A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses

Impact of an artificial intelligence decision support system among radiologists with different levels of experience in breast ultrasound: A prospective study in a tertiary center

PURPOSE

To assess the impact of an artificial intelligence decision support system (Koios DS) on the diagnostic performance of radiologists with different experience in breast ultrasound and to evaluate its potential to reduce unnecessary biopsies.

METHODS

This observational, prospective, single-centre study included consecutive patients scheduled for ultrasound-guided core-needle biopsy of suspicious breast lesions. Three radiologists with different experience in breast ultrasound (senior breast radiologist: 20 years; junior breast radiologist: 3 years; general radiologist: less than 1 year) independently evaluated the lesions, assigning BI-RADS categories before and after Koios DS application. Biopsy reports served as the reference standard. AUCs and the number of unnecessary biopsies before and after implementing Koios DS were compared using DeLong and McNemar's tests.

RESULTS

A total of 222 patients (median age 58 years, interquartile range 46-72 years) with 226 lesions were included, 89/226 (39.4 %) benign and 137/226 (60.6 %) malignant. The application of Koios DS significantly improved (p < 0.001) the AUC of all radiologists, with a 0.078 AUC Δ for the junior breast radiologist (from 0.786 to 0.864), a 0.062 AUC Δ for the general radiologist (from 0.719 to 0.781), and a 0.045 AUC Δ for the senior breast radiologist (from 0.823 to 0.868). Koios DS would have significantly reduced the number of unnecessary biopsies recommended by the senior breast radiologist (from 41/89 [46.1 %] to 30/89 [33.7 %], p < 0.001) and by the junior breast radiologist (from 46/89 [51.7 %] to 29/89 [32.6 %], p = 0.001).

CONCLUSION

The application of Koios DS improved the radiologists' diagnostic performance, particularly for less experienced ones, and could potentially reduce unnecessary biopsies.

An updated overview of radiomics-based artificial intelligence (AI) methods in breast cancer screening and diagnosis

Current imaging methods for diagnosing breast cancer (BC) are associated with limited sensitivity and specificity and modest positive predictive power. The recent progress in image analysis using artificial intelligence (AI) has created great promise to improve BC diagnosis and subtype differentiation. In this case, novel quantitative computational methods, such as radiomics, have been developed to enhance the sensitivity and specificity of early BC diagnosis and classification. The potential of radiomics in improving the diagnostic efficacy of imaging studies has been shown in several studies. In this review article, we discuss the radiomics workflow and current handcrafted radiomics methods in the diagnosis and classification of BC based on the most recent studies on different imaging modalities, e.g., MRI, mammography, contrast-enhanced spectral mammography (CESM), ultrasound imaging, and digital breast tumosynthesis (DBT). We also discuss current challenges and potential strategies to improve the specificity and sensitivity of radiomics in breast cancer to help achieve a higher level of BC classification and diagnosis in the clinical setting. The growing field of AI incorporation with imaging information has opened a great opportunity to provide a higher level of care for BC patients.

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.

An ultrasound-based nomogram model in the assessment of pathological complete response of neoadjuvant chemotherapy in breast cancer

Introduction

We aim to predict the pathological complete response (pCR) of neoadjuvant chemotherapy (NAC) in breast cancer patients by constructing a Nomogram based on radiomics models, clinicopathological features, and ultrasound features.

Methods

Ultrasound images of 464 breast cancer patients undergoing NAC were retrospectively analyzed. The patients were further divided into the training cohort and the validation cohort. The radiomics signatures (RS) before NAC treatment (RS1), after 2 cycles of NAC (RS2), and the different signatures between RS2 and RS1 (Delta-RS/RS1) were obtained. LASSO regression and random forest analysis were used for feature screening and model development, respectively. The independent predictors of pCR were screened from clinicopathological features, ultrasound features, and radiomics models by using univariate and multivariate analysis. The Nomogram model was constructed based on the optimal radiomics model and clinicopathological and ultrasound features. The predictive performance was evaluated with the receiver operating characteristic (ROC) curve.

Results

We found that RS2 had better predictive performance for pCR. In the validation cohort, the area under the ROC curve was 0.817 (95%CI: 0.734-0.900), which was higher than RS1 and Delta-RS/RS1. The Nomogram based on clinicopathological features, ultrasound features, and RS2 could accurately predict the pCR value, and had the area under the ROC curve of 0.897 (95%CI: 0.866-0.929) in the validation cohort. The decision curve analysis showed that the Nomogram model had certain clinical practical value.

Discussion

The Nomogram based on radiomics signatures after two cycles of NAC, and clinicopathological and ultrasound features have good performance in predicting the NAC efficacy of breast cancer.

Exploring the State of Machine Learning and Deep Learning in Medicine: A Survey of the Italian Research Community

Artificial intelligence (AI) is becoming increasingly important, especially in the medical field. While AI has been used in medicine for some time, its growth in the last decade is remarkable. Specifically, machine learning (ML) and deep learning (DL) techniques in medicine have been increasingly adopted due to the growing abundance of health-related data, the improved suitability of such techniques for managing large datasets, and more computational power. ML and DL methodologies are fostering the development of new “intelligent” tools and expert systems to process data, to automatize human–machine interactions, and to deliver advanced predictive systems that are changing every aspect of the scientific research, industry, and society. The Italian scientific community was instrumental in advancing this research area. This article aims to conduct a comprehensive investigation of the ML and DL methodologies and applications used in medicine by the Italian research community in the last five years. To this end, we selected all the papers published in the last five years with at least one of the authors affiliated to an Italian institution that in the title, in the abstract, or in the keywords present the terms “machine learning” or “deep learning” and reference a medical area. We focused our research on journal papers under the hypothesis that Italian researchers prefer to present novel but well-established research in scientific journals. We then analyzed the selected papers considering different dimensions, including the medical topic, the type of data, the pre-processing methods, the learning methods, and the evaluation methods. As a final outcome, a comprehensive overview of the Italian research landscape is given, highlighting how the community has increasingly worked on a very heterogeneous range of medical problems.

Artificial intelligence diagnosis based on breast ultrasound imaging

Breast cancer has now become the leading cancer in women. The development of breast ultrasound artificial intelligence (AI) diagnostic technology is conducive to promoting the precise diagnosis and treatment of breast cancer and alleviating the heavy medical burden due to the unbalanced regional development in China. In recent years, on the basis of improving diagnostic efficiency, AI technology has been continuously combined with various clinical application scenarios, thereby providing more comprehensive and reliable evidence-based suggestions for clinical decision-making. Although AI diagnostic technologies based on conventional breast ultrasound gray-scale images and cutting-edge technologies such as three-dimensional (3D) imaging and elastography have been developed to some extent, there are still technical pain points, diffusion difficulties and ethical dilemmas in the development of AI diagnostic technologies for breast ultrasound.

The Potential and Emerging Role of Quantitative Imaging Biomarkers for Cancer Characterization

Simple Summary

Modern, personalized therapy approaches are increasingly changing advanced cancer into a chronic disease. Compared to imaging, novel omics methodologies in molecular biology have already achieved an individual characterization of cancerous lesions. With quantitative imaging biomarkers, analyzed by radiomics or deep learning, an imaging-based assessment of tumoral biology can be brought into clinical practice. Combining these with other non-invasive methods, e.g., liquid profiling, could allow for more individual decision making regarding therapies and applications.

Abstract

Similar to the transformation towards personalized oncology treatment, emerging techniques for evaluating oncologic imaging are fostering a transition from traditional response assessment towards more comprehensive cancer characterization via imaging. This development can be seen as key to the achievement of truly personalized and optimized cancer diagnosis and treatment. This review gives a methodological introduction for clinicians interested in the potential of quantitative imaging biomarkers, treating of radiomics models, texture visualization, convolutional neural networks and automated segmentation, in particular. Based on an introduction to these methods, clinical evidence for the corresponding imaging biomarkers—(i) dignity and etiology assessment; (ii) tumoral heterogeneity; (iii) aggressiveness and response; and (iv) targeting for biopsy and therapy—is summarized. Further requirements for the clinical implementation of these imaging biomarkers and the synergistic potential of personalized molecular cancer diagnostics and liquid profiling are discussed.

Comparative study of breast core needle biopsy (CNB) findings with ultrasound BI-RADS subtyping

&lt;b&gt; Introduction:&lt;/b&gt; Given the high prevalence of breast cancer, developing quick and accessible diagnostics solutions is critical. The BIRADS classification is a reliable method for assessing and estimating the risk of malignancy in breast lesions. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Aim:&lt;/b&gt; The aim of this study was to compare the results of core needle biopsy of breast lesions and sonographic findings based on the BIRADS category in Yazd. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Materials and methods:&lt;/b&gt; This retrospective analytical study was done on all core needle biopsy specimens referred to Mortaz hospital, Yazd, Iran from 2010 to 2019. Demographic data such as age, laterality of the lesion, BIRADS category, and pathology reports were extracted from patients&apos; hospital folders. Data were analyzed by SPSS version 21. P &lt; 0.05 was considered statistically significant. &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Results:&lt;/b&gt; In total, 514 cases with a mean age of 43.9 9.4 years were studied. Among them, 104 cases (20.2%) were malignant and 410 cases (79.8%) were benign. The most common benign and malignant lesions were fibroadenoma (24.9%), and infiltrative ductal carcinoma (83.7%) respectively. The most common BIRADS was class 4A (54.9%). Patients with benign lesions were mostly in the 3rd and 4th decade of life, while malignant lesions were more in the 4th and 5th decades, and this difference was statistically significant (P = 0.001). The correlation between ultrasound diagnoses (BIRADS) and pathology findings was statistically significant (P &lt; 0.001). &lt;/br&gt;&lt;/br&gt; &lt;b&gt;Conclusion&lt;/b&gt;: Based on the results, there is a significant correlation between ultrasound outcomes according to BIRADS and pathology results, and the radiology-pathology accordance, owing to its high accuracy, can be very helpful in correctly diagnosing, monitoring, and managing the lesion.