Features of prospectively overlooked computer-aided detection marks on prior screening digital mammograms in women with breast cancer

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 HF were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the HF and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the HF that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of HF. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.

Breast cancer detected with screening US: reasons for nondetection at mammography

PURPOSE

To retrospectively review the mammograms of women with breast cancers detected at screening ultrasonography (US) to determine the reasons for nondetection at mammography.

MATERIALS AND METHODS

This study received institutional review board approval, and informed consent was waived. Between 2003 and 2011, a retrospective database review revealed 335 US-depicted cancers in 329 women (median age, 47 years; age range, 29-69 years) with Breast Imaging Reporting and Data System breast density type 2-4. Five blinded radiologists independently reviewed the mammograms to determine whether the findings on negative mammograms should be recalled. Three unblinded radiologists re-reviewed the mammograms to determine the reasons for nondetection by using the reference location of the cancer on mammograms obtained after US-guided wire localization or breast magnetic resonance imaging. The number of cancers recalled by the blinded radiologists were compared with the reasons for nondetection determined by the unblinded radiologists.

RESULTS

Of the 335 US-depicted cancers, 63 (19%) were recalled by three or more of the five blinded radiologists, and 272 (81%) showed no mammographic findings that required immediate action. In the unblinded repeat review, 263 (78%) cancers were obscured by overlapping dense breast tissue, and nine (3%) were not included at mammography owing to difficult anatomic location or poor positioning. Sixty-three (19%) cancers were considered interpretive errors. Of these, 52 (82%) were seen as subtle findings (46 asymmetries, six calcifications) and 11 (18%) were evident (six focal asymmetries, one distortion, four calcifications).

CONCLUSION

Most breast cancers (81%) detected at screening US were not seen at mammography, even in retrospect. In addition, 19% had subtle or evident findings missed at mammography.

Computer-aided detection system performance on current and previous digital mammograms in patients with contralateral metachronous breast cancer

BACKGROUND

The computer-aided detection (CAD) system is widely used for screening mammography. The performance of the CAD system for contralateral breast cancer has not been reported for women with a history of breast cancer.

PURPOSE

To retrospectively evaluate the performance of a CAD system on current and previous mammograms in patients with contralateral metachronous breast cancer.

MATERIAL AND METHODS

During a 3-year period, 4945 postoperative patients had follow-up examinations, from whom we selected 55 women with contralateral breast cancers. Among them, 38 had visible malignant signs on the current mammograms. We analyzed the sensitivity and false-positive marks of the system on the current and previous mammograms according to lesion type and breast density.

RESULTS

The total visible lesion components on the current mammograms included 27 masses and 14 calcifications in 38 patients. The case-based sensitivity for all lesion types was 63.2% (24/38) with false-positive marks of 0.71 per patient. The lesion-based sensitivity for masses and calcifications was 59.3% (16/27) and 71.4% (10/14), respectively. The lesion-based sensitivity for masses in fatty and dense breasts was 68.8% (11/16) and 45.5% (5/11), respectively. The lesion-based sensitivity for calcifications in fatty and dense breasts was 100.0% (3/3) and 63.6% (7/11), respectively. The total visible lesion components on the previous mammograms included 13 masses and three calcifications in 16 patients, and the sensitivity for all lesion types was 31.3% (5/16) with false-positive marks of 0.81 per patient. On these mammograms, the sensitivity for masses and calcifications was 30.8% (4/13) and 33.3% (1/3), respectively. The sensitivity in fatty and dense breasts was 28.6% (2/7) and 33.3% (3/9), respectively.

CONCLUSION

In the women with a history of breast cancer, the sensitivity of the CAD system in visible contralateral breast cancer was lower than in most previous reports using the same CAD system probably due to the relatively small size, subtlety of the lesion findings, and dense parenchymal pattern.

Mammography screening using independent double reading with consensus: is there a potential benefit for computer-aided detection?

BACKGROUND

Double reading improves the cancer detection rate in mammography screening. Single reading with computer-aided detection (CAD) has been considered to be an alternative to double reading. Little is known about the potential benefit of CAD in breast cancer screening with double reading.

PURPOSE

To compare prospective independent double reading of screen-film (SFM) and full-field digital (FFDM) mammography in population-based screening with retrospective standalone CAD performance on the baseline mammograms of the screen-detected cancers and subsequent cancers diagnosed during the follow-up period.

MATERIAL AND METHODS

The study had ethics committee approval. A 5-point rating scale for probability of cancer was used for 23,923 (SFM = 16,983; FFDM = 6940) screening mammograms. Of 208 evaluable cancers, 104 were screen-detected and 104 were subsequent (44 interval and 60 next screening round) cancers. Baseline mammograms of subsequent cancers were retrospectively classified in consensus without information about cancer location, histology, or CAD prompting as normal, non-specific minimal signs, significant minimal signs, and false-negatives. The baseline mammograms of the screen-detected cancers and subsequent cancers were evaluated by CAD. Significant minimal signs and false-negatives were considered 'actionable' and potentially diagnosable if correctly prompted by CAD.

RESULTS

CAD correctly marked 94% (98/104) of the baseline mammograms of the screen-detected cancers (SFM = 95% [61/64]; FFDM = 93% [37/40]), including 96% (23/24) of those with discordant interpretations. Considering only those baseline examinations of subsequent cancers prospectively interpreted as normal and retrospectively categorized as 'actionable', CAD input at baseline screening had the potential to increase the cancer detection rate from 0.43% to 0.51% (P = 0.13); and to increase cancer detection by 16% ([104 + 17]/104) and decrease interval cancers by 20% (from 44 to 35).

CONCLUSION

CAD may have the potential to increase cancer detection by up to 16%, and to reduce the number of interval cancers by up to 20% in SFM and FFDM screening programs using independent double reading with consensus review. The influence of true- and false-positive CAD marks on decision-making can, however, only be evaluated in a prospective clinical study.