A Review of Breast Imaging for Timely Diagnosis of Disease

Bicchierai, Giulia; Naro, Federica Di; Benedetto, Diego De; Cozzi, Diletta; Pradella, Silvia; Miele, Vittorio; Nori, Jacopo

doi:10.3390/ijerph18115509

Cited by 22 publications

(20 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It has been broadly used in the implementation of the prediction system for various diseases, such as heart disease [ 6 ], lung cancer [ 7 ], and thyroid cancer [ 8 ]. DM and ML techniques have been embedded for diagnosing breast cancer with computer-aided systems [ 9 ], and fuzzy-genetics [ 10 ]. The results of these studies successfully classify the features into two types of tumors by the evaluation of classifier and predicting the incoming tumor based on previous data.…”

Section: Introductionmentioning

confidence: 99%

Improved Machine Learning-Based Predictive Models for Breast Cancer Diagnosis

Rasool

Bunterngchit

Luo

et al. 2022

IJERPH

View full text Add to dashboard Cite

Breast cancer death rates are higher than any other cancer in American women. Machine learning-based predictive models promise earlier detection techniques for breast cancer diagnosis. However, making an evaluation for models that efficiently diagnose cancer is still challenging. In this work, we proposed data exploratory techniques (DET) and developed four different predictive models to improve breast cancer diagnostic accuracy. Prior to models, four-layered essential DET, e.g., feature distribution, correlation, elimination, and hyperparameter optimization, were deep-dived to identify the robust feature classification into malignant and benign classes. These proposed techniques and classifiers were implemented on the Wisconsin Diagnostic Breast Cancer (WDBC) and Breast Cancer Coimbra Dataset (BCCD) datasets. Standard performance metrics, including confusion matrices and K-fold cross-validation techniques, were applied to assess each classifier’s efficiency and training time. The models’ diagnostic capability improved with our DET, i.e., polynomial SVM gained 99.3%, LR with 98.06%, KNN acquired 97.35%, and EC achieved 97.61% accuracy with the WDBC dataset. We also compared our significant results with previous studies in terms of accuracy. The implementation procedure and findings can guide physicians to adopt an effective model for a practical understanding and prognosis of breast cancer tumors.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved Machine Learning-Based Predictive Models for Breast Cancer Diagnosis

Rasool

Bunterngchit

Luo

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…В настоящий момент существует немало зарубежных [14] и отечественных [15,16] сообщений о высокой эффективности контрастной спектральной двухэнергетической маммографии (КСДМ) в диагностике РМЖ, особенно у пациенток с рентгенологически плотной тканью молочной железы (МЖ). По некоторым данным, КСДМ в этой группе больных обладает более высокой чувствительностью в сравнении с ЦМГ и ультразвуковым исседованием [17][18][19].…”

Section: опухоли женской репродуктивной системы Tumors Of Female Reproductive Systemunclassified

Utility of dual-energy contrast-enhanced spectral mammography for the diagnosis of multicentric breast cancer

Chernaya

Ulyanova

Krivorotko

et al. 2022

Opuholi ženskoj reproduktivnoj sistemy

View full text Add to dashboard Cite

Background. Breast cancer (BC) can be unifocal, multifocal, multicentric (MCBC) and bilateral according to number and localization of tumors. MCBC has different clinical and biological characteristics compared to unifocal BC, for example, a higher risk of lymph node involvement, a more aggressive natural history and a worse prognosis. Therefore, accurate diagnosis and detection of MCBC is one of the main tasks of imaging.Objective: to compare diagnostic accuracy of contrast enhanced spectral mammography (CESM) and digital mammography (DM) in the diagnosis of MCBC.Materials and methods. The study included 438 women with suspected BC. The results of DM and CESM were compared with the results of a pathomorphological study performed after surgery or biopsy to assess the effectiveness of imaging modalities. DM was performed for all women using a Senographe DS (GE, USA) unit. CESM was performed after intravenous injection of non-ionic contrast agents using injector with breast compression in the craniocaudal and mediolateral projections. The study was performed for both glands regardless of the location of the suspicious lesion in order to timely diagnose clinically asymptomatic bilateral cancer. The final diagnosis was made based on the results of the pathomorphological examination. MCBC was diagnosed when two or more tumors at a distance of 3 cm or more from each other were detected. Visualization of additional grouped calcifications of malignant type occupying a small portion of breast tissue (more than 15 pieces per 1 sq. cm) was considered as another mammographic sign of MCBC.Results. According to the pathomorphological examination BC was diagnosed in 154 (35 %) women out of 438 examined patients. MCBC was identified in 25 (16 %) of 154 patients. CESM was more effective than DM in detecting MCBC with sensitivity of 88.0 % vs 48.0 % (p = 0.002), accuracy of 92.2 % vs 90.9 %, negative predictive value of 97.6 % vs 90.8 % (p = 0.02), respectively. But the specificity was significantly higher in DM than in CESM – 99.2 % vs 93.0 % (p = 0.009), respectively, and the positive predictive value did not differ significantly (p = 0.12).Conclusion. CESM is a more sensitive method for diagnosing MCBC compared to DM with sensitivity of 88.0 % vs 48.0 %. The high negative predictive value of CESM (97.6 %) confirms the fact that this modality is an effective method for planning surgery and radiation therapy.

show abstract

“…Breast cancer is a diverse disease with different subtypes and stages [84]. Traditional diagnostic methods, such as mammography [85] and tissue biopsy [86], are very effective but they are limited by the need for the smallest tumor size and may lead to radiation exposure. In addition, not all breast tumors can be found by mammography in the early stage.…”

Section: Exosomal Mirnas In Breast Cancer Diagnosismentioning

confidence: 99%

Advances of Exosomal miRNAs in Breast Cancer Progression and Diagnosis

Chen

Deng

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Breast cancer is one of the most commonly diagnosed malignancies and the leading cause of cancer death in women worldwide. Although many factors associated with breast cancer have been identified, the definite etiology of breast cancer is still unclear. In addition, early diagnosis of breast cancer remains challenging. Exosomes are membrane-bound nanovesicles secreted by most types of cells and contain a series of biologically important molecules, such as lipids, proteins, and miRNAs, etc. Emerging evidence shows that exosomes can affect the status of cells by transmitting substances and messages among cells and are involved in various physiological and pathological processes. In breast cancer, exosomes play a significant role in breast tumorigenesis and progression through transfer miRNAs which can be potential biomarkers for early diagnosis of breast cancer. This review discusses the potential utility of exosomal miRNAs in breast cancer progression such as tumorigenesis, metastasis, immune regulation and drug resistance, and further in breast cancer diagnosis.

show abstract

A Review of Breast Imaging for Timely Diagnosis of Disease

Cited by 22 publications

References 85 publications

Improved Machine Learning-Based Predictive Models for Breast Cancer Diagnosis

Improved Machine Learning-Based Predictive Models for Breast Cancer Diagnosis

Utility of dual-energy contrast-enhanced spectral mammography for the diagnosis of multicentric breast cancer

Advances of Exosomal miRNAs in Breast Cancer Progression and Diagnosis

Contact Info

Product

Resources

About