Impact of Computer-Aided CT and PET Analysis on Non-invasive T Staging in Patients with Lung Cancer and Atelectasis

Purpose

Tumor delineation within an atelectasis in lung cancer patients is not always accurate. When T staging is done by integrated 2-deoxy-2-[¹⁸F]fluoro-d-glucose ([¹⁸F]FDG)-positron emission tomography (PET)/X-ray computer tomography (CT), tumors of neuroendocrine differentiation and slowly growing tumors can present with reduced FDG uptake, thus aggravating an exact T staging. In order to further exhaust information derived from [¹⁸F]FDG-PET/CT, we evaluated the impact of CT density and maximum standardized uptake value (SUVmax) for the classification of different tumor subtypes within a surrounding atelectasis, as well as possible cutoff values for the differentiation between the primary tumor and atelectatic lung tissue.

Procedures

Seventy-two patients with histologically proven lung cancer and adjacent atelectasis were investigated. Non-contrast-enhanced [¹⁸F]FDG-PET/CT was performed within 2 weeks before surgery/biopsy. Boundaries of the primary within the atelectasis were determined visually on the basis of [¹⁸F]FDG uptake; CT density was quantified manually within each primary and each atelectasis.

Results

CT density of the primary (36.4 Hounsfield units (HU)?±?6.2) was significantly higher compared to that of atelectatic lung (24.3 HU?±?8.3; p?<?0.01), irrespective of the histological subtype. The discrimination between different malignant tumors using density analysis failed. SUVmax was increased in squamous cell carcinomas compared to adenocarcinomas. Irrespective of the malignant subtype, a possible cutoff value of 24 HU may help to exclude the presence of a primary in lesions below 24 HU, whereas a density above a threshold of 40 HU can help to exclude atelectatic lung.

Conclusion

Density measurements in patients with lung cancer and surrounding atelectasis may help to delineate the primary tumor, irrespective of the specific lung cancer subtype. This could improve T staging and radiation treatment planning (RTP) without additional application of a contrast agent in CT, or an additional magnetic resonance imaging (MRI), even in cases of lung tumors of neuroendocrine differentiation or in slowly growing tumors with less avidity to [¹⁸F]FDG.

     

Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations

Purpose 

Temporal Enhanced Ultrasound (TeUS) has been proposed as a new paradigm for tissue characterization based on a sequence of ultrasound radio frequency (RF) data. We previously used TeUS to successfully address the problem of prostate cancer detection in the fusion biopsies.

Methods 

In this paper, we use TeUS to address the problem of grading prostate cancer in a clinical study of 197 biopsy cores from 132 patients. Our method involves capturing high-level latent features of TeUS with a deep learning approach followed by distribution learning to cluster aggressive cancer in a biopsy core. In this hypothesis-generating study, we utilize deep learning based feature visualization as a means to obtain insight into the physical phenomenon governing the interaction of temporal ultrasound with tissue.

Results 

Based on the evidence derived from our feature visualization, and the structure of tissue from digital pathology, we build a simulation framework for studying the physical phenomenon underlying TeUS-based tissue characterization.

Conclusion 

Results from simulation and feature visualization corroborated with the hypothesis that micro-vibrations of tissue microstructure, captured by low-frequency spectral features of TeUS, can be used for detection of prostate cancer.

     

Impact of parametric imaging on contrast-enhanced ultrasound of breast cancer

Purpose

To prospectively evaluate the usefulness of contrast-enhanced ultrasound (CEUS) using parametric imaging for breast cancer in a multicenter study.

Methods

A total of 65 patients with breast cancer were included in this study. CEUS was performed, and still images on peak time (S), accumulated images (A) and parametric images (P) were generated from the raw data. Four blind reviewers ranked the best visible images as first place, and determined second and third place consecutively. We compared the average ranking of each image. The maximal diameter of the tumor determined on ultrasonography and MRI was compared with the corresponding pathological maximal diameter for 48 of the 65 patients. The correlation between the diameter determined by two experts and two beginners was analyzed.

Results

The average rank of visibility was as follows: P, 1.44; A, 2.04; and S, 2.52. The correlation between each image and the pathology was as follows: P, r = 0.664; A, r = 0.630; S, r = 0.717; and MRI, r = 0.936. There were no significant differences among the correlation between the experts and beginners in each image.

Conclusions

The use of parametric imaging improves the visibility of CEUS. The maximal diameter of the tumor determined on CEUS correlates substantially with the pathology.

     

BEM-based simulation of lung respiratory deformation for CT-guided biopsy

Purpose

Accurate and real-time prediction of the lung and lung tumor deformation during respiration are important considerations when performing a peripheral biopsy procedure. However, most existing work focused on offline whole lung simulation using 4D image data, which is not applicable in real-time image-guided biopsy with limited image resources. In this paper, we propose a patient-specific biomechanical model based on the boundary element method (BEM) computed from CT images to estimate the respiration motion of local target lesion region, vessel tree and lung surface for the real-time biopsy guidance.

Methods

This approach applies pre-computation of various BEM parameters to facilitate the requirement for real-time lung motion simulation. The resulting boundary condition at end inspiratory phase is obtained using a nonparametric discrete registration with convex optimization, and the simulation of the internal tissue is achieved by applying a tetrahedron-based interpolation method depend on expert-determined feature points on the vessel tree model. A reference needle is tracked to update the simulated lung motion during biopsy guidance.

Results

We evaluate the model by applying it for respiratory motion estimations of ten patients. The average symmetric surface distance (ASSD) and the mean target registration error (TRE) are employed to evaluate the proposed model. Results reveal that it is possible to predict the lung motion with ASSD of \(1.9\pm 0.8\) mm and a mean TRE of \(2.5\pm 2.1\) mm at largest over the entire respiratory cycle. In the CT-/electromagnetic-guided biopsy experiment, the whole process was assisted by our BEM model and final puncture errors in two studies were 3.1 and 2.0 mm, respectively.

Conclusion

The experiment results reveal that both the accuracy of simulation and real-time performance meet the demands of clinical biopsy guidance.

     

Central vascular structures as a characteristic finding of regenerative nodules using hepatobiliary phase gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid-enhanced MRI and arterial dominant phase contrast-enhanced US

Objective

We investigated the characteristic findings of regenerative nodules (RNs) for differentiating early hepatocellular carcinoma (HCC) from high-grade dysplastic nodules (HGDNs) using magnetic resonance imaging (MRI) with gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid (Gd-EOB-DTPA; EOB-MRI) and contrast-enhanced ultrasonography (CEUS) in patients with chronic liver disease.

Subjects and methods

Pathologically confirmed lesions (100 early HCCs, 7 HGDNs, and 20 RNs with a maximum diameter of more than 1 cm and mean maximal diameters of 15.5, 15.1, and 14.8 mm, respectively) were enrolled in this retrospective study. The signal intensities of these lesions during the hepatobiliary phase of EOB-MRI were investigated, and findings characteristic of RNs using this modality were also evaluated using CEUS.

Results

Ninety-eight of the 100 early HCCs that were hypo-intense (n = 95), iso-intense (n = 2), or hyper-intense (n = 1) and the seven HGDNs that were hypo-intense (n = 6) or hyper-intense (n = 1) during the hepatobiliary phase of EOB-MRI exhibited centripetal vessels during the arterial dominant phase of CEUS, although one early HCC that was hypo-intense exhibited both centrifugal and centripetal vessels. Eighteen of the 20 RNs and one early HCC that were hyper-intense with a small central hypo-intensity and the remaining two RNs that were hyper-intense on EOB-MRI exhibited centrifugal vessels during the arterial dominant phase of CEUS. The small central hypo-intense area corresponded to central vascular structures in the lesion, such as the hepatic artery and portal vein running from the center to the periphery, when viewed using CEUS.

Conclusion

Central vascular structures may be a characteristic finding of RNs when observed during the hepatobiliary phase of EOB-MRI and the arterial dominant phase of CEUS.

     

Contrast-enhanced ultrasonography with Sonazoid for diagnosis of gangrenous cholecystitis

Purpose

This prospective study investigated the ability of contrast-enhanced ultrasonography (CEUS) with Sonazoid to diagnose gangrenous cholecystitis and determined the inter-observer agreement.

Methods

From September 2012 to August 2014, 27 patients with acute cholecystitis underwent preoperative CEUS (registration number 1277). After Sonazoid injection, harmonic imaging of the gallbladder wall was performed, and the findings were recorded using movie clips. The signal intensity was classified as absence (uncomplicated) or presence of perfusion defects (gangrenous). The physician performing CEUS recorded the findings immediately after the examination. Another physician (blinded to the clinical information) then reviewed the movie clips and recorded the findings. The final diagnosis was determined by histological examination in all 27 patients.

Results

The final diagnosis was gangrenous cholecystitis in 15 patients and uncomplicated cholecystitis in 12. On CEUS examination, perfusion defects were detected in 10 patients with gangrenous cholecystitis, giving a sensitivity of 66.7 %, specificity of 100 %, positive predictive value of 100 %, and negative predictive value of 70.6 %. On review of the movie clips, these values were 73.3, 100, 100, and 75.0 %, respectively. The inter-observer agreement between physicians was good (κ coefficient, 0.64).

Conclusions

CEUS with Sonazoid is a useful and reproducible modality for diagnosing gangrenous cholecystitis.

     

Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study

Purpose

This paper presents the results of a large study involving fusion prostate biopsies to demonstrate that temporal ultrasound can be used to accurately classify tissue labels identified in multi-parametric magnetic resonance imaging (mp-MRI) as suspicious for cancer.

Methods

We use deep learning to analyze temporal ultrasound data obtained from 255 cancer foci identified in mp-MRI. Each target is sampled in axial and sagittal planes. A deep belief network is trained to automatically learn the high-level latent features of temporal ultrasound data. A support vector machine classifier is then applied to differentiate cancerous versus benign tissue, verified by histopathology. Data from 32 targets are used for the training, while the remaining 223 targets are used for testing.

Results

Our results indicate that the distance between the biopsy target and the prostate boundary, and the agreement between axial and sagittal histopathology of each target impact the classification accuracy. In 84 test cores that are 5 mm or farther to the prostate boundary, and have consistent pathology outcomes in axial and sagittal biopsy planes, we achieve an area under the curve of 0.80. In contrast, all of these targets were labeled as moderately suspicious in mp-MR.

Conclusion

Using temporal ultrasound data in a fusion prostate biopsy study, we achieved a high classification accuracy specifically for moderately scored mp-MRI targets. These targets are clinically common and contribute to the high false-positive rates associated with mp-MRI for prostate cancer detection. Temporal ultrasound data combined with mp-MRI have the potential to reduce the number of unnecessary biopsies in fusion biopsy settings.

     

Multimodality imaging to assess immediate response following irreversible electroporation in patients with malignant hepatic tumors

Purpose

To assess the diagnostic accuracy of contrast-enhanced ultrasound (CEUS), contrast-enhanced multiphase CT (CECT), and gadoxetic acid-enhanced MRI (EOB-MRI) in identifying residual tumor in the subacute follow-up of patients with malignant hepatic tumors treated by irreversible electroporation (IRE).

Methods

We enrolled 16 patients with 21 hepatic lesions treated by IRE and examined by CEUS and CECT at 1 day after IRE and by EOB-MRI at 7 days after IRE. Follow-up examinations by EOB-MRI or CECT and CEUS were performed at 3-month intervals. Two radiologists independently reviewed the images and assessed the probability of residual tumor using a five-point scale with receiver operating characteristic (ROC) curve analysis. The sensitivity and specificity were also evaluated. Verifiable local recurrence was assessed using follow-up imaging as the reference standard.

Results

The mean area under the ROC curve was significantly higher for CEUS (0.980) than for CECT (0.742, P < 0.01) and EOB-MRI (0.806, P < 0.01), as were the sensitivity and specificity (mean 85.7 and 85.7% for CEUS, respectively, vs 64.3 and 46.4% for CECT and 78.6 and 64.3% for EOB-MRI).

Conclusion

CEUS was found to be superior to CECT and EOB-MRI for the diagnosis of residual tumor in the subacute phase following IRE.

     

Differential diagnosis between benign and malignant soft tissue tumors utilizing ultrasound parameters

Purpose

Preoperative discrimination between benign and malignant soft tissue tumors is critical for the prevention of excess application of magnetic resonance imaging and biopsy as well as unplanned resection. Although ultrasound, including power Doppler imaging, is an easy, noninvasive, and cost-effective modality for screening soft tissue tumors, few studies have investigated reliable discrimination between benign and malignant soft tissue tumors.

Methods

To establish a modality for discrimination between benign and malignant soft tissue tumors using ultrasound, we extracted the significant risk factors for malignancy based on ultrasound information from 40 malignant and 56 benign pathologically diagnosed soft tissue tumors and established a scoring system based on these risk factors.

Results

The maximum size, tumor margin, and vascularity evaluated using ultrasound were extracted as significant risk factors. Using the odds ratio from a multivariate regression model, a scoring system was established. Receiver operating characteristic analyses revealed a high area under the curve value (0.85), confirming the accuracy of the scoring system.

Conclusion

Ultrasound is a useful modality for establishing the differential diagnosis between benign and malignant soft tissue tumors.

     

Fusion imaging with contrast-enhanced ultrasonography for evaluating the early therapeutic efficacy of radiofrequency ablation for small hypervascular hepatocellular carcinomas with iso-echoic or unclear margins on conventional ultrasonography

Purpose

We evaluated the efficacy of fusion imaging combining contrast-enhanced ultrasonography (CEUS) images and arterial phase contrast-enhanced CT (CECT) or hepatobiliary phase magnetic resonance imaging with gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (EOB-MRI) images for the early evaluation of the effectiveness of radiofrequency ablation (RFA) for small hypervascular hepatocellular carcinoma (HCC) with iso-echoic or unclear margins on conventional US.

Methods

Forty HCCs (22 iso-echoic and 18 unclear margin lesions) with mean diameters of 13.7 mm were treated using RFA under the guidance of fusion imaging with CEUS. The adequacy of RFA was evaluated using fusion imaging with CEUS 1 day after RFA. CECT or EOB-MRI was performed 1 month after RFA. We reviewed the images obtained using both modalities.

Results

When the 1-month CECT or EOB-MRI scans were used as the reference standard, the sensitivity, specificity, and accuracy of the 1-day fusion imaging for the diagnosis of the adequate ablation of these HCCs were 97, 100, and 98%, respectively; the kappa value for the agreement between the findings using the two modalities was 0.655.

Conclusion

Fusion imaging with CEUS appears to be a useful method for the early evaluation of the efficacy of RFA for the treatment of HCCs with iso-echoic or unclear margins on conventional US.

     

Patient-specific image denoising for ultra-low-dose CT-guided lung biopsies

Purpose

Low-dose CT screening of the lungs is becoming a reality, triggering many more CT-guided lung biopsies. During these biopsies, the patient is submitted to repeated guiding scans with substantial cumulated radiation dose. Extension of the dose reduction to the biopsy procedure is therefore necessary. We propose an image denoising algorithm that specifically addresses the setup of CT-guided lung biopsies. It minimizes radiation exposure while keeping the image quality appropriate for navigation to the target lesion.

Methods

A database of high-SNR CT patches is used to filter noisy pixels in a non-local means framework, while explicitly enforcing local spatial consistency in order to preserve fine image details and structures. The patch database may be created from a multi-patient set of high-SNR lung scans. Alternatively, the first scan, acquired at high-SNR right before the needle insertion, can provide a convenient patient-specific patch database.

Results

The proposed algorithm is compared to state-of-the-art denoising algorithms for a dataset of 43 real CT-guided biopsy scans. Ultra-low-dose scans were simulated by synthetic noise addition to the sinogram, equivalent to a 96% reduction in radiation dose. The feature similarity score for the proposed algorithm outperformed the compared methods for all the scans in the dataset. The benefit of the patient-specific patch database over the multi-patient one is demonstrated in terms of recovered contrast for a tiny porcine lung nodule, following denoising with both approaches.

Conclusions

The proposed method provides a promising approach to the denoising of ultra-low-dose CT-guided biopsy images.

     

Why patients with lung cancer do not want help with some needs

Goal

The purpose of this exploratory study was to understand what motivates patients to ask or not ask for assistance when they have expressed need in specific areas.

Materials and methods

A qualitative approach was used to explore the desire for assistance of patients with lung cancer who attended a regional cancer centre. The research questions were: (1) Why do patients with lung cancer not desire help for certain areas of need?; (2) What resources currently exist outside the cancer centre that patients with lung cancer use to help meet their needs?; and (3) What resources (internal and external to the cancer centre) would be helpful for patients with lung cancer? Fifty-nine patients participated in this study by completing a self-report questionnaire; 34 of these patients were then interviewed using a semi-structured interview guide.

Main results

The data indicated varied reasons for not asking for help, such as believing that staff were too busy or the problem would go away over time. Participants identified a number of outside resources they currently used and gave suggestions about needed resources within the cancer centre and in the community.

Conclusions

Patients with lung cancer may have a number of supportive care concerns, but they do not always ask for help with those issues. Some patients may be unaware of possible help, and others may not want help from professionals. Supportive care needs must be identified quickly and effectively so that appropriate interventions can be offered to those who want them.

     

A Comparison of microCT and microPET for Evaluating Lymph Node Metastasis in a Rat Model

Purpose

The demand to optimize multidisciplinary treatment strategies in patients with benign and malignant diseases of the lung and other organs has led to the increased need of mechanistic proof-of-concept studies in preclinical small animal models using new non-invasive imaging methods. Therefore, we evaluated the role of microPET and microCT for mediastinal lymph node staging in an orthotopic lung cancer model in rats.

Procedures

Human lung cancer cells (NCI-H460) were injected transthoracically in nude rats (NIH-RNU). After 2 weeks of tumour growth, animals underwent multiphase contrast-enhanced microCT using ExiTron nano 12000 as a contrast agent and dynamic microPET using the tracer 2-deoxy-2-[¹⁸F]fluoro-d-glucose ([¹⁸F]FDG). Thereafter, animals were sacrificed for histological analysis.

Results

Late phase micro X-ray computed tomography (microCT) revealed the best delineation of lymph node metastases, as compared to earlier scans. In terms of an increased [¹⁸F]FDG uptake over time, dynamic micro positron emission tomography (microPET) delineated lymph node metastases and enabled metabolic examinations of the induced lung cancer metastases.

Conclusion

The combination of contrast-enhanced microCT and dynamic microPET is feasible in rats for the visualization of mediastinal lymph node metastases.

     

Association between patient-provider communication and lung cancer stigma

Purpose

The majority (95 %) of lung cancer patients report stigma, with 48 % of lung cancer patients specifically reporting feeling stigmatized by their medical providers. Typically associated with the causal link to smoking and the historically poor prognosis, lung cancer stigma can be seen as a risk factor for poor psychosocial and medical outcomes in the context of lung cancer diagnosis and treatment. Thus, modifiable targets for lung cancer stigma-reducing interventions are needed. The present study sought to test the hypothesis that good patient-provider communication is associated with lower levels of lung cancer stigma.

Methods

Lung cancer patients (n?=?231) across varying stages of disease participated in a cross-sectional, multisite study designed to understand lung cancer stigma. Patients completed several survey measures, including demographic and clinical characteristics, a measure of patient-provider communication (Consumer Assessment of Healthcare Providers and Systems Program or CAHPS), and a measure of lung cancer stigma (Cataldo Lung Cancer Stigma Scale).

Results

As hypothesized, results indicated that good patient-provider communication was associated with lower levels of lung cancer stigma (r?=??0.18, p?<?0.05). These results remained significant, even when controlling for relevant demographic and clinical characteristics (Stan. β?=??0.15, p?<?0.05).

Conclusions

Results indicate that good patient-provider communication is associated with lower levels of lung cancer stigma, suggesting that improving patient-provider communication may be a good intervention target for reducing lung cancer stigma.

     

Reproducibility of Contrast-Enhanced Ultrasound in Mice with Controlled Injection

Purpose

Sensitivity of contrast-enhanced ultrasound (CEUS) to microvascular flow modifications can be limited by intra-injection variability (injected dose, rate, volume).

Procedures

To evaluate the effect of injection variability on microvascular flow evaluation, CEUS was compared between controlled and manual injections where enhancement was assessed in vitro within a flow phantom, in normal murine kidney (N?=?12) and in murine ectopic tumors (N?=?10).

Results

For both in vitro and in vivo measurements in the renal cortex, controlled injections significantly improved reproducibility of functional parameter estimation. Their coefficient of variation (CV) in the renal cortex ranged from 4 to 19 % for controlled injection vs. 5 to 43 % for manual injections. For measurements in tumors, controlled injection only decreased the CV significantly for the mean transit time. In tumors, multiple injections of contrast agent with a 15-min delay between each were shown to strongly modify contrast uptake by facilitating penetration of microbubbles.

Conclusion

Improved reproducibility of CEUS assessments in murine models should provide more robust quantification of flow parameters and more sensitive evaluation of tumor modifications in therapeutic models.

     

A meta-analysis on depression and subsequent cancer risk

Background

The authors tested the hypothesis that depression is a possible factor influencing the course of cancer by reviewing prospective epidemiological studies and calculating summary relative risks.

Methods

Studies were identified by computerized searches of Medline, Embase and PsycINFO. as well as manual searches of reference lists of selected publications. Inclusion criteria were cohort design, population-based sample, structured measurement of depression and outcome of cancer known for depressed and non-depressed subjects

Results

Thirteen eligible studies were identified. Based on eight studies with complete crude data on overall cancer, our summary relative risk (95% confidence interval) was 1.19 (1.06–1.32). After adjustment for confounders we pooled a summary relative risk of 1.12 (0.99–1.26).No significant association was found between depression and subsequent breast cancer risk, based on seven heterogeneous studies, with or without adjustment for possible confounders. Subgroup analysis of studies with a follow-up of ten years or more, however, resulted in a statistically significant summary relative risk of 2.50 (1.06–5.91).No significant associations were found for lung, colon or prostate cancer.

Conclusion

This review suggests a tendency towards a small and marginally significant association between depression and subsequent overall cancer risk and towards a stronger increase of breast cancer risk emerging many years after a previous depression.

     

Primary hepatic neuroendocrine tumors: clinical characteristics and imaging features on contrast-enhanced ultrasound and computed tomography

Objective

Primary hepatic neuroendocrine tumor (PHNET) is an extremely rare liver neoplasm, and its clinical characteristics and imaging features are not well understood. The aim of this study was to analyze the clinical profiles and imaging features of PHNETs on contrast-enhanced ultrasound (CEUS) and computed tomography (CT)

Methods

Patients with PHNET between January 2008 and December 2015 were retrospectively identified, and their demographics, laboratory data, and imaging characteristics on CEUS and CT analyzed.

Results

Ten consecutive patients with PHNETs were included (including one G1, seven G2, and two G3 of tumor grades).The median age of patient was 45 years (range: 27–72 years), and 60.0% of patients were male. The most common symptom was abdominal pain (60.0%), and cirrhosis was found in 40.0% of patients. Tumors were confined within the liver in 60.0% of patients, while the remaining patients had extra-hepatic metastasis. The tumors revealed hyperechoic in 60% of patients and mixed echoic in 30% of patients on conventional US, displaying intense arterial enhancement followed by washout in the portal and/or the late phases in 80.0% of patients on CEUS and 60% at CT.

Conclusions

Although PHNET is a very rare liver tumor, it should be considered as a possible differential diagnosis in the management of hepatic tumors. Most PHNETs were hyperechoic or mixed echoic on conventional US, showing similar enhancement patterns to that of hepatocellular carcinoma on CEUS.

     

Olanzapine vs haloperidol: treating delirium in a critical care setting

Objective

To compare the safety and estimate the response profile of olanzapine, a second-generation antipsychotic, to haloperidol in the treatment of delirium in the critical care setting.

Design

Prospective randomized trial

Setting

Tertiary care university affiliated critical care unit.

Patients

All admissions to a medical and surgical intensive care unit with a diagnosis of delirium.

Interventions

Patients were randomized to receive either enteral olanzapine or haloperidol.

Measurements

Patient’s delirium severity and benzodiazepine use were monitored over 5 days after the diagnosis of delirium.

Main results

Delirium Index decreased over time in both groups, as did the administered dose of benzodiazepines. Clinical improvement was similar in both treatment arms. No side effects were noted in the olanzapine group, whereas the use of haloperidol was associated with extrapyramidal side effects.

Conclusions

Olanzapine is a safe alternative to haloperidol in delirious critical care patients, and may be of particular interest in patients in whom haloperidol is contraindicated.

     

Automated pulmonary nodule CT image characterization in lung cancer screening

Purpose

In lung cancer screening, pulmonary nodules are first identified in low-dose chest CT images. Costly follow-up procedures could be avoided if it were possible to establish the malignancy status of these nodules from these initial images. Preliminary computer methods have been proposed to characterize the malignancy status of pulmonary nodules based on features extracted from a CT image. The parameters and performance of such a computer system in a lung cancer screening context are addressed.

Methods

A computer system that incorporates novel 3D image features to determine the malignancy status of pulmonary nodules is evaluated with a large dataset constructed from images from the NLST and ELCAP lung cancer studies. The system is evaluated with different data subsets to determine the impact of class size distribution imbalance in datasets and to evaluate different training and testing strategies.

Results

Results show a modest improvement in malignancy prediction compared to prediction by size alone for a traditional size-unbalanced dataset. Further, the advantage of size binning for classifier design and the advantages of a size-balanced dataset for both training and testing are demonstrated.

Conclusion

Nodule classification in the context of low-resolution low-dose whole-chest CT images for the clinically relevant size range in the context of lung cancer screening is highly challenging, and results are moderate compared to what has been reported in the literature for other clinical contexts. Nodule class size distribution imbalance needs to be considered in the training and evaluation of computer-aided diagnostic systems for producing patient-relevant outcomes.

     

Cancer Patient–Derived Circulating Microparticles Enhance Lung Metastasis in a Rat Model: Dual-Source CT,Cellular, and Molecular Studies

Purpose

This study aimed to test the hypothesis that lung cancer patient–derived circulating microparticles (LCC-MPs) enhance metastatic lung tumors in a rat model.

Procedures

The controls (n?=?6) and LCC-MP-treated rats (n?=?6) with N1S1-induced pulmonary metastatic hepatocellular carcinoma (HCC) underwent dual-source CT (DSCT) on days 10, 15, and 20. Cellular and molecular studies were performed subsequently.

Results

DSCT revealed slow progression of metastatic lung tumors in the controls. Compared with the controls, the LCC-MP-treated rats exhibited significantly more and larger metastatic tumors on days 15 and 20 on DSCT, enhanced angiogenesis with higher microvessel count (CD34+), more CXCR4+ and VEGF+ cells in immunohistofluorescence studies, and higher protein expression levels of eNOS, angiopoietin, vascular endothelial growth factor, and CD31 on western blotting (Mann–Whitney test, all P?<?0.05).

Conclusions

LCC-MPs can elicit oncogenic stimulation and accelerate metastatic HCC growth in rat lung as demonstrated on DSCT and enhanced tumoral angiogenesis as confirmed in cellular and molecular studies.