Computer-aided diagnosis system versus conventional reading system in low-dose (< 2 mSv) computed tomography: comparative study for patients at risk of lung cancer

ABSTRACT BACKGROUND: Computer-aided diagnosis in low-dose (≤ 3 mSv) computed tomography (CT) is a potential screening tool for lung nodules, with quality interpretation and less inter-observer variability among readers. Therefore, we aimed to determine the screening potential of CT using a radiation dose that does not exceed 2 mSv. OBJECTIVE: We aimed to compare the diagnostic parameters of low-dose (< 2 mSv) CT interpretation results using a computer-aided diagnosis system for lung cancer screening with those of a conventional reading system used by radiologists. DESIGN AND SETTING: We conducted a comparative study of chest CT images for lung cancer screening at three private institutions. METHODS: A database of low-dose (< 2 mSv) chest CT images of patients at risk of lung cancer was viewed with the conventional reading system (301 patients and 226 nodules) or computer-aided diagnosis system without any subsequent radiologist review (944 patients and 1,048 nodules). RESULTS: The numbers of detected and solid nodules per patient (both P < 0.0001) were higher using the computer-aided diagnosis system than those using the conventional reading system. The nodule size was reported as the maximum size in any plane in the computer-aided diagnosis system. Higher numbers of patients (102 [11%] versus 20 [7%], P = 0.0345) and nodules (154 [15%] versus 17 [8%], P = 0.0035) were diagnosed with cancer using the computer-aided diagnosis system. CONCLUSIONS: The computer-aided diagnosis system facilitates the diagnosis of cancerous nodules, especially solid nodules, in low-dose (< 2 mSv) CT among patients at risk for lung cancer.

Computer-Aided Detection with Automated Breast Ultrasonography for Suspicious Lesions Detected on Breast MRI

PURPOSE: The aim of this study was to evaluate the diagnostic performance of a computer-aided detection (CAD) system used with automated breast ultrasonography (ABUS) for suspicious lesions detected on breast MRI, and CAD-false lesions. MATERIALS AND METHODS: We included a total of 40 patients diagnosed with breast cancer who underwent ABUS (ACUSON S2000) to evaluate multiple suspicious lesions found on MRI. We used CAD (QVCAD™) in all the ABUS examinations. We evaluated the diagnostic accuracy of CAD and analyzed the characteristics of CAD-detected lesions and the factors underlying false-positive and false-negative cases. We also analyzed false-positive lesions with CAD on ABUS. RESULTS: Of a total of 122 suspicious lesions detected on MRI in 40 patients, we excluded 51 daughter nodules near the main breast cancer within the same quadrant and included 71 lesions. We also analyzed 23 false-positive lesions using CAD with ABUS. The sensitivity, specificity, positive predictive value, and negative predictive value of CAD (for 94 lesions) with ABUS were 75.5%, 44.4%, 59.7%, and 62.5%, respectively. CAD facilitated the detection of 81.4% (35/43) of the invasive ductal cancer and 84.9% (28/33) of the invasive ductal cancer that showed a mass (excluding non-mass). CAD also revealed 90.3% (28/31) of the invasive ductal cancers measuring larger than 1 cm (excluding non-mass and those less than 1 cm). The mean sizes of the true-positive versus false-negative mass lesions were 2.08 ± 0.85 cm versus 1.6 ± 1.28 cm (P < 0.05). False-positive lesions included sclerosing adenosis and usual ductal hyperplasia. In a total of 23 false cases of CAD, the most common (18/23) cause was marginal or subareolar shadowing, followed by three simple cysts, a hematoma, and a skin wart. CONCLUSION: CAD with ABUS showed promising sensitivity for the detection of invasive ductal cancer showing masses larger than 1 cm on MRI.

Effect of detection algorithm based on deep learning for pulmonary nodules in different lung lobes / 中国医学影像技术

Objective: To explore the effect of pulmonary nodules in different lung lobes detection algorithm based on deep learning (DL). Methods: Totally 493 eligible patients with pulmonary nodules on chest CT were included, and pulmonary nodules were labeled. The results of pulmonary nodules detection algorithm based on DL were compared with those of radiologist's labelling, and the match ratios in every lung lobe were counted, respectively. The radiologist finally re-evaluated the nodules that might be detected by algorithm but were missed during the initial inspection. Results: The match ratio of 4.1 -30.0 mm nodules of DL algorithm was 96.05% (73/76), 96.91% (94/97), 96.94% (95/98), 98.59% (70/71), 95.95% (71/74) and 96.30% (26/27) for pulmonary nodules in left upper lobe, left lower lobe, right upper lobe, right middle lobe, right lower lobe and interlobar pleura, respectively (all P>0.05). After re-evaluation, 50.92% (747/1467) of the no matched nodules detected by algorithm were reassigned as true positives. There were statistical differences among the missed nodules on different lobes (all P<0.05). Conclusion: The performance of pulmonary nodule detection algorithm based DL is not affected by nodule locations in terms of pulmonary lobes. The distribution of missed nodules meets the general consensus of medical profession.

Pulmonary nodule detection method based on convolutional neural network / 生物医学工程学杂志

A method was proposed to detect pulmonary nodules in low-dose computed tomography (CT) images by two-dimensional convolutional neural network under the condition of fine image preprocessing. Firstly, CT image preprocessing was carried out by image clipping, normalization and other algorithms. Then the positive samples were expanded to balance the number of positive and negative samples in convolutional neural network. Finally, the model with the best performance was obtained by training two-dimensional convolutional neural network and constantly optimizing network parameters. The model was evaluated in Lung Nodule Analysis 2016(LUNA16) dataset by means of five-fold cross validation, and each group's average model experiment results were obtained with the final accuracy of 92.3%, sensitivity of 92.1% and specificity of 92.6%.Compared with other existing automatic detection and classification methods for pulmonary nodules, all indexes were improved. Subsequently, the model perturbation experiment was carried out on this basis. The experimental results showed that the model is stable and has certain anti-interference ability, which could effectively identify pulmonary nodules and provide auxiliary diagnostic advice for early screening of lung cancer.

Effect of new model-based iterative reconstruction on computer-aided detection for quantitative analysis of airway tree in chest CT / 实用放射学杂志

Objective To compare the spatial resolution and density resolution balance algorithm(MBIRSTND)and spatial resolution preference algorithm (MBIRRP20)from new version of model-based iterative reconstruction(MBIRn),and adaptive statistical iterative reconstruction(ASIR) with lung kernel in routine dose about the performance of computer-aided detection (CAD)for quantitative analysis of airway.Methods 30 patients were involved who were scanned for pulmonary disease with spectrum CT.Data with a slice thinkness 0.625 mm were reconstructed with ASIR,MBIRSTNDand MBIRRP20.Airway dimensions from three reconstruction algorithm images were measured using an automated and quantitative software(Dexin-FACT)that was designed to segment and quantify the bronchial tree,and a skeletonization algorithm to extract the center-line of airway trees automatically.For each patient,reconstruction algorithm chose the right middle lobe bronchus,and the bronchial length of the matched airways was measured by this scheme.Two radiologists used a semiquantitative 5 scale (Score 0 stands for its image quality is similar to that with ASIR;Score±1 stand for a little better or a little worse;Score±2 stand for obviously better or obviously worse)to rate subjective image quality of airway trees about images reconstructed with MBIRSTNDand MBIRRP20.Paired t test and Wilcoxon signed-rank test were used.Results Algorithm impacts the measurement variability of bronchus length in chest CT.The bronchial length with MBIRRP20was longer than with MBIRSTND, while the length with ASIR were the shortest(P<0.05).In addition, the optimal reconstruction algorithm was found to affect the subjective noise,the continuity and completeness of bronchial wall,and the show of bronchial end.The subjective noise of MBIRSTNDwas better than that of MBIRRP20.The show of bronchial end of MBIRRP20was better than that of MBIRSTND(P<0.05).There was no significant difference in the continuity and completeness of bronchial wall compared with MBIRRP20and MBIRSTND(P>0.05),which was much better than with ASIR(P<0.05).Conclusion MBIRn can inmprove the analyzing ability of CAD airway.The MBIRSTNDcan significantly reduce the image noise,the MBIRRP20significantly improve the branching of the bronchial arteries,both of which can allow the desired airway quantification accuracy of CAD for chest CT of the bronchial wall.

Medical computer-aided detection method based on deep learning / 生物医学工程学杂志

This paper performs a comprehensive study on the computer-aided detection for the medical diagnosis with deep learning. Based on the region convolution neural network and the prior knowledge of target, this algorithm uses the region proposal network, the region of interest pooling strategy, introduces the multi-task loss function: classification loss, bounding box localization loss and object rotation loss, and optimizes it by end-to-end. For medical image it locates the target automatically, and provides the localization result for the next stage task of segmentation. For the detection of left ventricular in echocardiography, proposed additional landmarks such as mitral annulus, endocardial pad and apical position, were used to estimate the left ventricular posture effectively. In order to verify the robustness and effectiveness of the algorithm, the experimental data of ultrasonic and nuclear magnetic resonance images are selected. Experimental results show that the algorithm is fast, accurate and effective.

Low-dose computed tomography screening for lung cancer in Tianjin: a preliminary clinical analysis of baseline screening and follow-up results / 中国肿瘤临床

Objective:To explore the efficacy of low-dose computed tomography (LDCT) baseline and follow-up scans of lung cancer screening and to analyze lung nodules and other thoracic lesions detected from baseline and follow-up. Methods:A total of 650 sub-jects were enrolled in the LDCT lung cancer screening program, and investigators mainly focused on the analysis of 548 subjects who participated in the follow-up scan. The investigators recorded the nodules and other lesions of baseline screening, compared them with the follow-up images, and recorded their progress. Results:A total of 101 subjects were positive in the baseline screening, with a positivity rate of 18.4%. Six cases of lung cancer were confirmed by pathology, with a detection rate of 0.92%(6/650). The detection rate of lung cancer in female non-smokers (1.59%) was higher than that in male smokers (1.04%) without significant difference (P=0.624). Detected in the follow-up scan were 19 cases of new nodule-positive subjects. The positive rate for new nodules was 3.5%(19/548). The difference between the three-and two-dimensional levels was statistically significant. Conclusion:The effect of LDCT screen-ing for early lung cancer is significant. The detection rate in female non-smokers was not significantly higher than that in male smok-ers. Thus, LDCT lung cancer screening is equally significant for both sexes. The computer-aided detection (CAD) volume measurement technique is better to evaluate the progress of nodules during the follow-up interval.

Study on calcific signs in pulmonary nodules based on pattern classification / 实用放射学杂志

Objective To study feasibility in extraction of calcific sign within pulmonary nodules with pattern classification.Meth-ods 49 cases with pulmonary nodules (benign in 16 and malignant in 33)confirmed by pathology or clinical follow-up were included in this study and all cases underwent chest CT examinations.CT images were interpreted double-blind by two associate chief radiolo-gists to draw a conclusion that there were any calcification within pulmonary nodules.Meanwhile,the calcifications in the regions of interest(ROI)on CT images were estimated with extraction of the sign of gray value,geometric and lung markings in ROI,and based on pattern classification algorithm at supporting vector machine(SVM).Results According to the results assessed by senior radiologists for classification within pulmonary nodules,the area under ROC curve was 0.95 which was extracted by automatic pat-tern classification algorithm,the extraction performance was stable(k=1),and was goodness fit with visual observation by doctors (k=0.939).Conclusion The ability of automatic pattern classification in detecting calcification within pulmonary nodules is about the same as that of visual assessment by senior doctors.

Computer-Aided Detection of Malignant Lung Nodules on Chest Radiographs: Effect on Observers' Performance

OBJECTIVE: To evaluate the effect of computer-aided detection (CAD) system on observer performance in the detection of malignant lung nodules on chest radiograph. MATERIALS AND METHODS: Two hundred chest radiographs (100 normal and 100 abnormal with malignant solitary lung nodules) were evaluated. With CT and histological confirmation serving as a reference, the mean nodule size was 15.4 mm (range, 7-20 mm). Five chest radiologists and five radiology residents independently interpreted both the original radiographs and CAD output images using the sequential testing method. The performances of the observers for the detection of malignant nodules with and without CAD were compared using the jackknife free-response receiver operating characteristic analysis. RESULTS: Fifty-nine nodules were detected by the CAD system with a false positive rate of 1.9 nodules per case. The detection of malignant lung nodules significantly increased from 0.90 to 0.92 for a group of observers, excluding one first-year resident (p = 0.04). When lowering the confidence score was not allowed, the average figure of merit also increased from 0.90 to 0.91 (p = 0.04) for all observers after a CAD review. On average, the sensitivities with and without CAD were 87% and 84%, respectively; the false positive rates per case with and without CAD were 0.19 and 0.17, respectively. The number of additional malignancies detected following true positive CAD marks ranged from zero to seven for the various observers. CONCLUSION: The CAD system may help improve observer performance in detecting malignant lung nodules on chest radiographs and contribute to a decrease in missed lung cancer.

Usefulness of the CAD System for Detecting Pulmonary Nodule in Real Clinical Practice

OBJECTIVE: We wanted to evaluate the usefulness of the computer-aided detection (CAD) system for detecting pulmonary nodules in real clinical practice by using the CT images. MATERIALS AND METHODS: Our Institutional Review Board approved our retrospective study with a waiver of informed consent. This study included 166 CT examinations that were performed for the evaluation of pulmonary metastasis in 166 patients with colorectal cancer. All the CT examinations were interpreted by radiologists and they were also evaluated by the CAD system. All the nodules detected by the CAD system were evaluated with regard to whether or not they were true nodules, and they were classified into micronodules (MN, diameter < 4 mm) and significant nodules (SN, 4 < or = diameter < or = 10 mm). The radiologic reports and CAD results were compared. RESULTS: The CAD system helped detect 426 nodules; 115 (27%) of the 426 nodules were classified as true nodules and 35 (30%) of the 115 nodules were SNs, and 83 (72%) of the 115 were not mentioned in the radiologists' reports and three (4%) of the 83 nodules were non-calcified SNs. One of three non-calcified SNs was confirmed as a metastatic nodule. According to the radiologists' reports, 60 true nodules were detected, and 28 of the 60 were not detected by the CAD system. CONCLUSION: Although the CAD system missed many SNs that are detected by radiologists, it helps detect additional nodules that are missed by the radiologists in real clinical practice. Therefore, the CAD system can be useful to support a radiologist's detection performance.

Application of computer-aided detection in CT colonography / 中国医学影像技术

CT colonography (CTC) has been widely used in diagnosis of colon diseases. Computer-aided detection (CAD) automatically detects the locations of suspicious lesions on CTC, and provides radiologists with a second opinion. CAD has the potential to increase radiologists' diagnostic performance in the detection of lesions and to decrease variability of the diagnostic accuracy among readers. The current fundamental scheme, the key techniques used for detection of lesions on CTC, the detection performance, as well as the pitfalls, challenges, and the future of CAD were reviewed in this article.

Technological progress of computer-aided detection and diagnosis of lung nodule based on CT image analysis / 国际生物医学工程杂志

Lung nodules are one of the most common pathological changes, thus early detection of lung nodule is very important for the diagnosis medical treatment of lung eancer. In recent years, as the application of multi-slice spiral CT(MSCT), high-resolution CT(HRCT) and low-dose chest CTCLDCT), computer-aided diagnosis (CAD) system will be more essential and more important. Since CAD system can improve the working efficiency of doctors and provide service to more patients, has become the research hotspot and achievement has been made in relevant area internationally recently. This review summarizes the basic methods and applieations of computer-aided detection and diagnosis of lung nodule based on CT image.

Mammographic Mass Detection Using a Mass Template

OBJECTIVE: The purpose of this study was to develop a new method for automated mass detection in digital mammographic images using templates. MATERIALS AND METHODS: Masses were detected using a two steps process. First, the pixels in the mammogram images were scanned in 8 directions, and regions of interest (ROI) were identified using various thresholds. Then, a mass template was used to categorize the ROI as true masses or non-masses based on their morphologies. Each pixel of a ROI was scanned with a mass template to determine whether there was a shape (part of a ROI) similar to the mass in the template. The similarity was controlled using two thresholds. If a shape was detected, then the coordinates of the shape were recorded as part of a true mass. To test the system's efficiency, we applied this process to 52 mammogram images from the Mammographic Image Analysis Society (MIAS) database. RESULTS: Three hundred and thirty-two ROI were identified using the ROI specification methods. These ROI were classified using three templates whose diameters were 10, 20 and 30 pixels. The results of this experiment showed that using the templates with these diameters achieved sensitivities of 93%, 90% and 81% with 1.3, 0.7 and 0.33 false positives per image respectively. CONCLUSION: These results indicate that the detection performance of this template based algorithm is satisfactory, and may improve the performance of computer-aided analysis of mammographic images and early diagnosis of mammographic masses.

Lung Nodule Detection on Chest CT: Evaluation of a Computer-Aided Detection (CAD) System

OBJECTIVE: To evaluate the capacity of a computer-aided detection (CAD) system to detect lung nodules in clinical chest CT. MATERIALS AND METHODS: A total of 210 consecutive clinical chest CT scans and their reports were reviewed by two chest radiologists and 70 were selected (33 without nodules and 37 with 1-6 nodules, 4-15.4 mm in diameter). The CAD system (ImageChecker (R) CT LN-1000) developed by R2 Technology, Inc. (Sunnyvale, CA) was used. Its algorithm was designed to detect nodules with a diameter of 4-20 mm. The two chest radiologists working with the CAD system detected a total of 78 nodules. These 78 nodules form the database for this study. Four independent observers interpreted the studies with and without the CAD system. RESULTS: The detection rates of the four independent observers without CAD were 81% (63/78), 85% (66/78), 83% (65/78), and 83% (65/78), respectively. With CAD their rates were 87% (68/78), 85% (66/78), 86% (67/78), and 85% (66/78), respectively. The differences between these two sets of detection rates did not reach statistical significance. In addition, CAD detected eight nodules that were not mentioned in the original clinical radiology reports. The CAD system produced 1.56 false-positive nodules per CT study. The four test observers had 0, 0.1, 0.17, and 0.26 false-positive results per study without CAD and 0.07, 0.2, 0.23, and 0.39 with CAD, respectively. CONCLUSION: The CAD system can assist radiologists in detecting pulmonary nodules in chest CT, but with a potential increase in their false positive rates. Technological improvements to the system could increase the sensitivity and specificity for the detection of pulmonary nodules and reduce these false-positive results.

The value of computer aided detection in digital chest radiograph on the diagnosis of pulmonary nodules / 医学研究生学报

Objective:To evaluate the computer aided detection system on the diagnosis of pulmonary nodules. Methods: 120 cases of examined patients with solitary lung nodules up to 9-30 mm in diameter were evaluated. All nodules had been verified by means of biopsy. 120 cases of healthy patients were selected as control group on the basis of confirmation on the chest CT. All chest radiograph in the two group were obtained with a digital radiography system. Five experienced chest radiologists and five residents detected the chest radiograph with or without CAD output images. The scales of performance were evaluated with receiver operating characteristic curve(ROC curve). Results: The average area under the curve value increased significantly from 0.762 without to 0.825 with CAD output images(P

Utility of computer -aided detection in the diagnosis of breast carcinoma with mammography / 中国癌症杂志

Purpose: To determine breast carcinoma detection rate of a new mammographic computer-aided system (CAD) in order to assess its clinical usefulness. Methods: 467 cases of breast carcinoma proved by surgery and pathology were retrospectively analyzed. All the mammograms of the cases were reviewed by two radiologists working as a team and then analyzed by the CAD-system. The sensitivity for breast carcinoma detection (masses or calcification) was calculated respectively, and the results compared. Results: The sensitivity for breast carcinoma detection by the same radiologists without and with the CAD-system were 80. 94% , 88. 01% , respectively (P