Detection of the usual interstitial pneumonia pattern in chest CT: effect of computer-aided diagnosis on radiologist diagnostic performance

BACKGROUND

Anti-fibrotic drugs for interstitial pulmonary fibrosis (IPF) have been developed. Physicians are becoming increasingly aware of the need for better diagnosis of IPF.

PURPOSE

To evaluate whether a computer-aided system can improve the diagnostic performance of general radiologists in detecting the usual interstitial pneumonia (UIP) pattern on computed tomography (CT).

MATERIAL AND METHODS

We included 60 CT datasets from 30 patients with IPF and 30 with idiopathic fibrosing non-specific interstitial pneumonia (fNSIP), all diagnosed by a multidisciplinary diagnosis (MDD) procedure that included surgical biopsy. We analyzed the CT data using a computer-aided system (Gaussian histogram normalized correlation: GHNC). Five general radiologists with <6 years of experience each interpreted these CT scans with and without the GHNC results. We compared the likelihoods of a UIP-pattern diagnosis with the likelihood of the same diagnosis by MDD using the average area under the curve (AUC) of the receiver operating characteristics (ROC). We also evaluated the association between the radiologists' diagnosis and survival using the Kaplan-Meier method.

RESULTS

In the ROC analysis, the AUC increased significantly from 0.731 without GHNC to 0.829 with GHNC (P = 0.0396). The diagnosis without GHNC was not significantly associated with survival for any radiologist, but the UIP diagnosis with GHNC was significantly associated with a worse prognosis for four out of five radiologists.

CONCLUSION

The computer-aided system could increase the confidence level of UIP-pattern diagnosis by non-expert radiologists.

The Efficacy of CT Temporal Subtraction Images for Fibrodysplasia Ossificans Progressiva

Purpose: To evaluate the usefulness of CT temporal subtraction (TS) images for detecting emerging or growing ectopic bone lesions in fibrodysplasia ossificans progressiva (FOP). Materials and Methods: Four patients with FOP were retrospectively included in this study. TS images were produced by subtracting previously registered CT images from the current images. Two residents and two board-certified radiologists independently interpreted a pair of current and previous CT images for each subject with or without TS images. Changes in the visibility of the lesion, the usefulness of TS images for lesions with TS images, and the interpreter’s confidence level in their interpretation of each scan were assessed on a semiquantitative 5-point scale (0–4). The Wilcoxon signed-rank test was used to compare the evaluated scores between datasets with and without TS images. Results: The number of growing lesions tended to be larger than that of the emerging lesions in all cases. A higher sensitivity was found in residents and radiologists using TS compared to those not using TS. For all residents and radiologists, the dataset with TS tended to have more false-positive scans than the dataset without TS. All the interpreters recognized TS as useful, and confidence levels when using TS tended to be lower or the same as when not using TS for two residents and one radiologist. Conclusions: TS improved the sensitivity of all interpreters in detecting emerging or growing ectopic bone lesions in patients with FOP. TS could be applied further, including the areas of systematic bone disease.

Evaluation of the clinical utility of temporal subtraction using bone suppression processing in digital chest radiography

Rationale and objectives

To evaluate the usefulness of temporal subtraction using the bone suppression method in digital chest radiography for the detection of pulmonary lesions.

Materials and methods

The images of 31 patients with pulmonary lesions and 19 normal cases were included in the study. Conventional and bone suppression temporal subtraction were performed in the 50 cases selected and used for an observer performance study. Five radiologists participated in the study, and the differences between using conventional and bone suppression temporal subtraction were assessed using jackknife free-response receiver operating characteristic analysis.

Results

The average figure-of-merit values for all radiologists increased significantly using the bone suppression method, from 0.619 (conventional) to 0.696 (p = 0.032). The average sensitivity for detecting pulmonary lesions improved from 67.9% to 75.4%, and the average number of false-positive per case decreased from 0.336 to 0.252 using bone suppression temporal subtraction.

Conclusion

Bone suppression temporal subtraction processing can assist with the detection of subtle pulmonary lesions in digital chest radiographs.

Comparative evaluation of temporal subtraction computed tomography and non-echoplanar diffusion-weighted imaging for the mastoid extension of middle ear cholesteatoma

OBJECTIVE

Preoperative imaging assessment influences the decision to perform mastoidectomy for the mastoid extension of middle ear cholesteatoma. This study compared the performance of temporal subtraction CT (TSCT) and non-echoplanar diffusion-weighted imaging (non-EP DWI) in evaluating such mastoid extensions.

METHODS

We retrospectively evaluated 239 consecutive patients with surgically proven middle ear cholesteatoma between April 2016 and April 2021. The diagnostic performance of TSCT, wherein the presence of black color indicated progressive bone erosion, and non-EP DWI, wherein high signal intensity in the mastoid region suggested mastoid extension, was compared using Fisher's exact test.

RESULTS

In 34 patients with evaluable TSCT images, black color was significantly more common in patients with mastoid extension than in those without; the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of TSCT were 1.00, 0.95, 0.94, 1.00, and 0.97, respectively. In 90 patients with evaluable non-EP DWI, high signal intensity was significantly more common in patients with mastoid extension than in those without; the sensitivity, specificity, PPV, NPV, and accuracy of non-EP DWI were 0.88, 0.85, 0.91, 0.81, and 0.87, respectively. In 16 patients with both evaluable TSCT and non-EP DWI, the diagnostic performance of the TSCT was slightly superior to that of the non-EP DWI for predicting mastoid extension, although the difference was not significant.

CONCLUSIONS

TSCT images generated using consecutively acquired preoperative high-resolution CT images are useful for predicting mastoid extension of middle ear cholesteatoma, and the diagnostic performance of TSCT is non-inferior to that of non-EP DWI.

Improved assessment of middle ear recurrent/residual cholesteatomas using temporal subtraction CT

PURPOSE

The purpose of this study was to investigate the usefulness of temporal subtraction CT (TSCT) of temporal bone CT for the detection of postoperative recurrent/residual cholesteatoma of the middle ear.

METHODS

Thirty-two consecutive patients with surgically proven postoperative recurrent/residual cholesteatoma and 14 consecutive patients without recurrent/residual lesion matched the selection criteria and were retrospectively evaluated. TSCT imaging was generated with the use of serial postoperative CT. Two experienced radiologists and two residents evaluated the presence of bone erosive change by comparison serial CT studies, and CT and TSCT. The detection rate of bone erosive change, sensitivity and specificity of the recurrence/residual lesions, and reading time for each reader were evaluated.

RESULTS

TSCT + CT significantly improved the detection of bone erosive changes compared to CT-only evaluation (17.4-41.3% vs. 37.0-58.7%, p = 0.008-0.046). The mean sensitivity and specificity of TSCT + CT for experienced radiologists were 0.77 and 1.00, and 0.52 and 0.97 without TSCT. The mean sensitivity and specificity of TSCT + CT for residents were 0.64 and 1.00, and 0.41 and 1.00 without TSCT. Sensitivity showed an increase in all readers. The use of TSCT significantly reduced the reading time per case in all readers (p < 0.001).

CONCLUSION

TSCT improves the depiction of newly occurring progressive bone erosive changes, and detection sensitivity and reading time in postoperative recurrence/residual cholesteatoma of middle ear.

Preoperative prediction for mastoid extension of middle ear cholesteatoma using temporal subtraction serial HRCT studies

OBJECTIVES

This study investigated the utility of temporal subtraction computed tomography (TSCT) obtained with temporal bone high-resolution computed tomography (HRCT) for the preoperative prediction of mastoid extension of middle ear cholesteatomas.

METHODS

Twenty-eight consecutive patients with surgically proven middle ear cholesteatomas were retrospectively evaluated. The presence of black color in the mastoid region on TSCT suggested progressive changes caused by bone erosion. Enlarged width of the anterior part of mastoid on HRCT was interpreted as suggestive of mastoid extension. Fisher's exact test was used to compare the widths and black color on TSCT for cases with and without mastoid extension. The diagnostic accuracy of TSCT and HRCT for detecting mastoid extension and interobserver agreement during the evaluation of black color on TSCT were calculated.

RESULTS

There were 15 cases of surgically proven mastoid extension and 13 cases without mastoid extension. Patients with black color on TSCT were significantly more likely to have a mastoid extension (p < 0.001). The sensitivity and specificity of TSCT were 0.93 and 1.00, respectively. Patients in whom the width of the anterior part of the mastoid was enlarged were significantly more likely to have a mastoid extension (p = 0.007). The sensitivity and specificity of HRCT to detect the width of the anterior part of the mastoid were 0.80 and 0.77, respectively. Interobserver agreement during the evaluation of TSCT findings was good (k = 0.71).

CONCLUSIONS

This novel TSCT technique and preoperative evaluations are useful for assessing mastoid extension of middle ear cholesteatomas and making treatment decisions.

KEY POINTS

•TSCT shows a clear black color in the mastoid region when the middle ear cholesteatoma is accompanied by mastoid extension. •TSCT obtained with preoperative serial HRCT of the temporal bone is useful for assessing mastoid extension of middle ear cholesteatomas.

Preliminary Assessment of an Optical Flow Method (OFM) for Nonrigid Registration and Temporal Subtraction (TS) of Serial CT Examinations to Facilitate Evaluation of Interval Change in Metastatic Lung Nodules

RATIONALE AND OBJECTIVES

Accurate assessment of size change of lung nodules on chest computed tomography (CT) is important for diagnosis and response assessment. However, manual methods are time-consuming and error-prone. We therefore assessed whether an optical flow method (OFM) with temporal subtraction (TS) can facilitate detection and quantification of lung nodule change on serial CT datasets.

MATERIALS AND METHODS

Serial chest CT examinations were selected from 12 patients with multiple pulmonary metastases. Lung nodules were evaluated for change in size using: (1) OFM with TS and (2) reference standard visual and manual assessment. Average time required to assess interval change using both methods was recorded and compared. Concordance of agreement between OFM with TS and reference standard assessment for nodule change was examined.

RESULTS

285 solid pulmonary nodules were evaluated. The average time per nodule to assess interval change in nodule size by OFM with TS (mean 1.15 + 0.5 minutes) was significantly less (P = 0.02) than that the reference standard approach (mean 1.56 + 0.5 minutes). Agreement between OFM with TS and reference standard occurred for 63.2% of nodules overall (kappa = 0.50, standard error 0.35, P< 0.00001), and significantly increased with larger nodule size (kappa = 0.48 for nodules <5 mm; kappa = 0.94 for nodules >20 mm, P < 0.0001).

CONCLUSIONS

This preliminary study demonstrates the feasibility of an OFM with TS to assess for interval change in metastatic lung nodules on serial CT examinations with significantly improved reading speed and moderate agreement relative to reference standard assessment. Agreement improved with larger nodule size.

Artificial intelligence and radiomics in pulmonary nodule management: current status and future applications

Artificial intelligence (AI) has been present in some guise within the field of radiology for over 50 years. The first studies investigating computer-aided diagnosis in thoracic radiology date back to the 1960s, and in the subsequent years, the main application of these techniques has been the detection and classification of pulmonary nodules. In addition, there have been other less intensely researched applications, such as the diagnosis of interstitial lung disease, chronic obstructive pulmonary disease, and the detection of pulmonary emboli. Despite extensive literature on the use of convolutional neural networks in thoracic imaging over the last few decades, we are yet to see these systems in use in clinical practice. The article reviews current state-of-the-art applications of AI and in detection, classification, and follow-up of pulmonary nodules and how deep-learning techniques might influence these going forward. Finally, we postulate the impact of these advancements on the role of radiologists and the importance of radiologists in the development and evaluation of these techniques.

Diagnostic performance of static single-scan stress perfusion cardiac computed tomography in detecting hemodynamically significant coronary artery stenosis: a comparison with combined invasive coronary angiography and cardiovascular magnetic resonance-myocardial perfusion imaging

Background Non-invasive anatomical and physiological evaluations of coronary artery disease (CAD) may be obtained with static single-scan stress perfusion cardiac computed tomography (SSPCT). Purpose To determine the diagnostic performance of static SSPCT for identifying hemodynamically significant CAD. Material and Methods This prospective study included 29 patients with suspected or known CAD who underwent static SSPCT, cardiovascular magnetic resonance myocardial perfusion imaging (CMR-MPI), and invasive coronary angiography (ICA). CT was performed as follows: (i) coronary calcium scan; (ii) static SSPCT for both coronary artery (coronary CT angiography [CCTA]) and myocardial perfusion (perfusion CT [PCT]) during adenosine infusion; (iii) late-phase scan. The diagnostic performance of CCTA alone, PCT alone, and SSPCT for the detection of a hemodynamically significant CAD (a perfusion defect in a vascular territory subtended by a coronary vessel with ≥ 50% stenosis) was compared with that of combined ICA/CMR-MPI representing the standard of reference. Results Twenty-three (79%) patients and 47 (54%) vascular territories manifested ischemia-causing coronary stenoses by combined ICA/CMR-MPI. The per-vessel sensitivity, specificity, positive and negative predictive values, and area under the receiver operating characteristic curve (AUC) of the SSPCT were 92%, 88%, 90%, 90%, and 0.90, respectively, compared to those of the combined ICA/CMR-MPI. These values for the CCTA alone were 96%, 63%, 75%, 93%, and 0.79, respectively; and the values for the PCT alone were 94%, 83%, 86%, 92%, and 0.88, respectively. The AUC of SSPCT was significantly ( P = 0.013) higher than that of the CCTA alone. Conclusion Static SSPCT may facilitate detection of hemodynamically significant CAD.

Detection of suspected brain infarctions on CT can be significantly improved with temporal subtraction images

OBJECTIVE

To assess whether temporal subtraction (TS) images of brain CT improve the detection of suspected brain infarctions.

METHODS

Study protocols were approved by our institutional review board, and informed consent was waived because of the retrospective nature of this study. Forty-two sets of brain CT images of 41 patients, each consisting of a pair of brain CT images scanned at two time points (previous and current) between January 2011 and November 2016, were collected for an observer performance study. The 42 sets consisted of 23 cases with a total of 77 newly developed brain infarcts or hyperdense artery signs confirmed by two radiologists who referred to additional clinical information and 19 negative control cases. To create TS images, the previous images were registered to the current images by partly using a non-rigid registration algorithm and then subtracted. Fourteen radiologists independently interpreted the images to identify the lesions with and without TS images with an interval of over 4 weeks. A figure of merit (FOM) was calculated along with the jackknife alternative free-response receiver-operating characteristic analysis. Sensitivity, number of false positives per case (FPC) and reading time were analyzed by the Wilcoxon signed-rank test.

RESULTS

The mean FOM increased from 0.528 to 0.737 with TS images (p < 0.0001). The mean sensitivity and FPC improved from 26.5% and 0.243 to 56.0% and 0.153 (p < 0.0001 and p = 0.239), respectively. The mean reading time was 173 s without TS and 170 s with TS (p = 0.925).

CONCLUSION

The detectability of suspected brain infarctions was significantly improved with TS CT images.

KEY POINTS

• Although it is established that MRI is superior to CT in the detection of strokes, the first choice of modality for suspected stroke patients is often CT. • An observer performance study with 14 radiologists was performed to evaluate whether temporal subtraction images derived from a non-rigid transformation algorithm can significantly improve the detectability of newly developed brain infarcts on CT. • Temporal subtraction images were shown to significantly improve the detectability of newly developed brain infarcts on CT.

Evaluation of Deformable Image Registration for Three-Dimensional Temporal Subtraction of Chest Computed Tomography Images

Purpose

To perform lung image registration for reducing misregistration artifacts on three-dimensional (3D) temporal subtraction of chest computed tomography (CT) images, in order to enhance temporal changes in lung lesions and evaluate these changes after deformable image registration (DIR).

Methods

In 10 cases, mutual information (MI) lung mask affine mapping combined with cross-correlation (CC) lung diffeomorphic mapping was used to implement lung volume registration. With advanced normalization tools (ANTs), we used greedy symmetric normalization (greedy SyN) as a transformation model, which involved MI-CC-SyN implementation. The resulting displacement fields were applied to warp the previous (moving) image, which was subsequently subtracted from the current (fixed) image to obtain the lung subtraction image.

Results

The average minimum and maximum log-Jacobians were 0.31 and 3.74, respectively. When considering 3D landmark distance, the root-mean-square error changed from an average of 20.82 mm for P_fixed to P_moving to 0.5 mm for P_warped to P_fixed. Clear shadows were observed as enhanced lung nodules and lesions in subtraction images. The lesion shadows showed lesion shrinkage changes over time. Lesion tissue morphology was maintained after DIR.

Conclusions

DIR (greedy SyN) effectively and accurately enhanced temporal changes in chest CT images and decreased misregistration artifacts in temporal subtraction images.

Detection of lung carcinoma with predominant ground-glass opacity on CT using temporal subtraction method

PURPOSE

To evaluate the usefulness of the CT temporal subtraction (TS) method for the detection of the lung cancer with predominant ground-glass opacity (LC-pGGO).

MATERIALS AND METHODS

Twenty-five pairs of CT and their TS images in patients with LC-pGGO (31 lesions) and 25 pairs of those in patients without nodules were used for an observer performance study. Eight radiologists participated and the statistical significance of differences with and without the CT-TS was assessed by JAFROC analysis.

RESULTS

The average figure-of-merit (FOM) values for all radiologists increased to a statistically significant degree, from 0.861 without CT-TS to 0.912 with CT-TS (p < .001). The average sensitivity for detecting the actionable lesions improved from 73.4 % to 85.9 % using CT-TS. The reading time with CT-TS was not significantly different from that without.

CONCLUSION

The use of CT-TS improves the observer performance for the detection of LC-pGGO.

KEY POINTS

• CT temporal subtraction can improve the detection accuracy of lung cancer. • Reading time with temporal subtraction is not different from that without. • CT temporal subtraction improves observer performance for ground-glass/subsolid nodule detection.

Temporal Subtraction of Serial CT Images with Large Deformation Diffeomorphic Metric Mapping in the Identification of Bone Metastases

Purpose To determine the improvement of radiologist efficiency and performance in the detection of bone metastases at serial follow-up computed tomography (CT) by using a temporal subtraction (TS) technique based on an advanced nonrigid image registration algorithm. Materials and Methods This retrospective study was approved by the institutional review board, and informed consent was waived. CT image pairs (previous and current scans of the torso) in 60 patients with cancer (primary lesion location: prostate, n = 14; breast, n = 16; lung, n = 20; liver, n = 10) were included. These consisted of 30 positive cases with a total of 65 bone metastases depicted only on current images and confirmed by two radiologists who had access to additional imaging examinations and clinical courses and 30 matched negative control cases (no bone metastases). Previous CT images were semiautomatically registered to current CT images by the algorithm, and TS images were created. Seven radiologists independently interpreted CT image pairs to identify newly developed bone metastases without and with TS images with an interval of at least 30 days. Jackknife free-response receiver operating characteristics (JAFROC) analysis was conducted to assess observer performance. Reading time was recorded, and usefulness was evaluated with subjective scores of 1-5, with 5 being extremely useful and 1 being useless. Significance of these values was tested with the Wilcoxon signed-rank test. Results The subtraction images depicted various types of bone metastases (osteolytic, n = 28; osteoblastic, n = 26; mixed osteolytic and blastic, n = 11) as temporal changes. The average reading time was significantly reduced (384.3 vs 286.8 seconds; Wilcoxon signed rank test, P = .028). The average figure-of-merit value increased from 0.758 to 0.835; however, this difference was not significant (JAFROC analysis, P = .092). The subjective usefulness survey response showed a median score of 5 for use of the technique (range, 3-5). Conclusion TS images obtained from serial CT scans using nonrigid registration successfully depicted newly developed bone metastases and showed promise for their efficient detection. ^© RSNA, 2017 Online supplemental material is available for this article.

Thoracic Temporal Subtraction Three Dimensional Computed Tomography (3D-CT): Screening for Vertebral Metastases of Primary Lung Cancers

PURPOSE

We developed an original, computer-aided diagnosis (CAD) software that subtracts the initial thoracic vertebral three-dimensional computed tomography (3D-CT) image from the follow-up 3D-CT image. The aim of this study was to investigate the efficacy of this CAD software during screening for vertebral metastases on follow-up CT images of primary lung cancer patients.

MATERIALS AND METHODS

The interpretation experiment included 30 sets of follow-up CT scans in primary lung cancer patients and was performed by two readers (readers A and B), who each had 2.5 years' experience reading CT images. In 395 vertebrae from C6 to L3, 46 vertebral metastases were identified as follows: osteolytic metastases (n = 17), osteoblastic metastases (n = 14), combined osteolytic and osteoblastic metastases (n = 6), and pathological fractures (n = 9). Thirty-six lesions were in the anterior component (vertebral body), and 10 lesions were in the posterior component (vertebral arch, transverse process, and spinous process). The area under the curve (AUC) by receiver operating characteristic (ROC) curve analysis and the sensitivity and specificity for detecting vertebral metastases were compared with and without CAD for each observer.

RESULTS

Reader A detected 47 abnormalities on CT images without CAD, and 33 of them were true-positive metastatic lesions. Using CAD, reader A detected 57 abnormalities, and 38 were true positives. The sensitivity increased from 0.717 to 0.826, and on ROC curve analysis, AUC with CAD was significantly higher than that without CAD (0.849 vs. 0.902, p = 0.021). Reader B detected 40 abnormalities on CT images without CAD, and 36 of them were true-positive metastatic lesions. Using CAD, reader B detected 44 abnormalities, and 39 were true positives. The sensitivity increased from 0.783 to 0.848, and AUC with CAD was nonsignificantly higher than that without CAD (0.889 vs. 0.910, p = 0.341). Both readers detected more osteolytic and osteoblastic metastases with CAD than without CAD.

CONCLUSION

Our temporal 3D-CT subtraction CAD software easily detected vertebral metastases on the follow-up CT images of lung cancer patients regardless of the osteolytic or osteoblastic nature of the lesions.

Lung nodule and cancer detection in computed tomography screening

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

A comparison of axial versus coronal image viewing in computer-aided detection of lung nodules on CT

PURPOSE

To compare primarily viewing axial images (Axial mode) versus coronal reconstruction images (Coronal mode) in computer-aided detection (CAD) of lung nodules on multidetector computed tomography (CT) in terms of detection performance and reading time.

MATERIALS AND METHODS

Sixty CT data sets from two institutions were collected prospectively. Ten observers (6 radiologists, 4 pulmonologists) with varying degrees of experience interpreted the data sets using CAD as a second reader (performing nodule detection first without then with aid). The data sets were interpreted twice, once each for Axial and Coronal modes, in two sessions held 4 weeks apart. Jackknife free-response receiver-operating characteristic analysis was used to compare detection performances in the two modes.

RESULTS

Mean figure-of-merit values with and without aid were 0.717 and 0.684 in Axial mode and 0.702 and 0.671 in Coronal mode; use of CAD significantly increased the performance of observers in both modes (P < 0.01). Mean reading times for radiologists did not significantly differ between Axial (156 ± 74 s) and Coronal mode (164 ± 69 s; P = 0.08). Mean reading times for pulmonologists were significantly lower in Coronal (112 ± 53 s) than in Axial mode (130 ± 80 s; P < 0.01).

CONCLUSION

There was no statistically significant difference between Axial and Coronal modes for lung nodule detection with CAD.