Primary carcinoma of the lung overlooked at CT: analysis of findings in 14 patients

Incidental pulmonary nodules may lead to a high proportion of early-stage lung cancer: but it requires more than a high CT volume to achieve this

Background

The management of pulmonary nodules plays a critical role in early detection of lung cancer. Computed tomography (CT) has led to a stage-shift towards early-stage lung cancer, but regional differences in survival rates have been reported in Denmark. This study aimed to evaluate whether variations in nodule management among Danish health regions contributed to these differences.

Material and Methods

The Danish Health Data Authority and Danish Lung Cancer Registry provided data on CT usage and lung cancer stage distribution, respectively. Auditing of lung cancer stage IA patient referrals and nodule management of stage IV lung cancer patients was conducted in seven Danish lung cancer investigation centers, covering four of the five Danish health regions. CT scans were performed up to 2 years before the patients' diagnosis from 2019 to 2021.

Results

CT usage has increased steadily in Denmark over the past decade, with a simultaneous increase in the proportion of early-stage lung cancers, particularly stage IA. However, one Danish health region, Region Zealand, exhibited lower rates of early-stage lung cancer and overall survival despite a CT usage roughly similar to that of the other health regions. The audit did not find significant differences in pulmonary nodule management or a higher number of missed nodules by radiologists in this region compared to others.

Conclusion

This study suggests that a high CT scan volume alone is not sufficient for the early detection of lung cancer. Factors beyond hospital management practices, such as patient-related delays in socioeconomically disadvantaged areas, may contribute to regional differences in survival rates. This has implications for future strategies for reducing these differences.

SOX-1 antibodies in a patient with Crohn's disease: a case report

BACKGROUND

The anti-SOX-1 antibodies have been mainly associated with Lambert-Eaton Myasthenic Syndrome (LETMS) and Small-Cell Lung Cancer (SCLC). In this report, we describe the interesting case of a patient with serum anti-SOX-1 antibodies and Crohn's Disease (CD) with ensuing neurological symptoms.

CASE PRESENTATION

A Caucasian 67-year-old female was admitted to the Emergency Department with seizures, vertigo, emesis, nausea, postural instability and recurrent falls, over a period of 10 days. She had been affected by Crohn's Disease since 1991. A CT scan failed to detect any ischemic or haemorrhagic lesion. A brain MRI revealed signs of leukoencephalopathy. Western blot analysis of her serum revealed a high titre of the onconeural antibody anti-SOX1, consistent with a neurological, cerebellar type, paraneoplastic syndrome. In spite of multiple efforts to unmask a possible underlying malignancy, no neoplastic lesion cropped up during hospitalization. Her clinical conditions progressively deteriorated, up to respiratory failure; a few days later she died, due to ensuing septic shock and Multiple Organ Failure.

CONCLUSIONS

Our experience may usher and reveal a new role of anti-neural antibodies, so far reckoned an early indicator of associated malignancy, suggesting that neurological syndromes associated with such antibodies may complicate also chronic Gastrointestinal (GI) diseases. As of now, testing for anti-neuronal antibodies appeared unnecessary within the diagnostic assessment of gastroenterological disorders, which may lead to overlooking incident neurologic autoimmune diseases. Further exploration of such research hypothesis in clinical grounds appears intriguing.

Solitary Pulmonary Nodule Evaluation: Pearls and Pitfalls

Lung nodules are frequently encountered while interpreting chest CTs and are challenging to detect, characterize, and manage given they can represent both benign or malignant etiologies. An understanding of features associated with malignancy and causes of interpretive pitfalls is helpful to avoid misdiagnoses. This review addresses pertinent topics related to the etiologies for missed lung nodules on radiography and CT. Additionally, CT imaging technical pitfalls and challenges in addition to issues in the evaluation of nodule morphology, attenuation, and size will be discussed. Nodule management guidelines will be addressed as well as recent investigations that further our understanding of lung nodules.

Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population

OBJECTIVE

In this study, we evaluated a commercially available computer assisted diagnosis system (CAD). The deep learning algorithm of the CAD was trained with a lung cancer screening cohort and developed for detection, classification, quantification, and growth of actionable pulmonary nodules on chest CT scans. Here, we evaluated the CAD in a retrospective cohort of a routine clinical population.

MATERIALS AND METHODS

In total, a number of 337 scans of 314 different subjects with reported nodules of 3-30 mm in size were included into the evaluation. Two independent thoracic radiologists alternately reviewed scans with or without CAD assistance to detect, classify, segment, and register pulmonary nodules. A third, more experienced, radiologist served as an adjudicator. In addition, the cohort was analyzed by the CAD alone. The study cohort was divided into five different groups: 1) 178 CT studies without reported pulmonary nodules, 2) 95 studies with 1-10 pulmonary nodules, 23 studies from the same patients with 3) baseline and 4) follow-up studies, and 5) 18 CT studies with subsolid nodules. A reference standard for nodules was based on majority consensus with the third thoracic radiologist as required. Sensitivity, false positive (FP) rate and Dice inter-reader coefficient were calculated.

RESULTS

After analysis of 470 pulmonary nodules, the sensitivity readings for radiologists without CAD and radiologist with CAD, were 71.9% (95% CI: 66.0%, 77.0%) and 80.3% (95% CI: 75.2%, 85.0%) (p < 0.01), with average FP rate of 0.11 and 0.16 per CT scan, respectively. Accuracy and kappa of CAD for classifying solid vs sub-solid nodules was 94.2% and 0.77, respectively. Average inter-reader Dice coefficient for nodule segmentation was 0.83 (95% CI: 0.39, 0.96) and 0.86 (95% CI: 0.51, 0.95) for CAD versus readers. Mean growth percentage discrepancy of readers and CAD alone was 1.30 (95% CI: 1.02, 2.21) and 1.35 (95% CI: 1.01, 4.99), respectively.

CONCLUSION

The applied CAD significantly increased radiologist's detection of actionable nodules yet also minimally increasing the false positive rate. The CAD can automatically classify and quantify nodules and calculate nodule growth rate in a cohort of a routine clinical population. Results suggest this Deep Learning software has the potential to assist chest radiologists in the tasks of pulmonary nodule detection and management within their routine clinical practice.

A diagnostic dilemma of a pulmonary nodule of a patient who suffered advanced ovarian cancer: A case report and a hypothesis

INTRODUCTION

This report presents a case of lung cancer which can be easily misdiagnosed as distant metastasis. Along with a literature review on the morphological, pathological and prognostic characteristics of lung cancer associated with cystic airspaces (LCCA), it would help to improve our understanding of the dynamic evolution of LCCA, to avoid its delayed diagnosis and treatment. We also propose here a hypothesis on the etiology of LCCA.

CASE PRESENTATION

A patient with advanced ovarian cancer who presented with elevated serum CA125 at time of admission and had undergone TAHBSO at first, and second operation of sigmoid colon resection was performed due to her locoregional recurrence of ovarian cancer. After her second operation, patient showed further increment of serum CA125 and CECT scan indicated an airspace-related pulmonary nodule in the right middle lobe of her lungs. It was suspected that distant metastases of ovarian cancer had reoccurred postoperatively.

CLINICAL DISCUSSION

After comparing the characteristic of metastatic ovarian cancer with LCCA, we diagnosed the pulmonary nodule as primary lung cancer. Surgery eventually confirmed the pulmonary nodule as second primary lung cancer associated with cystic airspaces.

CONCLUSION

The rare occurrence of LCCA should merit special attention from clinicians and radiologists so as to avoid missed or delayed diagnosis. We propose here a hypothesis that LCCA is related to spreading of tumour cells during surgical procedures in lung cancer surgery. Should our hypothesis be substantiated in further studies, this would affect the operation procedures for surgeons in the future.

Prospective Study of Spatial Distribution of Missed Lung Nodules by Readers in CT Lung Screening Using Computer-assisted Detection

PURPOSE

To evaluate the spatial patterns of missed lung nodules in a real-life routine screening environment.

MATERIALS AND METHODS

In a screening institute, 4,822 consecutive adults underwent chest CT, and each image set was independently interpreted by two radiologists in three steps: (1) independently interpreted without computer-assisted detection (CAD) software, (2) independently referred to the CAD results, (3) determined by the consensus of the two radiologists. The locations of nodules and the detection performance data were semi-automatically collected using a CAD server integrated into the reporting system. Fisher's exact test was employed for evaluating findings in different lung divisions. Probability maps were drawn to illustrate the spatial distribution of radiologists' missed nodules.

RESULTS

Radiologists significantly tended to miss lung nodules in the bilateral hilar divisions (p < 0.01). Some radiologists had their own spatial pattern of missed lung nodules.

CONCLUSION

Radiologists tend to miss lung nodules present in the hilar regions significantly more often than in the rest of the lung.

Missed lung cancer: when, where, and why?

Missed lung cancer is a source of concern among radiologists and an important medicolegal challenge. In 90% of the cases, errors in diagnosis of lung cancer occur on chest radiographs. It may be challenging for radiologists to distinguish a lung lesion from bones, pulmonary vessels, mediastinal structures, and other complex anatomical structures on chest radiographs. Nevertheless, lung cancer can also be overlooked on computed tomography (CT) scans, regardless of the context, either if a clinical or radiologic suspect exists or for other reasons. Awareness of the possible causes of overlooking a pulmonary lesion can give radiologists a chance to reduce the occurrence of this eventuality. Various factors contribute to a misdiagnosis of lung cancer on chest radiographs and on CT, often very similar in nature to each other. Observer error is the most significant one and comprises scanning error, recognition error, decision-making error, and satisfaction of search. Tumor characteristics such as lesion size, conspicuity, and location are also crucial in this context. Even technical aspects can contribute to the probability of skipping lung cancer, including image quality and patient positioning and movement. Albeit it is hard to remove missed lung cancer completely, strategies to reduce observer error and methods to improve technique and automated detection may be valuable in reducing its likelihood.

Evidence-based anatomical review areas derived from systematic analysis of cases from a radiological departmental discrepancy meeting

AIM

To produce short checklists of specific anatomical review sites for different regions of the body based on the frequency of radiological errors reviewed at radiology discrepancy meetings, thereby creating "evidence-based" review areas for radiology reporting.

MATERIALS AND METHODS

A single centre discrepancy database was retrospectively reviewed from a 5-year period. All errors were classified by type, modality, body system, and specific anatomical location. Errors were assigned to one of four body regions: chest, abdominopelvic, central nervous system (CNS), and musculoskeletal (MSK). Frequencies of errors in anatomical locations were then analysed.

RESULTS

There were 561 errors in 477 examinations; 290 (46%) errors occurred in the abdomen/pelvis, 99 (15.7%) in the chest, 117 (18.5%) in the CNS, and 125 (19.9%) in the MSK system. In each body system, the five most common location were chest: lung bases on computed tomography (CT), apices on radiography, pulmonary vasculature, bones, and mediastinum; abdominopelvic: vasculature, colon, kidneys, liver, and pancreas; CNS: intracranial vasculature, peripheral cerebral grey matter, bone, parafalcine, and the frontotemporal lobes surrounding the Sylvian fissure; and MSK: calvarium, sacrum, pelvis, chest, and spine.

CONCLUSION

The five listed locations accounted for >50% of all perceptual errors suggesting an avenue for focused review at the end of reporting.

Interval lung cancer after a negative CT screening examination: CT findings and outcomes in National Lung Screening Trial participants

OBJECTIVES

This study retrospectively analyses the screening CT examinations and outcomes of the National Lung Screening Trial (NLST) participants who had interval lung cancer diagnosed within 1 year after a negative CT screen and before the next annual screen.

METHODS

The screening CTs of all 44 participants diagnosed with interval lung cancer (cases) were matched with negative CT screens of participants who did not develop lung cancer (controls). A majority consensus process was used to classify each CT screen as positive or negative according to the NLST criteria and to estimate the likelihood that any abnormalities detected retrospectively were due to lung cancer.

RESULTS

By retrospective review, 40/44 cases (91%) and 17/44 controls (39%) met the NLST criteria for a positive screen (P < 0.001). Cases had higher estimated likelihood of lung cancer (P < 0.001). Abnormalities included pulmonary nodules ≥4 mm (n = 16), mediastinal (n = 8) and hilar (n = 6) masses, and bronchial lesions (n = 6). Cancers were stage III or IV at diagnosis in 32/44 cases (73%); 37/44 patients (84%) died of lung cancer, compared to 225/649 (35%) for all screen-detected cancers (P < 0.0001).

CONCLUSION

Most cases met the NLST criteria for a positive screen. Awareness of missed abnormalities and interpretation errors may aid lung cancer identification in CT screening.

KEY POINTS

• Lung cancer within a year of a negative CT screen was rare. • Abnormalities likely due to lung cancer were identified retrospectively in most patients. • Awareness of error types may help identify lung cancer sooner.

Comparing the performance of trained radiographers against experienced radiologists in the UK lung cancer screening (UKLS) trial

OBJECTIVE

To compare the performance of radiographers against that of radiologists for CT lung nodule detection in the UK Lung Cancer Screening (UKLS) pilot trial.

METHODS

Four radiographers, trained in CT nodule detection, and three radiologists were prospectively evaluated. 290 CTs performed for the UKLS were independently read by 2 radiologists and 2 radiographers. The reference standard comprised all radiologist-identified positive nodules after arbitration of discrepancies. For each radiographer and radiologist, relative sensitivity and average false positives (FPs) per case were compared for all cases read, as well as for subsets of cases read by each radiographer-radiologist combination (10 combinations).

RESULTS

599 nodules in 209/290 (72.1%) CT studies comprised the reference standard. The relative mean (±standard deviation) sensitivity of the four radiographers was 71.6 ± 8.5% compared with 83.3 ± 8.1% for the three radiologists. Radiographers were less sensitive and detected more FPs per case than radiologists in 7/10 and 8/10 radiographer-radiologist combinations, respectively (ranges of difference 11.2-33.8% and 0.4-2.6; p < 0.05). In 3/10 and 2/10 combinations, there was no difference in sensitivity and FPs per case between radiographers and radiologists. For nodules ≥100 mm(3) in volume or ≥5 mm in maximum diameter, radiographers were relatively less sensitive than radiologists in only 5/10 radiographer-radiologist combinations (range of difference 16.1-30.6%; p < 0.05) and not significantly different in the remaining 5/10 combinations.

CONCLUSION

Although overall radiographer performance was lower than that of experienced radiologists in this study, some radiographer performances were comparable with that of radiologists.

ADVANCES IN KNOWLEDGE

Overall, radiographers were less sensitive than radiologists reading the same CTs and also displayed higher average FP detections per case when compared with a reference standard derived from radiologist readings. However, some radiographers compared favourably with radiologists, especially when considering larger potentially clinically relevant nodules. Thus, while probably not sensitive enough to function as first readers, radiographers may still be able to fulfil the role of an assistant reader-that is, as a first or concurrent reader, who presents detected nodules for verification to a reading radiologist.

Computed tomography: revolutionizing the practice of medicine for 40 years

Computed tomography (CT) has had a profound effect on the practice of medicine. Both the spectrum of clinical applications and the role that CT has played in enhancing the depth of our understanding of disease have been profound. Although almost 90 000 articles on CT have been published in peer-reviewed journals over the past 40 years, fewer than 5% of these have been published in Radiology. Nevertheless, these almost 4000 articles have provided a basis for many important medical advances. By enabling a deepened understanding of anatomy, physiology, and pathology, CT has facilitated key advances in the detection and management of disease. This article celebrates this breadth of scientific discovery and development by examining the impact that CT has had on the diagnosis, characterization, and management of a sampling of major health challenges, including stroke, vascular diseases, cancer, trauma, acute abdominal pain, and diffuse lung diseases, as related to key technical advances in CT and manifested in Radiology.

Multiple diagnostic task performance in CT examination of the chest

Objectives In three experiments, we studied the detection of multiple abnormality types using the satisfaction of search (SOS) paradigm, the provision of a computer-aided detection (CAD) of pulmonary nodules and a focused nodule detection task. Methods 51 chest CT examinations (24 that demonstrated subtle pulmonary nodules and 27 that demonstrated no pulmonary nodules) were read by 15 radiology residents and fellows under two experimental conditions: (1) when there were no other abnormalities present except test abnormalities in the exams (non-SOS condition), and (2) when other abnormalities were present in the exams (SOS condition). Trials from the two conditions were intermixed. Readers were invited to return for two sessions: one in which the SOS condition was repeated with a simulated CAD; another in which only the non-SOS condition was presented. Detection accuracy was measured using receiver operating characteristic (ROC) analysis. Results An SOS effect (reduced detection accuracy for the test nodules in the presence of the diverse added abnormalities) was not found. Average accuracy was much higher when the CAD prompt was provided, without cost in the detection of the added abnormalities. Accuracy for detecting nodules appearing without intermixed SOS trials was also substantially improved. Conclusions CT interpretation was highly task dependent. Nodule detection was poor in the general search task. Therefore, CAD may offer a greater performance improvement than demonstrated in experiments assessing CAD using focused search. The absence of SOS may be due to limited nodule detection even without other abnormalities. Advances in knowledge CAD prompts of nodules increase the detection accuracy of nodules and decrease the time to detection-without impairing the detection accuracy-of non-nodule abnormalities.

Satisfaction of search from detection of pulmonary nodules in computed tomography of the chest

RATIONALE AND OBJECTIVES

We tested whether satisfaction of search (SOS) effects that occur in computed tomography (CT) examination of the chest on detection of native abnormalities are produced by the addition of simulated pulmonary nodules.

MATERIALS AND METHODS

Two experiments were conducted. In the first experiment, 70 CT examinations, half that demonstrated diverse, subtle abnormalities and half that demonstrated no native lesions, were read by 18 radiology residents and fellows under two experimental conditions: presented with and without pulmonary nodules. In a second experiment, many of the examinations were replaced to include more salient native abnormalities. This set was read by 14 additional radiology residents and fellows. In both experiments, detection of the natural abnormalities was studied. Receiver operating characteristic (ROC) curve areas for each reader-treatment combination were estimated using empirical and proper ROC models. Additional analyses focused on decision thresholds and visual search time on abnormality-free CT slice ranges. Institutional review board approval and informed consent from 32 participants were obtained.

RESULTS

Observers more often missed diverse native abnormalities when pulmonary nodules were added, but also made fewer false-positive responses. There was no change in ROC area, but decision criteria grew more conservative. The SOS effect on decision thresholds was accompanied by a reduction in search time on abnormality-free CT slice ranges.

CONCLUSION

The SOS effect in CT examination of the chest is similar to that found in contrast examination of the abdomen, involving induced visual neglect.

Multiple diagnostic task performance in CT examination of the chest

OBJECTIVES

In three experiments, we studied the detection of multiple abnormality types using the satisfaction of search (SOS) paradigm, the provision of a computer-aided detection (CAD) of pulmonary nodules and a focused nodule detection task.

METHODS

51 chest CT examinations (24 that demonstrated subtle pulmonary nodules and 27 that demonstrated no pulmonary nodules) were read by 15 radiology residents and fellows under two experimental conditions: (1) when there were no other abnormalities present except test abnormalities in the exams (non-SOS condition), and (2) when other abnormalities were present in the exams (SOS condition). Trials from the two conditions were intermixed. Readers were invited to return for two sessions: one in which the SOS condition was repeated with a simulated CAD; another in which only the non-SOS condition was presented. Detection accuracy was measured using receiver operating characteristic (ROC) analysis.

RESULTS

An SOS effect (reduced detection accuracy for the test nodules in the presence of the diverse added abnormalities) was not found. Average accuracy was much higher when the CAD prompt was provided, without cost in the detection of the added abnormalities. Accuracy for detecting nodules appearing without intermixed SOS trials was also substantially improved.

CONCLUSIONS

CT interpretation was highly task dependent. Nodule detection was poor in the general search task. Therefore, CAD may offer a greater performance improvement than demonstrated in experiments assessing CAD using focused search. The absence of SOS may be due to limited nodule detection even without other abnormalities. Advances in knowledge CAD prompts of nodules increase the detection accuracy of nodules and decrease the time to detection-without impairing the detection accuracy-of non-nodule abnormalities.

Blind spots at oncological CT: lessons learned from PET/CT

Improved accuracy in oncological computed tomography (CT) could lead to a decrease in morbidity and improved survival for oncology patients. Visualization of metabolic activity using the glucose analogue [¹⁸F]fluorodeoxyglucose (FDG) in combination with the high anatomic resolution of CT in an integrated positron emission tomography (PET)/CT examination has the highest sensitivity and specificity for the detection of primary and metastatic lesions. However, PET/CT costs are high and patient access is limited; thus CT remains the primary imaging modality in oncology patients. We have noted that subtle lesions are more easily detected on CT by radiologists with PET/CT experience. We aimed to provide a brief review of the literature with comparisons of multi-detector computed tomography (MDCT) and PET/CT in primary and metastatic disease with an emphasis on findings that may be overlooked on MDCT in cancer of the breast, lung, colon, and ovaries, and in melanoma, as well as thrombosis in oncology patients. We further reviewed our experience for illustrative comparisons of PET/CT and MDCT studies. Experience in interpreting conventional CT scans alongside PET/CT can help the reader develop an appreciation for the subtle appearance of some lesions on CT that might otherwise be missed. This could improve detection rates, reduce errors, and improve patient management.

Endobronchial tumours in a campaign for early detection of bronchial cancer: Computed tomography versus endoscopy

OBJECTIVE

To study endobronchial cancers occurring in a population at high risk of bronchial cancer (history of surgically treated bronchial or ENT cancer in complete remission, and symptoms due to smoking) detected by annual volume CT scans and biannual fibroscopy.

MATERIAL AND METHODS

Two hundred and sixty-six patients were included in this single centre prospective study; 27 bronchopulmonary cancers were detected. Ten endobronchial cancers (37%) were identified by fibroscopy (nine invasive cancers and one carcinoma in situ) in 10 patients (nine men) (51-78 years old) nine of whom were smokers (dark tobacco: seven). The screening CTs were reappraised by two radiologists.

RESULTS

Three cancers out of 10 were detected by CT during the initial reading. The sensitivity of the reappraised CT was 80% with seven false positives. In five cases, the mean period between the first CT scan where the lesion was visible retrospectively, but not described, and the diagnostic fibroscopy was 463 days (213-808 days); two cancers were not visible in the CT scan. Seven curative treatments were undertaken.

CONCLUSION

In this population, the sensitivity of the initial reading of the CT scan for detecting endobronchial tumours was 30%, while 80% of the tumours were visible retrospectively, underlining the importance of careful analysis of the proximal bronchial tree.

Interphase cytogenetics of sputum cells for the early detection of lung carcinogenesis

This perspective on Varella-Garcia et al. (beginning on p. 447 in this issue of the journal) examines the role of interphase fluorescence in situ hybridization for the early detection of lung cancer. This work is an important step toward identifying and validating a molecular marker in sputum samples for lung cancer early detection and highlights the value of establishing cohort studies with biorepositories of samples collected from participants followed over time for disease development.

Errors in cancer diagnosis: current understanding and future directions

PURPOSE

Errors in cancer diagnosis are likely the most harmful and expensive types of diagnostic errors. We reviewed the literature to understand the prevalence, origins, and prevention of errors in cancer diagnosis, focusing on common cancers for which early diagnosis offers clear benefit (melanoma and cancers of the breast, colon, and lung).

METHODS

We searched the Cochrane Library and PubMed from 1966 until April 2007 for publications that met our review criteria and manually searched references of key publications. Our search yielded 110 studies, of which nine were prospective studies and the remaining were retrospective studies.

RESULTS

Errors in cancer diagnosis were not uncommon in autopsy studies and were associated with significant harm and expense in malpractice claims. Literature on prevalence was scant. For each type of cancer, we classified preventable errors according to their origins in patient-physician encounters in the clinic setting, diagnostic test or procedure performance, pathologic confirmation of diagnosis, follow-up of patient or test result, or patient-related delays.

CONCLUSION

The literature reflects advanced knowledge of contributory factors and prevention for diagnostic errors related to the performance of procedures and imaging tests and emerging understanding of pathology errors. However, prospective studies are few, as are studies of diagnostic errors arising from the clinical encounter and patient follow-up. Future research should examine further the system and cognitive problems that lead to the many contributory factors we identified, and address interdisciplinary interventions to prevent errors in cancer diagnosis.

Computer-aided detection of pulmonary nodules in computed tomography: analysis and review of the literature

PURPOSE

To evaluate diagnostic sensitivity of the pulmonary nodules computer-aided detection (CAD) in computed tomography. To analyze parameters that modify CAD performance. We made a critical analysis of the literature, and we described CAD sensitivity. Moreover, we compared CAD and CAD plus radiologist sensitivity in detection of pulmonary nodules, and we compared different acquisition techniques (thin slice vs thick slice and low dose vs normal dose).

MATERIALS AND METHODS

We used as major data sources the medical literature database of PubMed and MEDLINE, where we searched for articles in English language published from January 2001 to November 2006. We included studies that used spiral or multidetector row CT for CAD.

RESULTS

Twenty studies met the inclusion criteria containing a total of more than 827 patients and 2717 pulmonary nodules detected by CAD. We observed an overall sensitivity of 79% for the CAD and of 92% for CAD plus radiologist; CAD sensitivity was 80% and 74% for thin slice and thick slice protocols, respectively.

CONCLUSIONS

Results of our study suggest that CAD technique is an accurate tool in detection of pulmonary nodules, by working as useful second look for the physician. Sensitivity becomes higher by using it together with radiologist. Actually, the main limitation about the use of CAD to be solved is represented by the persistent high false-positive rate.

Evaluating computer-aided detection algorithms

Computer-aided detection (CAD) has been attracting extensive research interest during the last two decades. It is recognized that the full potential of CAD can only be realized by improving the performance and robustness of CAD algorithms and this requires good evaluation methodology that would permit CAD designers to optimize their algorithms. Free-response receiver operating characteristic (FROC) curves are widely used to assess CAD performance, however, evaluation rarely proceeds beyond determination of lesion localization fraction (sensitivity) at an arbitrarily selected value of nonlesion localizations (false marks) per image. This work describes a FROC curve fitting procedure that uses a recent model of visual search that serves as a framework for the free-response task. A maximum likelihood procedure for estimating the parameters of the model from free-response data and fitting CAD generated FROC curves was implemented. Procedures were implemented to estimate two figures of merit and associated statistics such as 95% confidence intervals and goodness of fit. One of the figures of merit does not require the arbitrary specification of an operating point at which to evaluate CAD performance. For comparison a related method termed initial detection and candidate analysis was also implemented that is applicable when all suspicious regions are reported. The two methods were tested on seven mammography CAD data sets and both yielded good to excellent fits. The search model approach has the advantage that it can potentially be applied to radiologist generated free-response data where not all suspicious regions are reported, only the ones that are deemed sufficiently suspicious to warrant clinical follow-up. This work represents the first practical application of the search model to an important evaluation problem in diagnostic radiology. Software based on this work is expected to benefit CAD developers working in diverse areas of medical imaging.

Coronary Artery Imaging with Contrast-Enhanced MDCT: Extracardiac Findings

OBJECTIVE

The purpose of our study was to evaluate the incidence of extracardiac findings on contrast-enhanced MDCT of the coronary arteries and to assess the effect of different field-of-view settings.

SUBJECTS AND METHODS

Patients with suspected coronary artery disease (n = 166) were examined with contrast-enhanced MDCT (16 x 0.75 mm focused on the heart) during injection of contrast material (80 mL injected at a rate of 4 mL/sec) followed by saline (20 mL injected at 4 mL/sec). Retrospectively gated images were reconstructed at a 1-mm slice thickness and a 0.5-mm increment with isotropic voxels of 1 mm3. Images were reviewed for extracardiac findings, which were then classified as none, minor, or major with respect to their impact on patient management and treatment. In a different group of patients (n = 20), chest scans (16 x 1.5 mm) were used for measuring volumes of displayed body structures on wholechest scans, coronary artery MDCT images, and coronary artery MDCT images reconstructed with the maximum field of view.

RESULTS

Extracardiac findings were detected in 41 patients (24.7%). Findings were classified as minor (19.9%) or major (4.8%). Among the major findings, which had an immediate impact on patient management and treatment, were bronchial carcinoma and pulmonary emboli. Volume analysis revealed that 35.5% of the total chest volume was displayed on dedicated coronary artery MDCT focused on the heart, whereas 70.3% of the chest was visible when coronary artery MDCT raw data were reconstructed with the maximal field of view (p < 0.001).

CONCLUSION

Coronary artery MDCT can reveal important findings and disease in extracardiac structures. Thus, the entire examination should be reconstructed with the maximum field of view and should be reviewed by a qualified radiologist.

CT and MRI of Lung Cancer

Computed tomography (CT) is still the cornerstone of imaging studies in the preoperative staging and post- therapeutic evaluation of lung cancer. The most recent developments in multidetector technology have dramatically improved the temporal and spatial resolution of CT. In the mean time, magnetic resonance imaging (MRI) has not become a routine examination in lung imaging and is today only used as a problem-solving tool in patients in whom CT remains equivocal. This article will describe the current tools developed in the multidetector CT era for evaluating the lung, and state-of-the-art MR examination of the chest. Then, the role of CT and MRI in nodule detection, the distinction between benign and malignant nodules, and the benefit of CT and MRI in the staging and post-therapeutic evaluation of lung cancer will be covered.

Pulmonary nodule detection in CT images with quantized convergence index filter

A novel filter termed quantized convergence index filter (QCI filter) that is capable of enhancing the conspicuity of rounded lesions is proposed as part of a CAD (computer-aided diagnosis) scheme for detecting pulmonary nodules in computed tomography (CT) images. In this filter and its predecessor, the convergence index filter (CI filter), the output at a pixel represents the degree of convergence toward the pixel shown by the directions of gray-level gradients at surrounding pixels. The QCI filter and the CAD scheme were evaluated using five clinical datasets containing 50 nodules. With the support region of 9 x 9 pixels, the QCI filter showed more selective response to the nodules than the CI filter. In the CAD scheme, intermediate nodule candidates are generated based on the QCI filter output and then classified using linear discriminant analysis of eight features that are attributed to each intermediate nodule candidate. The QCI filter output level itself was used as one of the features. The scheme achieved a sensitivity of 90% with 1.67 false positives per slice. The QCI filter output level was most effective among the features in correctly classifying intermediate nodule candidates. The QCI filter is promising as a tool of preprocessing for automated pulmonary nodule detection in CT images.

Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization

PURPOSE

To retrospectively evaluate whether a difference-image computer-aided detection (CAD) scheme can help radiologists detect peripheral lung cancers missed at low-dose computed tomography (CT).

MATERIALS AND METHODS

Institutional review board approval and informed patient and observer consent were obtained. Seventeen patients (eight men and nine women; mean age, 60 years) with a missed peripheral lung cancer and 10 control subjects (five men and five women; mean age, 63 years) without cancer at low-dose CT were included in an observer study. Fourteen radiologists were divided into two groups on the basis of different image display formats: Six radiologists (group 1) reviewed CT scans with a multiformat display, and eight radiologists (group 2) reviewed images with a "stacked" cine-mode display. The radiologists, first without and then with the CAD scheme, indicated their confidence level regarding the presence (or absence) of cancer and the most likely position of a lesion on each CT scan. Receiver operating characteristic (ROC) curves were calculated without and with localization to evaluate the observers' performance.

RESULTS

With the CAD scheme, the average area under the ROC curve improved from 0.763 to 0.854 for all radiologists (P = .002), from 0.757 to 0.862 for group 1 (P = .04), and from 0.768 to 0.848 for group 2 (P = .01). The average sensitivity in the detection of 17 cancers improved from 52% (124 of 238 observations) to 68% (163 of 238 observations) for all radiologists (P < .001), from 49% (50 of 102 observations) to 71% (72 of 102 observations) for group 1 (P = .02), and from 54% (74 of 136 observations) to 67% (91 of 136 observations) for group 2 (P = .006). The localization ROC curve also improved.

CONCLUSION

Lung cancers missed at low-dose CT were very difficult to detect, even in an observer study. The use of CAD, however, can improve radiologists' performance in the detection of these subtle cancers.

Computer-aided diagnosis as a second reader: spectrum of findings in CT studies of the chest interpreted as normal

STUDY OBJECTIVES

To assess the performance of an automated computer-aided detection (CAD) system as a second reader on chest CT studies interpreted as normal at routine clinical interpretation.

DESIGN

Chest CT studies were processed using a prototype CAD system for automated detection of lung lesions. Three experienced radiologists analyzed each CAD finding and confirmed or dismissed the marked image features as lung lesions. Noncalcified, focal lung lesions were classified according to size as being of high (> or = 10 mm), intermediate (5 to 9 mm), or low (< or = 4 mm) significance.

SETTING

Two sub-specialized academic tertiary referral centers in the United States and Germany.

PATIENTS

Chest CT studies were performed in 100 patients, with results initially reported as normal at clinical double reading. Indications for chest CT were suspected pulmonary embolism (PE) [n = 33], lung cancer screening in a high-risk population (n = 28), or follow-up for a cancer history (n = 39).

INTERVENTIONS

Reevaluation of all chest CT studies for focal lung lesions with the CAD system as a second reader.

MEASUREMENTS

Prevalence and spectrum of lung lesions missed at routine clinical interpretation but found by the CAD system.

RESULTS

In 33% (33 of 100 patients), CAD detected significant lung lesions that were not previously reported. Fifty-three significant lesions were detected (mean, 1.6 lesions per case), of which 5 lesions (9.4%) were of high significance, 21 lesions (39.6%) were of intermediate significance, and 27 lesions (50.9%) were of low significance. In the PE group, the lung cancer screening group, and the group with a cancer history, four patients (12.1%), six patients (21.4%), and nine patients (23.1%), respectively, had focal lung lesions of high and/or intermediate significance. The false-positive rate of the CAD system was an average of 1.25 per case (range, 0 to 11).

CONCLUSIONS

Significant lung lesions are frequently missed at routine clinical interpretation of chest CT studies but may be detected if CAD is used as an additional reader.

Lung Nodule Detection and Characterization With Multi-Slice CT

The influence of MSCT on nodule detection and characterization will be discussed. The objective is to improve understanding of the clinical issues involved in nodule detection, characterization, and management in light of technological advances. Topics to be covered are noninvasive characterization techniques, such as morphologic and density inspection on CT, nodule enhancement techniques, CT-PET, temporal nodule size assessment, and computer aided diagnosis for both detection and characterization.

The imaging manifestations of lung cancer

Imaging plays an integral role in diagnosing, staging, and following patients with lung cancer. Many lung neoplasms are detected on chest radiographs, but the majority of patients have advanced stage disease at the time of presentation. There is a wide spectrum of radiologic manifestations of lung cancer, and recognition of these findings is essential for patient management. As we continue to understand more about tumor biology, new imaging techniques likely will emerge. Nevertheless, the chest radiograph and CT remain important tools in establishing the diagnosis of lung cancer.

Vessel tree reconstruction in thoracic CT scans with application to nodule detection

Vessel tree reconstruction in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automated lung nodule detection in thoracic computed tomography (CT) scans, vessel trees can be used to resolve local ambiguities based on global considerations and so improve the performance of nodule detection algorithms. In this study, a novel approach to vessel tree reconstruction and its application to nodule detection in thoracic CT scans was developed by using correlation-based enhancement filters and a fuzzy shape representation of the data. The proposed correlation-based enhancement filters depend on first-order partial derivatives and so are less sensitive to noise compared with Hessian-based filters. Additionally, multiple sets of eigenvalues are used so that a distinction between nodules and vessel junctions becomes possible. The proposed fuzzy shape representation is based on regulated morphological operations that are less sensitive to noise. Consequently, the vessel tree reconstruction algorithm can accommodate vessel bifurcation and discontinuities. A quantitative performance evaluation of the enhancement filters and of the vessel tree reconstruction algorithm was performed. Moreover, the proposed vessel tree reconstruction algorithm reduced the number of false positives generated by an existing nodule detection algorithm by 38%.

Knowledge-driven automated detection of pleural plaques and thickening in high resolution CT of the lung

Consistent efforts are being made to build Computer-Aided Detection and Diagnosis systems for radiological images. Such systems depend on automated detection of various disease patterns, which are then combined together to obtain differential diagnosis. For diffuse lung diseases, over 12 disease patterns are of interest in High Resolution Computed Tomography (HRCT) scans of the lung. In this paper, we present an automated detection method for two such patterns, namely Pleural Plaque and Diffuse Pleural Thickening. These are characteristic features of asbestos-related benign pleural disease. The attributes used for detection are derived from anatomical knowledge and the heuristics normally used by radiologists, and are computed automatically for each scan. A probabilistic model built on the attributes using naïve Bayes classifier is applied to recognise the features in new scans, and preliminary results are presented. The technique is tested on 140 images from 13 studies and validated by an experienced radiologist.

Effect of temporal subtraction images on radiologists' detection of lung cancer on CT: results of the observer performance study with use of film computed tomography images

RATIONALE AND OBJECTIVES

To evaluate the effect of temporal subtraction images on the radiologists' detection of early primary lung cancer in computed tomography (CT) scans.

MATERIALS AND METHODS

Fourteen cases with primary lung cancer and 16 normal cases were used for this study from a database of low-dose CT images, which were obtained from a lung cancer screening program in Nagano, Japan. Images were obtained with a single-detector helical CT scanner using 10 mm collimation and 2:1 pitch. Each case had both previous and current CT scans. Temporal subtraction images were obtained by subtracting the warped previous images from the current images. Seven radiologists, including four attendings and three residents, provided their confidence levels for the presence or absence of lung cancers with use of film CT images without and with temporal subtraction images. Receiver operating characteristic analysis was used to compare their performance without and with temporal subtraction images.

RESULTS

The mean Az values (area under the receiver operating characteristic curve) of seven observers without and with temporal subtraction images were 0.868 and 0.930, respectively. Diagnostic accuracy was significantly improved by using temporal subtraction images (P = .007). Temporal subtraction images were especially useful when a nodule was present near the pulmonary hilum, where radiologists tended to overlook it.

CONCLUSION

The temporal subtraction technique can significantly improve the sensitivity and specificity for detection of lung cancer on CT scans.

Pulmonary nodules on multi-detector row CT scans: performance comparison of radiologists and computer-aided detection

PURPOSE

To compare the performance of radiologists and of a computer-aided detection (CAD) algorithm for pulmonary nodule detection on thin-section thoracic computed tomographic (CT) scans.

MATERIALS AND METHODS

The study was approved by the institutional review board. The requirement of informed consent was waived. Twenty outpatients (age range, 15-91 years; mean, 64 years) were examined with chest CT (multi-detector row scanner, four detector rows, 1.25-mm section thickness, and 0.6-mm interval) for pulmonary nodules. Three radiologists independently analyzed CT scans, recorded the locus of each nodule candidate, and assigned each a confidence score. A CAD algorithm with parameters chosen by using cross validation was applied to the 20 scans. The reference standard was established by two experienced thoracic radiologists in consensus, with blind review of all nodule candidates and free search for additional nodules at a dedicated workstation for three-dimensional image analysis. True-positive (TP) and false-positive (FP) results and confidence levels were used to generate free-response receiver operating characteristic (ROC) plots. Double-reading performance was determined on the basis of TP detections by either reader.

RESULTS

The 20 scans showed 195 noncalcified nodules with a diameter of 3 mm or more (reference reading). Area under the alternative free-response ROC curve was 0.54, 0.48, 0.55, and 0.36 for CAD and readers 1-3, respectively. Differences between reader 3 and CAD and between readers 2 and 3 were significant (P < .05); those between CAD and readers 1 and 2 were not significant. Mean sensitivity for individual readings was 50% (range, 41%-60%); double reading resulted in increase to 63% (range, 56%-67%). With CAD used at a threshold allowing only three FP detections per CT scan, mean sensitivity was increased to 76% (range, 73%-78%). CAD complemented individual readers by detecting additional nodules more effectively than did a second reader; CAD-reader weighted kappa values were significantly lower than reader-reader weighted kappa values (Wilcoxon rank sum test, P < .05).

CONCLUSION

With CAD used at a level allowing only three FP detections per CT scan, sensitivity was substantially higher than with conventional double reading.

Lung image database consortium: developing a resource for the medical imaging research community

To stimulate the advancement of computer-aided diagnostic (CAD) research for lung nodules in thoracic computed tomography (CT), the National Cancer Institute launched a cooperative effort known as the Lung Image Database Consortium (LIDC). The LIDC is composed of five academic institutions from across the United States that are working together to develop an image database that will serve as an international research resource for the development, training, and evaluation of CAD methods in the detection of lung nodules on CT scans. Prior to the collection of CT images and associated patient data, the LIDC has been engaged in a consensus process to identify, address, and resolve a host of challenging technical and clinical issues to provide a solid foundation for a scientifically robust database. These issues include the establishment of (a) a governing mission statement, (b) criteria to determine whether a CT scan is eligible for inclusion in the database, (c) an appropriate definition of the term qualifying nodule, (d) an appropriate definition of "truth" requirements, (e) a process model through which the database will be populated, and (f) a statistical framework to guide the application of assessment methods by users of the database. Through a consensus process in which careful planning and proper consideration of fundamental issues have been emphasized, the LIDC database is expected to provide a powerful resource for the medical imaging research community. This article is intended to share with the community the breadth and depth of these key issues.

Use of a clinical pathway to manage unsuspected radiographic findings

STUDY OBJECTIVES

To describe our 5-year experience with a clinical pathway used to ensure the timely communication and evaluation of unsuspected radiologic findings (URFs) noted on clinically requested chest imaging.

DESIGN

Prospective data collection on clinical practice.

SETTING

Academically affiliated Veterans Affairs medical center.

PARTICIPANTS

Pulmonary physicians, nurses, and radiologists.

RESULTS

Over a period of 5 years, 1,629 URFs were referred to the pathway (from chest radiographs, 1,359 [83.4%]; from CT scans, 270 [16.6%]). Most URFs (78%) were nodules, with a specific diagnosis made in one third of URFs, and with a specific diagnosis thought to be clinically significant in another one third of URFs. The most common diagnosis was neoplasm, with over two thirds of these diagnoses being lung cancer. One third of lung cancers detected were either stage 1 or 2, with 1 in 17 of all URFs being stage IA lung cancer. The cost of the pathway was estimated at 28,600 dollars per year.

CONCLUSIONS

URFs noted on chest imaging are frequently clinically significant, and a systematic approach to managing URFs, such as a clinical pathway, can significantly improve care in a large teaching hospital.

Progression of focal pure ground-glass opacity detected by low-dose helical computed tomography screening for lung cancer

OBJECTIVE

To clarify the progression of focal pure ground-glass opacity (pGGO) detected by low-dose helical computed tomography (CT) screening for lung cancer.

METHODS

A total of 15,938 low-dose helical CT examinations were performed in 2052 participants in the screening project, and 1566 of them were judged to have yielded abnormal findings requiring further examination. Patients with peripheral nodules exhibiting pGGO at the time of the first thin-section CT examination and confirmed histologically by thin-section CT after follow-up of more than 6 months were enrolled in the current study. Progression was classified based on the follow-up thin-section CT findings.

RESULTS

The progression of the 8 cases was classified into 3 types: increasing size (n = 5: bronchioloalveolar carcinoma [BAC]), decreasing size and the appearance of a solid component (n = 2: BAC, n = 1; adenocarcinoma with mixed subtype [Ad], n = 1), and stable size and increasing density (n = 1: BAC). In addition, the decreasing size group was further divided into 2 subtypes: a rapid-decreasing type (Ad: n = 1) and a slow-decreasing type (BAC: n = 1). The mean period between the first thin-section CT and surgery was 18 months (range: 7-38 months). All but one of the follow-up cases of lung cancer were noninvasive whereas the remaining GGO with a solid component was minimally invasive.

CONCLUSIONS

The pGGOs of lung cancer nodules do not only increase in size or density, but may also decrease rapidly or slowly with the appearance of solid components. Close follow-up until the appearance of a solid component may be a valid option for the management of pGGO.

Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm

Increasingly, computed tomography (CT) offers higher resolution and faster acquisition times. This has resulted in the opportunity to detect small lung nodules, which may represent lung cancers at earlier and potentially more curable stages. However, in the current clinical practice, hundreds of such thin-sectional CT images are generated for each patient and are evaluated by a radiologist in the traditional sense of looking at each image in the axial mode. This results in the potential to miss small nodules and thus potentially miss a cancer. In this paper, we present a computerized method for automated identification of small lung nodules on multislice CT (MSCT) images. The method consists of three steps: (i) separation of the lungs from the other anatomic structures, (ii) detection of nodule candidates in the extracted lungs, and (iii) reduction of false-positives among the detected nodule candidates. A three-dimensional lung mask can be extracted by analyzing density histogram of volumetric chest images followed by a morphological operation. Higher density structures including nodules scattered throughout the lungs can be identified by using a local density maximum algorithm. Information about nodules such as size and compact shape are then incorporated into the algorithm to reduce the detected nodule candidates which are not likely to be nodules. The method was applied to the detection of computer simulated small lung nodules (2 to 7 mm in diameter) and achieved a sensitivity of 84.2% with, on average, five false-positive results per scan. The preliminary results demonstrate the potential of this technique for assisting the detection of small nodules from chest MSCT images.

Lung nodule detection and characterization with multislice CT

The ability to identify and characterize pulmonary nodules has been dramatically increased by the introduction of multislice CT (MSCT) technology. Using high-resolution sections, MSCT allows considerable improvement in assessing nodule morphology, enhancement patterns, and growth. MSCT also has facilitated the development and potential of clinical application of computer-assisted diagnosis.

Automated detection of lung nodules in CT scans: effect of image reconstruction algorithm

We have investigated the effect of computed tomography (CT) image reconstruction algorithm on the performance of our automated lung nodule detection method. Commercial CT scanners offer a choice of several algorithms for the reconstruction of projection data into transaxial images. Different algorithms produce images with substantially different properties that are apparent not only quantitatively, but also through visual assessment. During some clinical thoracic CT examinations, patient scans are reconstructed with multiple reconstruction algorithms. Thirty-eight such cases were collected to form two databases: one with patient projection data reconstructed with the "standard" reconstruction algorithm and the other with the same patient projection data reconstructed with the "lung" reconstruction algorithm. The automated nodule detection method was applied to both databases. This method is based on gray-level-thresholding techniques to segment the lung regions from each CT section to create a segmented lung volume. Further gray-level-thresholding techniques are applied within the segmented lung volume to identify a set of lung nodule candidates. Rule-based and linear discriminant classifiers are used to differentiate between lung nodule candidates that correspond to actual nodules and those that correspond to non-nodules. The automated method that was applied to both databases was exactly the same, except that the classifiers were calibrated separately for each database. For comparison, the classifier then was trained on one database and tested independently on the other database. When applied to the databases in this manner, the automated method demonstrated overall a similar level of performance, indicating an encouraging degree of robustness.

Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm

Increasingly, computed tomography (CT) offers higher resolution and faster acquisition times. This has resulted in the opportunity to detect small lung nodules, which may represent lung cancers at earlier and potentially more curable stages. However, in the current clinical practice, hundreds of such thin-sectional CT images are generated for each patient and are evaluated by a radiologist in the traditional sense of looking at each image in the axial mode. This results in the potential to miss small nodules and thus potentially miss a cancer. In this paper, we present a computerized method for automated identification of small lung nodules on multislice CT (MSCT) images. The method consists of three steps: (i) separation of the lungs from the other anatomic structures, (ii) detection of nodule candidates in the extracted lungs, and (iii) reduction of false-positives among the detected nodule candidates. A three-dimensional lung mask can be extracted by analyzing density histogram of volumetric chest images followed by a morphological operation. Higher density structures including nodules scattered throughout the lungs can be identified by using a local density maximum algorithm. Information about nodules such as size and compact shape are then incorporated into the algorithm to reduce the detected nodule candidates which are not likely to be nodules. The method was applied to the detection of computer simulated small lung nodules (2 to 7 mm in diameter) and achieved a sensitivity of 84.2% with, on average, five false-positive results per scan. The preliminary results demonstrate the potential of this technique for assisting the detection of small nodules from chest MSCT images.