Cellular fibroadenoma versus phyllodes tumors: A pre‐operative diagnostic approach based on radiological and cytological features

Rana, Chanchal; Kamal, Nidhi; Mishra, Prabhakar; Singh, Akanksha; Ramakant, Pooja; Mishra, Anand; Singh, Kamleshwar

doi:10.1002/dc.24965

Cited by 2 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may explain the improved performance after including age in the ResNet model. Tumor size is one of the key factors that must be considered in the differential diagnosis of PTs and FAs [10,20,32,33]. In accordance with previous studies, we found that PTs are usually larger than FAs in tumor size.…”

Section: Discussionsupporting

confidence: 91%

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians

Shi

et al. 2023

Sensors

View full text Add to dashboard Cite

The preoperative differentiation of breast phyllodes tumors (PTs) from fibroadenomas (FAs) plays a critical role in identifying an appropriate surgical treatment. Although several imaging modalities are available, reliable differentiation between PT and FA remains a great challenge for radiologists in clinical work. Artificial intelligence (AI)-assisted diagnosis has shown promise in distinguishing PT from FA. However, a very small sample size was adopted in previous studies. In this work, we retrospectively enrolled 656 breast tumors (372 FAs and 284 PTs) with 1945 ultrasound images in total. Two experienced ultrasound physicians independently evaluated the ultrasound images. Meanwhile, three deep-learning models (i.e., ResNet, VGG, and GoogLeNet) were applied to classify FAs and PTs. The robustness of the models was evaluated by fivefold cross validation. The performance of each model was assessed by using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were also calculated. Among the three models, the ResNet model yielded the highest AUC value, of 0.91, with an accuracy value of 95.3%, a sensitivity value of 96.2%, and a specificity value of 94.7% in the testing data set. In contrast, the two physicians yielded an average AUC value of 0.69, an accuracy value of 70.7%, a sensitivity value of 54.4%, and a specificity value of 53.2%. Our findings indicate that the diagnostic performance of deep learning is better than that of physicians in the distinction of PTs from FAs. This further suggests that AI is a valuable tool for aiding clinical diagnosis, thereby advancing precision therapy.

show abstract

Section: Discussionsupporting

confidence: 91%

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians

Shi

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Much of the debate involving phyllodes tumors is focused on preoperative diagnosis, probability of recurrence, and adjuvant therapy after surgical excision has been performed depending on the classification of the tumor. Due to the numerous histological similarities between phyllodes tumors and cellular fibroadenomas which both display increased stromal cellularity, it can be difficult to distinguish between the two through fine needle aspiration or core needle biopsy alone [ 5 , 7 ]. The ability to distinguish between these two tumors preoperatively can not only aid in the intraoperative planning for determining proper excisional margins and management of the axilla but can also help to prevent overtreatment or undertreatment of the patient [ 4 , 5 ].…”

Section: Discussionmentioning

confidence: 99%

“…Due to the numerous histological similarities between phyllodes tumors and cellular fibroadenomas which both display increased stromal cellularity, it can be difficult to distinguish between the two through fine needle aspiration or core needle biopsy alone [ 5 , 7 ]. The ability to distinguish between these two tumors preoperatively can not only aid in the intraoperative planning for determining proper excisional margins and management of the axilla but can also help to prevent overtreatment or undertreatment of the patient [ 4 , 5 ]. Wide surgical margins of at least 1 cm were originally thought to be optimal for local control [ 3 , 6 , 7 ].…”

Section: Discussionmentioning

confidence: 99%

“…Phyllodes tumors are a rare type of fibroepithelial neoplasms of the breast typically occurring in women of ages 35-55 years, and accounting for approximately 0.3-0.9% of all primary breast neoplasms [1][2][3][4][5][6][7]. Phyllodes tumors and fibroadenomas are both included in the category of biphasic fibroepithelial lesions of the breast; fibroadenomas are far more common in clinical practice and constitute the majority of benign breast masses in younger women [2,[7][8][9].…”

Section: Introductionmentioning

confidence: 99%

“…Diagnosis is typically made with a core needle biopsy. Due to the numerous similarities between cellular fibroadenomas and phyllodes tumors, determination may be difficult without excision of the mass [ 5 ]. Core biopsy is typically followed by surgical resection with clear margins to minimize the likelihood of recurrence [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Giant Phyllodes Tumor in an 82-Year-Old Female Initially Diagnosed a Fibroadenoma: A Case Report

Hefelfinger¹,

Hefelfinger²,

Hernandez³

2022

Cureus

View full text Add to dashboard Cite

Phyllodes tumors are a rare fibroepithelial neoplasm of the breast occurring in approximately 2.1 in every 1 million women with no clear predilection for women of specific races. They are characterized by spindleshaped stromal cells with increased stromal cellularity and increased mitotic activity. The histologic characteristics are similar to that of cellular fibroadenomas making them frequently difficult to differentiate on core biopsy. We present a case of an 82-year-old female with a right breast mass which was initially diagnosed as a fibroadenoma in 2009. She was lost to follow-up and presented in 2021 with complaint of a right breast mass for which diagnostic imaging was performed. A diagnostic mammogram demonstrated a macrolobulated mass measuring 14×12×12 cm which corresponded to the palpable abnormality. The patient subsequently underwent simple mastectomy demonstrating a 14 cm mass with a fibroepithelial structure consistent with a borderline phyllodes tumor. The patient received adjuvant radiotherapy to minimize the likelihood of local recurrence. We concluded that reliable preoperative diagnosis and further studies regarding guidelines for adequate tumor margins and indication for adjuvant radiotherapy are crucial for proper surgical planning and follow-up after excision.

show abstract

Cellular fibroadenoma versus phyllodes tumors: A pre‐operative diagnostic approach based on radiological and cytological features

Cited by 2 publications

References 32 publications

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians

Giant Phyllodes Tumor in an 82-Year-Old Female Initially Diagnosed a Fibroadenoma: A Case Report

Contact Info

Product

Resources

About