MR Imaging of Mucinous Carcinoma of the Breast

Kawashima, Miho; Tamaki, Yasuhiro; Nonaka, Tetsuo; Higuchi, Keiko; Kimura, Morihiko; Koida, T; Yanagita, Yasuhiro; Sugihara, Shiro

doi:10.2214/ajr.179.1.1790179

Cited by 79 publications

(57 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kawashima and colleagues have reported high signal intensity on T2-weighted images and gradual enhancement pattern on dynamic MR imaging to be speciˆcˆndings of MU of the breast. 29 We suppose that high ADC may be an additional speciˆcˆnding for diagnosing MU. Compared to other cancers andˆbroadenoma, MU demonstrated lower cell density and higher extracellular water content, which re‰ected a mucin pool.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Apparent Diffusion Coefficients of Breast Tumors: Clinical Application

Hatakenaka

Soeda

Yabuuchi

et al. 2008

MRMS

216

176

View full text Add to dashboard Cite

Purpose: To evaluate the usefulness of apparent diŠusion coe‹cient (ADC) for the diŠerential diagnosis of breast tumors and to determine the relation between ADC and tumor cellularity.Materials and Methods: One hundred and thirty-six female patients (age range, 17-83 years; average age, 51.7 years) with 140 histologically proven breast tumors underwent diŠusion-weighted magnetic resonance (MR) imaging (DWI) using the spin-echo echo-planar technique, and the ADCs of the tumors were calculated using 3 diŠerent b values, 0, 500, and 1000 s/mm 2 . The diagnoses consisted ofˆbroadenoma (FA, n＝16), invasive ductal carcinoma, not otherwise speciˆed (IDC, n＝117), medullary carcinoma (ME, n＝3) and mucinous carcinoma (MU, n＝4). Tumor cellularity was calculated from surgical specimens. The ADCs of breast tumors and cellularity were compared between diŠerent histological types by analysis of variance and ScheŠe's post hoc test. The correlation between tumor cellularity and ADC was analyzed by Pearson correlation test.Results: Signiˆcant diŠerences were observed in ADCs between FA and all types of cancers (Pº0.05) and between MU and other types of cancers (Pº0.01) and in cellularity between FA and cancers except MU (Pº0.01) and between MU and other types of cancers (Pº0.01). There was an inverse correlation between ADC and tumor cellularity (Pº0.01, r 2 ＝0.451).Conclusions: The ADC may potentially help in diŠerentiating benign and malignant breast tumors. Tumor ADC correlates inversely with tumor cellularity.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Our study is limited because it includes only 4 cases of MU because MU is rare and comprises only one to 4z of primary breast malignancies. 29 Further study will be needed to clarify details.…”

Section: Discussionmentioning

confidence: 99%

Apparent Diffusion Coefficients of Breast Tumors: Clinical Application

Hatakenaka

Soeda

Yabuuchi

et al. 2008

MRMS

216

176

View full text Add to dashboard Cite

show abstract

“…Mucinous carcinoma typically shows gradual enhancement on dynamic contrast enhancement study. 12 In invasive ductal carcinoma with massive necrotic tumors or other metaplastic carcinomas, internal components with high signal intensity on T 2 images correspond to necrosis, cysts, or chondroid matrix and do not enhance in contrast study. Yuen's group reported that nonmucinous carcinomas with strong high signal intensity on T 2 -weighted images frequently showed washout phenomenon and rim enhancement, but there were no cases withˆbrous capsule showing expanding growth pattern.…”

Section: Discussionmentioning

confidence: 94%

Spindle Cell Carcinoma of the Breast: MR Findings Correlated with Histopathology

et al. 2011

View full text Add to dashboard Cite

We correlateˆndings from magnetic resonance (MR) imaging and pathology in a 55-year-old woman with spindle cell carcinoma of the breast. Pathological examination showed aˆbrous capsule at the margins and abundantˆbromyxoid stroma within the mass. Spindle cell carcinoma may be included in the diŠerential diagnosis of expanding round masses with internal components that demonstrate rapid initial enhancement with high signal intensity on T 2 -weighted images in postmenopausal women.

show abstract

“…Various studies suggest that high signal intensities in lesions on T2-w MRI cannot differentiate benign and malignant lesions [6,60,61,62,63,64,65,66]. However, numerous other studies indicate that the high signal intensity in lesions on T2-w MRI is distinctive in the discrimination between benign and malignant lesions [67,68,69,70,71,72]. Few other studies conclude that T2-w features are promising diagnostic features for the classification of benign and malignant lesions [73,74,75].…”

Section: Breast Mri Databasementioning

confidence: 99%

Multiple Instance Learning for Breast Cancer Magnetic Resonance Imaging

Maken

Gal

McClymont

et al. 2014

2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

View full text Add to dashboard Cite

In this thesis we evaluate the efficacy of multiple instance learning (MIL) as a 'pure' machine learning approach for the diagnosis of breast cancer in magnetic resonance images (MRI). The traditional approach for the diagnosis of breast cancer is based on region-of-interest (ROI) based single instance learning (SIL). In the ROI-based SIL, the classification of benign and malignant lesions depends on the features, which are extracted from segmented ROIs. But, an accurate segmentation of a ROI is a challenging task due to poor signal-to-noise-ratio and faint edges due to partial volume effects. Therefore, variations in the segmentation of ROIs can affect the diagnostic outcome. MIL is a relatively new method in the supervised learning, where each sample is represented as a bag of instances. An image in the context of MIL can be considered as a bag of pixels, tiles, or ROIs, which correspond to instances. Here we apply tile-based MIL, where the diagnosis of breast cancer is based on tile-based features which do not require the segmentation of ROIs. Therefore, tile-based MIL has the potential to provide the classification of breast cancer without segmenting the ROIs. This is the motivation for the main objective of this thesis: to estimate the efficacy of tile-based MIL in the detection and the diagnosis of breast cancer MRI.We initially evaluate the potential of MIL for the detection and the diagnosis of breast cancer in anatomical T2-weighted MRI. In particular, we compare the performance of a MIL-based learner, i.e., citation-kNN (CkNN) against conventional kNN and a Random Forest classifier. We utilise both (generic) tile-based spatial features and (domain specific) ROI-based features. We perform experiments on two datasets consisting of 77 mass-like lesions and 129 both mass-like and non-mass-like lesions. The performance of CkNN as both a diagnostic and screening tool is evaluated using the area under the receiver operating characteristic curve (AUC), estimated over 10-fold cross validation. Results demonstrate that the tile-based CkNN has equivalent performance to the ROI-based classification. However, tile-based MIL has an advantage that it does not require the domain specific ROI-based features typically used in breast MRI. This not only has the potential to make the tile-based classification robust to inaccuracies in the delineation of suspicious lesions, but also makes it suitable for the detection of suspicious lesions prior to segmentation.Next, we investigate the performance of CkNN for the diagnosis of breast cancer using dynamic MRI. Specifically we use generic tile-based spatio-temporal features derived from T2-weighted MRI and T1-weighted dynamic contrast enhanced MRI. We utilise a discrete cosine transform and contrast enhancement models as feature extraction techniques. We compare the III performance of CkNN and kNN against a traditional approach based on bespoke ROI-based features using the 77 mass-like lesions. Empirical results show the equivalent classification performance of both ti...

show abstract

MR Imaging of Mucinous Carcinoma of the Breast

Abstract: The MR imaging findings in mucinous carcinomas include dynamic curves of the gradually enhancing type and a very high signal intensity on T2-weighted images compared with other histologic types of invasive ductal carcinoma. These findings appear to be useful for diagnosis.

Cited by 79 publications

References 8 publications

Apparent Diffusion Coefficients of Breast Tumors: Clinical Application

Apparent Diffusion Coefficients of Breast Tumors: Clinical Application

Spindle Cell Carcinoma of the Breast: MR Findings Correlated with Histopathology

Multiple Instance Learning for Breast Cancer Magnetic Resonance Imaging

Contact Info

Product

Resources

About