Performance and Reading Time of Automated Breast US with or without Computer-aided Detection

Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies?

RATIONALE AND OBJECTIVES

Artificial intelligence (AI) systems have been increasingly applied to breast ultrasonography. They are expected to decrease the workload of radiologists and to improve diagnostic accuracy. The aim of this study is to evaluate the performance of an AI system for the BI-RADS category assessment in breast masses detected on breast ultrasound. MATERIALS AND METHODS: A total of 715 masses detected in 530 patients were analyzed. Three breast imaging centers of the same institution and nine breast radiologists participated in this study. Ultrasound was performed by one radiologist who obtained two orthogonal views of each detected lesion. These images were retrospectively reviewed by a second radiologist blinded to the patient's clinical data. A commercial AI system evaluated images. The level of agreement between the AI system and the two radiologists and their diagnostic performance were calculated according to dichotomic BI-RADS category assessment.

RESULTS

This study included 715 breast masses. Of these, 134 (18.75%) were malignant, and 581 (81.25%) were benign. In discriminating benign and probably benign from suspicious lesions, the agreement between AI and the first and second radiologists was moderate statistically. The sensitivity and specificity of radiologist 1, radiologist 2, and AI were calculated as 98.51% and 80.72%, 97.76% and 75.56%, and 98.51% and 65.40%, respectively. For radiologist 1, the positive predictive value (PPV) was 54.10%, the negative predictive value (NPV) was 99.58%, and the accuracy was 84.06%. Radiologist 2 achieved a PPV of 47.99%, NPV of 99.32%, and accuracy of 79.72%. The AI system exhibited a PPV of 39.64%, NPV of 99.48%, and accuracy of 71.61%. Notably, none of the lesions categorized as BI-RADS 2 by AI were malignant, while 2 of the lesions classified as BI-RADS 3 by AI were subsequently confirmed as malignant. By considering AI-assigned BI-RADS 2 as safe, we could potentially avoid 11% (18 out of 163) of benign lesion biopsies and 46.2% (110 out of 238) of follow-ups.

CONCLUSION

AI proves effective in predicting malignancy. Integrating it into the clinical workflow has the potential to reduce unnecessary biopsies and short-term follow-ups, which, in turn, can contribute to sustainability in healthcare practices.

Assessing Diagnostic Performance Using the Transverse Plane Plus Coronal Plane Compared With the Transverse Plane Alone in Screening Automated Breast Ultrasound

OBJECTIVES

The coronal plane is the unique display mode of automated breast (AB) ultrasound (US), which has valuable features of showing the entire breast anatomy and providing additional diagnostic value for breast lesions. However, whether adding the coronal plane could improve the diagnostic performance in screening breast cancer remains uncertain. This study aimed to evaluate the value of adding the coronal plane in interpretation for AB US screening.

METHODS

In this retrospective study, AB US images from 644 women (396 in the no-finding group, 143 with benign lesions, and 105 with malignant lesions) aged 40-70 years were collected between January 2016 and October 2020. Four novice radiologists (with 1-5 years of experience with breast US) and four experienced radiologists (with >5 years of experience with breast US) were assigned to read all AB US images in the transverse plane plus coronal plane (T + C planes) and transverse plane (T plane) alone in separate reading sessions. Diagnostic performance, lesion conspicuity, and reading time were compared using analysis of variance.

RESULTS

The mean reading time of all radiologists was significantly shorter in the T + C planes reading mode than in the T plane alone (115 ± 32 vs 128 ± 31 s, respectively; P < .05), and cancers had a higher conspicuity (odds ratio, 1.76; 95% confidence interval [CI], 1.00-3.08; P = .04). No significant differences were noted in the two reading modes (T + C planes vs T plane) in the sensitivity (82% [95% CI, 74-89%] vs 81% [95% CI, 74-88%], respectively; P = .68) and specificity (68% [95% CI, 62-75%] vs 70% [95% CI, 64-75%], respectively; P = .39) when Breast Imaging-Reporting and Data System (BI-RADS) 3 was set as the threshold. There were also no significant differences in the two reading modes (T + C planes vs T plane) in the sensitivity (70% [95% CI, 64-76%] vs 69% [95% CI, 63-75%], respectively; P = .39) and specificity (91% [95% CI, 87-96%] vs 91% [95% CI, 88-95%], respectively; P = .90) when BI-RADS 4 was set as the threshold. In addition, the mean areas under the receiver operating characteristic curves of all radiologists in the two reading modes (T + C planes vs T plane) were not significantly different (0.84 [95% CI, 0.79-0.89] vs 0.83 [95% CI, 0.78-0.89], respectively; P = .61).

CONCLUSIONS

Adding a coronal plane in the AB US screening setting saved the reading time and improved the conspicuity of breast cancers but not the diagnostic performance.

Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Detection Software for Automated Breast Ultrasound

RATIONALE AND OBJECTIVES

This study aimed to evaluate the diagnostic performance of radiologists following the utilization of artificial intelligence (AI)-based computer-aided detection software (CAD) in detecting suspicious lesions in automated breast ultrasounds (ABUS).

MATERIALS AND METHODS

ABUS-detected 262 breast lesions (histopathological verification; January 2020 to December 2022) were included. Two radiologists reviewed the images and assigned a Breast Imaging Reporting and Data System (BI-RADS) category. ABUS images were classified as positive or negative using AI-CAD. The BI-RADS category was readjusted in four ways: the radiologists modified the BI-RADS category using the AI results (AI-aided 1), upgraded or downgraded based on AI results (AI-aided 2), only upgraded for positive results (AI-aided 3), or only downgraded for negative results (AI-aided 4). The AI-aided diagnostic performances were compared to radiologists. The AI-CAD-positive and AI-CAD-negative cancer characteristics were compared.

RESULTS

For 262 lesions (145 malignant and 117 benign) in 231 women (mean age, 52.2 years), the area under the receiver operator characteristic curve (AUC) of radiologists was 0.870 (95% confidence interval [CI], 0.832-0.908). The AUC significantly improved to 0.919 (95% CI, 0.890-0.947; P = 0.001) using AI-aided 1, whereas it improved without significance to 0.884 (95% CI, 0.844-0.923), 0.890 (95% CI, 0.852-0.929), and 0.890 (95% CI, 0.853-0.928) using AI-aided 2, 3, and 4, respectively. AI-CAD-negative cancers were smaller, less frequently exhibited retraction phenomenon, and had lower BI-RADS category. Among nonmass lesions, AI-CAD-negative cancers showed no posterior shadowing.

CONCLUSION

AI-CAD implementation significantly improved the radiologists' diagnostic performance and may serve as a valuable diagnostic tool.

Exploring the Potential of Artificial Intelligence in Breast Ultrasound

Breast ultrasound has emerged as a valuable imaging modality in the detection and characterization of breast lesions, particularly in women with dense breast tissue or contraindications for mammography. Within this framework, artificial intelligence (AI) has garnered significant attention for its potential to improve diagnostic accuracy in breast ultrasound and revolutionize the workflow. This review article aims to comprehensively explore the current state of research and development in harnessing AI's capabilities for breast ultrasound. We delve into various AI techniques, including machine learning, deep learning, as well as their applications in automating lesion detection, segmentation, and classification tasks. Furthermore, the review addresses the challenges and hurdles faced in implementing AI systems in breast ultrasound diagnostics, such as data privacy, interpretability, and regulatory approval. Ethical considerations pertaining to the integration of AI into clinical practice are also discussed, emphasizing the importance of maintaining a patient-centered approach. The integration of AI into breast ultrasound holds great promise for improving diagnostic accuracy, enhancing efficiency, and ultimately advancing patient's care. By examining the current state of research and identifying future opportunities, this review aims to contribute to the understanding and utilization of AI in breast ultrasound and encourage further interdisciplinary collaboration to maximize its potential in clinical practice.

Deep learning system improved detection efficacy of fetal intracranial malformations in a randomized controlled trial

Congenital malformations of the central nervous system are among the most common major congenital malformations. Deep learning systems have come to the fore in prenatal diagnosis of congenital malformation, but the impact of deep learning-assisted detection of congenital intracranial malformations from fetal neurosonographic images has not been evaluated. Here we report a three-way crossover, randomized control trial (Trial Registration: ChiCTR2100048233) that assesses the efficacy of a deep learning system, the Prenatal Ultrasound Diagnosis Artificial Intelligence Conduct System (PAICS), in assisting fetal intracranial malformation detection. A total of 709 fetal neurosonographic images/videos are read interactively by 36 sonologists of different expertise levels in three reading modes: unassisted mode (without PAICS assistance), concurrent mode (using PAICS at the beginning of the assessment) and second mode (using PAICS after a fully unaided interpretation). Aided by PAICS, the average accuracy of the unassisted mode (73%) is increased by the concurrent mode (80%; P < 0.001) and the second mode (82%; P < 0.001). Correspondingly, the AUC is increased from 0.85 to 0.89 and to 0.90, respectively (P < 0.001 for all). The median read time per data is slightly increased in concurrent mode but substantially prolonged in the second mode, from 6 s to 7 s and to 11 s (P < 0.001 for all). In conclusion, PAICS in both concurrent and second modes has the potential to improve sonologists' performance in detecting fetal intracranial malformations from neurosonographic data. PAICS is more efficient when used concurrently for all readers.

Pearls and Pitfalls of Interpretation of Automated Breast US

Dense breast tissue is an independent risk factor for breast cancer and reduces the sensitivity of mammography. Patients with dense breast tissue are more likely to present with interval cancers and higher-stage disease. Successful breast cancer screening outcomes rely on detection of early-stage breast cancers; therefore, several supplemental screening modalities have been developed to improve cancer detection in dense breast tissue. US is the most widely used supplemental screening modality worldwide and has been proven to demonstrate additional mammographically occult cancers that are predominantly invasive and node negative. According to the American College of Radiology, intermediate-risk women with dense breast tissue may benefit from adjunctive screening US due to the limitations of mammography. Several studies have demonstrated handheld US (HHUS) and automated breast US (AUS) to be comparable in the screening setting. The advantages of AUS over HHUS include lack of operator dependence and a formal training requirement, image reproducibility, and ability for temporal comparison. However, AUS exhibits unique features that can result in high false-positive rates and long interpretation times for new users. Familiarity with the common appearance of benign mammographic findings and artifacts, technical challenges, and unique AUS features is essential for fast, efficient, and accurate interpretation. The goals of this article are to (a) examine the role of AUS as a supplemental screening modality and (b) review the pearls and pitfalls of AUS interpretation. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

The Diagnostic Significance of the BI-RADS Classification Combined With Automated Breast Volume Scanner and Shear Wave Elastography for Breast Lesions

OBJECTIVE

We herein compared the diagnostic accuracy of the BI-RADS, ABVS, SWE, and combined techniques for the classification of breast lesions.

METHODS

Breast lesions were appraised using the BI-RADS classification system as well as the combinations of BI-RADS plus ABVS (BI-RADS + ABVS) and BI-RADS plus SWE (BI-RADS + SWE), and both methods (BI-RADS + ABVS + SWE) by two specialties Medical Ultrasound physician. The Fisher's exact and χ² tests were performed to compare the degree of malignancy for the various methods with a pathology ground truth. Receiver operating characteristic curves (ROC) were generated and the corresponding area under the curve (AUC) values were determined to test the diagnostic efficacy of the various methods and identify the optimal SWE cut-off indicative of malignancy.

RESULTS

The incidence of the retraction phenomenon on ABVS images of the malignant group was significantly higher (P < .001) than that of the benign group. The specificity, sensitivity, and positive and negative predictive values of the BI-RADS classification were 88.72, 79.38, 83.70, and 85.50%, respectively. BI-RADS plus SWE-Max exhibited enhanced specificity, sensitivity, and positive and negative predictive values of 88.72, 92.78, 85.70, and 94.40%, respectively. Similarly, when BI-RADS + ABVS was utilized, the sensitivity and negative predictive value increased to 95.88 and 96.40%, respectively. BI-RADS + ABVS + SWE possessed the highest overall sensitivity (96.91%), specificity (94.74%), and positive (93.10%) and negative (97.70%) predictive values from all four indices.

CONCLUSION

ABVS and SWE can reduce the subjectivity of BI-RADS. As a result, BI-RADS + ABVS + SWE resulted in the best diagnostic accuracy.

Automated Facial Acne Lesion Detecting and Counting Algorithm for Acne Severity Evaluation and Its Utility in Assisting Dermatologists

BACKGROUND

Although lesion counting is an evaluation method that effectively analyzes facial acne severity, its usage is limited because of difficult implementation.

OBJECTIVES

We aimed to develop and validate an automated algorithm that detects and counts acne lesions by type, and to evaluate its clinical applicability as an assistance tool through a reader test.

METHODS

A total of 20,699 lesions (closed and open comedones, papules, nodules/cysts, and pustules) were manually labeled on 1213 facial images of 398 facial acne photography sets (frontal and both lateral views) acquired from 258 patients and used for training and validating algorithms based on a convolutional neural network for classifying five classes of acne lesions or for binary classification into noninflammatory and inflammatory lesions.

RESULTS

In the validation dataset, the highest mean average precision was 28.48 for the binary classification algorithm. Pearson's correlation of lesion counts between algorithm and ground-truth was 0.72 (noninflammatory) and 0.90 (inflammatory), respectively. In the reader test, eight readers (100.0%) detected and counted lesions more accurately using the algorithm compared with the reader-alone evaluation.

CONCLUSIONS

Overall, our algorithm demonstrated clinically applicable performance in detecting and counting facial acne lesions by type and its utility as an assistance tool for evaluating acne severity.

Automated Breast Ultrasound (ABUS)-based radiomics nomogram: an individualized tool for predicting axillary lymph node tumor burden in patients with early breast cancer

OBJECTIVES

Preoperative evaluation of axillary lymph node (ALN) status is an essential part of deciding the appropriate treatment. According to ACOSOG Z0011 trials, the new goal of the ALN status evaluation is tumor burden (low burden, < 3 positive ALNs; high burden, ≥ 3 positive ALNs), instead of metastasis or non-metastasis. We aimed to develop a radiomics nomogram integrating clinicopathologic features, ABUS imaging features and radiomics features from ABUS for predicting ALN tumor burden in early breast cancer.

METHODS

A total of 310 patients with breast cancer were enrolled. Radiomics score was generated from the ABUS images. Multivariate logistic regression analysis was used to develop the predicting model, we incorporated the radiomics score, ABUS imaging features and clinicopathologic features, and this was presented with a radiomics nomogram. Besides, we separately constructed an ABUS model to analyze the performance of ABUS imaging features in predicting ALN tumor burden. The performance of the models was assessed through discrimination, calibration curve, and decision curve.

RESULTS

The radiomics score, which consisted of 13 selected features, showed moderate discriminative ability (AUC 0.794 and 0.789 in the training and test sets). The ABUS model, comprising diameter, hyperechoic halo, and retraction phenomenon, showed moderate predictive ability (AUC 0.772 and 0.736 in the training and test sets). The ABUS radiomics nomogram, integrating radiomics score with retraction phenomenon and US-reported ALN status, showed an accurate agreement between ALN tumor burden and pathological verification (AUC 0.876 and 0.851 in the training and test sets). The decision curves showed that ABUS radiomics nomogram was clinically useful and more excellent than US-reported ALN status by experienced radiologists.

CONCLUSIONS

The ABUS radiomics nomogram, with non-invasive, individualized and precise assessment, may assist clinicians to determine the optimal treatment strategy and avoid overtreatment.

A study on the optimal condition of ground truth area for liver tumor detection in ultrasound images using deep learning

PURPOSE

In recent years, efforts to apply artificial intelligence (AI) to the medical field have been growing. In general, a vast amount of high-quality training data is necessary to make great AI. For tumor detection AI, annotation quality is important. In diagnosis and detection of tumors using ultrasound images, humans use not only the tumor area but also the surrounding information, such as the back echo of the tumor. Therefore, we investigated changes in detection accuracy when changing the size of the region of interest (ROI, ground truth area) relative to liver tumors in the training data for the detection AI.

METHODS

We defined D/L as the ratio of the maximum diameter (D) of the liver tumor to the ROI size (L). We created training data by changing the D/L value, and performed learning and testing with YOLOv3.

RESULTS

Our results showed that the detection accuracy was highest when the training data were created with a D/L ratio between 0.8 and 1.0. In other words, it was found that the detection accuracy was improved by setting the ground true bounding box for detection AI training to be in contact with the tumor or slightly larger. We also found that when the D/L ratio was distributed in the training data, the wider the distribution, the lower the detection accuracy.

CONCLUSIONS

Therefore, we recommend that the detector be trained with the D/L value close to a certain value between 0.8 and 1.0 for liver tumor detection from ultrasound images.

Ultrasound for Breast Cancer Screening in Resource-Limited Settings: Current Practice and Future Directions

Breast cancer (BC) is the most prevalent cancer among women globally. Cancer screening can reduce mortality and improve women’s health. In developed countries, mammography (MAM) has been primarily utilized for population-based BC screening for several decades. However, it is usually unavailable in low-resource settings due to the lack of equipment, personnel, and time necessary to conduct and interpret the examinations. Ultrasound (US) with high detection sensitivity for women of younger ages and with dense breasts has become a supplement to MAM for breast examination. Some guidelines suggest using US as the primary screening tool in certain settings where MAM is unavailable and infeasible, but global recommendations have not yet reached a unanimous consensus. With the development of smart devices and artificial intelligence (AI) in medical imaging, clinical applications and preclinical studies have shown the potential of US combined with AI in BC screening. Nevertheless, there are few comprehensive reviews focused on the role of US in screening BC in underserved conditions, especially in technological, economical, and global perspectives. This work presents the benefits, limitations, advances, and future directions of BC screening with technology-assisted and resource-appropriate strategies, which may be helpful to implement screening initiatives in resource-limited countries.

False-negative and false-positive outcomes of computer-aided detection on brain metastasis: Secondary analysis of a multicenter, multireader study

BACKGROUND

Errors have seldom been evaluated in computer-aided detection on brain metastases. This study aimed to analyze false negatives (FNs) and false positives (FPs) generated by a brain metastasis detection system (BMDS) and by readers.

METHODS

A deep learning-based BMDS was developed and prospectively validated in a multicenter, multireader study. Ad hoc secondary analysis was restricted to the prospective participants (148 with 1,066 brain metastases and 152 normal controls). Three trainees and 3 experienced radiologists read the MRI images without and with the BMDS. The number of FNs and FPs per patient, jackknife alternative free-response receiver operating characteristic figure of merit (FOM), and lesion features associated with FNs were analyzed for the BMDS and readers using binary logistic regression.

RESULTS

The FNs, FPs, and the FOM of the stand-alone BMDS were 0.49, 0.38, and 0.97, respectively. Compared with independent reading, BMDS-assisted reading generated 79% fewer FNs (1.98 vs 0.42, P < .001); 41% more FPs (0.17 vs 0.24, P < .001) but 125% more FPs for trainees (P < .001); and higher FOM (0.87 vs 0.98, P < .001). Lesions with small size, greater number, irregular shape, lower signal intensity, and located on nonbrain surface were associated with FNs for readers. Small, irregular, and necrotic lesions were more frequently found in FNs for BMDS. The FPs mainly resulted from small blood vessels for the BMDS and the readers.

CONCLUSIONS

Despite the improvement in detection performance, attention should be paid to FPs and small lesions with lower enhancement for radiologists, especially for less-experienced radiologists.

Artificial Intelligence for Breast US

US is a widely available, commonly used, and indispensable imaging modality for breast evaluation. It is often the primary imaging modality for the detection and diagnosis of breast cancer in low-resource settings. In addition, it is frequently employed as a supplemental screening tool via either whole breast handheld US or automated breast US among women with dense breasts. In recent years, a variety of artificial intelligence systems have been developed to assist radiologists with the detection and diagnosis of breast lesions on US. This article reviews the background and evidence supporting the use of artificial intelligence tools for breast US, describes implementation strategies and impact on clinical workflow, and discusses potential emerging roles and future directions.

Evaluation of physician performance using a concurrent-read artificial intelligence system to support breast ultrasound interpretation

Purpose

The purpose of this study was to compare the diagnostic performance and the interpretation time of breast ultrasound examination between reading without and with the artificial intelligence (AI) system as a concurrent reading aid.

Material and methods

A fully crossed multi-reader and multi-case (MRMC) reader study was conducted. Sixteen participating physicians were recruited and retrospectively interpreted 172 breast ultrasound cases in two reading scenarios, once without and once with the AI system (BU-CAD™, TaiHao Medical Inc.) assistance for concurrent reading. Interpretations of any given case set with and without the AI system were separated by at least 5 weeks. These reading results were compared to the reference standard and the area under the LROC curve (AUCLROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for performance evaluations. The interpretation time was also compared between the unaided and aided scenarios.

Results

With the help of the AI system, the readers had higher diagnostic performance with an increase in the average AUCLROC from 0.7582 to 0.8294 with statistically significant. The sensitivity, specificity, PPV, and NPV were also improved from 95.77%, 24.07%, 44.18%, and 93.50%–98.17%, 30.67%, 46.91%, and 96.10%, respectively. Of these, the improvement in specificity reached statistical significance. The average interpretation time was significantly reduced by approximately 40% when the readers were assisted by the AI system.

Conclusion

The concurrent-read AI system improves the diagnostic performance in detecting and diagnosing breast lesions on breast ultrasound images. In addition, the interpretation time is effectively reduced for the interpreting physicians.

•

A reader study was conducted to compare the breast ultrasound interpreting performance without and with the aid of AI system.

•

The performance of breast ultrasound interpretation was improved by the AI system as a concurrent reading aid.

•

The breast ultrasound interpretation time is significantly reduced by the AI system as a concurrent reading aid.

•

The reproducibility experiments of the same lesion cropped by different rectangular proved the robustness of the AI system.

Mask Branch Network: Weakly Supervised Branch Network with a Template Mask for Classifying Masses in 3D Automated Breast Ultrasound

Automated breast ultrasound (ABUS) is being rapidly utilized for screening and diagnosing breast cancer. Breast masses, including cancers shown in ABUS scans, often appear as irregular hypoechoic areas that are hard to distinguish from background shadings. We propose a novel branch network architecture incorporating segmentation information of masses in the training process. The branch network is integrated into neural network, providing the spatial attention effect. The branch network boosts the performance of existing classifiers, helping to learn meaningful features around the target breast mass. For the segmentation information, we leverage the existing radiology reports without additional labeling efforts. The reports, which is generated in medical image reading process, should include the characteristics of breast masses, such as shape and orientation, and a template mask can be created in a rule-based manner. Experimental results show that the proposed branch network with a template mask significantly improves the performance of existing classifiers. We also provide qualitative interpretation of the proposed method by visualizing the attention effect on target objects.

Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound

OBJECTIVE

To develop novel deep learning network (DLN) with the incorporation of the automatic segmentation network (ASN) for morphological analysis and determined the performance for diagnosis breast cancer in automated breast ultrasound (ABUS).

METHODS

A total of 769 breast tumors were enrolled in this study and were randomly divided into training set and test set at 600 vs. 169. The novel DLNs (Resent v2, ResNet50 v2, ResNet101 v2) added a new ASN to the traditional ResNet networks and extracted morphological information of breast tumors. The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic (ROC) curve (AUC), and average precision (AP) were calculated. The diagnostic performances of novel DLNs were compared with those of two radiologists with different experience.

RESULTS

The ResNet34 v2 model had higher specificity (76.81%) and PPV (82.22%) than the other two, the ResNet50 v2 model had higher accuracy (78.11%) and NPV (72.86%), and the ResNet101 v2 model had higher sensitivity (85.00%). According to the AUCs and APs, the novel ResNet101 v2 model produced the best result (AUC 0.85 and AP 0.90) compared with the remaining five DLNs. Compared with the novice radiologist, the novel DLNs performed better. The F1 score was increased from 0.77 to 0.78, 0.81, and 0.82 by three novel DLNs. However, their diagnostic performance was worse than that of the experienced radiologist.

CONCLUSIONS

The novel DLNs performed better than traditional DLNs and may be helpful for novice radiologists to improve their diagnostic performance of breast cancer in ABUS.

KEY POINTS

• A novel automatic segmentation network to extract morphological information was successfully developed and implemented with ResNet deep learning networks. • The novel deep learning networks in our research performed better than the traditional deep learning networks in the diagnosis of breast cancer using ABUS images. • The novel deep learning networks in our research may be useful for novice radiologists to improve diagnostic performance.

Evaluation of Computer-Aided Detection (CAD) in Screening Automated Breast Ultrasound Based on Characteristics of CAD Marks and False-Positive Marks

The present study evaluated the effectiveness of computer-aided detection (CAD) system in screening automated breast ultrasound (ABUS) and analyzed the characteristics of CAD marks and the causes of false-positive marks. A total of 846 women who underwent ABUS for screening from January 2017 to December 2017 were included. Commercial CAD was used in all ABUS examinations, and its diagnostic performance and efficacy in shortening the reading time (RT) were evaluated. In addition, we analyzed the characteristics of CAD marks and the causes of false-positive marks. A total of 1032 CAD marks were displayed based on the patient and 534 CAD marks on the lesion. Five cases of breast cancer were diagnosed. The sensitivity, specificity, PPV, and NPV of CAD were 60.0%, 59.0%, 0.9%, and 99.6% for 846 patients. In the case of a negative study, it was less time-consuming and easier to make a decision. Among 530 false-positive marks, 459 were identified clearly for pseudo-lesions; the most common cause was marginal shadowing, followed by Cooper’s ligament shadowing, peri-areolar shadowing, rib, and skin lesions. Even though CAD does not improve the performance of ABUS and a large number of false-positive marks were detected, the addition of CAD reduces RT, especially in the case of negative screening ultrasound.

The lesion detection efficacy of deep learning on automatic breast ultrasound and factors affecting its efficacy: a pilot study

OBJECTIVES

The aim of this study was to investigate the detection efficacy of deep learning (DL) for automatic breast ultrasound (ABUS) and factors affecting its efficacy.

METHODS

Females who underwent ABUS and handheld ultrasound from May 2016 to June 2017 (N = 397) were enrolled and divided into training (n = 163 patients with breast cancer and 33 with benign lesions), test (n = 57) and control (n = 144) groups. A convolutional neural network was optimized to detect lesions in ABUS. The sensitivity and false positives (FPs) were evaluated and compared for different breast tissue compositions, lesion sizes, morphologies and echo patterns.

RESULTS

In the training set, with 688 lesion regions (LRs), the network achieved sensitivities of 93.8%, 97.2% and 100%, based on volume, lesion and patient, respectively, with 1.9 FPs per volume. In the test group with 247 LRs, the sensitivities were 92.7%, 94.5% and 96.5%, respectively, with 2.4 FPs per volume. The control group, with 900 volumes, showed 0.24 FPs per volume. The sensitivity was 98% for lesions > 1 cm³, but 87% for those ≤1 cm³ (p < 0.05). Similar sensitivities and FPs were observed for different breast tissue compositions (homogeneous, 97.5%, 2.1; heterogeneous, 93.6%, 2.1), lesion morphologies (mass, 96.3%, 2.1; non-mass, 95.8%, 2.0) and echo patterns (homogeneous, 96.1%, 2.1; heterogeneous 96.8%, 2.1).

CONCLUSIONS

DL had high detection sensitivity with a low FP but was affected by lesion size.

ADVANCES IN KNOWLEDGE

DL is technically feasible for the automatic detection of lesions in ABUS.

Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study

Background

Preoperative determination of breast cancer molecular subtypes facilitates individualized treatment plan-making and improves patient prognosis. We aimed to develop an assembled convolutional neural network (ACNN) model for the preoperative prediction of molecular subtypes using multimodal ultrasound (US) images.

Methods

This multicentre study prospectively evaluated a dataset of greyscale US, colour Doppler flow imaging (CDFI), and shear-wave elastography (SWE) images in 807 patients with 818 breast cancers from November 2016 to February 2021. The St. Gallen molecular subtypes of breast cancer were confirmed by postoperative immunohistochemical examination. The monomodal ACNN model based on greyscale US images, the dual-modal ACNN model based on greyscale US and CDFI images, and the multimodal ACNN model based on greyscale US and CDFI as well as SWE images were constructed in the training cohort. The performances of three ACNN models in predicting four- and five-classification molecular subtypes and identifying triple negative from non-triple negative subtypes were assessed and compared. The performance of the multimodal ACNN was also compared with preoperative core needle biopsy (CNB).

Finding

The performance of the multimodal ACNN model (macroaverage area under the curve [AUC]: 0.89–0.96) was superior to that of the dual-modal ACNN model (macroaverage AUC: 0.81–0.84) and the monomodal ACNN model (macroaverage AUC: 0.73–0.75) in predicting four-classification breast cancer molecular subtypes, which was also better than that of preoperative CNB (AUC: 0.89–0.99 vs. 0.67–0.82, p < 0.05). In addition, the multimodal ACNN model outperformed the other two ACNN models in predicting five-classification molecular subtypes (AUC: 0.87–0.94 vs. 0.78-0.81 vs. 0.71–0.78) and identifying triple negative from non-triple negative breast cancers (AUC: 0.934–0.970 vs. 0.688–0.830 vs. 0.536–0.650, p < 0.05). Moreover, the multimodal ACNN model obtained satisfactory prediction performance for both T1 and non-T1 lesions (AUC: 0.957–0.958 and 0.932–0.985).

Interpretation

The multimodal US-based ACNN model is a potential noninvasive decision-making method for the management of patients with breast cancer in clinical practice.

Funding

This work was supported in part by the National Natural Science Foundation of China (Grants 81725008 and 81927801), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), and the Science and Technology Commission of Shanghai Municipality (Grants 19441903200, 19DZ2251100, and 21Y11910800).

Clinical evaluation of AI software for rib fracture detection and its impact on junior radiologist performance

BACKGROUND

The detection of rib fractures (RFs) on computed tomography (CT) images is time-consuming and susceptible to missed diagnosis. An automated artificial intelligence (AI) detection system may be helpful to improve the diagnostic efficiency for junior radiologists.

PURPOSE

To compare the diagnostic performance of junior radiologists with and without AI software for RF detection on chest CT images.

MATERIALS AND METHODS

Six junior radiologists from three institutions interpreted 393 CT images of patients with acute chest trauma, with and without AI software. The CT images were randomly split into two sets at each institution, with each set assigned to a different radiologist First, the detection of all fractures (AFs), including displaced fractures (DFs), non-displaced fractures and buckle fractures, was analyzed. Next, the DFs were selected for analysis. The sensitivity and specificity of the radiologist-only and radiologist-AI groups at the patient level were set as primary endpoints, and secondary endpoints were at the rib and lesion level.

RESULTS

Regarding AFs, the sensitivity difference between the radiologist-AI group and the radiologist-only group were significant at different levels (patient-level: 26.20%; rib-level: 22.18%; lesion-level: 23.74%; P < 0.001). Regarding DFs, the sensitivity difference was 16.67%, 14.19%, and 16.16% at the patient, rib, and lesion levels, respectively (P < 0.001). No significant difference was found in the specificity between the two groups for AFs and DFs at the patient and rib levels (P > 0.05).

CONCLUSION

AI software improved the sensitivity of RF detection on CT images for junior radiologists and reduced the reading time by approximately 1 min per patient without decreasing the specificity.

Opportunities in cancer imaging: risk-adapted breast imaging in screening

In the UK, women between 50-70 years are invited for 3-yearly mammography screening irrespective of their likelihood of developing breast cancer. The only risk adaption is for women with >30% lifetime risk who are offered annual magnetic resonance imaging (MRI) and mammography, and annual mammography for some moderate-risk women. Using questionnaires, breast density, and polygenic risk scores, it is possible to stratify the population into the lowest 20% risk, who will develop <4% of cancers and the top 4%, who will develop 18% of cancers. Mammography is a good screening test but has low sensitivity of 60% in the 9% of women with the highest category of breast density (BIRADS D) who have a 2.5- to fourfold breast cancer risk. There is evidence that adding ultrasound to the screening mammogram can increase the cancer detection rate and reduce advanced stage interval and next round cancers. Similarly, alternative tests such as contrast-enhanced mammography (CESM) or abbreviated MRI (ABB-MRI) are much more effective in detecting cancer in women with dense breasts. Scintimammography has been shown to be a viable alternative for dense breasts or for follow-up in those with a personal history of breast cancer and scarring as result of treatment. For supplemental screening to be worthwhile in these women, new technologies need to reduce the number of stage II cancers and be cost effective when tested in large scale trials. This article reviews the evidence for supplemental imaging and examines whether a risk-stratified approach is feasible.

Improved Inception V3 method and its effect on radiologists' performance of tumor classification with automated breast ultrasound system

BACKGROUND

The automated breast ultrasound system (ABUS) is recognized as a valuable detection tool in addition to mammography. The purpose of this study was to propose a novel computer-aided diagnosis (CAD) system by extracting the textural features from ABUS images and to investigate the efficiency of using this CAD for breast cancer detection.

METHODS

This retrospective study involved 149 breast nodules [maximum diameter: mean size 18.89 mm, standard deviation (SD) 10.238, and range 5-59 mm] in 135. We assigned 3 novice readers (<3 years of experience and 3 experienced readers (≥10 years of experience to review the imaging data and stratify the 149 breast nodules as either malignant or benign. The Improved Inception V3 (II3) method was developed and used as an assistant tool to help the 6 readers to re-interpret the images.

RESULTS

Our method (II3) achieved an accuracy of 88.6% for the final result. The 3 novice readers had an average accuracy of 71.37%±4.067% while the 3 experienced readers was 83.03%±3.371% on the first-reading. With the help of II3 on the second-reading, the average accuracy of the novice readers increased to 84.13%±1.662% and the experienced readers increased to 89.50%±0.346%.The areas under the curve (AUCs) were similar compared with linear algorithms. The mean AUC of the novice readers was improved from 0.7751 (without II3) to 0.8232 (with II3). The mean AUC of the experienced readers was improved from 0.8939 (without II3) to 0.9211 (with II3). The mean AUC for all readers improved in both the second-reading mode (from 0.8345 to 0.8722, P=0.0081<0.05).

CONCLUSIONS

With the help of the II3, the diagnostic accuracy of the two groups were both improved, and II3 was more helpful for novice readers than for experienced readers. Our results showed that II3 is valuable in the differentiation of benign and malignant breast nodules and it also improves the experience and skill of some novice radiologists. The II3 cannot completely replace the influence of experience in the diagnostic process and will retain an auxiliary role in the clinic at present.

Automated Breast Ultrasound: Technical Aspects, Impact on Breast Screening, and Future Perspectives

Purpose of Review

Automated breast ultrasound (ABUS) is a three-dimensional imaging technique, used as a supplemental screening tool in women with dense breasts. This review considers the technical aspects, pitfalls, and the use of ABUS in screening and clinical practice, together with new developments and future perspectives.

Recent Findings

ABUS has been approved in the USA and Europe as a screening tool for asymptomatic women with dense breasts in addition to mammography. Supplemental US screening has high sensitivity for cancer detection, especially early-stage invasive cancers, and reduces the frequency of interval cancers. ABUS has similar diagnostic performance to handheld ultrasound (HHUS) and is designed to overcome the drawbacks of operator dependence and poor reproducibility. Concerns with ABUS, like HHUS, include relatively high recall rates and lengthy reading time when compared to mammography. ABUS is a new technique with unique features; therefore, adequate training is required to improve detection and reduce false positives. Computer-aided detection may reduce reading times and improve cancer detection. Other potential applications of ABUS include local staging, treatment response evaluation, breast density assessment, and integration of radiomics.

Summary

ABUS provides an efficient, reproducible, and comprehensive supplemental imaging technique in breast screening. Developments with computer-aided detection may improve the sensitivity and specificity as well as radiologist confidence and reduce reading times, making this modality acceptable in large volume screening centers.

Computer-Aided Diagnosis Improves the Detection of Clinically Significant Prostate Cancer on Multiparametric-MRI: A Multi-Observer Performance Study Involving Inexperienced Readers

Recently, Computer Aided Diagnosis (CAD) systems have been proposed to help radiologists in detecting and characterizing Prostate Cancer (PCa). However, few studies evaluated the performances of these systems in a clinical setting, especially when used by non-experienced readers. The main aim of this study is to assess the diagnostic performance of non-experienced readers when reporting assisted by the likelihood map generated by a CAD system, and to compare the results with the unassisted interpretation. Three resident radiologists were asked to review multiparametric-MRI of patients with and without PCa, both unassisted and assisted by a CAD system. In both reading sessions, residents recorded all positive cases, and sensitivity, specificity, negative and positive predictive values were computed and compared. The dataset comprised 90 patients (45 with at least one clinically significant biopsy-confirmed PCa). Sensitivity significantly increased in the CAD assisted mode for patients with at least one clinically significant lesion (GS > 6) (68.7% vs. 78.1%, p = 0.018). Overall specificity was not statistically different between unassisted and assisted sessions (94.8% vs. 89.6, p = 0.072). The use of the CAD system significantly increases the per-patient sensitivity of inexperienced readers in the detection of clinically significant PCa, without negatively affecting specificity, while significantly reducing overall reporting time.

Impact of Original and Artificially Improved Artificial Intelligence-based Computer-aided Diagnosis on Breast US Interpretation

OBJECTIVE

For breast US interpretation, to assess impact of computer-aided diagnosis (CADx) in original mode or with improved sensitivity or specificity.

METHODS

In this IRB approved protocol, orthogonal-paired US images of 319 lesions identified on screening, including 88 (27.6%) cancers (median 7 mm, range 1-34 mm), were reviewed by 9 breast imaging radiologists. Each observer provided BI-RADS assessments (2, 3, 4A, 4B, 4C, 5) before and after CADx in a mode-balanced design: mode 1, original CADx (outputs benign, probably benign, suspicious, or malignant); mode 2, artificially-high-sensitivity CADx (benign or malignant); and mode 3, artificially-high-specificity CADx (benign or malignant). Area under the receiver operating characteristic curve (AUC) was estimated under each modality and for standalone CADx outputs. Multi-reader analysis accounted for inter-reader variability and correlation between same-lesion assessments.

RESULTS

AUC of standalone CADx was 0.77 (95% CI: 0.72-0.83). For mode 1, average reader AUC was 0.82 (range 0.76-0.84) without CADx and not significantly changed with CADx. In high-sensitivity mode, all observers' AUCs increased: average AUC 0.83 (range 0.78-0.86) before CADx increased to 0.88 (range 0.84-0.90), P < 0.001. In high-specificity mode, all observers' AUCs increased: average AUC 0.82 (range 0.76-0.84) before CADx increased to 0.89 (range 0.87-0.92), P < 0.0001. Radiologists responded more frequently to malignant CADx cues in high-specificity mode (42.7% vs 23.2% mode 1, and 27.0% mode 2, P = 0.008).

CONCLUSION

Original CADx did not substantially impact radiologists' interpretations. Radiologists showed improved performance and were more responsive when CADx produced fewer false-positive malignant cues.

The value of the Demetics ultrasound-assisted diagnosis system in the differential diagnosis of benign from malignant thyroid nodules and analysis of the influencing factors

OBJECTIVES

To evaluate the value of Demetics and to explore whether Demetics can help radiologists with varying years of experience in the differential diagnosis of benign from malignant thyroid nodules.

METHODS

The clinical application value of Demetics was assessed by comparing the diagnostic accuracy of radiologists before and after applying Demetics. This retrospective analysis included 284 thyroid nodules that underwent pathological examinations. Two different combined methods were applied. Using method 1: the original TI-RADS classification was forcibly upgraded or downgraded by one level when Demetics classified the thyroid nodules as malignant or benign. Using method 2: the TI-RADS and benign or malignant classification of the thyroid nodules were flexibly adjusted after the physician learned the Demetics' results.

RESULTS

Demetics exhibited a higher sensitivity than did junior radiologist 1 (p_D1 = 0.029) and was similar in sensitivity to the two senior radiologists. Demetics had a higher AUC than both junior radiologists (p_D1 = 0.042, p_D2 = 0.038) and an AUC similar to that of the senior radiologists. The sensitivity (p = 0.035) and AUC (p = 0.031) of junior radiologist 1 and the specificity (p < 0.001) and AUC (p = 0.026) of junior radiologist 2 improved with combined method 1. The AUC of junior radiologist 2 improved with combined method 2 (p = 0.045). The factors influencing the diagnostic results of Demetics include sonographic signs (echogenicity and echogenic foci), contrast of the image, and nodule size.

CONCLUSION

Demetics exhibited high sensitivity and accuracy in the differential diagnosis of benign from malignant thyroid nodules. Demetics could improve the diagnostic accuracy of junior radiologists.

KEY POINTS

• Demetics exhibited a high sensitivity and accuracy in the differential diagnosis of benign from malignant thyroid nodules. • Demetics could improve the diagnostic accuracy of junior radiologists in the differential diagnosis of benign from malignant thyroid nodules. • Factors influencing the diagnostic results of Demetics include the sonographic signs (echogenicity and echogenic foci), contrast of the image, and nodule size.

Medical imaging and nuclear medicine: a Lancet Oncology Commission

The diagnosis and treatment of patients with cancer requires access to imaging to ensure accurate management decisions and optimal outcomes. Our global assessment of imaging and nuclear medicine resources identified substantial shortages in equipment and workforce, particularly in low-income and middle-income countries (LMICs). A microsimulation model of 11 cancers showed that the scale-up of imaging would avert 3·2% (2·46 million) of all 76·0 million deaths caused by the modelled cancers worldwide between 2020 and 2030, saving 54·92 million life-years. A comprehensive scale-up of imaging, treatment, and care quality would avert 9·55 million (12·5%) of all cancer deaths caused by the modelled cancers worldwide, saving 232·30 million life-years. Scale-up of imaging would cost US$6·84 billion in 2020-30 but yield lifetime productivity gains of $1·23 trillion worldwide, a net return of $179·19 per $1 invested. Combining the scale-up of imaging, treatment, and quality of care would provide a net benefit of $2·66 trillion and a net return of $12·43 per $1 invested. With the use of a conservative approach regarding human capital, the scale-up of imaging alone would provide a net benefit of $209·46 billion and net return of $31·61 per $1 invested. With comprehensive scale-up, the worldwide net benefit using the human capital approach is $340·42 billion and the return per dollar invested is $2·46. These improved health and economic outcomes hold true across all geographical regions. We propose actions and investments that would enhance access to imaging equipment, workforce capacity, digital technology, radiopharmaceuticals, and research and training programmes in LMICs, to produce massive health and economic benefits and reduce the burden of cancer globally.

Automated breast US as the primary screening test for breast cancer among East Asian women aged 40-49 years: a multicenter prospective study

OBJECTIVES

To prospectively evaluate the diagnostic performance of screening ABUS as the primary screening test for breast cancer among Korean women aged 40-49 years.

METHODS

This prospective, multicenter study included asymptomatic Korean women aged 40-49 years from three academic centers between February 2017 and October 2019. Each participant underwent ABUS without mammography, and the ABUS images were interpreted at each hospital with double-reading by two breast radiologists. Biopsy and at least 1 year of follow-up was considered the reference standard. Diagnostic performance of ABUS screening and subgroup analyses according to patient and tumor characteristics were evaluated.

RESULTS

Reference standard data were available for 959 women. The recall rate was 9.8% (95% confidence interval [CI]: 7.9%, 11.7%; 94 of 959 women) and the cancer detection yield was 5.2 per 1000 women (95% CI: -0.6, 11.1; 5 of 959 women). There was only one interval cancer. The sensitivity was 83.3% (95% CI: 53.5%, 100%; 5 of 6 cancers) and the specificity was 90.7% (95% CI: 88.8%, 92.5%; 864 of 95. women). The positive predictive values of biopsies performed (PPV₃) was 20.0% (95% CI: 4.3%, 35.7%; 5 of 25 women). Women with heterogeneous background echotexture had a higher recall rate (p = .009) and lower specificity (p = .036). Women with body mass index values < 25 kg/m² had a higher mean recall rate (p = .046).

CONCLUSION

In East Asia, screening automated breast US may be an alternative to screening mammography for detecting breast cancers in women aged 40-49 years.

KEY POINTS

• Automated breast US screening for breast cancer in asymptomatic women aged 40-49 is effective with 5.2 per 1000 cancer detection yield. • Women with heterogeneous background echotexture had a higher recall rate and lower specificity. • Women with body mass index < 25 kg/m² had a higher recall rate.

The Utility of Deep Learning in Breast Ultrasonic Imaging: A Review

Breast cancer is the most frequently diagnosed cancer in women; it poses a serious threat to women's health. Thus, early detection and proper treatment can improve patient prognosis. Breast ultrasound is one of the most commonly used modalities for diagnosing and detecting breast cancer in clinical practice. Deep learning technology has made significant progress in data extraction and analysis for medical images in recent years. Therefore, the use of deep learning for breast ultrasonic imaging in clinical practice is extremely important, as it saves time, reduces radiologist fatigue, and compensates for a lack of experience and skills in some cases. This review article discusses the basic technical knowledge and algorithms of deep learning for breast ultrasound and the application of deep learning technology in image classification, object detection, segmentation, and image synthesis. Finally, we discuss the current issues and future perspectives of deep learning technology in breast ultrasound.

Artificial intelligence in breast ultrasonography

Although breast ultrasonography is the mainstay modality for differentiating between benign and malignant breast masses, it has intrinsic problems with false positives and substantial interobserver variability. Artificial intelligence (AI), particularly with deep learning models, is expected to improve workflow efficiency and serve as a second opinion. AI is highly useful for performing three main clinical tasks in breast ultrasonography: detection (localization/segmentation), differential diagnosis (classification), and prognostication (prediction). This article provides a current overview of AI applications in breast ultrasonography, with a discussion of methodological considerations in the development of AI models and an up-to-date literature review of potential clinical applications.