Pneumothorax and other lung diseases: effect of altered resolution and edge enhancement on diagnosis with digitized radiographs

Prior studies have shown that pneumothorax is one of the more difficult entities to diagnose with digitized radiography. This study was designed to test whether increasing resolution from 1.25 to 2.5 line pairs per millimeter (lp/mm) and image processing (edge enhancement from unsharp masking) would increase accuracy and confidence in the diagnosis of pneumothorax, as well as normal cases and other forms of lung disease. Conventional radiographs were digitized with use of a laser reader and then reformatted as film hard copy. Eleven observers read 35 cases reformatted in three different ways (1.25 lp/mm, 2.5 lp/mm, 1.25 lp/mm unsharp mask). The images with finer resolution (2.5 lp/mm) and unsharp mask images were superior to those with coarser resolution (1.25 lp/mm) for the diagnosis of pneumothorax. There was no difference in diagnostic accuracy for normal patients. For abnormalities other than pneumothorax, the unsharp mask images were significantly worse. Confidence in the diagnosis of pneumothorax and other abnormalities was highest with the finest resolution (2.5 lp/mm).     

Subtle pulmonary nodules: detection and identification with storage phosphor radiographs and conventional chest films

To determine the value of digital storage-phosphor radiography (SR) on the detection and identification of subtle lung nodules, postero-anterior (PA) and lateral (LAT) film-screen (FR) chest radiographs were compared with isodose SR images of 45 patients with metastatic malignancies. The SR postprocessing was done with a particular mode previously optimized for routine chest radiography. Pulmonary metastases were found in 34 patients and were proved or excluded by CT (n = 28) or longterm follow-up FR (n = 17). Chest images were divided into four regions for evaluation of image quality, number of lung nodules per region and marked pulmonary structures by receiver-operating characteristics (ROC) analysis (45 patients; 125 nodules; 2810 observations; five readers). Of the nodules selected for an ROC study 82 % were 0.5–1.0 cm in diameter. Overall image quality was rated better for FR concerning lung fields (PA) and mediastinum/hilum (LAT). More lung-field nodules were detected on FR than on SR chest images (P < 0.05). Use of FR was superior to SR in the general identification of nodules (PA chest), especially concerning intermediate (P < 0.01) and subtle abnormalities (P < 0.05), whereas there was no significant difference for LAT chest images. Our results show, that currently FR still has advantages over SR in the detection and identification of subtle lung nodules in routine clinical radiography. Correspondence to: R. Scheck     

Using edge enhancement to identify subtle findings on soft-copy neonatal chest radiographs.

OBJECTIVE: The purpose of this study was to evaluate whether edge enhancement could improve the visibility of subtle findings on soft copies of neonatal chest radiographs. MATERIALS AND METHODS: Two radiologists reviewed 82 soft-copy neonatal chest radiographs before and after the application of edge enhancement on our picture archiving and communication system (PACS). The visibility of a pneumothorax (n = 22), central venous catheter (n = 32), umbilical arterial catheter (n = 36), endotracheal tube (n = 40), and normal anatomic structures (the minor fissure, anterior segmental bronchus of the right upper lobe, and aortic arch, n = 57) was evaluated. Six of 22 soft-copy images depicting a pneumothorax were excluded from the evaluation of image quality either because of the large size of the pneumothorax itself (n = 7) or because of the lack of confirmatory evidence that would have been provided by an additional lateral decubitus (n = 6) or cross-table lateral radiograph (n = 3). Image quality was evaluated by visual grading analysis. RESULTS: The visibility of a pneumothorax (p < 0.01), vascular catheters (p < 0.001), the minor fissure (p < 0.001), and the anterior segmental bronchus of the right upper lobe (p < 0.001) improved significantly after applying edge enhancement to soft copies of neonatal chest radiographs, whereas the visibility of the aortic arch did not improve. Evaluations of the improvements in the visibility of the endotracheal tube were inconsistent. CONCLUSION: Application of edge enhancement to soft copies of neonatal chest radiographs helps radiologists to identify small pneumothoraces, vascular catheters, and delicate normal structures, thereby improving the detection of subtle chest findings in the neonatal intensive care unit.     

Computer-aided diagnosis for the detection and classification of lung cancers on chest radiographs ROC analysis of radiologists' performance

RATIONALE AND OBJECTIVES: The aim of the study is to investigate the effect of a computer-aided diagnostic (CAD) scheme on radiologist performance in the detection of lung cancers on chest radiographs. MATERIALS AND METHODS: We combined two independent CAD schemes for the detection and classification of lung nodules into one new CAD scheme by use of a database of 150 chest images, including 108 cases with solitary pulmonary nodules and 42 cases without nodules. For the observer study, we selected 48 chest images, including 24 lung cancers, 12 benign nodules, and 12 cases without nodules, from the database to investigate radiologist performance in the detection of lung cancers. Nine radiologists participated in a receiver operating characteristic (ROC) study in which cases were interpreted first without and then with computer output, which indicated locations of possible lung nodules, together with a five-color scale illustrating the computer-estimated likelihood of malignancy of the detected nodules. RESULTS: Performance of the CAD scheme indicated that sensitivity in detecting lung nodules was 80.6%, with 1.2 false-positive results per image, and sensitivity and specificity for classification of nodules by use of the same database for training and testing the CAD scheme were 87.7% and 66.7%, respectively. Average area under the ROC curve value for detection of lung cancers improved significantly (P = .008) from without (0.724) to with CAD (0.778). CONCLUSION: This type of CAD scheme, which includes two functions, namely detection and classification, can improve radiologist accuracy in the diagnosis of lung cancer.     

胸片中肺癌的计算机辅助检测(CAD):对阅片者绩效的影响

目的评价在胸片发现的早期肺癌中,计算机辅助检测(CAD)是如何影响阅片者的绩效。材料与方法经伦理委员会批准,本回顾性研究包括46例CT发现并经组织学证实     

Differentiation of benign from malignant pulmonary nodules with digitized chest radiographs

To assess whether it is possible to distinguish benign from malignant solitary pulmonary nodules with digital techniques, a retrospective study of 68 patients with proved solitary nodules was performed. The conventional chest radiograph for each patient was digitized to 2,048 X 2,048 X 12 bits, and changes in the optical density within the nodule were analyzed. A number (the corrected gradient number) was then generated that reflected this variation. Striking differences were noted between 26 malignant nodules and 21 calcified granulomas. The technique was then applied to 21 benign nodules that had initially required thoracotomy or further study for diagnosis. In nine of these 21 patients (43%), the corrected gradient number allowed correct classification as a benign lesion.     

Effects of image processing on nodule detection rates in digitized chest radiographs: ROC study of observer performance

To evaluate the effects of image processing in digitized chest radiographs when high-resolution images are used, an examination was done in which the detection of pulmonary nodules in unprocessed digitized chest radiographs was compared with that in images that had undergone processing with two methods, adaptive filtration and histogram equalization. The processing techniques have been optimized in previous work to selectively enhance the retrocardiac and subdiaphragmatic areas without significant alteration of detail in the lung. Eight observers were shown 150 test radiographs (50 unprocessed, 50 processed with adaptive filtration, 50 processed with histogram equalization) containing 150 nodules. The results indicate a statistically significant (P less than .03) difference, with highest observer performance in the chest radiographs processed with adaptive filtration (median area under ROC curve = 0.78), compared with unprocessed images (median = 0.68) and chest radiographs processed with histogram equalization (median = 0.62). Performance in the lung was not significantly different. Adaptive filtration applied to selectively enhance underexposed areas of film images may improve nodule detection. Histogram equalization provided no improvement in performance.     

Pneumothorax post CT-guided lung biopsy: a comparison between detection on chest radiographs and CT

Pneumothorax is reported to be a more common complication of lung biopsy performed under computed tomography (CT) than under fluoroscopic guidance. This may simply reflect the greater sensitivity of CT over chest radiographs (CXRs) in the detection of small pneumothoraces. This study aimed to determine the incidence of pneumothorax detected by CXR and by CT after CT-guided biopsy of non-pleurally based pulmonary masses, and to compare these incidences with previous reports in the literature of pneumothorax incidence post fluoroscopic biopsy. 88 consecutive CT-guided lung biopsies of masses not abutting the pleural surface were included. Immediate post-biopsy CT images, and 1 and 4 h CXRs were assessed independently by two observers for the presence and size of pneumothorax. 72 biopsies were fine needle aspirations (FNAs) performed with 22 G spinal needles only, seven were cutting needle biopsies (CNBs) performed with 18 G cutting needles only, and nine were both. 37 patients (42%) developed a pneumothorax. 35 were detected on CT (40%) and 22 on CXR (25%). None required tube drainage. Of the patients in whom CT demonstrated a pneumothorax, the average depth of this was significantly greater for those in whom CXR also detected a pneumothorax compared with those in whom CXR was negative (7.3 mm versus 3.4 mm, p < 0.05). The incidence of pneumothorax detected on CXR post CT-guided biopsy is similar to the reported incidence post fluoroscopic biopsy.     

肋骨抑制成像在胸部平片肺结节检出中的应用

目的 评价肋骨抑制成像技术在胸部平片检出肺结节中的价值.方法 回顾性分析141例胸部后前位X线片,其中95例有单发肺结节,作为研究组,46例无肺结节作为对照组.2名高年资与2名低年资放射科医师分别独立阅读所有胸部后前位X线片和经肋骨抑制成像技术处理后的胸部后前位X线片.阅读、记录结节的部位、大小并对结节存在的肯定度进行评分.观察的结果采用受试者工作特征(ROC)曲线进行分析.结果 肺结节的平均直径为(1.9±1)cm,直径范围是0.9~2.9 cm.胸部后前位X线片ROC曲线下面积(AUC)为0.844,肋骨抑制成像技术处理后的胸部后前位X线片AUC为0.873,两者有统计学差异(P<0.01).结论 肋骨抑制成像技术可以显著提高放射科医师对胸部后前位X片中肺结节的检出率.     

Comparative studies on physical characteristics and clinical efficacy of conventional and digitized chest radiographs

Comparative studies were performed between digitized and conventional radiographs of the chest in terms of their physical characteristics and diagnostic efficacy. The purpose of these studies is to confirm the diagnostic capability of digitized image whether it can use for primary diagnosis in routine works. The results of two studies show good correlation each other. It is strongly suggested that the conventional chest radiographs should be digitized with 100 microns pixel in 12 bit density resolution.     

Computer-aided detection (CAD) of lung nodules and small tumours on chest radiographs

Detection of focal pulmonary lesions is limited by quantum and anatomic noise and highly influenced by variable perception capacity of the reader. Multiple studies have proven that lesions - missed at time of primary interpretation - were visible on the chest radiographs in retrospect. Computer-aided diagnosis (CAD) schemes do not alter the anatomic noise but aim at decreasing the intrinsic limitations and variations of human perception by alerting the reader to suspicious areas in a chest radiograph when used as a ‘second reader’.Multiple studies have shown that the detection performance can be improved using CAD especially for less experienced readers at a variable amount of decreased specificity. There seem to be a substantial learning process for both, experienced and inexperienced readers, to be able to optimally differentiate between false positive and true positive lesions and to build up sufficient trust in the capabilities of these systems to be able to use them at their full advantage. Studies so far focussed on stand-alone performance of the CAD schemes to reveal the magnitude of potential impact or on retrospective evaluation of CAD as a second reader for selected study groups. Further research is needed to assess the performance of these systems in clinical routine and to determine the trade-off between performance increase in terms of increased sensitivity and decreased inter-reader variability and loss of specificity and secondary indicated follow-up examinations for further diagnostic workup.     

Improved detection of lung cancer arising in diffuse lung diseases on chest radiographs using temporal subtraction

RATIONALE AND OBJECTIVES: The purpose of this study was to evaluate the usefulness of temporal subtraction for the detection of lung cancer arising in pneumoconiosis, idiopathic pulmonary fibrosis, and pulmonary emphysema. MATERIALS AND METHODS: Fifteen cases of lung cancer arising in diffuse lung diseases, including three cases of pneumoconiosis, six of idiopathic pulmonary fibrosis, and six of pulmonary emphysema, were evaluated. Pathologic proof was obtained by surgery or transbronchial lung biopsy. The average interval between previous and current radiographs was 356 days (range, 31-947 days). All chest radiographs were obtained with a computed radiography system, and temporal subtraction images were produced by subtracting of a previous image from a current one with a nonlinear image-warping technique. The effect of the temporal subtraction image was evaluated by observer performance study with receiver operating characteristic analysis. RESULTS: The average observer performance with temporal subtraction was significantly improved (Az = 0.935) compared with that without temporal subtraction (Az = 0.857, P < .0001). CONCLUSION: The temporal subtraction technique is useful for the detection of lung cancer arising in pneumoconiosis, idiopathic pulmonary fibrosis, and pulmonary emphysema.     

New methods for using computer-aided detection information for the detection of lung nodules on chest radiographs

Objective:

To investigate two new methods of using computer-aided detection (CAD) system information for the detection of lung nodules on chest radiographs. We evaluated an interactive CAD application and an independent combination of radiologists and CAD scores.

Methods:

300 posteroanterior and lateral digital chest radiographs were selected, including 111 with a solitary pulmonary nodule (average diameter, 16 mm). Both nodule and control cases were verified by CT. Six radiologists and six residents reviewed the chest radiographs without CAD and with CAD (ClearRead +Detect™ 5.2; Riverain Technologies, Miamisburg, OH) in two reading sessions. The CAD system was used in an interactive manner; CAD marks, accompanied by a score of suspicion, remained hidden unless the location was queried by the radiologist. Jackknife alternative free response receiver operating characteristics multireader multicase analysis was used to measure detection performance. Area under the curve (AUC) and partial AUC (pAUC) between a specificity of 80% and 100% served as the measure for detection performance. We also evaluated the results of a weighted combination of CAD scores and reader scores, at the location of reader findings.

Results:

AUC for the observers without CAD was 0.824. No significant improvement was seen with interactive use of CAD (AUC = 0.834; p = 0.15). Independent combination significantly improved detection performance (AUC = 0.834; p = 0.006). pAUCs without and with interactive CAD were similar (0.128), but improved with independent combination (0.137).

Conclusion:

Interactive CAD did not improve reader performance for the detection of lung nodules on chest radiographs. Independent combination of reader and CAD scores improved the detection performance of lung nodules.

Advances in knowledge:

(1) Interactive use of currently available CAD software did not improve the radiologists'' detection performance of lung nodules on chest radiographs. (2) Independently combining the interpretations of the radiologist and the CAD system improved detection of lung nodules on chest radiographs.Chest radiography can be considered the workhorse of the radiology department. It is being used for the detection and diagnosis of multiple diseases, including lung nodules, which may represent early lung cancer. Since a chest radiograph is a two-dimensional image, overprojection of multiple anatomical structures is inevitable. This so-called anatomical noise substantially impedes interpretation of chest radiographs. Multiple studies have shown that a substantial amount of lung cancers are missed, ranging from 19% to 26%,^1,2 and even up to 90%.^3–5 More recent studies have shown that the problem of missing lung nodules is still present with the most modern digital radiographic technology.^6,7 Abnormalities can be missed as a result of inadequate search, perception errors or interpretation errors. It has been stated that interpretation by the radiologist is the most important factor for missing lung cancer on chest radiographs.^8,9To reduce miss rates, computer-aided detection (CAD) systems have been developed. Thus far, all studies dealing with chest radiography apply CAD as a second reader to the radiologist, meaning that the CAD marks are made available only after the radiologist has made a primary review. It remains the reader''s discretion to accept or disregard the CAD marks. Results of these studies were contradictory: some found an increased accuracy for the detection of lung nodules,^10–12 whereas other studies reported an increase in sensitivity only at the expense of loss in specificity.^13–16 One problem ameliorating the potential of CAD is the radiologist''s limited ability to reliably discriminate between true-positive (TP) and false-positive (FP) CAD marks.We therefore decided to explore alternative methods of using CAD information. First, we used CAD interactively. In the interactive mode, CAD marks remained hidden unless the radiologist queried a position in the image by clicking with the mouse on that location. If a CAD mark was present in this location, it was shown to the radiologist together with a score of suspicion. Such an interactive CAD system had been shown to be beneficial in chest radiography in an observer study that only used non-radiologists.¹⁷ Second, we computed a mathematical combination of reader and CAD scores. With this method, observers did not need to view the CAD marks at all during their reading of the images, but a mathematical combination of the reader and the CAD scores was computed afterwards. Both methods have been reported to outperform the use of CAD as a second reader for lesion detection in mammograms.^18–20The purpose of this observer study was to test the impact of these two alternative methods of using CAD information on nodule detection on chest radiographs. To optimize baseline performance without CAD, digitally bone-suppressed images (BSIs) were added to the original chest radiographs. BSIs have been shown to improve accuracy for the detection of focal lesions on chest radiographs;^21–24 a further increase in detection performance beyond that of BSIs by adding CAD has also been documented.²⁵     

Visibility of small peripheral lung cancers on chest radiographs: influence of densitometric parameters, CT values and tumour type

The purpose of this study was to determine the effects of tumour density and tumour type on the visibility of small peripheral lung cancers on chest radiographs. We retrospectively evaluated the visibility of 63 small (< or = 20 mm) peripheral lung cancers on chest radiographs. 48 (76%) were detected in our low dose CT screening for lung cancer and 15 (24%) in routine clinical examination. Analysis was based on tumour optical contrast, gradient at the tumour margin, CT values and tumour type. There were 31 (49%) visible cancers and 32 (51%) invisible cancers on chest radiographs. Visible tumours had an optical density of 0.1-0.3 OD and a gradient of 0.03-0.11 OD mm-1. The mean size of visible tumour (14.3 mm) was larger than that of invisible tumour (11.1 mm; p < 0.001). The mean CT value (-140 HU) of visible tumour was higher than that of invisible tumour (-490 HU; p < 0.001). The detection rates of adenocarcinomas with lepidic growth (0% for type A, 29% for type B and 68% for type C) were less than those with hilic growth (100% for types D-F). All squamous and small cell carcinomas with hilic growth were visible on chest radiographs, but the numbers of each were small. In summary, tumour type influenced the contrast, gradient, CT values and margin of the tumour. Small adenocarcinomas with a lepidic tumour growth were less well seen on chest radiographs compared with small lung cancers with hilic tumour growth.     

Improved detection of lung nodules on chest radiographs using a commercial computer-aided diagnosis system

OBJECTIVE: The aim of this study was to evaluate the usefulness of a new commercially available computer-aided diagnosis (CAD) system with an automated method of detecting nodules due to lung cancers on chest radiograph. MATERIALS AND METHODS: For patients with cancer, 45 cases with solitary lung nodules up to 25 mm in diameter (nodule size range, 8-25 mm in diameter; mean, 18 mm; median, 20 mm) were used. For healthy patients, 45 cases were selected on the basis of confirmation on chest CT. All chest radiographs were obtained with a computed radiography system. The CAD output images were produced with a newly developed CAD system, which consisted of an image server including CAD software called EpiSight/XR. Eight radiologists (four board-certified radiologists and four radiology residents) participated in observer performance studies and interpreted both the original radiographs and CAD output images using a sequential testing method. The observers' performance was evaluated with receiver operating characteristic analysis. RESULTS: The average area under the curve value increased significantly from 0.924 without to 0.986 with CAD output images. Individually, the use of CAD output images was more beneficial to radiology residents than to board-certified radiologists. CONCLUSION: This CAD system for digital chest radiographs can assist radiologists and has the potential to improve the detection of lung nodules due to lung cancer.