TB regimen.

DIAGNOSIS

The co-existence of WDFA and TB was confirmed via histopathological evaluation of postoperative samples.

INTERVENTIONS

The patient was subjected to a right lower lobectomy together with a wedge resection of the right upper lobe using video-assisted thoracoscopic surgery, with systemic lymphadenectomy.

OUTCOMES

The patient tolerated the surgical procedure well and underwent an uneventful postoperative course.

LESSONS

To our knowledge, no previous reports exist of cases with WDFA accompanied by TB. The present case indicated that a prior diagnosis of TB might predispose to lung cancer regardless of smoking history. It is also essential to distinguish WDFA from TB because of the similarity in clinical features and sites of pathological changes. Patients with WDFA usually have a better prognosis and surgery is the preferred treatment.