Phyllodes Tumor of the Breast: Correlation between MR Findings and Histologic Grade

Yabuuchi, Hidetake; Soeda, Hiroyasu; Matsuo, Yoshio; Okafuji, Takashi; Eguchi, Takashi; Sakai, Shuji; Kuroki, Shin-Ichiro; Tokunaga, Eriko; Ohno, Shinji; Nishiyama, Kenichi; Hatakenaka, Masamitsu; Honda, Hiroshi

doi:10.1148/radiol.2413051470

Cited by 106 publications

(76 citation statements)

References 13 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, GS correlates somewhat with the degree of tumor cellularity. In recent years it has been reported that ADC values are correlated with histological grade in various malignant tumors, with high-grade tumors tending to show low ADC values (7)(8)(9). It has been suggested that, in dense cellular tissue, reduced extracellular space may restrict the movement of water molecules, resulting in decreased ADC values.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, the apparent diffusion coefficient (ADC) value has been reported to correlate with histological grade for various malignant tumors (7)(8)(9). In prostate cancer, Zakian et al (10) reported a correlation between proton magnetic resonance imaging (MRI) spectroscopic imaging and GS, while Wang et al (11) reported a correlation between MR signal intensity and GS.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Clinical utility of apparent diffusion coefficient (ADC) values in patients with prostate cancer: Can ADC values contribute to assess the aggressiveness of prostate cancer?

Itou

Nakanishi

Narumi

et al. 2010

Magnetic Resonance Imaging

109

View full text Add to dashboard Cite

Purpose: To retrospectively evaluate the relationship between apparent diffusion coefficient (ADC) values and Gleason score (GS) in prostate cancer.Methods: A total of 60 patients who underwent radical prostatectomy for clinically localized prostate cancer were selected for this study. Diffusion-weighted magnetic resonance (MR) images were obtained using a 1.5 T system. ADC values were analyzed between three groups: GS of 6 or less (n ¼ 7); GS of 7 (n ¼ 37); and GS of 8 or higher (n ¼ 16). ADC values of the three GS groups were statistically analyzed in order to determine the relationship with GS. In the 37 patients with GS ¼ 7 the difference in ADC values between GS 3þ4 and GS 4þ3 was analyzed. Results: Median ADC values (10À3 mm 2 /s) of the three GS groups were 1.04 (GS ¼ 6 or less), 0.867 (GS ¼ 7), and 0.729 (GS ¼ 8 or higher). Although there was considerable overlap among the groups, the differences in ADC were statistically significant (P < 0.0001). There was a significant inverse correlation between GS and ADC values (z ¼ À0.437, P < 0.0005). Median ADC values (10 À3 mm 2 /s) of GS 3þ4 and GS 4þ3 patients were 0.88 and 0.814, respectively (P < 0.05). Conclusion: ADC values showed a negative correlation with GS. Pathologically, however, there was considerable intrasubject heterogeneity.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Clinical utility of apparent diffusion coefficient (ADC) values in patients with prostate cancer: Can ADC values contribute to assess the aggressiveness of prostate cancer?

Itou

Nakanishi

Narumi

et al. 2010

Magnetic Resonance Imaging

109

View full text Add to dashboard Cite

show abstract

“…On MRI, these tumours usually show heterogeneous non-enhancing areas reflecting haemorrhagic necrosis in the centre of the mass with a thick enhancing wall. The contrast-enhancing pattern on dynamic MRI tends to show rapid wash-in/wash-out as a typical malignant pattern in these breast tumours [4][5][6][7].…”

Section: Discussionmentioning

confidence: 97%

“…All these tumours have highgrade malignant potential and show active tumour cell proliferation. Therefore, these tumours may contain haemorrhage reflecting internal haemorrhagic necrosis [4][5][6]. On MRI, these tumours usually show heterogeneous non-enhancing areas reflecting haemorrhagic necrosis in the centre of the mass with a thick enhancing wall.…”

Section: Discussionmentioning

confidence: 99%

Post-traumatic rapidly enlarging mucinous carcinoma of the breast with intratumoural haemorrhage: MRI appearances with pathological correlation

Tsuji

Goto²,

Yuen³

et al. 2011

BJR

View full text Add to dashboard Cite

ABSTRACT. Pure mucinous carcinoma of the breast is a histological type of invasive carcinoma and generally shows a slow growth pattern. Rapid growth and intratumoural haemorrhage are rare and there have been no reports presenting such a clinical course and associated radiographic findings. We report a case with atypical rapidly enlarging mucinous carcinoma of the breast after trauma, in which MRI closely reflected the histopathological background and was thought to be useful for differential diagnosis from other highly malignant breast tumours.

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

Phyllodes Tumor of the Breast: Correlation between MR Findings and Histologic Grade

Abstract: Several MR findings can be used to help determine the histologic grade of phyllodes breast tumors.

Cited by 106 publications

References 13 publications

Clinical utility of apparent diffusion coefficient (ADC) values in patients with prostate cancer: Can ADC values contribute to assess the aggressiveness of prostate cancer?

Clinical utility of apparent diffusion coefficient (ADC) values in patients with prostate cancer: Can ADC values contribute to assess the aggressiveness of prostate cancer?

Post-traumatic rapidly enlarging mucinous carcinoma of the breast with intratumoural haemorrhage: MRI appearances with pathological correlation

Multiple Instance Learning for Breast Cancer Magnetic Resonance Imaging

Contact Info

Product

Resources

About