Saliency of breast lesions in breast cancer detection using artificial intelligence

Pertuz, Said; Ortega, David; Suarez, Érika; Cancino, William; Africano, Gerson; Rinta-Kiikka, Irina; Arponen, Otso; Paris, Sara; Lozano, Alfonso

doi:10.1038/s41598-023-46921-3

Cited by 4 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Breast cancer and benign breast masses have different morphological features and distribution of the vascularity, and contrast-enhanced US can characterize these features and provide information for studying malignancy risk 16 , 17 . Deep learning and artificial intelligence have offered a new way to improve the prediction of malignancy risk based on breast US 18 , 19 . Despite the progress, the features of breast masses acquired by conventional gray-scale US are still essential, so further study on the US features and associated data of breast masses is still relevant.…”

Section: Introductionmentioning

confidence: 99%

The utility of quantifying the orientation of breast masses in ultrasound imaging

Chen,

2024

Sci Rep

View full text Add to dashboard Cite

The aim of this study was to quantify the orientation of breast masses and determine whether it can enhance the utility of a not parallel orientation in predicting breast mass malignancy. A total of 15,746 subjects who underwent breast ultrasound examinations were initially enrolled in the study. Further evaluation was performed on subjects with solid breast masses (≤ 5 cm) intended for surgical resection and/or biopsy. The orientation angle, defined as the acute angle between the align of the maximal longitudinal diameter of the breast mass and the surface of the breast skin, was measured. Receiver operating characteristic (ROC) curve analysis was conducted, and various performance measures including sensitivity, specificity, positive and negative predictive values, accuracy, odds ratio, and the area under the ROC curve (AUC) were calculated. Multivariate analysis was performed to determine if the orientation angle was an independent predictor of breast malignancy. Decision curve analysis (DCA) was also conducted to assess the net benefit of adopting the orientation angle for predicting breast mass malignancy. The final analysis included 83 subjects with breast cancer and 135 subjects with benign masses. The intra-group correlation coefficient for the measurement of the orientation angle of breast masses was 0.986 (P = 0.001), indicating high reproducibility. The orientation angles of malignant and benign breast masses were 36.51 ± 14.90 (range: 10.7–88.6) degrees and 15.28 ± 8.40 (range: 0.0–58.7) degrees, respectively, and there was a significant difference between them (P < 0.001). The cutoff value for the orientation angle was determined to be 22.9°. The sensitivity, specificity, positive and negative predictive values, accuracy, odds ratio, and AUC for the prediction of breast malignancy using the orientation angle were 88.0%, 87.4%, 81.1%, 92.2%, 87.6%, 50.67%, and 0.925%, respectively. Multivariate analysis revealed that the orientation angle (> 22.9°), not circumscribed margin, and calcifications of the breast mass were independent factors predicting breast malignancy. The net benefit of adopting the orientation angle for predicting breast malignancy was 0.303. Based on these findings, it can be concluded that quantifying the orientation angle of breast masses is useful in predicting breast malignancy, as it demonstrates high sensitivity, specificity, AUC, and standardized net benefit. It optimizes the utility of the not parallel orientation in assessing breast mass malignancy.

show abstract

Section: Introductionmentioning

confidence: 99%

The utility of quantifying the orientation of breast masses in ultrasound imaging

Chen,

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

Longitudinal interpretability of deep learning based breast cancer risk prediction

Klanecek,

Wang,

Wagner

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Deep-learning-based models have achieved state-of-the-art breast cancer risk (BCR) prediction performance. However, these models are highly complex, and the underlying mechanisms of BCR prediction are not fully understood. Key questions include whether these models can detect breast morphologic changes that lead to cancer. These findings would boost confidence in utilizing BCR models in practice and provide clinicians with new perspectives. In this work, we aimed to determine when oncogenic processes in the breast provide sufficient signal for the models to detect these changes.Approach: In total, 1210 screening mammograms were collected for patients screened at different times before the cancer was screen-detected and 2400 mammograms for patients with at least ten years of follow-up. MIRAI, a BCR risk prediction model, was used to estimate the BCR. Attribution Heterogeneity was defined as the relative difference between the attributions obtained from the right and left breasts using one of the eight interpretability techniques. Model reliance on the side of the breast with cancer was quantified with AUC. The Mann-Whitney U test was used to check for significant differences in median absolute Attribution Heterogeneity between cancer patients and healthy individuals.Results: All tested attribution methods showed a similar longitudinal trend, where the model reliance on the side of the breast with cancer was the highest for the 0-1 Years-To-Cancer interval (AUC=0.85–0.95), dropped for the 1-3 Years-To-Cancer interval (AUC=0.64–0.71), and remained above the threshold for random performance for the 3-5 Years-To-Cancer interval (AUC=0.51–0.58). For all eight attribution methods, the median values of absolute attribution heterogeneity were significantly larger for patients diagnosed with cancer at one point (p<0.01).Significance: Interpretability of BCR prediction has revealed that long-term predictions (beyond three years) are most likely based on typical breast characteristics, such as breast density; for mid-term predictions (one to three years), the model appears to detect early signs of tumor development, while for short-term predictions (up to a year), the BCR model essentially functions as a breast cancer detection model.

show abstract

Artificial Intelligence in Breast Cancer Diagnosis and Treatment: Advances in Imaging, Pathology, and Personalized Care

Uchikov,

Khalid,

Dedaj-Salad

et al. 2024

Life

View full text Add to dashboard Cite

Breast cancer is the most prevalent cancer worldwide, affecting both low- and middle-income countries, with a growing number of cases. In 2024, about 310,720 women in the U.S. are projected to receive an invasive breast cancer diagnosis, alongside 56,500 cases of ductal carcinoma in situ (DCIS). Breast cancer occurs in every country of the world in women at any age after puberty but with increasing rates in later life. About 65% of women with the BRCA1 and 45% with the BRCA2 gene variants develop breast cancer by age 70. While these genes account for 5% of breast cancers, their prevalence is higher in certain populations. Advances in early detection, personalised medicine, and AI-driven diagnostics are improving outcomes by enabling a more precise analysis, reducing recurrence, and minimising treatment side effects. Our paper aims to explore the vast applications of artificial intelligence within the diagnosis and treatment of breast cancer and how these advancements can contribute to elevating patient care as well as discussing the potential drawbacks of such integrations into modern medicine. We structured our paper as a non-systematic review and utilised Google Scholar and PubMed databases to review literature regarding the incorporation of AI in the diagnosis and treatment of non-palpable breast masses. AI is revolutionising breast cancer management by enhancing imaging, pathology, and personalised treatment. In imaging, AI can improve the detection of cancer in mammography, MRIs, and ultrasounds, rivalling expert radiologists in accuracy. In pathology, AI enhances biomarker detection, improving HER2 and Ki67 assessments. Personalised medicine benefits from AI’s predictive power, aiding risk stratification and treatment response. AI also shows promise in triple-negative breast cancer management, offering better prognosis and subtype classification. However, challenges include data variability, ethical concerns, and real-world validation. Despite limitations, AI integration offers significant potential in improving breast cancer diagnosis, prognosis, and treatment outcomes.

show abstract

Saliency of breast lesions in breast cancer detection using artificial intelligence

Cited by 4 publications

References 39 publications

The utility of quantifying the orientation of breast masses in ultrasound imaging

The utility of quantifying the orientation of breast masses in ultrasound imaging

Longitudinal interpretability of deep learning based breast cancer risk prediction

Artificial Intelligence in Breast Cancer Diagnosis and Treatment: Advances in Imaging, Pathology, and Personalized Care

Contact Info

Product

Resources

About