Detection of Small Pulmonary Nodules Using Direct Digital Radiography and Picture Archiving and Communication Systems

Comparison of digital tomosynthesis and chest radiography for the detection of pulmonary nodules: systematic review and meta-analysis

OBJECTIVE

To compare the diagnostic accuracy of digital tomosynthesis (DTS) with that of chest radiography for the detection of pulmonary nodules by meta-analysis.

METHODS

A systematic literature search was performed to identify relevant original studies from 1 January 1 1976 to 31 August 31 2016. The quality of included studies was assessed by quality assessment of diagnostic accuracy studies-2. Per-patient data were used to calculate the sensitivity and specificity and per-lesion data were used to calculate the detection rate. Summary receiver-operating characteristic curves were drawn for pulmonary nodule detection.

RESULTS

16 studies met the inclusion criteria. 1017 patients on a per-patient basis and 2159 lesions on a per-lesion basis from 16 eligible studies were evaluated. The pooled patient-based sensitivity of DTS was 0.85 [95% confidence interval (CI) 0.83-0.88] and the specificity was 0.95 (0.93-0.96). The pooled sensitivity and specificity of chest radiography were 0.47 (0.44-0.51) and 0.37 (0.34-0.40), respectively. The per-lesion detection rate was 2.90 (95% CI 2.63-3.19).

CONCLUSION

DTS has higher diagnostic accuracy than chest radiography for detection of pulmonary nodules. Chest radiography has low sensitivity but similar specificity, comparable with that of DTS. Advances in knowledge: DTS has higher diagnostic accuracy than chest radiography for the detection of pulmonary nodules.

Diagnostic imaging costs before and after digital tomosynthesis implementation in patient management after detection of suspected thoracic lesions on chest radiography

Objectives

To evaluate diagnostic imaging costs before and after DTS implementation in patients with suspected thoracic lesions on CXR.

Methods

Four hundred sixty-five patients (263 male, 202 female; age, 72.47 ± 11.33 years) with suspected thoracic lesion(s) after CXR underwent DTS. Each patient underwent CT when a pulmonary non-calcified lesion was identified by DTS while CT was not performed when a benign pulmonary or extrapulmonary lesion or pseudolesion was identified. The average per-patient imaging cost was calculated by normalising the costs before and after DTS implementation.

Results

In 229/465 patients who underwent DTS after suspicious CXR, DTS showed 193 pulmonary lesions and 36 pleural lesions, while in the remaining 236/465 patients, lesions were ruled out as pseudolesions of CXR. Chest CT examination was performed in 127/465 (27 %) patients while in the remaining 338/465 patients (73 %) CXR doubtful findings were resolved by DTS. The average per-patient costs of CXR, DTS and CT were €15.15, 41.55 and 113.66. DTS allowed an annual cost saving of €8,090.2 considering unenhanced CT and €19,298.12 considering contrast-enhanced CT. Considering a DTS reimbursement rate of € 62.7 the break even point corresponds to 479 DTS examinations.

Conclusion

Per-patient diagnostic imaging costs decreased after DTS implementation in patients with suspected thoracic lesions.

Main Messages

• Digital tomosynthesis improves the diagnostic accuracy and confidence in chest radiography

• Digital tomosynthesis reduces the need for CT for a suspected pulmonary lesion

• Digital tomosynthesis requires a dose level equivalent to that of around two chest radiographies

• Digital tomosynthesis produces a significant per-patient saving in diagnostic imaging costs

Histopathological image analysis for centroblasts classification through dimensionality reduction approaches

We present two novel automated image analysis methods to differentiate centroblast (CB) cells from noncentroblast (non-CB) cells in digital images of H&E-stained tissues of follicular lymphoma. CB cells are often confused by similar looking cells within the tissue, therefore a system to help their classification is necessary. Our methods extract the discriminatory features of cells by approximating the intrinsic dimensionality from the subspace spanned by CB and non-CB cells. In the first method, discriminatory features are approximated with the help of singular value decomposition (SVD), whereas in the second method they are extracted using Laplacian Eigenmaps. Five hundred high-power field images were extracted from 17 slides, which are then used to compose a database of 213 CB and 234 non-CB region of interest images. The recall, precision, and overall accuracy rates of the developed methods were measured and compared with existing classification methods. Moreover, the reproducibility of both classification methods was also examined. The average values of the overall accuracy were 99.22% ± 0.75% and 99.07% ± 1.53% for COB and CLEM, respectively. The experimental results demonstrate that both proposed methods provide better classification accuracy of CB/non-CB in comparison with the state of the art methods.

Analysis of the impact of digital tomosynthesis on the radiological investigation of patients with suspected pulmonary lesions on chest radiography

OBJECTIVE

To assess the impact of digital tomosynthesis (DTS) on the radiological investigation of patients with suspected pulmonary lesions on chest radiography (CXR).

METHODS

Three hundred thirty-nine patients (200 male; age, 71.19 ± 11.9 years) with suspected pulmonary lesion(s) on CXR underwent DTS. Two readers prospectively analysed CXR and DTS images, and recorded their diagnostic confidence: 1 or 2 = definite or probable benign lesion or pseudolesion deserving no further diagnostic workup; 3 = indeterminate; 4 or 5 = probable or definite pulmonary lesion deserving further diagnostic workup by computed tomography (CT). Imaging follow-up by CT (n = 76 patients), CXR (n = 256) or histology (n = 7) was the reference standard.

RESULTS

DTS resolved doubtful CXR findings in 256/339 (76 %) patients, while 83/339 (24 %) patients proceeded to CT. The mean interpretation time for DTS (mean ± SD, 220 ± 40 s) was higher (P < 0.05; Wilcoxon test) than for CXR (110 ± 30 s), but lower than CT (600 ± 150 s). Mean effective dose was 0.06 mSv (range 0.03-0.1 mSv) for CXR, 0.107 mSv (range 0.094-0.12 mSv) for DTS, and 3 mSv (range 2-4 mSv) for CT.

CONCLUSIONS

DTS avoided the need for CT in about three-quarters of patients with a slight increase in the interpretation time and effective dose compared to CXR.

Automatic detection of follicular regions in H&E images using iterative shape index

Follicular Lymphoma (FL) accounts for 20-25% of non-Hodgkin lymphomas in the United States. The first step in grading FL is identifying follicles. Our paper discusses a novel technique to segment follicular regions in H&E stained images. The method is based on three successive steps: (1) region-based segmentation, (2) iterative shape index (concavity index) calculation, (3) and recursive watershed. A novel aspect of this method is the use of iterative Concavity Index (CI) to control the follicular splitting process in recursive watershed. CI takes into consideration the convex hull of the object and the closest area surrounding it. The mean Zijbendos similarity index (ZSI) final segmentation score on fifteen cases was 78.33%, with a standard deviation of 2.83.

The value of digital tomosynthesis in the diagnosis of suspected pulmonary lesions on chest radiography: analysis of diagnostic accuracy and confidence

RATIONALE AND OBJECTIVES

The aim of this study was to investigate the value of digital tomosynthesis in the diagnosis of suspected pulmonary lesions on chest radiography.

MATERIALS AND METHODS

Two-hundred twenty-eight patients (133 men, 95 women; mean age, 70.8 ± 11.1 years) with suspected pulmonary lesions after initial analysis of chest radiography underwent digital tomosynthesis. Two independent readers (with 3 and 20 years of experience) prospectively analyzed the chest radiographic and digital tomosynthesis images on a picture archiving and communication system workstation and proposed a diagnostic confidence score for each lesion (1 or 2 = definitely or probably extrapulmonary lesion or pseudolesion, 3 = indeterminate, 4 or 5 = probably or definitely pulmonary lesion). Chest computed tomography was the reference standard examination.

RESULTS

A total of 251 suspected pulmonary lesions were identified. In 71 patients, digital tomosynthesis and computed tomography did not confirm any lesion. In the remaining 157 patients, 180 lesions were identified, including 112 pulmonary and 68 extrapulmonary lesions. In 110 (reader 1) and 123 (reader 2) lesions, correct diagnoses were provided after analysis of the chest radiographs. All lesions were correctly classified after digital tomosynthesis except for 14 extrapulmonary lesions (both readers) that were misinterpreted as pulmonary and 10 (reader 1) and six (reader 2) pulmonary lesions that were misinterpreted as pleural. Digital radiography versus tomosynthesis differed in accuracy (reader 1, 43% vs 90%; reader 2, 49% vs 92%; P < .05) and confidence by area under the receiver-operating characteristic curve (reader 1, 0.788 vs 0.944; reader 2, 0.840 vs 0.997; P < .05).

CONCLUSIONS

Digital tomosynthesis improved diagnostic accuracy and confidence in the diagnosis of suspected pulmonary lesions on chest radiography.

Extraction of color features in the spectral domain to recognize centroblasts in histopathology

In this paper, we are proposing a novel automated method to recognize centroblast (CB) cells from non-centroblast (non-CB) cells for computer-assisted evaluation of follicular lymphoma tissue samples. The method is based on training and testing of a quadratic discriminant analysis (QDA) classifier. The novel aspects of this method are the identification of the CB object with prior information, and the introduction of the principal component analysis (PCA) in the spectral domain to extract color texture features. Both geometric and texture features are used to achieve the classification. Experimental results on real follicular lymphoma images demonstrate that the combined feature space improved the performance of the system significantly. The implemented method can identify centroblast cells (CB) from non-centroblast cells (non-CB) with a classification accuracy of 82.56%.

Comparison of radiologist and CAD performance in the detection of CT-confirmed subtle pulmonary nodules on digital chest radiographs

OBJECTIVES

Detection of subtle pulmonary nodules on digital radiography is a challenging task for radiologists. The aim of this study was to evaluate the performance of a newly approved computer aided detection (CAD) system.

MATERIALS AND METHODS

The sensitivity of 3 radiologists and of a CAD system for the detection of pulmonary nodules from 5 to 15 mm in size on digital chest radiography of 117 patients was compared. The reference standard was established by consensus reading of computed tomography scans by 2 experienced radiologists. Computed tomography scans and chest radiographs were performed within 4 weeks. Sixty-six pulmonary nodules from 42 patients, with a mean nodule diameter of 7.5 mm (standard deviation: 2.2 mm), were included in the statistical analysis. Seventy-five of the 117 patients did not have nodules from 5 to 15 mm of size.

RESULTS

Two hundred and eighty-eight false-positive detections of the CAD system were found with an average of 2.5 false-positives per image. Sensitivity of the CAD system was 39.4% (95% confidence interval: 11.8%), when compared with 18.2% to 30.3% (95% confidence interval 9.3% to 11.1%) of the 3 radiologists. Substantial agreement for nodule detection ([kappa]N: 0.64-0.73) was found among the 3 radiologists, whereas only moderate agreement was found between the radiologists and the CAD performance ([kappa]N: 0.45-0.52).

CONCLUSIONS

The CAD system's diagnostic sensitivity in detecting pulmonary nodules of 5 to 15 mm of size was superior to the 1 of radiologists. The CAD system may be used for assisting the radiologist in the detection of lung nodules on digital chest radiographs.

Evaluation of a real-time interactive pulmonary nodule analysis system on chest digital radiographic images: a prospective study

RATIONALE AND OBJECTIVES

We sought to assess the performance of a real-time interactive pulmonary nodule analysis system for evaluation of chest digital radiographic (DR) images in a routine clinical environment.

MATERIALS AND METHODS

A real-time interactive pulmonary nodule analysis system for chest DR image softcopy reading (IQQA-Chest; EDDA Technology, Princeton Junction, NJ) was used in daily practice with a Picture Archiving and Communication System in a National Cancer Institute-designated cancer teaching hospital. Patients referred for follow-up of known cancer underwent digital chest radiography. Posteroanterior and lateral DR images were first read by resident radiologists along with experienced chest radiologists using a Picture Archiving and Communication System work station. The computer-assisted detection (CAD) program was subsequently applied to the posteroanterior DR images, and changes (if any) in diagnosis were recorded. For reference standard, a follow-up chest radiograph at least 6 months following the initial examination or a follow-up computed tomographic scan of the chest within 3 months was used to establish diagnostic accuracy.

RESULTS

Of 324 DR examinations, follow-up imaging according to our parameters was available for 214 patients (67%). Lung nodules were found and subsequently confirmed in 35 patients (10%) without CAD. Using CAD, nodules were found and subsequently confirmed in 51 patients (15%), improving sensitivity from 63.8% (95% confidence interval [CI], 0.49%-0.76%) to 92.7% (95% CI, 0.82%-0.98%) (P < .0001, McNemar). Nodules were subsequently proved to be malignant in five of the 16 additional cases (31%). False-positive readings increased from three to six cases; specificity decreased from 98.1% (95% CI, 0.95%-0.99%) to 96.2% (95% CI, 0.92%-0.98%) (not significant). There were 153 true-negative cases (71.4%).

CONCLUSIONS

This study suggests that the interpretation of chest radiographs for lung nodules can be improved using an automated CAD nodule detection system. This improvement in reader performance comes with a minimal number of false-positive interpretations.