Ultrasonographic features of ductal carcinoma in situ: analysis of 219 lesions

Li, Jun Kang; Wang, Huan Fan; He, Yan; Huang, Yong; Liu, Gang; Wang, Zhi Li

doi:10.21037/gs-20-428

Cited by 7 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, as far as we know, most DCIS lesions present as non- mass structures. Second, in terms of the disease itself, non-mass DCIS lesions have various structural patterns on ultrasound, have no clear boundaries, and have been described using various methods ( 14 - 17 , 60 , 61 ). For example, some lesions only show echogenic foci or duct dilations ( 60 , 61 ).…”

Section: Discussionmentioning

confidence: 99%

“…Second, in terms of the disease itself, non-mass DCIS lesions have various structural patterns on ultrasound, have no clear boundaries, and have been described using various methods ( 14 - 17 , 60 , 61 ). For example, some lesions only show echogenic foci or duct dilations ( 60 , 61 ). We used the DL method because it can reduce the deviation caused by manual feature extraction based on tumor heterogeneity, but it seems that clinical experience is more reliable.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ

Zhu,

Kuang,

Jiang

et al. 2024

Gland Surg

View full text Add to dashboard Cite

Background Low nuclear grade ductal carcinoma in situ (DCIS) patients can adopt proactive management strategies to avoid unnecessary surgical resection. Different personalized treatment modalities may be selected based on the expression status of molecular markers, which is also predictive of different outcomes and risks of recurrence. DCIS ultrasound findings are mostly non mass lesions, making it difficult to determine boundaries. Currently, studies have shown that models based on deep learning radiomics (DLR) have advantages in automatic recognition of tumor contours. Machine learning models based on clinical imaging features can explain the importance of imaging features. Methods The available ultrasound data of 349 patients with pure DCIS confirmed by surgical pathology [54 low nuclear grade, 175 positive estrogen receptor (ER+), 163 positive progesterone receptor (PR+), and 81 positive human epidermal growth factor receptor 2 (HER2+)] were collected. Radiologists extracted ultrasonographic features of DCIS lesions based on the 5 th Edition of Breast Imaging Reporting and Data System (BI-RADS). Patient age and BI-RADS characteristics were used to construct clinical machine learning (CML) models. The RadImageNet pretrained network was used for extracting radiomics features and as an input for DLR modeling. For training and validation datasets, 80% and 20% of the data, respectively, were used. Logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms were performed and compared for the final classification modeling. Each task used the area under the receiver operating characteristic curve (AUC) to evaluate the effectiveness of DLR and CML models. Results In the training dataset, low nuclear grade, ER+, PR+, and HER2+ DCIS lesions accounted for 19.20%, 65.12%, 61.21%, and 30.19%, respectively; the validation set, they consisted of 19.30%, 62.50%, 57.14%, and 30.91%, respectively. In the DLR models we developed, the best AUC values for identifying features were 0.633 for identifying low nuclear grade, completed by the XGBoost Classifier of ResNet50; 0.618 for identifying ER, completed by the RF Classifier of InceptionV3; 0.755 for identifying PR, completed by the XGBoost Classifier of InceptionV3; and 0.713 for identifying HER2, completed by the LR Classifier of ResNet50. The CML models had better performance than DLR in predicting low nuclear grade, ER+, PR+, and HER2+ DCIS lesions. The best AUC values by classification were as follows: for low nuclear grade by RF classification, AUC: 0.719; for ER+ by XGBoost classification, AUC: 0.761; for PR+ by XGBoost classification, AUC: 0.780; and for HER2+ by RF classification, AUC: 0.723. Conclusions Based on small-scale datasets, our study showed that the DLR models developed using RadImageNet pretrained network and CML models may help predict low nuclear grade, ER+, PR+...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ

Zhu,

Kuang,

Jiang

et al. 2024

Gland Surg

View full text Add to dashboard Cite

show abstract

“…Инвазивная протоковая карцинома представляет собой вид неинвазивного рака молочной железы, характеризующийся злокачественной пролиферацией эпителиальных клеток протоков МЖ, ограниченных системой протоков, без прорыва базальной мембраны в окружающую строму [8]. Относится к наиболее часто встречаемым первичным злокачественным новообразованиям МЖ [9].…”

Section: инвазивная протоковая инвазивная протоковая карцинома молочн...unclassified

Hyperechogenic Breast Malignant Formations: Modern Ultrasonic Diagnosis

Danzanova

Гудилина²,

Sinyukova³

et al. 2022

jour

View full text Add to dashboard Cite

show abstract

“…El carcinoma ductal in situ (CDIS) es la proliferación de células malignas en los conductos galactóforos, sin que extiendan más allá de la membrana basal 1,2 (Fig. 1).…”

Section: Introductionunclassified

“…Los factores de riesgo para CDIS son similares a los del cáncer de mama infiltrante, aumentando el riesgo con la edad, con incidencia máxima de 96.7 casos por 100,000 mujeres de 65 a 69 años, mayor cuando hay antecedentes familiares con cáncer de mama, nuliparidad y si la mujer si tiene 50 años o más. Existe una fuerte asociación entre el historial de biopsia mamaria y CDIS 1,2 . Es poco común en mujeres menores de 30 años.…”

Section: Introductionunclassified

Manifestaciones radiológicas del carcinoma ductal <i>in situ</i>. ¿Cómo lo diagnosticamos?

Domínguez-García,

Larios-Cruz,

Moguel-Molina

et al. 2023

ARM

View full text Add to dashboard Cite

Identificar los hallazgos radiológicos en sus diferentes modalidades de imagen del carcinoma ductal in situ (CDIS) de la mama. Material y métodos: Se hizo una búsqueda de información en PubMed con las palabras "breast" AND "ductal carcinoma in situ", eligiendo artículos de radiología para la obtención de información. Se realizó una búsqueda de imágenes radiológicas y reportes de patología del archivo clínico y radiológico digital del hospital. Resultados: Los hallazgos mastográficos del CDIS son microcalcificaciones en 80% de los casos, de tipo amorfas, pleomorfas, gruesas heterogéneas, finas ramificadas y finas lineales. El hallazgo más común por ultrasonido es el nódulo irregular, hipervascular, hipoecoico y sin sombra acústica posterior. En resonancia magnética y mastografía contrastada el hallazgo más frecuente es el realce no masa. Conclusiones: El CDIS es asintomático; el tamizaje es muy importante en su detección. La morfología, distribución y densidad de las microcalcificaciones sospechosas, motivan al radiólogo a solicitar imágenes adicionales, para categorizar el hallazgo y elegir el mejor método de guía de imagen para la realización de la biopsia.Palabras clave: Microcalcificaciones. BIRADS. Carcinoma ductal in situ (CDIS). Mamografía. HISTOPATOLOGÍALos patrones arquitectónicos son comedón, cribiforme, micropapilar, papilar y sólido 4 . Los CDIS micropapilar, cribiforme y papilar se consideran patrones de bajo grado. Los CDIS con características sólidas o de comedón se consideran patrones de alto grado y tiene más propensión a convertirse en carcinoma infiltrante 4 .El CDIS se clasifica en tres grados nucleares designados como bajo, intermedio o alto. El

show abstract

Ultrasonographic features of ductal carcinoma in situ: analysis of 219 lesions

Cited by 7 publications

References 42 publications

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ

Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ

Hyperechogenic Breast Malignant Formations: Modern Ultrasonic Diagnosis

Manifestaciones radiológicas del carcinoma ductal <i>in situ</i>. ¿Cómo lo diagnosticamos?

Contact Info

Product

Resources

About