Computer-aided diagnosis in lung nodule assessment

A segmentation tool for pulmonary nodules in lung cancer screening: Testing and clinical usage

PURPOSE

With the future goal of defining a large dataset based on low-dose CT with labelled pulmonary lesions for lung cancer screening (LCS) research, the aim of this work is to propose and evaluate into a clinical context a tool for semi-automatic segmentation able to facilitate the process of labels collection from a LCS study (COSMOS, Continuous Observation of SMOking Subjects).

METHODS

Considering a preliminary set of manual annotations, a segmentation model based on a 2D-Unet was trained from scratch. Contour quality of the final 2D-Unet was assessed on an internal test set of manual annotations and on a subset of the public available LIDC dataset used as external test set. The tool for semi-automatic segmentation was then designed integrating the tested model into a Graphical User Interface. According to the opinion of two clinical users, the percentage of lesions properly contoured through the tool was quantified (Acceptance Rate, AR). The variability between segmentations derived by the two readers was estimated as mean percentage of difference (MPD) between the two sets of volumes and comparing the likelihood of malignancy derived from Volume Doubling Time (VDT).

RESULTS

Performance in test sets were found similar (DICE ~ 0.75(0.15)). Accordingly, a good mean AR (80.1%) resulted from the two readers. Variability in terms of MPD was equal to 23.6% while 2.7% was the VDTs percentage of disagreement.

CONCLUSIONS

A semi-automatic segmentation tool was developed and its applicability evaluated into a clinical context demonstrating the efficacy of the tool in facilitating the collection of labelled data.

External validation of radiomics-based predictive models in low-dose CT screening for early lung cancer diagnosis

PURPOSE

Low-dose CT screening allows early lung cancer detection, but is affected by frequent false positive results, inter/intra observer variation and uncertain diagnoses of lung nodules. Radiomics-based models have recently been introduced to overcome these issues, but limitations in demonstrating their generalizability on independent datasets are slowing their introduction to clinic. The aim of this study is to evaluate two radiomics-based models to classify malignant pulmonary nodules in low-dose CT screening, and to externally validate them on an independent cohort. The effect of a radiomics features harmonization technique is also investigated to evaluate its impact on the classification of lung nodules from a multicenter data.

METHODS

Pulmonary nodules from two independent cohorts were considered in this study; the first cohort (110 subjects, 113 nodules) was used to train prediction models, and the second cohort (72 nodules) to externally validate them. Literature-based radiomics features were extracted and, after feature selection, used as predictive variables in models for malignancy identification. An in-house prediction model based on artificial neural network (ANN) was implemented and evaluated, along with an alternative model from the literature, based on a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). External validation was performed on the second cohort to evaluate models' generalization ability. Additionally, the impact of the Combat harmonization method was investigated to compensate for multicenter datasets variabilities. A new training of the models based on harmonized features was performed on the first cohort, then tested separately on the harmonized and non-harmonized features of the second cohort.

RESULTS

Preliminary results showed a good accuracy of the investigated models in distinguishing benign from malignant pulmonary nodules with both sets of radiomics features (i.e., non-harmonized and harmonized). The performance of the models, quantified in terms of Area Under the Curve (AUC), was > 0.89 in the training set and > 0.82 in the external validation set for all the investigated scenarios, outperforming the clinical standard (AUC of 0.76). Slightly higher performance was observed for the SVM-LASSO model than the ANN in the external dataset, although they did not result significantly different. For both harmonized and non-harmonized features, no statistical difference was found between Receiver operating characteristic (ROC) curves related to training and test set for both models.

CONCLUSIONS

Although no significant improvements were observed when applying the Combat harmonization method, both in-house and literature-based models were able to classify lung nodules with good generalization to an independent dataset, thus showing their potential as tools for clinical decision-making in lung cancer screening.

Quantitative Imaging features Improve Discrimination of Malignancy in Pulmonary nodules

Pulmonary nodules are frequently detected radiological abnormalities in lung cancer screening. Nodules of the highest- and lowest-risk for cancer are often easily diagnosed by a trained radiologist there is still a high rate of indeterminate pulmonary nodules (IPN) of unknown risk. Here, we test the hypothesis that computer extracted quantitative features (“radiomics”) can provide improved risk-assessment in the diagnostic setting. Nodules were segmented in 3D and 219 quantitative features are extracted from these volumes. Using these features novel malignancy risk predictors are formed with various stratifications based on size, shape and texture feature categories. We used images and data from the National Lung Screening Trial (NLST), curated a subset of 479 participants (244 for training and 235 for testing) that included incident lung cancers and nodule-positive controls. After removing redundant and non-reproducible features, optimal linear classifiers with area under the receiver operator characteristics (AUROC) curves were used with an exhaustive search approach to find a discriminant set of image features, which were validated in an independent test dataset. We identified several strong predictive models, using size and shape features the highest AUROC was 0.80. Using non-size based features the highest AUROC was 0.85. Combining features from all the categories, the highest AUROC were 0.83.

Performance and clinical impact of machine learning based lung nodule detection using vessel suppression in melanoma patients

PURPOSE

To evaluate performance and the clinical impact of a novel machine learning based vessel-suppressing computer-aided detection (CAD) software in chest computed tomography (CT) of patients with malignant melanoma.

MATERIALS AND METHODS

We retrospectively included consecutive malignant melanoma patients with a chest CT between 01/2015 and 01/2016. Machine learning based CAD software was used to reconstruct additional vessel-suppressed axial images. Three radiologists independently reviewed a maximum of 15 lung nodules per patient. Vessel-suppressed reconstructions were reviewed independently and results were compared. Follow-up CT examinations and clinical follow-up were used to assess the outcome. Impact of additional nodules on clinical management was assessed.

RESULTS

In 46 patients, vessel-suppressed axial images led to the detection of additional nodules in 25/46 (54.3%) patients. CT or clinical follow up was available in 25/25 (100%) patients with additionally detected nodules. 2/25 (8%) of these patients developed new pulmonary metastases. None of the additionally detected nodules were found to be metastases. None of the lung nodules detected by the radiologists was missed by the CAD software. The mean diameter of the 92 additional nodules was 1.5 ± 0.8 mm. The additional nodules did not affect therapeutic management. However, in 14/46 (30.4%) of patients the additional nodules might have had an impact on the radiological follow-up recommendations.

CONCLUSION

Machine learning based vessel suppression led to the detection of significantly more lung nodules in melanoma patients. Radiological follow-up recommendations were altered in 30% of the patients. However, all lung nodules turned out to be non-malignant on follow-up.

A novel pixel value space statistics map of the pulmonary nodule for classification in computerized tomography images

Accurate assessment of pulmonary nodules can help to diagnose the serious degree of lung cancer. In most computed aided diagnosis (CADx) systems, the feature extraction module plays quite an important role in classifying pulmonary nodules based on different attributes of them. To precisely evaluate the malignancy of an unknown pulmonary nodule, this paper first proposes a novel pixel value space statistics map (PVSSM) for pulmonary nodules classification. By means of PVSSM this study can transform an original two-dimensional (2D) or three-dimensional (3D) pulmonary nodule into a 2D feature matrix, which contributes to better classifying a pulmonary nodule. To validate the proposed method, this study assembled 5385 valid 3D nodules from 1006 cases in LIDC-IDRI database. This study extracts sets of features from the created feature matrixes by singular value decomposition (SVD) method. Using several popular classifiers including KNN, random forest and SVM, we acquire the classification accuracies of 77.29%, 80.07% and 84.21%, respectively. Moreover, this study also utilizes the convolutional neural network (CNN) to assess the malignancy of nodules and the sensitivity, specificity and area under the curve (AUC) reach up to 86.0%, 88.5% and 0.913, respectively. Experiments demonstrate that the PVSSM has a benefit for nodules classification.

Combination of computer extracted shape and texture features enables discrimination of granulomas from adenocarcinoma on chest computed tomography

Differentiation between benign and malignant nodules is a problem encountered by radiologists when visualizing computed tomography (CT) scans. Adenocarcinomas and granulomas have a characteristic spiculated appearance and may be fluorodeoxyglucose avid, making them difficult to distinguish for human readers. In this retrospective study, we aimed to evaluate whether a combination of radiomic texture and shape features from noncontrast CT scans can enable discrimination between granulomas and adenocarcinomas. Our study is composed of CT scans of 195 patients from two institutions, one cohort for training ([Formula: see text]) and the other ([Formula: see text]) for independent validation. A set of 645 three-dimensional texture and 24 shape features were extracted from CT scans in the training cohort. Feature selection was employed to identify the most informative features using this set. The top ranked features were also assessed in terms of their stability and reproducibility across the training and testing cohorts and between scans of different slice thickness. Three different classifiers were constructed using the top ranked features identified from the training set. These classifiers were then validated on the test set and the best classifier (support vector machine) yielded an area under the receiver operating characteristic curve of 77.8%.

Predicting survival time of lung cancer patients using radiomic analysis

OBJECTIVES

This study investigates the prediction of Non-small cell lung cancer (NSCLC) patient survival outcomes based on radiomic texture and shape features automatically extracted from tumor image data.

MATERIALS AND METHODS

Retrospective analysis involves CT scans of 315 NSCLC patients from The Cancer Imaging Archive (TCIA). A total of 24 image features are computed from labeled tumor volumes of patients within groups defined using NSCLC subtype and TNM staging information. Spearman's rank correlation, Kaplan-Meier estimation and log-rank tests were used to identify features related to long/short NSCLC patient survival groups. Automatic random forest classification was used to predict patient survival group from multivariate feature data. Significance is assessed at P < 0.05 following Holm-Bonferroni correction for multiple comparisons.

RESULTS

Significant correlations between radiomic features and survival were observed for four clinical groups: (group, [absolute correlation range]): (large cell carcinoma (LCC) [0.35, 0.43]), (tumor size T2, [0.31, 0.39]), (non lymph node metastasis N0, [0.3, 0.33]), (TNM stage I, [0.39, 0.48]). Significant log-rank relationships between features and survival time were observed for three clinical groups: (group, hazard ratio): (LCC, 3.0), (LCC, 3.9), (T2, 2.5) and (stage I, 2.9). Automatic survival prediction performance (i.e. below/above median) is superior for combined radiomic features with age-TNM in comparison to standard TNM clinical staging information (clinical group, mean area-under-the-ROC-curve (AUC)): (LCC, 75.73%), (N0, 70.33%), (T2, 70.28%) and (TNM-I, 76.17%).

CONCLUSION

Quantitative lung CT imaging features can be used as indicators of survival, in particular for patients with large-cell-carcinoma (LCC), primary-tumor-sizes (T2) and no lymph-node-metastasis (N0).

Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule

The Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule (SPN) remains unclear. 240 patients with SPNs (malignant, n = 180; benign, n = 60) underwent non-contrast CT (NECT) and contrast-enhanced CT (CECT) which were reconstructed with different slice thickness and convolution kernel. 150 radiomics features were extracted separately from each set of CT and diagnostic performance of each feature were assessed. After feature selection and radiomics signature construction, diagnostic performance of radiomics signature for discriminating benign and malignant SPN was also assessed with respect to the discrimination and classification and compared with net reclassification improvement (NRI). Our results showed NECT-based radiomics signature demonstrated better discrimination and classification capability than CECT in both primary (AUC: 0.862 vs. 0.829, p = 0.032; NRI = 0.578) and validation cohort (AUC: 0.750 vs. 0.735, p = 0.014; NRI = 0.023). Thin-slice (1.25 mm) CT-based radiomics signature had better diagnostic performance than thick-slice CT (5 mm) in both primary (AUC: 0.862 vs. 0.785, p = 0.015; NRI = 0.867) and validation cohort (AUC: 0.750 vs. 0.725, p = 0.025; NRI = 0.467). Standard convolution kernel-based radiomics signature had better diagnostic performance than lung convolution kernel-based CT in both primary (AUC: 0.785 vs. 0.770, p = 0.015; NRI = 0.156) and validation cohort (AUC: 0.725 vs.0.686, p = 0.039; NRI = 0.467). Therefore, this study indicates that the contrast-enhancement, reconstruction slice thickness and convolution kernel can affect the diagnostic performance of radiomics signature in SPN, of which non-contrast, thin-slice and standard convolution kernel-based CT is more informative.

Toward Understanding the Size Dependence of Shape Features for Predicting Spiculation in Lung Nodules for Computer-Aided Diagnosis

We analyze the importance of shape features for predicting spiculation ratings assigned by radiologists to lung nodules in computed tomography (CT) scans. Using the Lung Image Database Consortium (LIDC) data and classification models based on decision trees, we demonstrate that the importance of several shape features increases disproportionately relative to other image features with increasing size of the nodule. Our shaped-based classification results show an area under the receiver operating characteristic (ROC) curve of 0.65 when classifying spiculation for small nodules and an area of 0.91 for large nodules, resulting in a 26% difference in classification performance using shape features. An analysis of the results illustrates that this change in performance is driven by features that measure boundary complexity, which perform well for large nodules but perform relatively poorly and do no better than other features for small nodules. For large nodules, the roughness of the segmented boundary maps well to the semantic concept of spiculation. For small nodules, measuring directly the complexity of hard segmentations does not yield good results for predicting spiculation due to limits imposed by spatial resolution and the uncertainty in boundary location. Therefore, a wider range of features, including shape, texture, and intensity features, are needed to predict spiculation ratings for small nodules. A further implication is that the efficacy of shape features for a particular classifier used to create computer-aided diagnosis systems depends on the distribution of nodule sizes in the training and testing sets, which may not be consistent across different research studies.

Lung nodule and cancer detection in computed tomography screening

Fundamental to the diagnosis of lung cancer in computed tomography (CT) scans is the detection and interpretation of lung nodules. As the capabilities of CT scanners have advanced, higher levels of spatial resolution reveal tinier lung abnormalities. Not all detected lung nodules should be reported; however, radiologists strive to detect all nodules that might have relevance to cancer diagnosis. Although medium to large lung nodules are detected consistently, interreader agreement and reader sensitivity for lung nodule detection diminish substantially as the nodule size falls below 8 to 10 mm. The difficulty in establishing an absolute reference standard presents a challenge to the reliability of studies performed to evaluate lung nodule detection. In the interest of improving detection performance, investigators are using eye tracking to analyze the effectiveness with which radiologists search CT scans relative to their ability to recognize nodules within their search path in order to determine whether strategies might exist to improve performance across readers. Beyond the viewing of transverse CT reconstructions, image processing techniques such as thin-slab maximum-intensity projections are used to substantially improve reader performance. Finally, the development of computer-aided detection has continued to evolve with the expectation that one day it will serve routinely as a tireless partner to the radiologist to enhance detection performance without significant prolongation of the interpretive process. This review provides an introduction to the current understanding of these varied issues as we enter the era of widespread lung cancer screening.

Manifestations and pathological features of solitary thin-walled cavity lung cancer observed by CT and PET/CT imaging

The aim of the present study was to analyze and improve the understanding of computed tomography (CT) and positron emission tomography (PET)/CT imaging and the pathological features of solitary thin-walled cavity lung cancer. A total of 16 patients with pathologically confirmed solitary thin-walled cavity lung cancer were included in the present study. All of the patients received CT scans. Among these, two patients underwent an additional PET/CT examination. The CT and PET/CT images were analyzed and a cross-check analysis of the pathological results was conducted. In total, 16 cases of lesions demonstrated thin-walled cavities on the CT images. Among these cases, three presented with an uneven thickening of the cavity walls, 10 cases exhibited wall nodules and three cases presented with compartments in the cavity. The standard uptake value (SUV) of the cavity wall increased in two patients who underwent PET/CT examinations. The 16 cases of lesions were pathologically confirmed as adenocarcinomas. Light microscopy revealed that the tumor cells, which were observed in 12 cases of lesions, had diffused along the inner cavity wall and the tumor cells of four cases had invaded the bronchial wall. Images of the chest that demonstrated a single thin-walled cavity accompanied by uneven thickening of the cavity wall or wall nodules, in addition to an increase in the SUV and compartments in the cavity, indicated potential lung cancer. Valves formed as a result of bronchial wall damage may have led to the cavity.

Investigation of computer-aided diagnosis system for bone scans: a retrospective analysis in 406 patients

OBJECTIVE

The aim of this study was to investigate the diagnostic ability of a completely automated computer-assisted diagnosis (CAD) system to detect metastases in bone scans by two patterns: one was per region, and the other was per patient.

MATERIALS AND METHODS

This study included 406 patients with suspected metastatic bone tumors who underwent whole-body bone scans that were analyzed by the automated CAD system. The patients were divided into four groups: a group with prostatic cancer (N = 71), breast cancer (N = 109), males with other cancers (N = 153), and females with other cancers (N = 73). We investigated the bone scan index and artificial neural network (ANN), which are parameters that can be used to classify bone scans to determine whether there are metastases. The sensitivities, specificities, positive predictive value (PPV), negative predictive value (NPV), and accuracies for the four groups were compared. Receiver operating characteristic (ROC) analyses of region-based ANN were performed to compare the diagnostic performance of the automated CAD system.

RESULTS

There were no significant differences in the sensitivity, specificity, or NPV between the four groups. The PPVs of the group with prostatic cancer (51.0 %) were significantly higher than those of the other groups (P < 0.01). The accuracy of the group with prostatic cancer (81.5 %) was significantly higher than that of the group with breast cancer (68.6 %) and the females with other cancers (65.9 %) (P < 0.01). For the evaluation of the ROC analysis of region-based ANN, the highest Az values for the groups with prostatic cancer, breast cancer, males with other cancers, and females with other cancers were 0.82 (ANN = 0.4, 0.5, 0.6, 0.7, and 0.8), 0.83 (ANN = 0.7), 0.81 (ANN = 0.5), and 0.81 (ANN = 0.6), respectively.

CONCLUSION

The special CAD system "BONENAVI" trained with a Japanese database appears to have significant potential in assisting physicians in their clinical routine. However, an improved CAD system depending on the primary lesion of the cancer is required to decrease the proportion of false-positive findings.

Impact of a computer-aided detection (CAD) system integrated into a picture archiving and communication system (PACS) on reader sensitivity and efficiency for the detection of lung nodules in thoracic CT exams

The objective of this study is to assess the impact on nodule detection and efficiency using a computer-aided detection (CAD) device seamlessly integrated into a commercially available picture archiving and communication system (PACS). Forty-eight consecutive low-dose thoracic computed tomography studies were retrospectively included from an ongoing multi-institutional screening study. CAD results were sent to PACS as a separate image series for each study. Five fellowship-trained thoracic radiologists interpreted each case first on contiguous 5 mm sections, then evaluated the CAD output series (with CAD marks on corresponding axial sections). The standard of reference was based on three-reader agreement with expert adjudication. The time to interpret CAD marking was automatically recorded. A total of 134 true-positive nodules, measuring 3 mm and larger were included in our study; with 85 ≥ 4 and 50 ≥ 5 mm in size. Readers detection improved significantly in each size category when using CAD, respectively, from 44 to 57 % for ≥3 mm, 48 to 61 % for ≥4 mm, and 44 to 60 % for ≥5 mm. CAD stand-alone sensitivity was 65, 68, and 66 % for nodules ≥3, ≥4, and ≥5 mm, respectively, with CAD significantly increasing the false positives for two readers only. The average time to interpret and annotate a CAD mark was 15.1 s, after localizing it in the original image series. The integration of CAD into PACS increases reader sensitivity with minimal impact on interpretation time and supports such implementation into daily clinical practice.

Computer-aided diagnosis systems for lung cancer: challenges and methodologies

This paper overviews one of the most important, interesting, and challenging problems in oncology, the problem of lung cancer diagnosis. Developing an effective computer-aided diagnosis (CAD) system for lung cancer is of great clinical importance and can increase the patient's chance of survival. For this reason, CAD systems for lung cancer have been investigated in a huge number of research studies. A typical CAD system for lung cancer diagnosis is composed of four main processing steps: segmentation of the lung fields, detection of nodules inside the lung fields, segmentation of the detected nodules, and diagnosis of the nodules as benign or malignant. This paper overviews the current state-of-the-art techniques that have been developed to implement each of these CAD processing steps. For each technique, various aspects of technical issues, implemented methodologies, training and testing databases, and validation methods, as well as achieved performances, are described. In addition, the paper addresses several challenges that researchers face in each implementation step and outlines the strengths and drawbacks of the existing approaches for lung cancer CAD systems.

Missed lung cancer on chest radiography and computed tomography

Missed lung cancer raises an important medicolegal issue and contributes to one of the most common causes for malpractice actions against radiologists. Lung cancer may be missed on either chest radiography or computed tomography. Although most malpractice cases involve lesions overlooked on the former, a small and increasing portion of cases are related to chest computed tomography scan. Factors contributing to overlooked lung cancer can be attributed to observer performance, lesion characteristics, and technical considerations.

Computer-aided diagnosis system for bone scintigrams from Japanese patients: importance of training database

AIM

Computer-aided diagnosis (CAD) software for bone scintigrams have recently been introduced as a clinical quality assurance tool. The purpose of this study was to compare the diagnostic accuracy of two CAD systems, one based on a European and one on a Japanese training database, in a group of bone scans from Japanese patients.

METHOD

The two CAD software are trained to interpret bone scans using training databases consisting of bone scans with the desired interpretation, metastatic disease or not. One software was trained using 795 bone scans from European patients and the other with 904 bone scans from Japanese patients. The two CAD softwares were evaluated using the same group of 257 Japanese patients, who underwent bone scintigraphy because of suspected metastases of malignant tumors in 2009. The final diagnostic results made by clinicians were used as gold standard.

RESULTS

The Japanese CAD software showed a higher specificity and accuracy compared to the European CAD software [81 vs. 57 % (p < 0.05) and 82 vs. 61 % (p < 0.05), respectively]. The sensitivity was 90 % for the Japanese CAD software and 83 % for the European CAD software (n.s).

CONCLUSION

The CAD software trained with a Japanese database showed significantly higher performance than the corresponding CAD software trained with a European database for the analysis of bone scans from Japanese patients. These results could at least partly be caused by the physical differences between Japanese and European patients resulting in less influence of attenuation in Japanese patients and possible different judgement of count intensities of hot spots.

Automated temporal tracking and segmentation of lymphoma on serial CT examinations

PURPOSE

It is challenging to reproducibly measure and compare cancer lesions on numerous follow-up studies; the process is time-consuming and error-prone. In this paper, we show a method to automatically and reproducibly identify and segment abnormal lymph nodes in serial computed tomography (CT) exams.

METHODS

Our method leverages initial identification of enlarged (abnormal) lymph nodes in the baseline scan. We then identify an approximate region for the node in the follow-up scans using nonrigid image registration. The baseline scan is also used to locate regions of normal, non-nodal tissue surrounding the lymph node and to map them onto the follow-up scans, in order to reduce the search space to locate the lymph node on the follow-up scans. Adaptive region-growing and clustering algorithms are then used to obtain the final contours for segmentation. We applied our method to 24 distinct enlarged lymph nodes at multiple time points from 14 patients. The scan at the earlier time point was used as the baseline scan to be used in evaluating the follow-up scan, resulting in 70 total test cases (e.g., a series of scans obtained at 4 time points results in 3 test cases). For each of the 70 cases, a "reference standard" was obtained by manual segmentation by a radiologist. Assessment according to response evaluation criteria in solid tumors (RECIST) using our method agreed with RECIST assessments made using the reference standard segmentations in all test cases, and by calculating node overlap ratio and Hausdorff distance between the computer and radiologist-generated contours.

RESULTS

Compared to the reference standard, our method made the correct RECIST assessment for all 70 cases. The average overlap ratio was 80.7 ± 9.7% s.d., and the average Hausdorff distance was 3.2 ± 1.8 mm s.d. The concordance correlation between automated and manual segmentations was 0.978 (95% confidence interval 0.962, 0.984). The 100% agreement in our sample between our method and the standard with regard to RECIST classification suggests that the true disagreement rate is no more than 6%.

CONCLUSIONS

Our automated lymph node segmentation method achieves excellent overall segmentation performance and provides equivalent RECIST assessment. It potentially will be useful to streamline and improve cancer lesion measurement and tracking and to improve assessment of cancer treatment response.

Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival

PURPOSE

To establish the potential for tumour heterogeneity in non-small cell lung cancer (NSCLC) as assessed by CT texture analysis (CTTA) to provide an independent marker of survival for patients with NSCLC.

MATERIALS AND METHODS

Tumour heterogeneity was assessed by CTTA of unenhanced images of primary pulmonary lesions from 54 patients undergoing (18)F-fluorodeoxyglucose (FDG) PET-CT for staging of NSCLC. CTTA comprised image filtration to extract fine, medium and coarse features with quantification of the distribution of pixel values (uniformity) within the filtered images. Receiver operating characteristics identified thresholds for PET and CTTA parameters that were related to patient survival using Kaplan-Meier analysis.

RESULTS

The median (range) survival was 29.5 (1-38) months. 24, 10, 14 and 6 patients had tumour stages I, II, III and IV respectively. PET stage and tumour heterogeneity assessed by CTTA were significant independent predictors of survival (PET stage: Odds ratio 3.85, 95% confidence limits 0.9-8.09, P = 0.002; CTTA: Odds ratio 56.4, 95% confidence limits 4.79-666, p = 0.001). SUV was not a significantly associated with survival.

CONCLUSION

Assessment of tumour heterogeneity by CTTA of non-contrast enhanced images has the potential for to provide a novel, independent predictor of survival for patients with NSCLC.

KEY POINTS

Computed tomography is a routine staging procedure in non-small cell lung cancer. CT texture analysis (CTTA) can quantify heterogeneity within these lung tumours. CTTA seems to offer a novel independent predictor of survival for NSCLC. CTTA could contribute to disease risk-stratification for patients with NSCLC.

A systematic review of computer-assisted diagnosis in diagnostic cancer imaging

OBJECTIVES

This study reviews the evidence for the effectiveness of computer-assisted diagnosis (CAD) in cancer imaging. Diagnostic applications were studied to estimate the impact of CAD on radiologists' detection and diagnosis of cancer lesions.

METHODS

Online databases were searched and 48 studies from 1992 to 2010 were included: 16 with radiologists using CAD to detect lesions (CADe) and 32 with radiologists using CAD to classify or diagnose lesions (CADx). Weighted means, statistics, summary receiver operating characteristics (SROC) curves, and related measures were used for analysis.

RESULTS

There is evidence that CADx significantly improves diagnosis in mammography and breast ultrasound. In contrast, studies of CADx applied to lung CT and dermatologic imaging show an adverse impact on diagnosis. Overall, there is no evidence of a benefit due to the use of CADe. The area under the SROC curves was not significantly increased for radiologists using either CADe or CADx.

CONCLUSIONS

From this analysis it seems CADx can offer some benefit to radiologists in specific imaging applications for breast cancer diagnosis. There is no evidence of a beneficial effect in other applications of CAD and some evidence of a detrimental one.

The future of PACS in healthcare enterprises

Picture Archiving and Communication System (PACS), which was originally designed as a tool for facilitating radiologists in interpreting images more efficiently, is evolving into a hospital-integrated system storing diagnostic imaging information that often reaches far beyond Radiology. The continuous evolution of PACS technology has led to a gradual broadening of its applications, ranging from teleradiology to CAD (Computer-Assisted Diagnosis) and multidimensional imaging, and is moving into the direction of providing access to image data outside the Radiology department, so to reach all the branches of the healthcare enterprise. New perspectives have been created thanks to new technologies (such as holographic media and GRID computing) that are likely due to expand PACS-based applications even further, improving patient care and enhancing overall productivity.

Evaluation of a method of computer-aided detection (CAD) of pulmonary nodules with computed tomography

PURPOSE

The authors sought to compare the sensitivity and reading time obtained using computer-aided detection (CAD) software as second reader (SR) or concurrent reader (CR) in the identification of pulmonary nodules.

MATERIALS AND METHODS

Unenhanced CT scans of 100 consecutive cancer patients were retrospectively reviewed by four readers to identify all solid, noncalcified pulmonary nodules ranging from 3 to 30 mm in diameter. The sensitivity and reading time of each reader and of CAD alone were calculated at 3-mm and 5-mm thresholds with respect to the reference standard, consisting of a consensus reading by the four radiologists involved in the study. The McNemar test was used to compare the sensitivities obtained by reading without CAD (readers 1 and 2), with CAD as SR (readers 1 and 2 with a 2-month delay), and with CAD as CR (readers 3 and 4). The paired Student's t test was used to compare reading times. A value of p<0.05 was considered statistically significant.

RESULTS

A total of 258 and 224 nodules were identified at 3-mm and 5-mm thresholds, respectively. The sensitivity of CAD alone was 62.79% and 67.41% at the 3-mm and 5-mm threshold values respectively, with 4.15 and 2.96 false-positive findings per examination. CAD as SR produced a significant increase in sensitivity (p<0.001) in nodule detection with respect to reading without CAD both at 3 mm (12.01%) and 5 mm (10.04%); the average increase in sensitivity obtained when comparing CAD as SR to CAD as CR was statistically significant (p<0.025) both at the 3-mm (5.35%) and 5-mm (4.68%) thresholds. CAD as CR produced a nonsignificant increase in sensitivity compared with reading without CAD (p>0.05). Mean reading time using CAD as SR (330 s) was significantly longer than reading without CAD (135 s, p<0.001) and reading with CAD as CR (195 s, p<0.025).

CONCLUSIONS

The use of CAD as CR, without any significant increase in reading time, produces no significant increase in sensitivity in pulmonary nodule detection when compared with reading without CAD (p>0.05); CAD as SR, at the cost of longer reading times, increases sensitivity when compared with reading without CAD (p<0.001) or with CAD as CR (p<0.025).

Computer-aided detection of lung nodules: influence of the image reconstruction kernel for computer-aided detection performance

OBJECTIVE

To evaluate the relationship between a computed tomographic reconstruction kernel and the sensitivity of a computer-aided detection (CAD) system for lung nodule detection.

METHODS

We retrospectively studied 36 consecutive patients with no known pulmonary nodules who underwent low-dose computed tomography for lung cancer screening with 3 different reconstruction kernels (B, C, and L). All series were reviewed with a commercial CAD system for lung nodule detection.

RESULTS

The 36 scans showed 231 uncalcified nodules (170 micronodules and 61 nodules). There was little variation of sensitivities for each series (82%, 88%, and 82% for the nodules of B, C, and L, respectively). When the results of 2 series were combined, sensitivities were boosted (B + C, 89%; B + L, 95%; and C + L, 96% for the nodules).

CONCLUSIONS

Sensitivity of the CAD system was influenced by the selection of the reconstruction kernel. By combining data from 2 different kernels, CAD sensitivity can be elevated without further patient radiation exposure.

CAD (computed-aided detection) and CADx (computer aided diagnosis) systems in identifying and characterising lung nodules on chest CT: overview of research, developments and new prospects

Computer-aided detection (CAD) systems allow the automatic identification of lung nodules on chest computed tomography (CT), providing a second opinion to the radiologist's judgement and a volumetric evaluation of lesions - a very important aspect in oncological patients. The natural evolution of these systems has led to the introduction of computer-aided diagnosis (CADx) systems, which are able not only to identify nodules but also to characterise them by determining a likelihood of malignancy or benignity. The aim of this article is to describe the main technical principles of CAD and CADx systems, their applicability and influence in clinical practice and new prospects for their future development.

Improved classifications of planar whole-body bone scans using a computer-assisted diagnosis system: a multicenter, multiple-reader, multiple-case study

The aim of this multicenter study was to investigate whether a computer-assisted diagnosis (CAD) system could improve performance and reduce interobserver variation in bone-scan interpretations of the presence or absence of bone metastases.

METHODS

The whole-body bone scans (anterior and posterior views) of 59 patients with breast or prostate cancer who had undergone scintigraphy for suspected bone metastatic disease were studied. The patients were selected to reflect the spectrum of pathology found in everyday clinical work. Thirty-five physicians working at 18 of the 30 nuclear medicine departments in Sweden agreed to participate. The physicians were asked to classify each case for the presence or absence of bone metastasis, without (baseline) and with the aid of the CAD system (1 y later), using a 4-point scale. The final clinical assessments, based on follow-up scans and other clinical data including the results of laboratory tests and available diagnostic images (such as MRI, CT, and radiographs from a mean follow-up period of 4.8 y), were used as the gold standard. Each physician's classification was pairwise compared with the classifications made by all the other physicians, resulting in 595 pairs of comparisons, both at baseline and after using the CAD system.

RESULTS

The physicians increased their sensitivity from 78% without to 88% with the aid of the CAD system (P < 0.001). The specificity did not change significantly with CAD. Percentage agreement and kappa-values between paired physicians on average increased from 64% to 70% and from 0.48 to 0.55, respectively, with the CAD system.

CONCLUSION

A CAD system improved physicians' sensitivity in detecting metastases and reduced interobserver variation in planar whole-body bone scans. The CAD system appears to have significant potential in assisting physicians in their clinical routine.