Accuracy in tumor size measurements: Comparison of digital mammography, digital breast tomosynthesis and synthetic mammography

Şendur, Halit Nahit; Cerit, Mahi Nur; Gültekin, Serap; Cındıl, Emetullah; Aslan, Aydan Avdan; Erdal, Zeynep Sezgi; Gültekin, Işıl İmge; Teke, Furkan

doi:10.1016/j.clinimag.2020.07.004

Cited by 3 publications

(3 citation statements)

References 21 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mammograms are used to detect cancers at early stages either before or at the time of measuring density through compression and x-ray radiography. Digital Breast Tomosynthesis (DBT) provides the most accurate tumours size measurements among mammographic imaging techniques (7). Malignant growth in breast cells makes masses of tissue in each division like thickening of lumps, skin infuriation or curve in the vicinity of the breasts or underneath the arms, a change in size and breasts' form, a change in the color or texture of the areola or nipple of the breast which might be dimpled, scaly or puckered, nipple discharge, erosion, tenderness or inversion are breast cancer symptoms.…”

Section: Introductionmentioning

confidence: 99%

A Novel Transfer Learning Technique for Detecting Breast Cancer Mammograms Using VGG16 Bottleneck Feature

2022

View full text Add to dashboard Cite

Breast cancer represents the highest percentage of cancers and the second most common cancer overall that affect women with 87,090 deaths approximately as reported by ICMR, 2018 in India (1). Breast tumours are classified into two types as a) benign, which is not very harmful and would not cause breast cancer and b) malignant, the tumours are extremely dangerous and would form an abnormal cell that may cause cancer. One transfer learning model called VGG16 (Visual Geometry Group (16) has been implemented with a focus on breast cancer classification using mammography images taken from the MIAS dataset. Moreover, at the preprocessing step, all the breast images are enhanced by using CLAHE (Contrast Limited Adaptive Histogram Equalization) technique that specifically maintains adaptive techniques to remove the lines, letters, and other boxes irrelevant to the Breast Image. As the name suggests, this VGG16 has taken 13 convolutional layers and 3 fully connected layers to train the dataset. In the training period, this model could predict whether the breast images contain any type of cancerous cells or not. And finally, the model has successfully implemented and produced Network’s test score of 87.999 percent.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Transfer Learning Technique for Detecting Breast Cancer Mammograms Using VGG16 Bottleneck Feature

2022

View full text Add to dashboard Cite

show abstract

“…According to domestic statistics, >1.6 million individuals are diagnosed with breast cancer every year, and its morbidity shows an upward tendency year by year [1,2] . Several techniques have been applied for breast cancer diagnosis, mainly including molybdenum palladium X-ray, breast ultrasound, and breast magnetic resonance imaging (MRI) [3–7] . However, major defect of these techniques lies in their insufficiency in reaching pathological diagnosis, failing to determine the nature of the tumor [8] …”

Section: Introductionmentioning

confidence: 99%

“…[1,2] Several techniques have been applied for breast cancer diagnosis, mainly including molybdenum palladium X-ray, breast ultrasound, and breast magnetic resonance imaging (MRI). [3][4][5][6][7] However, major defect of these techniques lies in their insufficiency in reaching pathological diagnosis, failing to determine the nature of the tumor. [8] Core needle biopsy (CNB) is minimally invasive and intrusive, which could help doctors obtain sufficient breast tissues for pathological diagnosis without invasive surgery.…”

Section: Introductionmentioning

confidence: 99%

Comparison between core needle biopsy and excisional biopsy for breast neoplasm

et al. 2021

View full text Add to dashboard Cite

This study aimed to explore clinical significance of core needle biopsy (CNB) in pathological diagnosis of breast neoplasm. Seventy one breast neoplasm samples were obtained from Tongzhou Maternal and Child Health Hospital of Beijing between the years of 2006 and 2014. Forty five specimens were obtained via CNB and cases offering 26 of them received neoadjuvant chemotherapy. Pathology, histology, and immunohistochemistry results were compared between CNB specimens and excisional biopsy. Upward and downward tendencies could be observed in CNB specimens and excisional biopsy, respectively, in all items. Tumor proportion of CNB tissues was (33 + 2)/45 = 77.78%, when ductal carcinoma in situ detected by both CNB and excisional biopsy was 31/45 = 68.89%, with a consistency of (31 + 3)/45 = 75.56%. Tumor thrombus detected by both CNB and excisional biopsy was 2/45 = 4.44%. Among cases receiving neoadjuvant chemotherapy, CNB and excisional biopsy, in mitotic figure, cytological scoring and histological grading, showed a total change rate of >50% (50%–75%), while changes in duct and cellular heteromorphism were not distinct. Cases showing changes were up to 73.08%, with 8/26 = 30.77% for rise and 11/26 = 42.31% for descent. CNB could be used for preoperative diagnosis of breast neoplasm, and help to determine proper treatment regimen, thus elevating the rate of breast conserving. However, this method still has several limitations, particularly in immunohistochemical tests of human epidermal receptor protein-2. Neoadjuvant chemotherapy may influence the accuracy of CNB diagnosis.

show abstract