Decrease in interpretation time for both novice and experienced readers using a concurrent computer-aided detection system for digital breast tomosynthesis.

OBJECTIVES: To compare the diagnostic performance and interpretation time of digital breast tomosynthesis (DBT) for both novice and experienced readers with and without using a computer-aided detection (CAD) system for concurrent read. METHODS: CAD system was developed for concurrent read in DBT interpretation. In this observer performance study, we used an enriched sample of 100 DBT cases including 70 with and 30 without breast cancers. Image interpretation was performed by four radiologists with different experience levels (two experienced and two novice). Each reader completed two reading sessions (at a minimum 2-month interval), once with and once without CAD. Three different rating scales were used to record each reader's interpretation. Reader performance with and without CAD was reported and compared for each radiologist. Reading time for each case was also recorded. RESULTS: Average area under the receiver operating characteristic curve values for BI-RADS scale on using CAD were 0.778 and 0.776 without using CAD, demonstrating no statistically significant differences. Results were consistent when the probability of malignancy and percentage probability of malignancy scales were used. Reading times per case were 72.07 s and 62.03 s (SD, 37.54 s vs 34.38 s) without and with CAD, respectively. The average difference in reading time on using CAD was a statistically significant decrease of 10.04 ± 1.85 s, providing 14% decrease in time. The time-reducing effect was consistently observed in both novice and experienced readers. CONCLUSION: DBT combined with CAD reduced interpretation time without diagnostic performance loss to novice and experienced readers. KEY POINTS: • The use of a concurrent DBT-CAD system shortened interpretation time. • The shortened interpretation time with DBT-CAD did not come at a cost to diagnostic performance to novice or experienced readers. • The concurrent DBT-CAD system improved the efficiency of DBT interpretation.

Evaluations of patient-specific bolus fabricated by mold-and-cast method using computer numerical control machine tools†.

The patient-specific bolus fabricated by a mold-and-cast method using a 3D printer (3DP) and silicon rubber has been adopted in clinical practices. Manufacturing a mold using 3DP, however, can cause time delays due to failures during the 3D printing process. Thereby, we investigated an alternative method of the mold fabrication using computer numerical control (CNC) machine tools. Treatment plans were conducted concerning a keloid scar formed on the ear and nose. The bolus structures were determined in a treatment planning system (TPS), and the molds were fabricated using the same structure file but with 3DP and CNC independently. Boluses were then manufactured using each mold with silicone rubbers. We compared the geometrical difference between the boluses and the planned structure using computed tomography (CT) images of the boluses. In addition, dosimetric differences between the two measurements using each bolus and the differences between the measured and calculated dose from TPS were evaluated using an anthropomorphic head phantom. Geometrically, the CT images of the boluses fabricated by the 3DP mold and the CNC mold showed differences compared to the planned structure within 2.6 mm of Hausdorff distance. The relative dose difference between the measurements using either bolus was within 2.3%. In conclusion, the bolus made by the CNC mold benefits from a stable fabricating process, retaining the performance of the bolus made by the 3DP mold.

MFA-net: Object detection for complex X-ray cargo and baggage security imagery.

Deep convolutional networks have been developed to detect prohibited items for automated inspection of X-ray screening systems in the transport security system. To our knowledge, the existing frameworks were developed to recognize threats using only baggage security X-ray scans. Therefore, the detection accuracy in other domains of security X-ray scans, such as cargo X-ray scans, cannot be ensured. We propose an object detection method for efficiently detecting contraband items in both cargo and baggage for X-ray security scans. The proposed network, MFA-net, consists of three plug-and-play modules, including the multiscale dilated convolutional module, fusion feature pyramid network, and auxiliary point detection head. First, the multiscale dilated convolutional module converts the standard convolution of the detector backbone to a conditional convolution by aggregating the features from multiple dilated convolutions using dynamic feature selection to overcome the object-scale variant issue. Second, the fusion feature pyramid network combines the proposed attention and fusion modules to enhance multiscale object recognition and alleviate the object and occlusion problem. Third, the auxiliary point detection head adopts an auxiliary head to predict the new keypoints of the bounding box to emphasize the localizability without requiring further ground-truth information. We tested the performance of the MFA-net on two large-scale X-ray security image datasets from different domains: a Security Inspection X-ray (SIXray) dataset in the baggage domain and our dataset, named CargoX, in the cargo domain. Moreover, MFA-net outperformed state-of-the-art object detectors in both domains. Thus, adopting the proposed modules can further increase the detection capability of the current object detectors on X-ray security images.

Multichannel Acoustic Spectroscopy of the Human Body for Inviolable Biometric Authentication.

Specific features of the human body, such as fingerprint, iris, and face, are extensively used in biometric authentication. Conversely, the internal structure and material features of the body have not been explored extensively in biometrics. Bioacoustics technology is suitable for extracting information about the internal structure and biological and material characteristics of the human body. Herein, we report a biometric authentication method that enables multichannel bioacoustic signal acquisition with a systematic approach to study the effects of selectively distilled frequency features, increasing the number of sensing channels with respect to multiple fingers. The accuracy of identity recognition according to the number of sensing channels and the number of selectively chosen frequency features was evaluated using exhaustive combination searches and forward-feature selection. The technique was applied to test the accuracy of machine learning classification using 5,232 datasets from 54 subjects. By optimizing the scanning frequency and sensing channels, our method achieved an accuracy of 99.62%, which is comparable to existing biometric methods. Overall, the proposed biometric method not only provides an unbreakable, inviolable biometric but also can be applied anywhere in the body and can substantially broaden the use of biometrics by enabling continuous identity recognition on various body parts for biometric identity authentication.

Precisely Tunable Synthesis of Binder-Free Cobalt Oxide-Based Li-Ion Battery Anode Using Scalable Electrothermal Waves.

Binder-free transition metal oxide-based anodes for lithium-ion batteries (LIBs), having high capacity and abundance, have received considerable attention. However, their low conductivity and unstable charge-discharge cycles must be addressed, and scalable fabrication routes for binder-free design with optimal phase tuning are necessary. Herein, we report a precisely tunable synthesis of binder-free cobalt oxide-based LIB anodes using scalable electrothermal waves. Needle-like nanoarrays of cobalt hydroxide on nickel foams are prepared as precursors, and Joule-heating-driven electrothermal waves passing through the metal foams cause transition to cobalt oxides with preserved structures and adjustable phase tuning of grains and oxygen vacancies. The rapid heating-cooling environment using electrothermal waves causes extreme input thermal energy over the activation energy of phase transitions and metastable phase trapping. This programmable route completes the selective grain characteristics and vacancy concentrations. The electrothermally tuned binder-free LIB anodes employing the CoO/Co3O4@Ni foam-based electrodes exhibit a high-rate capacity (3.7 mAh cm-2) at 2.4 mA cm-2 for 70 charge-discharge cycles. Accumulated electrothermal waves from multiple cycles broaden the tunable ranges of the morphological and chemical transitions causing rapid screening of the optimal phases for LIB anodes. This phase-tuning strategy will inspire precise yet efficient synthesis routes for diverse binder-free electrodes and catalysts.

Identity Recognition Based on Bioacoustics of Human Body.

Current biometrics rely on images obtained from the structural information of physiological characteristics, which is inherently a fatal problem of being vulnerable to spoofing. Here, we studied personal identification using the frequency-domain information based on human body vibration. We developed a bioacoustic frequency spectroscopy system and applied it to the fingers to obtain information on the anatomy, biomechanics, and biomaterial properties of the tissues. As a result, modulated microvibrations propagated through our body could capture a unique spectral trait of a person and the biomechanical transfer characteristics persisted for two months and resulted in 97.16% accuracy of identity authentication in 41 subjects. Ultimately, our method not only eliminates the practical means of creating fake copies of the relevant characteristics but also provides reliable features.

Fully automated nipple detection in digital breast tomosynthesis.

BACKGROUND AND OBJECTIVE: We propose a nipple detection algorithm for use with digital breast tomosynthesis (DBT) images. DBT images have been developed to overcome the weaknesses of 2D mammograms for denser breasts by providing 3D breast images. The nipple location acts as an invaluable landmark in DBT images for aligning the right and left breasts and describing the relative location of any existing lesions. METHODS: Nipples may be visible or invisible in a breast image, and therefore a nipple detection method must be able to detect the nipples for both cases. The detection method for visible nipples based on their shape is simple and highly efficient. However, it is difficult to detect invisible nipples because they do not have a prominent shape. Fibroglandular tissue in a breast is anatomically connected with the nipple. Thus, the nipple location can be detected by analyzing the location of such tissue. In this paper, we propose a method for detecting the location of both visible and invisible nipples using fibroglandular tissue and changes in the breast area. RESULTS: Our algorithm was applied to 138 DBT images, and its nipple detection accuracy was evaluated based on the mean Euclidean distance. The results indicate that our proposed method achieves a mean Euclidean distance of 3.10±2.58mm. CONCLUSIONS: The nipple location can be a very important piece of information in the process of a DBT image registration. This paper presents a method for the automatic nipple detection in a DBT image. The extracted nipple location plays an essential role in classifying any existing lesions and comparing both the right and left breasts. Thus, the proposed method can help with computer-aided detection for a more efficient DBT image analysis.

Three-Dimensional Computer-Aided Detection of Microcalcification Clusters in Digital Breast Tomosynthesis.

We propose computer-aided detection (CADe) algorithm for microcalcification (MC) clusters in reconstructed digital breast tomosynthesis (DBT) images. The algorithm consists of prescreening, MC detection, clustering, and false-positive (FP) reduction steps. The DBT images containing the MC-like objects were enhanced by a multiscale Hessian-based three-dimensional (3D) objectness response function and a connected-component segmentation method was applied to extract the cluster seed objects as potential clustering centers of MCs. Secondly, a signal-to-noise ratio (SNR) enhanced image was also generated to detect the individual MC candidates and prescreen the MC-like objects. Each cluster seed candidate was prescreened by counting neighboring individual MC candidates nearby the cluster seed object according to several microcalcification clustering criteria. As a second step, we introduced bounding boxes for the accepted seed candidate, clustered all the overlapping cubes, and examined. After the FP reduction step, the average number of FPs per case was estimated to be 2.47 per DBT volume with a sensitivity of 83.3%.