Computer-aided detection of breast masses on mammograms: performance improvement using a dual system

We are developing a two-view information fusion method to improve the performance of our CAD system for mass detection. Mass candidates on each mammogram were first detected with our single-view CAD system. Potential object pairs on the two-view mammograms were then identified by using the distance between the object and the nipple. Morphological features, Hessian feature, correlation coefficients between the two paired objects and texture features were used as input to train a similarity classifier that estimated a similarity scores for each pair. Finally, a linear discriminant analysis (LDA) classifier was used to fuse the score from the single-view CAD system and the similarity score. A data set of 475 patients containing 972 mammograms with 475 biopsy-proven masses was used to train and test the CAD system. All cases contained the CC view and the MLO or LM view. We randomly divided the data set into two independent sets of 243 cases and 232 cases. The training and testing were performed using the 2-fold cross validation method. The detection performance of the CAD system was assessed by free response receiver operating characteristic (FROC) analysis. The average test FROC curve was obtained from averaging the FP rates at the same sensitivity along the two corresponding test FROC curves from the 2-fold cross validation. At the case-based sensitivities of 90%, 85% and 80% on the test set, the single-view CAD system achieved an FP rate of 2.0, 1.5, and 1.2 FPs/image, respectively. With the two-view fusion system, the FP rates were reduced to 1.7, 1.3, and 1.0 FPs/image, respectively, at the corresponding sensitivities. The improvement was found to be statistically significant (<i>p</i><0.05) by the AFROC method. Our results indicate that the two-view fusion scheme can improve the performance of mass detection on mammograms.

Effect of CAD on Radiologists' Detection of Lung Nodules on Thoracic CT Scans: Analysis of an Observer Performance Study by Nodule Size

We are developing a computer-aided detection (CAD) system for masses on digital breast tomosynthesis mammograms (DBTs). The CAD system includes two parallel processes. In the first process, mass detection and feature analysis are performed in the reconstructed 3D DBT volume. A mass likelihood score is estimated for each mass candidate using a linear discriminant (LDA) classifier. In the second process, mass detection and feature analysis are applied to the individual projection view (PV) images. A mass likelihood score is estimated for each mass candidate using another LDA classifier. The mass likelihood images derived from the PVs are back-projected to the breast volume to estimate the 3D spatial distribution of the mass likelihood scores. The mass likelihood scores estimated by the two processes at the corresponding 3D location are then merged and evaluated using FROC analysis. In this preliminary study, a data set of 52 DBT cases acquired with a GE prototype system at the Massachusetts General Hospital was used. The LDA classifiers with stepwise feature selection were designed with leave-one-case-out resampling. In an FROC analysis, the CAD system for detection in the DBT volume alone achieved test sensitivities of 80% and 90% at an average FP rate of 1.6 and 3.0 per breast, respectively. In comparison, the average FP rates of the combined system were 1.2 and 2.3 per breast, respectively, at the same sensitivities. The combined system is a promising approach to improving mass detection on DBTs.

Computer-Aided Mass Detection Based on Ipsilateral Multiview Mammograms

In this paper we will present a computer-aided detection (CAD) system for mass detection and classification. This CAD system performs mass detection on regions of interest (ROIs) and performs the normal-abnormal classification on detected masses. To enhance the ROIs, histogram equalization and average filtering were employed. ROIs or suspicious lesions were detected by an edge-base segmentation technique. Each ROI was represented by 12 textural features calculated from spatial gray-level co-occurrence matrix (GLCM). Finally, a back propagation neural network was used to classify a ROI to normal or abnormal one. Performance of the proposed system was analyzed in mini-MIAS data set by means of receiver operating characteristics curve (ROC curve) and free-response ROC curve (FROC curve). We archived area under the ROC curve AZ = 0,815. This value lied in the range from 0.7 to 0.9 so that our CAD system could be considered accurate enough.

The objective of this study was to evaluate the performance of a computer-aided detection (CAD) system for the detection of breast cancer, based on mammographic appearance and histopathology. From 1000 consecutive screening mammograms from women with biopsy-proven breast carcinoma, 273 mammograms were selected randomly for retrospective evaluation by CAD. The sensitivity of the CAD system for breast cancer was assessed from the proportion of masses and microcalcifications detected. The corresponding tumor histopathologies also were evaluated. Normal mammograms (n = 155 patients) were used to determine the false-positive rate of the system. Of the 273 breast carcinomas, 149 appeared mammographically as masses, and 88 appeared as microcalcifications, including 36 carcinomas that presented as mixed lesions. The CAD system marked 125 of 149 masses correctly (84%), marked 86 of 88 microcalcifications correctly (98%), and marked 32 of 36 of mixed lesions correctly (89%.). The system showed a high sensitivity for the detection of ductal carcinoma in situ (95%; 73 of 77 lesions), invasive lobular carcinoma (95%; 18 of 19 lesions), invasive ductal carcinoma (85%; 125 of 147 lesions), and invasive mammary carcinoma (90%; 27 of 30 lesions). The highest CAD system sensitivity was for all invasive carcinomas that presented as microcalcifications (100%). On normal mammograms, there was an average of 1.3 false-positive CAD marks per image. The CAD system correctly marked a large majority of biopsy-proven breast cancers, with a greater sensitivity for lesions with microcalcifications and without significant impact of performance based on tumor histopathology. CAD was highly effective in detecting invasive lobular carcinoma (sensitivity, 95%) and ductal carcinoma in situ (sensitivity, 95%). CAD represents a useful tool for the detection of breast cancer.

Computer-aided detection (CADe) systems could assist endoscopists in detecting early neoplasia in Barrett's oesophagus, which could be difficult to detect in endoscopic images. The aim of this study was to develop, test, and benchmark a CADe system for early neoplasia in Barrett's oesophagus. The CADe system was first pretrained with ImageNet followed by domain-specific pretraining with GastroNet. We trained the CADe system on a dataset of 14 046 images (2506 patients) of confirmed Barrett's oesophagus neoplasia and non-dysplastic Barrett's oesophagus from 15 centres. Neoplasia was delineated by 14 Barrett's oesophagus experts for all datasets. We tested the performance of the CADe system on two independent test sets. The all-comers test set comprised 327 (73 patients) non-dysplastic Barrett's oesophagus images, 82 (46 patients) neoplastic images, 180 (66 of the same patients) non-dysplastic Barrett's oesophagus videos, and 71 (45 of the same patients) neoplastic videos. The benchmarking test set comprised 100 (50 patients) neoplastic images, 300 (125 patients) non-dysplastic images, 47 (47 of the same patients) neoplastic videos, and 141 (82 of the same patients) non-dysplastic videos, and was enriched with subtle neoplasia cases. The benchmarking test set was evaluated by 112 endoscopists from six countries (first without CADe and, after 6 weeks, with CADe) and by 28 external international Barrett's oesophagus experts. The primary outcome was the sensitivity of Barrett's neoplasia detection by general endoscopists without CADe assistance versus with CADe assistance on the benchmarking test set. We compared sensitivity using a mixed-effects logistic regression model with conditional odds ratios (ORs; likelihood profile 95% CIs). Sensitivity for neoplasia detection among endoscopists increased from 74% to 88% with CADe assistance (OR 2·04; 95% CI 1·73-2·42; p<0·0001 for images and from 67% to 79% [2·35; 1·90-2·94; p<0·0001] for video) without compromising specificity (from 89% to 90% [1·07; 0·96-1·19; p=0·20] for images and from 96% to 94% [0·94; 0·79-1·11; ] for video; p=0·46). In the all-comers test set, CADe detected neoplastic lesions in 95% (88-98) of images and 97% (90-99) of videos. In the benchmarking test set, the CADe system was superior to endoscopists in detecting neoplasia (90% vs 74% [OR 3·75; 95% CI 1·93-8·05; p=0·0002] for images and 91% vs 67% [11·68; 3·85-47·53; p<0·0001] for video) and non-inferior to Barrett's oesophagus experts (90% vs 87% [OR 1·74; 95% CI 0·83-3·65] for images and 91% vs 86% [2·94; 0·99-11·40] for video). CADe outperformed endoscopists in detecting Barrett's oesophagus neoplasia and, when used as an assistive tool, it improved their detection rate. CADe detected virtually all neoplasia in a test set of consecutive cases. Olympus.

Development and validation of artificial neural networks model for detection of Barrett’s neoplasia: a multicenter pragmatic nonrandomized trial (with video)

Physicians use sonographic characteristics as a reference for the possible diagnosis of thyroid cancers. The purpose of this study was to investigate whether physicians were more effective in their tentative diagnosis based on the information provided by a computer-aided detection (CAD) system. A computer compared software-defined and physician-adjusted tumor loci. A multicenter, multireader, and multicase (MRMC) study was designed to compare clinician performance without and with the use of CAD. Interobserver variability was also analyzed. Excellent, satisfactory, and poor segmentations were observed in 25.3%, 58.9%, and 15.8% of nodules, respectively. There were 200 patients with 265 nodules in the study set. Nineteen physicians scored the malignancy potential of the nodules. The average area under the curve (AUC) of all readers was 0.728 without CAD and significantly increased to 0.792 with CAD. The average standard deviation of the malignant potential score significantly decreased from 18.97 to 16.29. The mean malignant potential score significantly decreased from 35.01 to 31.24 for benign cases. With the CAD system, an additional 7.6% of malignant nodules would be suggested for further evaluation, and biopsy would not be recommended for an additional 10.8% of benign nodules. The results demonstrated that applying a CAD system would improve clinicians’ interpretations and lessen the variability in diagnosis. However, more studies are needed to explore the use of the CAD system in an actual ultrasound diagnostic situation where much more benign thyroid nodules would be seen.

Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.

Artificial intelligence in breast imaging

To evaluate the efficacy of a new automatic computer-aided detection (CAD) system for mass screening of retinal nerve fibre layer (RNFL) defects in a large population using fundus photographs. Among the fundus photographs of 1200 consecutive subjects who visited a healthcare centre, a total of 2270 photographs appropriate for analysis were tested. The photographs were first reviewed by two expert ophthalmologists for detection of RNFL defects (gold standard manual detection). The images were then analysed using an automatic CAD system for detecting RNFL defects in various cases of glaucomatous and non-glaucomatous optic neuropathy. A free-response receiver operating characteristics curve was generated to evaluate the validity of the CAD system. The results of the automatic detection were compared with those of manual detection, and sensitivity and specificity of the CAD system were calculated. In manual detection of 2270 photographs, 41 RNFL defects from 36 photographs (1.6%) were detected, and no RNFL defects were found in 2234 photographs (98.4%). The sensitivity of the CAD system for detecting RNFL defects was 90.2% (37/41 RNFL defects) and the specificity was 72.5% (1620/2234 photographs with no RNFL defects) at a false-positive rate of 0.36 per image. The new CAD system successfully detected RNFL defects during mass screening of fundus photographs in a large population who visited a healthcare centre. The proposed algorithm can be useful for clinicians in screening RNFL defects in healthcare centres. The false-positive rate is still unsatisfactory, although improved compared with the previous study. Further studies are needed to enhance the speed and specificity of image analysis using the CAD system.

DBT is one of the promising imaging modalities that may improve the sensitivity and specificity for breast cancer detection. We are developing a computer-aided detection (CADe) system for clustered microcalcifications (MC) in DBT. A data set of two-view DBTs from 42 breasts was collected with a GE prototype system. We investigated a 2D approach to MC detection using projection view (PV) images rather than reconstructed 3D DBT volume. Our 2D approach consisted of two major stages: 1) detecting individual MC candidates on each PV, and 2) correlating the MC candidates from the different PVs and detecting clusters in the breast volume. With the MC candidates detected by prescreening on PVs, a trained multi-channel (MCH) filter bank was used to extract signal response from each MC candidate. A ray-tracing process was performed to fuse the MCH responses and localize the MC candidates in 3D using the geometrical information of the DBT system. Potential MC clusters were then identified by dynamic clustering of the MCs in 3D. A two-fold cross-validation method was used to train and test the CADe system. The detection performance of clustered MCs was assessed by free receiver operating characteristic (FROC) analysis. It was found that the CADe system achieved a case-based sensitivity of 90% at an average false positive rate of 2.1 clusters per DBT volume. Our study demonstrated that the CADe system using 2D MCH filter bank is promising for detection of clustered MCs in DBT.

Currently reported computer-aided detection (CAD) approaches face difficulties in identifying the diverse pulmonary nodules in thoracic computed tomography (CT) images, especially in heterogeneous datasets. We present a novel CAD system specifically designed to identify multisize nodule candidates in multiple heterogeneous datasets. The proposed CAD scheme is divided into two phases: primary phase and final phase. The primary phase started with the lung segmentation algorithm and the segmented lungs were further refined using morphological closing process to include the pleural nodules. Next, we empirically formulated three subalgorithms modules to detect different sizes of nodule candidates (≥3 and <6mm; ≥6 and <10mm; and ≥10mm). Each subalgorithm module included a multistage flow of rule-based thresholding and morphological processes. In the final phase, the nodule candidates were augmented to boost the performance of the classifier. The CAD system was trained using a total number of nodule candidates=201,654 (after augmentation) and nonnodule candidates=731,486. A rich set of 515 features based on cluster, texture, and voxel-based intensity features were utilized to train a neural network classifier. The proposed method was trained on 899 scans from the Lung Image Database Consortium/Image Database Resource Initiative (LIDC-IDRI). The CAD system was also independently tested on 153 CT scans taken from the AAPM-SPIE-LungX Dataset and two subsets from the Early Lung Cancer Action Project (ELCAP and PCF). For the LIDC-IDRI training set, the proposed CAD scheme yielded an overall sensitivity of 85.6% (1189/1390) and 83.5% (1161/1390) at 8 FP/scan and 1 FP/scan, respectively. For the three independent test sets, the CAD system achieved an average sensitivity of 68.4% at 8 FP/scan. The authors conclude that the proposed CAD system can identify dissimilar nodule candidates in the multiple heterogeneous datasets. It could be considered as a useful tool to support radiologists during screening trials.

Costal cartilage fractures are associated with poor prognosis in patients with blunt chest trauma. A Computer-Aided Detection (CAD) system for detecting rib fractures has been used in practice, but it is unclear whether this system recognizes costal cartilage fractures. This study investigated whether the CAD system for rib fracture can detect costal cartilage fractures. A total of 89 patients with costal cartilage fractures from participating hospitals over an 18-year period were included in the study. The presence of a costal cartilage fracture was determined by three radiologists. We reviewed fracture location, cartilage calcification, dislocation, and callus formation. The percentage of agreement between the radiologists and the CAD system (Rib fracture CAD, Fujifilm Medical Co., Ltd) was assessed. We detected 246 costal cartilage fractures in 89 patients. The costal cartilage of rib 7 was injured most frequently. Costal cartilage fractures were categorized as either mid-chondral, costochondral, or chondro-sternal. The CAD system detected 33 lesions; 16 were consistent with the costal cartilage fractures determined by the radiologists (costochondral junction 13, mid-chondral 2, chondro-sternal 1). The CAD system for rib fracture can detect costal cartilage fractures at the costochondral junction but is not sufficiently sensitive to detect costal cartilage fractures without calcification. The CAD system for rib fracture needs further development before it can be used to detect rib cartilage fractures.