Computer-aided Detection Program Research Articles

EP01.04-003 Effectiveness of Cloud-based Computer Aided Quality Control System in Korean National Lung Cancer Screening

Korean national lung cancer screening program (KNLCS) targeting high-risk smoking population using low-dose CT (LDCT) was implemented in 2019. A cloud-based quality control system (CQCS) using computer aided detection program (CAD) was used to assist radiologists in detection, measurement and categorization of lung nodules in LDCT. From 2021, Artificial Intelligence (AI)-based CAD has been launched as a developed version of CQCS. This study aimed to evaluate the effectiveness of CQCS on positive rate and inter-observer variability in KNLCS on national level.

Computer-aided detection of cerebral aneurysms with magnetic resonance angiography: usefulness of volume rendering to display lesion candidates

The clinical usefulness of computer-aided detection of cerebral aneurysms has been investigated using different methods to present lesion candidates, but suboptimal methods may have limited its usefulness. We compared three presentation methods to determine which can benefit radiologists the most by enabling them to detect more aneurysms. We conducted a multireader multicase observer performance study involving six radiologists and using 470 lesion candidates output by a computer-aided detection program, and compared the following three different presentation methods using the receiver operating characteristic analysis: (1) a lesion candidate is encircled on axial slices, (2) a lesion candidate is overlaid on a volume-rendered image, and (3) combination of (1) and (2). The response time was also compared. As compared with axial slices, radiologists showed significantly better detection performance when presented with volume-rendered images. There was no significant difference in response time between the two methods. The combined method was associated with a significantly longer response time, but had no added merit in terms of diagnostic accuracy. Even with the aid of computer-aided detection, radiologists overlook many aneurysms if the presentation method is not optimal. Overlaying colored lesion candidates on volume-rendered images can help them detect more aneurysms.

Identification of acute intracranial bleed on computed tomography using computer aided detection

Intracranial haemorrhage can be life threatening. Timely detection of acute intracranial haemorrhage in an emergency room is essential so that the patient can be given medical attention without delay. This has led to the use of Computer Aided Detection (CAD) systems which can help to pick up and prioritize patients with high risk of bleeding. A CAD for identification of acute intracranial haemorrhage in Computed Tomography (CT) on a per patient basis was developed in this project. The CAD is aimed to be a triage tool which determines the priority of image being read by radiologists. It was developed and validated using 119 and 108 volumes of brain CT images respectively. The volumes were first registered to standard Montreal Neurological Institute (MNI) space. Slices close to the base and top of the skull that tend to contribute to false positives were omitted. Then, the volumes were analysed by a fully automated CAD program developed in MATLAB. The algorithm involved multiple thresholding and symmetry detection in 3D to detect acute intracranial haemorrhage. The evaluation took around 5s per volume. On a per patient basis, the CAD achieved sensitivity of 75.0%, specificity of 83.8%, and accuracy of 80.6% in the validation set.

Development of Protocol for Korean Lung Cancer Screening Project (K-LUCAS) to Evaluate Effectiveness and Feasibility to Implement National Cancer Screening Program.

PurposeTo reduce lung cancer mortality, lung cancer screening was recommended using low-dose computed tomography (LDCT) to high-risk population. A protocol for multicenter lung cancer screening pilot project was developed to evaluate the effectiveness and feasibility of lung cancer screening to implement National Cancer Screening Program in Korea.Materials and MethodsMultidisciplinary expert committee was comprised to develop a standardized protocol for Korean Lung Cancer Screening Project (K-LUCAS). K-LUCAS is a population-based single arm trial that targets high-risk population aged 55-74 years with at least 30 pack-year smoking history. LDCT results are reported by Lung-RADS suggested by American Radiology Society. Network-based system using computer-aided detection program is prepared to assist reducing diagnostic errors. Smoking cessation counselling is provided to all currently smoking participants. A small pilot test was conducted to check the feasibility and compliance of the protocols for K-LUCAS.ResultsIn pilot test, 256 were participated. The average age of participants was 63.2 years and only three participants (1.2%) were female. The participants had a smoking history of 40.5 pack-year on average and 53.9% were current smokers. Among them, 86.3% had willing to participate in lung cancer screening again. The average willingness to quit smoking among current smokers was 12.7% higher than before screening. In Lung-RADS reports, 10 (3.9%) were grade 3 and nine (3.5%) were grade 4. One participant was diagnosed as lung cancer.ConclusionThe protocol developed by this study is assessed to be feasible to perform K-LUCAS in multicenter nationwide scale.

Treatment Response Evaluation of Breast Cancer after Neoadjuvant Chemotherapy and Usefulness of the Imaging Parameters of MRI and PET/CT.

This study was aimed to evaluate the ability of imaging parameters measured on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), diffusion-weighted MRI (DWI) and positron emission tomography/computed tomography (PET/CT) to serve as response markers in breast cancer after neoadjuvant chemotherapy (NAC). In 20 patients with breast cancer, DCE-MRI and DWI using a 3 T scanner and PET/CT were performed before and after NAC. DCE-MRI was analyzed using an automatic computer-aided detection program (MR-CAD). The response imaging parameters were compared with the pathologic response. The areas under the curve (AUCs) for DCE-MRI using MR-CAD analysis, DWI and PET/CT were 0.77, 0.59 and 0.76, respectively. The combination of all parameters measured by MR-CAD showed the highest diagnostic performance and accuracy (AUC = 0.77, accuracy = 90%). The combined use of the parameters of PET/CT with DCE-MRI or DWI showed a trend toward improved specificity and negative predictive value (100%, 100%, accuracy = 87.5%). The use of DCE-MRI using MR-CAD parameters indicated better diagnostic performance in predicting the final pathological response compared with DWI and PET/CT, although no statistically significant difference was observed. The combined use of PET/CT with DCE-MRI or DWI may improve the specificity for predicting a pathological response.

Comparison of Dual-Energy Subtraction and Electronic Bone Suppression Combined With Computer-Aided Detection on Chest Radiographs: Effect on Human Observers' Performance in Nodule Detection

The objective of our study was to compare the effect of dual-energy subtraction and bone suppression software alone and in combination with computer-aided detection (CAD) on the performance of human observers in lung nodule detection. One hundred one patients with from one to five lung nodules measuring 5-29 mm and 42 subjects with no nodules were retrospectively selected and randomized. Three independent radiologists marked suspicious-appearing lesions on the original chest radiographs, dual-energy subtraction images, and bone-suppressed images before and after postprocessing with CAD. Marks of the observers and CAD marks were compared with CT as the reference standard. Data were analyzed using nonparametric tests and the jackknife alternative free-response receiver operating characteristic (JAFROC) method. Using dual-energy subtraction alone (p = 0.0198) or CAD alone (p = 0.0095) improved the detection rate compared with using the original conventional chest radiograph. The combination of bone suppression and CAD provided the highest sensitivity (51.6%) and the original nonenhanced conventional chest radiograph alone provided the lowest (46.9%; p = 0.0049). Dual-energy subtraction and bone suppression provided the same false-positive (p = 0.2702) and true-positive (p = 0.8451) rates. Up to 22.9% of lesions were found only by the CAD program and were missed by the readers. JAFROC showed no difference in the performance between modalities (p = 0.2742-0.5442). Dual-energy subtraction and the electronic bone suppression program used in this study provided similar detection rates for pulmonary nodules. Additionally, CAD alone or combined with bone suppression can significantly improve the sensitivity of human observers for pulmonary nodule detection.

Dual Energy Subtraction Digital Radiography Improves Performance of a Next Generation Computer-aided Detection Program

Computer-aided detection (CAD) has shown potential to assist physicians in the detection of lung nodules on chest radiographs, but widespread acceptance has been stymied by high false-positive rates. Few studies have examined the potential for dual energy subtraction (DES) to improve CAD performance. Institutional review board approval was obtained, the requirement for informed consent was waived because the study was retrospective, and practices conformed to Health Insurance Portability and Accountability Act regulations. The CAD program was applied retrospectively to dual energy posteroanterior (PA) chest radiographs of 36 patients (17 women, 19 men, mean age 69 y) with 48 pathology proven lung nodules. Results were analyzed to determine the stand-alone CAD program false-positive rates, and sensitivity by nodule subtlety and location. Statistical analysis was performed using the chi(2) or Fisher exact tests for independence of sensitivities between standard PA and DES radiography. Differences in the mean false-positives per image (FPPI) between radiographic modalities were determined using the paired Students t test, and bootstrap confidence intervals were obtained to confirm results. The sensitivity of the CAD program with the standard PA was 46% (22 of 48 nodules) compared with 67% (32 of 48 nodules) using the DES soft tissue or bone-subtracted view (P=0.064). The average number of FPPI identified by CAD was significantly lower using DES (FPPI(soft tissue) = 1.64) when compared with the standard PA chest radiograph (FPPI(PA) = 2.39) (P<0.01). DES has the potential to improve stand-alone CAD performance by both increasing sensitivity for certain subtle lung cancer lesions and decreasing overall CAD false-positive rates.

True Detection Versus “Accidental” Detection of Small Lung Cancer by a Computer-Aided Detection (CAD) Program on Chest Radiographs

To evaluate the number of actual detections versus "accidental" detections by a computer-aided detection (CAD) system for small nodular lung cancers (<or=30 mm) on chest radiographs, using two different criteria for measuring performance. A Food-and-Drug-Administration-approved CAD program (version 1.0; Riverain Medical) was applied to 34 chest radiographs with a "radiologist-missed" nodular cancer and 36 radiographs with a radiologist-mentioned nodule (a newer version 3.0 was also applied to the 36-case database). The marks applied by this CAD system consisted of 5-cm-diameter circles. A strict "nodule-in-center" criterion and a generous "nodule-in-circle" criterion were compared as methods for the calculation of CAD sensitivity. The increased sensitivities by the nodule-in-circle criterion were considered as nodules detected by chance. The number of false-positive (FP) marks was also analyzed. For the 34 radiologist-missed cancers, the nodule-in-circle criterion caused eight more cancers (24%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results. For the 36 radiologist-mentioned nodules, the nodule-in-circle criterion caused seven more lesions (19%) to be detected by chance, as compared to the nodule-in-center criterion, when using the version 1.0 results, and three more lesions (8%) to be detected by chance when using the version 3.0 results. Version 1.0 yielded a mean of six FP marks per image, while version 3.0 yielded only three FP marks per image. The specific criteria used to define true- and false-positive CAD detections can substantially influence the apparent accuracy of a CAD system.

Optimizing computer‐aided colonic polyp detection for CT colonography by evolving the Pareto fronta)

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6-9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p = 7.78 x 10(-5)) for the size category of 6-9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p = 7.95 x 10(-5)) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95% CI [0.75%, 16%], p = 0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists.

Lung Cancers Missed on Chest Radiographs: Results Obtained with a Commercial Computer-aided Detection Program

To retrospectively determine the sensitivity of and number of false-positive marks made by a commercially available computer-aided detection (CAD) system for identifying lung cancers previously missed on chest radiographs by radiologists, with histopathologic results as the reference standard. Institutional review board approval was obtained for this HIPAA-compliant study; the requirement for informed patient consent was waived. A CAD nodule detection program was applied to 34 posteroanterior digital chest radiographs obtained in 34 patients (21 men, 13 women; mean age, 69 years). All 34 radiographs showed a nodular lung cancer that was apparent in retrospect but had not been mentioned in the report. Two radiologists identified these radiologist-missed cancers on the chest radiographs and graded them for visibility, location, subtlety (extremely subtle to extremely obvious on a 10-point scale), and actionability (actionable or not actionable according to whether the radiologists probably would have recommended follow-up if the nodule had been detected). The CAD results were analyzed to determine the numbers of cancers and false-positive nodules marked and to correlate the CAD results with the nodule grades for subtlety and actionability. The chi2 test or Fisher exact test for independence was used to compare CAD sensitivity between the very subtle (grade 1-3) and relatively obvious (grade > 3) cancers and between the actionable and not actionable cancers. The CAD program had an overall sensitivity of 35% (12 of 34 cancers), identifying seven (30%) of 23 very subtle and five (45%) of 11 relatively obvious radiologist-missed cancers (P = .21) and detecting two (25%) of eight missed not actionable and ten (38%) of 26 missed actionable cancers (P = .33). The CAD program made an average of 5.9 false-positive marks per radiograph. The described CAD system can mark a substantial proportion of visually subtle lung cancers that are likely to be missed by radiologists.

Pulmonary Nodules: Automated Detection on CT Images with Morphologic Matching Algorithm—Preliminary Results

Institutional review board approval was obtained. Informed patient consent was not required for this retrospective study, which involved review of previously obtained image data. Patient confidentiality was protected; the study was compliant with the Health Insurance Portability and Accountability Act. An automated pulmonary nodule detection program that takes advantage of three-dimensional volumetric data was developed and tested with multi-detector row computed tomographic (CT) images from 20 patients (13 men, seven women; age range, 40-75 years) with pulmonary nodules. A total of 164 nodules 3 mm in diameter and larger were detected by two radiologists in consensus and were used as a reference standard to evaluate the computer-aided detection (CAD) program. The CAD algorithm was structured to process nodules that were categorized into three types: isolated, juxtapleural, and juxtavascular. Overall sensitivity for nodule detection with the CAD program was 95.1% (156 of 164 nodules). The sensitivity according to nodule size was 91.2% (52 of 57 nodules) for nodules 3 mm to less than 5 mm and 97.2% (104 of 107 nodules) for nodules 5 mm and larger. The number of false-positive detections per patient was 6.9 for false nodule structures 3 mm and larger and 4.0 for false nodule structures 5 mm and larger.

Computer-aided detection output on 172 subtle findings on normal mammograms previously obtained in women with breast cancer detected at follow-up screening mammography.

To evaluate, by using a computer-aided detection (CAD) program, the nonspecific findings on normal screening mammograms obtained in women in whom breast cancer was later detected at follow-up screening mammography. Four hundred ninety-three mammogram pairs-an initial negative screening mammogram and a subsequently obtained screening mammogram showing cancer-were collected. The mean interval between examinations was 14.6 months. In 169 cases, in which 172 cancers were later depicted, findings on the initial mammogram were subtle enough that either none or only one or two of five blinded radiologists recommended screening recall. On the initial negative mammograms, of the 172 areas where cancer later developed, 137 (80%) had subtle nonspecific findings and were retrospectively judged as having a benign or normal appearance. The mammograms with these subtle findings were evaluated with a commercially available CAD program, and the numbers of CAD marks on these nonspecific findings were analyzed. Of the 172 cancers, 129 (75%) were invasive and 43 (25%) were ductal carcinoma in situ. The CAD program marked 72 (42%) of the 172 findings that subsequently developed into cancer: 24 (29%) of 82 findings recalled by none, 25 (49%) of 51 findings recalled by one, and 23 (59%) of 39 findings recalled by two of the five radiologists. Among the 137 areas with nonspecific normal or benign findings, 41 (30%) areas where cancer subsequently developed were marked by the CAD program. A subset of cancers have perceptible but nonspecific mammographic findings that may be marked by a CAD program, even when the findings do not warrant recall as judged at blinded and unblinded radiologist review. The authors believe failure to act on such nonspecific but CAD-marked findings prospectively does not constitute interpretation below a reasonable standard of care.

Mammographic characteristics of 115 missed cancers later detected with screening mammography and the potential utility of computer-aided detection.

To retrospectively determine the mammographic characteristics of cancers missed at screening mammography and assess the ability of computer-aided detection (CAD) to mark the missed cancers. A multicenter retrospective study accrued 1,083 consecutive cases of breast cancer detected at screening mammography. Prior mammograms were available in 427 cases. Of these, 286 had lesions visible in retrospect. The 286 cases underwent blinded review by panels of radiologists; a majority recommended recall for 112 cases. Two experienced radiologists compared prior mammograms in 110 of these cases with the subsequent screening mammograms (when cancer was detected), noting mammographic characteristics of breast density, lesion type, size, morphology, and subjective reasons for possible miss. The prior mammograms were then analyzed with a CAD program. There were 110 patients with 115 cancers. On the prior mammograms with missed cancers, 35 (30%) of the 115 lesions were calcifications, with 17 of 35 (49%) clustered or pleomorphic. Eighty of the 115 (70%) were mass lesions, with 32 of 80 (40%) spiculated or irregular. For calcifications and masses, the most frequently suggested reasons for possible miss were dense breasts (12 of 35; 34%) and distracting lesions (35 of 80; 44%), respectively. CAD marked 30 (86%) of 35 missed calcifications and 58 (73%) of 80 missed masses. Detection errors affected cases with calcifications and masses. CAD marked most (77%; 88 of 115) cancers missed at screening mammography that radiologists retrospectively judged to merit recall.