Nyctale: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction

Chest CT for Known or Suspected Lung Cancer

Objective To evaluate the correlation between multi-slice CT perfusion imaging features and tumor angiogenesis in solitary pulmonary nodules(SPN).Methods Thirty-four patients with SPN underwent multi-location dynamic contrast enhanced(nonionic contrast material was administrated via the antecubital vein at a rate of 4 ml/ s by using an autoinjector) serial CT.Precontrast and postcontrast attenuation on every scan was recorded.Perfusion,peak height,and ratio of peak height of the SPN to that of the aorta were calculated.Perfusion was calculated from the maximum gradient of the time-attenuation curve and the peak height of the aorta.The quantitative parameters(perfusion,peak height,ratio of peak height of the SPN to that of the aorta) of blood flow pattern were compared with microvessel densities(MVD) and VEGF expression by immunohistochemistry.Results Peak height of malignant [(96.15±11.55)HU] and inflammatory [(101.15±8.41)HU] SPN were significantly higher than that of benign [(47.24±9.15)HU] SPN(F=72.730,P0.001;F=9.728,P0.001).SPN-to-aorta ratios in malignant and inflammatory SPN were significantly higher than that in benign SPN(F=87.51,P0.001;F=8.20,P0.001).No statistically significant differences in the peak height and SPN-to-aorta ratio were found between malignant and inflammatory SPN(F=0.77,P= 0.472;F=0.11,P=0.897).Precontrast density of inflammatory SPN was lower than that of malignant SPN(χ~2=8.49,P0.05).Perfusion values in malignant and inflammatory SPN were significantly higher than that of the benign SPN(F=103.15,P0.01;F=16.88,P0.01).The VEGF positive expressions were found in 16 malignant SPN and 1 benign SPN,and the average value of MVD in malignant(36.88±6.76) was higher than that of benign(4.51±0.60) and inflammatory(26.11±5.43) SPN(F=91.31,P0.01;F=9.39,P0.001).There were statistically significant correlations between CT perfusion parameters and MVD,respectively.The highest correlation,however,was between the PH_(SPN) and MVD(r=0.657,P0.05).Conclusion Tumor microvessel density and VEGF expression are the pathophysiological basis of CT perfusion in SPN.Multi-slice CT perfusion has strong positive correlations with angiogensis in SPN.

The present study was undertaken in order to investigate the penetration of cefonicid, a long-acting parenteral cephalosporin, with enhanced activity against most gram-positive and gram-negative pathogens, into human lung tissue and lymph nodes in patients undergoing open thoracotomy. Samples of lung tissue, lymph nodes and serum were obtained at various times after a single intramuscular dose of 1 g. The concentration of cefonicid was assayed by an agar diffusion method with Bacillus subtilis used as the test organism. The mean concentrations of cefonicid in serum at 2, 4, 8, 12 and 24 h after the injection were 91.5, 66.1, 35.7, 21.8 and 2.9 micrograms/ml, respectively. The mean levels of cefonicid into the hilar lymph nodes at the same times were 22.3, 18.7, 12.0, 6.9 and 1.5 micrograms/ml, respectively, while its concentrations in lung tissue were lower than those in lung lymph nodes up to the 12th hour (12.1, 14.6, 7.8, 5.4 and 1.9 micrograms/ml, respectively). Our results show that cefonicid was well distributed in interstitial fluid from which pulmonary lymph is formed and that its concentrations in lung tissue and lymph nodes were sufficient to inhibit most pathogens involved in respiratory tract infections. This finding was considered important, because it demonstrated that the high binding by plasma protein of cefonicid did not prevent it from entering lung tissue and fluids in useful quantities.

背景与目的中国澳门肺癌发病率逐年上升，吸烟人群是肺癌的高发人群，本研究旨在了解中国澳门长期吸烟人群的肺癌发病情况及胸部低剂量计算机断层扫描(low-dose computed tomography, LDCT)肺结节特点。方法通过澳门中华医学会会员私家医生推荐及宣传招募中国澳门无症状长期吸烟人士，行胸部LDCT检查，分析肺癌、肺部结节检出率及影像学特点。结果符合纳入条件者291例，检出肺癌10例，检出率3.44%(95%CI: 2.78%-4.01%)，其中，肺腺癌5例，鳞癌、小细胞肺癌各2例，腺鳞癌1例。早期肺癌4例，占40%。212例检出肺结节，肺结节总检出率72.9%(95%CI: 67.8%-78.0%); 疑似肺癌结节44例，检出率15.1%(95%CI: 11.0%-19.2%)。单发结节51例，无肺癌检出; 多发结节161例，检出肺癌9例，两组肺癌检出率无统计学差异(P > 0.05)。 < 6 mm实性结节与 < 5 mm非实性结节组168例，未检出肺癌; ≥6 mm实性结节与≥5 mm非实性结节组44例，检出肺癌9例，两组比较有统计学差异(P < 0.05)。结论长期吸烟人群中肺癌检出率高，类型以腺癌为主，肺部结节发生率高，当实性结节≥6 mm或非实性结节≥5 mm时，肺癌检出率增高。建议在符合高危因素的男性吸烟人群中推行胸部LDCT筛查肺癌，女性肺癌筛查，应重新界定高危因素。

8569 Background: With the wide use of CT for lung cancer screening and diagnosis, detection of pulmonary nodules increases drastically. Brock malignancy risk scoring is a validated risk prediction model for distinguishing malignant nodules, but it only provides a snapshot without incorporating the dynamic changes of lung nodules. Our study tested the performance of Brock malignancy risk scoring system in patients with persistent lung nodules. Methods: We prospectively studied a cohort of 304 patients with persistent lung nodules (at least 2 CT scans, 3 months apart with no evidence of shrinkage) who were under management at MD Anderson Cancer Center from 11/28/2018 to 12/14/2022. These lung nodules were assessed by radiologists with Brock full model. These patients were followed up routinely and subjected to biopsy as determined by treating physicians. The area under the receiver operating characteristic curve (AUC) and the optimal cut-off of Brock model was studied. Additionally, we studied another cohort with 130 patients with histologically confirmed lung cancer. We retrospectively reviewed the CT or PET/CT scans and assessed the corresponding persistent lung nodules as defined above prior to the cancer diagnosis. We explored the correlations among nodule characteristics, demographic factors and Brock cancer risk scores. Cox proportional hazards model was built for multivariate analysis. Results: The median follow-up time for the prospective cohort was 337 days and 40 of the 304 patients (13.16%) were diagnosed with lung cancer with a median lung cancer-free survival of 228 days. The mean risk score was 24.20% (0.12%-62.86%) for histologically confirmed malignant vs 11.01% (0.07%-61.84%) for the remaining lung nodules (P &lt; 0.001). Of note, 4 of 46 (8.70%) patients with persistent lung nodules of risk scores between 5%-10% and 8 of 134 (5.97%) patients with risk score &lt; 5% were diagnosed with lung cancer. The AUC for Brock model was 0.72 and the optimal cut-off value is 10.64% (sensitivity: 0.702, specificity:0.677). Among the retrospective cohort of 130 lung cancer patients (82.3% adenocarcinoma, 13.1% squamous cell carcinoma and 4.6% others), the predicted risk score ranged from 0.09% to 85.82%, including 33.85% of patients with risk score &lt; 10% and 26.15% of patients with predicted risk score &lt; 5%. The risk score was not correlated with age, sex, race, ethnicity, smoking history, family history of lung cancer, emphysema, nodule types or locations. The low-risk patients had a longer median cancer-free time (P = 0.001). Conclusions: Persistency is an important risk factor for malignant lung nodules. Using Brock criteria, a substantial proportion of lung nodules with true malignant potential can be overlooked because of predicted “low risk”. Improved prediction models incorporating the dynamic changes of lung nodules are warranted to guide early diagnosis of lung cancer.

To explore the role of the texture features of images in the diagnosis of solitary pulmonary nodules (SPNs) in different sizes. A total of 379 patients with pathologically confirmed SPNs were enrolled in this study. They were divided into three groups based on the SPN sizes: ≤10, 11-20, and >20 mm. Their texture features were segmented and extracted. The differences in the image features between benign and malignant SPNs were compared. The SPNs in these three groups were determined and analyzed with the texture features of images. These 379 SPNs were successfully segmented using the 2D Otsu threshold method and the self-adaptive threshold segmentation method. The texture features of these SPNs were obtained using the method of grey level co-occurrence matrix (GLCM). Of these 379 patients, 120 had benign SPNs and 259 had malignant SPNs. The entropy, contrast, energy, homogeneity, and correlation were 3.5597±0.6470, 0.5384±0.2561, 0.1921±0.1256, 0.8281±0.0604, and 0.8748±0.0740 in the benign SPNs and 3.8007±0.6235, 0.6088±0.2961, 0.1673±0.1070, 0.7980±0.0555, and 0.8550±0.0869 in the malignant SPNs (all P<0.05). The sensitivity, specificity, and accuracy of the texture features of images were 83.3%, 90.0%, and 86.8%, respectively, for SPNs sized ≤10 mm, and were 86.6%, 88.2%, and 87.1%, respectively, for SPNs sized 11-20 mm and 94.7%, 91.8%, and 93.9%, respectively, for SPNs sized >20 mm. The entropy and contrast of malignant pulmonary nodules have been demonstrated to be higher in comparison to those of benign pulmonary nodules, while the energy, homogeneity correlation of malignant pulmonary nodules are lower than those of benign pulmonary nodules. The texture features of images can reflect the tissue features and have high sensitivity, specificity, and accuracy in differentiating SPNs. The sensitivity and accuracy increase for larger SPNs.

The purposes of this study were to analyze the relation between enhancement patterns on dynamic enhanced MRI and histologic microvessel patterns of solitary pulmonary nodules (SPNs) and to address the topic of false-positive findings in differentiating SPNs with dynamic MRI. Sixty-eight patients with 68 pathologically proven SPNs (diameter <or= 30 mm) underwent dynamic 1.5-T MRI. On time-signal intensity curves generated after bolus injection of contrast material, steepest slope, peak height, and enhancement ratios of signal intensity at the first, second, and fourth minutes were calculated. The relation between dynamic MRI values and microvessel density was analyzed. The morphologic differences between malignant SPNs and active inflammatory SPNs also were analyzed. Threshold dynamic MRI values for differential diagnosis were determined. The dynamic MRI values of benign SPNs were significantly lower than those of the other SPNs (p < 0.01). The enhancement ratio at the fourth minute for active inflammatory SPNs was significantly higher than that of malignant SPNs (p < 0.01). A high correlation coefficient (r = 0.87, p < 0.001) was found between steepest slope and microvessel density. With steepest slope 1.5%/s or less, benign SPNs were clearly differentiated from other SPNs. With enhancement ratio at the fourth minute 65% or less, malignant SPNs were differentiated from active inflammatory SPNs with high sensitivity (93%) and high specificity (100%). Dynamic MRI values reflect the quantitative and morphologic characteristics of microvessels in SPNs and are a useful tool for differentiating SPNs with little overlap.

Background: The diagnosis, classification and management of a solitary pulmonary nodule (SPN) have always been a challenge for the clinicians and radiologists. All SPNs should be considered malignant until proven otherwise. Malignancy risk rises with increasing nodule size. Hence evaluation of the various clinical and pathological presentations of SPN is essential. Methodology: A hospital-based cross-sectional study was conducted in a tertiary care teaching hospital on 70 cases of SPN. Chest X-ray, CT (Computed Tomography) and bronchoalveolar lavage were used for analysing the SPN. IBM SPSS version 22 was used for statistical analysis. Results: The incidence of SPN in this study was 1.33 per 1000 population. The total number of chest X-rays screened were 5263. The most common risk factors were exposure to PTB (Pulmonary Tuberculosis) or history of PTB (97.1%), followed by smoking (81.4%), history of STD (32.9%). Dry cough was the most common symptom among (20%). In X-ray, in 57.1% of subjects, the upper lobes were involved. Lesions were central in 41.4% while peripheral in 58.6%. The proportion of nodules with 1.1 to 2cm and above 2 cm was 22.85% and 77.15%. No calcification was found in 78.6% of nodules. In SPN the most common final diagnosis was tuberculosis (14.3%) followed by Pneumonia/abscess (8.6%) and Squamous cell carcinoma and Pseudotumor (5.71% each). 20% of SPN were malignant. 11.42% of nodules turned out to be primary lung malignancy while 1.42% were metastasis and 7.1% were small cell carcinoma. Conclusions: SPN is a common incidental and radiologic finding. Some internal features of SPNs can help in differentiating benign from malignant lesions. Despite radiological imaging, still, a large number of nodules have to be described as “indeterminate” and advanced and often more invasive techniques are needed for further work-up. Keywords: Solitary pulmonary nodule (SPN); Malignancy, Incidence; Bronchoalveolar lavage.

Lung cancer is the leading cause of cancer death among both men and women. The solitary pulmonary nodule (SPN) is frequently seen on radiographs and computed tomography (CT) and often provokes additional clinical and imaging activities as an SPN alerts possible early stage lung cancer. However, reliable diagnosis of malignant lung nodules in the workup of SPN is challenging, making it difficult for early stage cancer management to avoid morbidity due to malignant cancer, patient distress, and increased costs caused by more invasive and unwarranted procedures for benign cases. We developed a deep learning model based on convolutional neural networks (CNNs) to predict lung cancer risk for incidental SPN. The model can help better management of incidental lung cancer by providing a reliable characterization of SPNs. Deep learning models currently are applied to nodule detection in low-dose CT scans of lung cancer screening for at-risk population. Our work aims to investigate whether deep learning can differentiate benign from malignant incidental SPN during normal dose CT exams, where the number of patients with SPN is an order more than that of lung screening population. We collected an incidental SPN dataset containing 139 CT scans to generate the nodule malignancy prediction model using 3D CNN. This dataset was collected from either contrast or non-contrast CT scans with regular doses. All 139 patients went through surgeries to remove the tumors. CT images were collected within one year before the surgery. 90 cases are malignant and the rest are benign. Ground truth labels were obtained from biopsies. Data were preprocessed by resampling, normalization, and cropping to unique volume around the SPN. The radiologists annotated the SPN location. Since the two nodule classes are imbalanced, we did online data augmentation to increase the variety of lung nodule images and balance the two classes. We used 80% of the data for training and 20% for testing. The deep learning structure adapted is a 3D Resnet with 68 layers and 33M parameters. The area under the receiving operating characteristics curve (AUC) of the prediction result was 0.81 while the accuracy was 79.6%. Applying GradCam to visualize important regions in CT scans contributing to the final predictions, we found that our trained ResNet model focuses on meaningful areas in lung nodules and detects malignant SPNs in most cases. Our preliminary results shows the feasibility of using deep learning to predict incidental lung nodules and improve diagnostic speed and accuracy. Citation Format: Pengyu Yuan, Tiancheng He, Hien Nguyen, Stephen T. Wong. A deep learning model-based lung cancer risk assessment for incidental pulmonary nodules [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2614.

Objective To evaluate the value of CT-guided percutaneous biopsy for diagnosis of solitary ground glass nodules(GGO) around the lung. Methods Fifty-nine patients with solitary frosted glass nodules around the lungs who underwent CT examinations from January 2017 to December 2017 were enrolled in the study. All patients underwent CT-guided percutaneous biopsy, which was confirmed by surgery, clinical, or follow-up, in accordance with the maximum diameter of the lung GGO axial position, the proportion of solid components, the location of the lesion, the distance from the pleura, the angle of the needle-pleural, and the number of needle adjustments. Univariate analysis was used to determine the diagnostic accuracy, sensitivity, specificity, and incidence of complications. A chi-square test was used to compare the benign and malignant between solid components ≤50% and >50% in mixed GGO. Results The accuracy, sensitivity, and specificity of the diagnosis of 59 patients with solitary pulmonary GGO were 89.8%(53/59), 84.2%(32/38), and 100%(21/21), respectively, thereby confirming the disease as adenocarcinoma. According to different groups used in the method, the accuracy of the diagnosis is higher than 80%, the sensitivity is higher than 75%, and the specificity is 100%, but the incidence of overall complications is also higher. The difference between the mixed GGO solid components ≤50% and >50% was statistically significant(χ2=6.13, P<0.05). Conclusions CT-guided percutaneous biopsy has high diagnostic value for isolated GGO. The proportion of solid components in GGO has a certain correlation with the degree of malignancy. Key words: Tomography, X-ray computed; Solitary pulmonary nodule; Ground-glass nodule; Percutaneous biopsy

The diagnostic yield from fluoroscopy-guided bronchoscopic transbronchial biopsy of small solitary pulmonary nodules is low. The hypothesis tested in the present study was that the diagnostic yield can be significantly increased by combining flexible bronchoscopy with CT-guidance using a dedicated low-dose protocol. CT-guided transbronchial biopsies were performed in 15 patients with a newly diagnosed solitary peripheral pulmonary nodule and negative conventional bronchoscopic biopsies under fluoroscopic guidance. For imaging, a multi-detector helical CT unit, adjusted at 120 kV, 15 mAs/slice, 4 x 5 mm collimation, 10 mm reconstructed slice thickness and a maximal scan length of 150 mm, was used. After advancing the biopsy forceps towards the lesion, a CT scan was obtained. When the tip of the forceps reached or penetrated the lesion a biopsy was taken, otherwise the procedure was repeated with a maximum of eight attempts. The effective radiation dose was calculated. The average diameter of the nodules was 23 +/- 6 mm (mean +/- SD) with a maximum distance to the parietal pleura of 18 mm (mean 6.5 mm). A mean of 4.1 (range 2-8) CT scans was performed to localize the lesion. In four patients, the forceps only reached the periphery of the nodule. In one patient, the nodule was missed in all attempts. Histology was malignant in eight patients and benign in four patients. In three patients, biopsy results were false negative (benign or non-specific instead of malignant). The overall diagnostic yield was 73%. Complications consisted of two pneumothoraces, one of which necessitated a chest tube. Mean effective radiation dose was 0.55 mSv (range 0.3-1.0). CT-guided transbronchial biopsy can be a valuable diagnostic tool in evaluating solitary pulmonary nodules. This applies for selected patients when other diagnostic methods are either unavailable or inappropriate. The diagnostic yield is high and, when a low-dose protocol is used, radiation exposure can be kept at a minimum.

To evaluate the efficacy of dynamic computed tomography (CT) for differentiating benign from malignant solitary pulmonary nodules (SPNs). Sixty-five patients with noncalcified SPNs (diameter, < or = 30 mm; 42 malignant, 16 benign, seven inflammatory) underwent single-location dynamic contrast material-enhanced (100 mL, 4 mL/sec) serial CT. Peak height of time-attenuation curves and ratio of peak height of the SPN to that of the aorta were measured. Precontrast attenuation and enhancement pattern were recorded. Perfusion was calculated from the maximum gradient of the time-attenuation curve and the peak height of the aorta. Peak heights of malignant (41.9 HU +/- 2.8) and inflammatory (43.6 HU +/- 7.7) SPNs were significantly higher than that (13.4 HU +/- 2.2) of benign SPNs (P < .001; P < .01). SPN-to-aorta ratios in malignant and inflammatory SPNs were significantly higher than that in benign SPNs (P < .001, P < .05). No statistically significant differences in the peak height and SPN-to-aorta ratio were found between malignant and inflammatory SPNs. Precontrast attenuation of inflammatory SPNs was lower than that of malignant SPNs (P < .05). Perfusion values in malignant and inflammatory SPNs were significantly higher than that of the benign SPNs (P < .01). Dynamic CT provides quantitative information about blood flow patterns of SPNs and is an applicable diagnostic method for differentiating SPNs.

Objective To evaluate the application value of circulating tumor cell (CTC) in the differential diagnosis of solitary pulmonary nodule (SPN). Methods Peripheral blood samples were collected from 134 patients with solitary pulmonary nodule in Shanghai Chest Hospital from September 2013 to January 2015, including 80 patients with malignant nodule and 54 with benign nodule. CTC levels of the above subjects were detected by ligand-targeted polymerase chain reaction (LT-PCR) assay, and serum carcinoembryonic antigen (CEA) and cytokeratin 19 fragment (CYFRA21-1) were detected by flow fluorescence assay. Results By Mann-Whitney U Test, the CTC levels of malignant SPN patients [11.06(8.77-14.41)units/3 ml] were significantly higher than those of benign SPN patients [6.65(4.49-7.84)units/3 ml] (Z=-6.217, P<0.001). The sensitivity and specificity of differential diagnosis of SPN for CTC were 80%(64/80)and 85%(46/54)respectively. According to the diameter of SPN, the patients were divided into three groups to evaluate the diagnostic value of CTC in SPN with different size. For SPN with diameter less than 8 mm, the sensitivity and specificity of CTC were 6/9 and 4/5 respectively. For SPN with diameter between 8 mm and 20 mm, the sensitivity and specificity of CTC were 83%(35/42) and 85%(29/34). For SPN with diameter greater than 20 mm, the sensitivity and specificity of CTC were 79% (23/29)and 13/15. Conclusion Comparing with the traditional tumor markers, CTC could provide more clinical value in the differential diagnosis of solitary pulmonary nodule. (Chin J Lab Med, 2016, 39: 941-945) Key words: Solitary pulmonary nodule; Neoplastic cells, circulating; Diagnosis, differential

Objective: To evaluate the efficacy of dynamic multi-slice spiral computed tomography (MSCT) for providing quantitative information about blood flow patterns of solitary pulmonary nodules (SPNs) and differentiating solitary pulmonary nodules (SPNs). Methods: 37 patients with SPNs (diameter≤4 cm; 24 with maliagnant; 6 with benign; 7 with inflammatory) underwent multi-location dynamic contrast material-enhanced (90 mL, 4 mL/s) serial CT. Peak height and ratio of peak height of the SPN to that of the aorta were measured. Precontrast attenuation was recorded. Perfusion was calculated from the maxi- mum gradient of the time-attenuation curve and the peak height of the aorta. Results: Peak heights of malignant (37.98 HU±17.97) and inflammatory (43.86 HU±14.20) SPNs were significantly higher than those of benign SPNs (5.65 HU±6.43) (P 0.01). SPN-to-aorta ratio in inflammatory SPNs (20.78%±4.14) was significantly higher than that in benign (2.00%±2.26) and malig- nant (14.63%±6.22) SPNs (P 0.01). Conclusion: MSCT provides quanti- tative information about blood flow patterns of solitary pulmonary nodules (SPNs) and is applicable diagnostic method for differentiating SPNs.

ObjectivesTo determine the factors associated with lung cancer diagnosis and mortality after detecting a solitary pulmonary nodule (SPN) in routine clinical practice, in men and in women for both chest radiograph and CT.Materials and methodsA 5-year follow-up of a retrospective cohort of of 25,422 (12,594 men, 12,827 women) patients aged ≥35 years referred for chest radiograph or CT in two hospitals in Spain (2010–2011). SPN were detected in 893 (546 men, 347 women) patients. We estimated the cumulative incidence of lung cancer at 5-years, the association of patient and nodule characteristics with SPN malignancy using Poisson logistic regression, stratifying by sex and type of imaging test. We calculated lung cancer specific mortality rate by sex and SPN detection and hazard rates by cox regression.Results133 (14.9%) out of 893 patients with an SPN and 505 (2.06%) of the 24,529 patients without SPN were diagnosed with lung cancer. Median diameter of SPN in women who developed cancer was larger than in men. Men who had a chest radiograph were more likely to develop a lung cancer if the nodule was in the upper-lobes, which was not the case for women. In patients with an SPN, smoking increased the risk of lung cancer among men (chest radiograph: RR = 11.3, 95%CI 1.5–83.3; CT: RR = 7.5, 95%CI 2.2, 26.0) but smoking was not significantly associated with lung cancer diagnosis or mortality among women with an SPN. The relative risk of lung cancer diagnosis in women with SPN versus those without was much higher compared to men (13.7; 95%CI 9.2, 20.4 versus 6.2; 95%CI 4.9,7.9).ConclusionThe factors associated with SPN malignancy and 5-year lung cancer mortality were different among men and women, especially regarding smoking history and SPN characteristics, where we observed a relatively high rate of lung cancer diagnosis among female non-smokers.