scholarly journals Breast invasive ductal carcinoma classification on whole slide images with weakly-supervised and transfer learning

2021 ◽  
Author(s):  
Fahdi Kanavati ◽  
Masayuki Tsuneki
Keyword(s):  
Transfer Learning ◽  
Invasive Ductal Carcinoma ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Ductal Carcinoma ◽  
Benign Lesion ◽  
Classification Model ◽  
Histopathological Diagnosis ◽  
Core Needle ◽  
Weakly Supervised

Invasive ductal carcinoma (IDC) is the most common form of breast cancer. For the non-operative diagnosis of breast carcinoma, core needle biopsy has been widely used in recent years which allows evaluation of both cytologic and tissue architectural features; so that it can provide a definitive diagnosis between IDC and benign lesion (e.g., fibroadenoma). Histopathological diagnosis based on core needle biopsy specimens is currently the cost effective method; therefore, it is an area that could benefit from AI-based tools to aid pathologists in their pathological diagnosis workflows. In this paper, we trained an Invasive Ductal Carcinoma (IDC) Whole Slide Image (WSI) classification model using transfer learning and weakly-supervised learning. We evaluated the model on a core needle biopsy (n=522) test set as well as three surgical test sets (n=1,129) obtaining ROC AUCs in the range of 0.95-0.98.

scholarly journals Encapsulated Papillary Carcinoma of the Breast: Imaging Features with Histopathologic Correlation

2020 ◽  
Vol 2 (6) ◽  
pp. 590-597
Author(s):  
Sarah E Bonnet ◽  
Gloria J Carter ◽  
Wendie A Berg
Keyword(s):  
Papillary Carcinoma ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Breast Imaging ◽  
Ductal Carcinoma ◽  
Imaging Features ◽  
Term Survival ◽  
Core Needle ◽  
Cystic Component

Abstract Encapsulated papillary carcinoma (EPC) is a rare, clinically indolent breast malignancy most common in postmenopausal women. Absence of myoepithelial cells at the periphery is a characteristic feature. Mammographically, EPC typically presents as a mostly circumscribed, noncalcified, dense mass that can have focally indistinct margins when there is associated frank invasive carcinoma. Ultrasound shows a circumscribed solid or complex cystic and solid mass, and occasional hemorrhage in the cystic component may produce a fluid-debris level; the solid components typically show intense washout enhancement on MRI. Color Doppler may demonstrate a prominent vascular pedicle and blood flow within solid papillary fronds. Encapsulated papillary carcinoma can exist in pure form; however, EPC is often associated with conventional ductal carcinoma in-situ and/or invasive ductal carcinoma, no special type. Adjacent in-situ and invasive disease may be only focally present at the periphery of EPC and potentially unsampled at core-needle biopsy. In order to facilitate diagnosis, the mass wall should be included on core-needle biopsy, which will show absence of myoepithelial markers. Staging and prognosis are determined by any associated frankly invasive component, with usually excellent long-term survival and rare distant metastases.

scholarly journals Necessity of sentinel lymph node biopsy in ductal carcinoma in situ patients: a retrospective analysis

BMC Surgery ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Young Duck Shin ◽  
Hyung-Min Lee ◽  
Young Jin Choi
Keyword(s):  
Lymph Node ◽  
Sentinel Lymph Node ◽  
Lymph Node Metastasis ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Ductal Carcinoma ◽  
Invasive Cancer ◽  
Total Mastectomy ◽  
Core Needle ◽  
Node Metastasis

Abstract Background Sentinel lymph node biopsy (SLNB) is unnecessarily performed too often, owing to the high upstaging rates of ductal carcinoma in situ (DCIS). This study aimed to evaluate the upstaging rates of DCIS to invasive cancer, determine the prevalence of axillary lymph node metastasis, and identify the clinicopathological factors associated with upstaging and lymph node metastasis. We also examined surgical patterns among DCIS patients and determined whether SLNB guidelines were followed. Methods We retrospectively analysed 307 consecutive DCIS patients diagnosed by preoperative biopsy in a single centre between 2014 and 2018. Data from clinical records, including imaging studies, axillary and breast surgery types, and pathology results from preoperative and postoperative biopsies, were extracted. Univariate analyses using Chi-square tests and multiple logistic regression analyses were used to analyse the data. Results The rate of upstaging to invasive cancer was 19.2% (59/307). DCIS diagnosed by core-needle biopsy (odds ratio [OR]: 6.861, 95% confidence interval [CI]: 2.429–19.379), the presence of ultrasonic mass-forming lesions (OR: 2.782, 95% CI: 1.224–6.320), and progesterone receptor-negative status (OR: 3.156, 95% CI: 1.197–8.323) were found to be associated with upstaging. The rate of sentinel lymph node metastasis was only 1.9% (4/202), and all were total mastectomy patients diagnosed by core-needle biopsy. SLNB was performed in 37.2% of 145 breast-conserving surgery patients and 91.4% of 162 total mastectomy patients. Among the 202 patients who underwent SLNB, 145 (71.7%) without invasive cancer on final pathology had redundant SLNB. Two of 59 patients (3.4%) with disease upstaged to invasive cancer had inadequate primary staging of the axilla, as the rate seemed sufficiently small. Conclusions In patients with a preoperative diagnosis of DCIS, although an unavoidable possibility of upstaging to invasive cancer exists, axillary metastasis is unlikely. Only 2.7% of patients with DCIS undergoing total mastectomy were found to have sentinel lymph node metastases. SLNB should not be performed in breast-conserving surgery patients and should be reserved only for total mastectomy patients diagnosed by core-needle biopsy.

scholarly journals Histopathological spectrum of neoplastic and non-neoplastic breast lesions: A three years study in rural tertiary care center.

2020 ◽  
Vol 7 (01) ◽  
pp. 4721-4725
Author(s):  
Dr. Sanjeev Kumar Singh ◽  
Dr. Geeta Maurya ◽  
Dr. Pinki Pandey ◽  
Dr. Rashmi
Keyword(s):  
Invasive Ductal Carcinoma ◽  
Ductal Carcinoma ◽  
Care Center ◽  
Benign Lesion ◽  
Tertiary Care ◽  
Age Distribution ◽  
Morbidity And Mortality ◽  
Histopathological Diagnosis ◽  
Breast Lesions ◽  
Neoplastic Lesions

Background: Breast tumours are very common cause of morbidity and mortality worldwide specially in developing countries. Breast lesions show broad spectrum of disease patterns in respect to benign, malignant, and non-neoplastic. Breast cancer is one of the most frequently occurring cancer among women. Objective: To study the frequency, age distribution, clinical and histological patterns of neoplastic and non-neoplastic lesions of breast in this rural population. Material and methods: This observational study was conducted over a duration of three years. In which we studied 210 cases of breast lesions. Specimens were received in department of pathology. Grossing, tissue processing, staining done according to standard protocol. Haematoxylin and eosin (H&E) stained sections were examined under microscope to categorise different type of lesions in the form of non-neoplastic and neoplastic. Results:  Out of 210 breast lesions, fibroadenoma was the commonest (114 cases) benign lesion. While invasive ductal carcinoma (70 cases) was commonest in malignant category. Non neoplastic lesions stand on third place, study showed 6 cases out of 210 total cases, in which acute mastitis (4 cases) was most common. Benign tumours were mostly seen in 2nd and 3rd decade and malignant tumour mainly in 5th and 6th decade Conclusion: Early histopathological diagnosis of breast lesions is very important to differentiate between benign and malignant lesions. Large number of cases of invasive ductal carcinoma (>33% of all cases) were seen in our study, which is a serious concern. So, generation of awareness among women is need of time to reduce the morbidity and mortality specially in Indian rural setup

scholarly journals Ductal Carcinoma in situ after Core Needle Biopsy: In Which Cases Is a Sentinel Node Biopsy Necessary?

Breast Care ◽  
2019 ◽  
Vol 15 (3) ◽  
pp. 260-264
Author(s):  
Robbert J.H. van Leeuwen ◽  
Birgitta Kortmann ◽  
Herman Rijna
Keyword(s):  
Sentinel Node ◽  
Sentinel Node Biopsy ◽  
Ductal Carcinoma In Situ ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Carcinoma In Situ ◽  
Ductal Carcinoma ◽  
Core Needle ◽  
Node Biopsy

Introduction: In some hospitals it is still common practice to carry out a sentinel node biopsy (SNB) if ductal carcinoma in situ (DCIS) is determined in preoperative staging, although this is against international guidelines. The reason for this is because an infiltrative component can be demonstrated frequently in the final pathohistological examination. In this study, we wanted to investigate possible predictors for infiltrative growth, to select patients to do an SNB or to omit it. Material and Methods: All patients with DCIS in the core needle biopsy (CNB), who were treated with surgery including an SNB, were included in a prospective data registry. Patient characteristics were collected through physical examination, mammography and ultrasonography. All characteristics of the DCIS were noted. After surgery, the pathological results were collected. Results: From the 287 patients, 39 (13.6%) had an infiltrative component in the definitive pathological examination despite only DCIS in preoperative CNB. In total, there were only 14 (4.9%) positive SNBs, of which 11 patients had infiltrative growth in the breast tumor and 3 (1.2% of patients with DCIS alone in the final pathology) did not. In addition, characteristics of the CNB, including microcalcifications and comedonecrosis, did not show a statistically significant higher risk for infiltration. Discussion: Considering the low rates of positive SNBs in our population, we think that an SNB should not be performed in advance when DCIS is diagnosed, because if infiltrative growth is found in the final biopsy, an SNB could always be performed afterwards. Only if an SNB cannot be performed afterwards is an SNB indicated.

Ductal carcinoma in situ presenting as microcalcifications: the effect of stereotactic large-core needle biopsy on surgical therapy

The Breast ◽  
2004 ◽  
Vol 13 (6) ◽  
pp. 461-467 ◽  
Author(s):  
M.A.J. de Roos ◽  
R.M. Pijnappel ◽  
A.D. Groote ◽  
J. de Vries ◽  
W.J. Post ◽  
...  
Keyword(s):  
Surgical Therapy ◽  
Ductal Carcinoma In Situ ◽  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Carcinoma In Situ ◽  
Ductal Carcinoma ◽  
Large Core ◽  
Core Needle

Does 8-guage stereotactic core needle biopsy improve the accuracy over 11-gauge devices? Evaluation of pure DCIS on stereotactic biopsy and the rate of upstaging.

2014 ◽  
Vol 32 (26_suppl) ◽  
pp. 97-97
Author(s):  
Deepa R. Halaharvi ◽  
Mark H. Cripe
Keyword(s):  
Core Needle Biopsy ◽  
Needle Biopsy ◽  
Stereotactic Biopsy ◽  
Ductal Carcinoma ◽  
P Value ◽  
Breast Cancers ◽  
Surgical Biopsy ◽  
Core Needle ◽  
Stereotactic Core Needle Biopsy ◽  
Stereotactic Core

97 Background: Ductal carcinoma in situ (DCIS) accounts for 25% of newly diagnosed breast cancers. Core needle biopsy (CNB) has replaced open surgical biopsy for mammographic calcifications. We compare our experience with 8-gauge vs. 11-gauge vacuum assisted core needle biopsy in pure DCIS. We hypothesize that the diagnosis of DCIS with use of an 8-gauge vacuum-assisted core needle will lead to a lower rate of upstaging to invasive cancer at definitive surgical excision compared to 11-gauge vacuum-assisted core needle biopsy. Methods: A retrospective study was performed evaluating all patients who underwent a stereotactic core needle biopsy at our institution for DCIS during 2008-2012.We then compared the upstaging rates between patients biopsied using 8 or 11-gauge biopsy devices. Results: A total of 580 patients underwent STCNB during 2008-2012 at our institution, there were 461 patients excluded as they did not meet inclusion criteria and 119 patients were included. The most common mammographic finding was calcifications in 104/119 (87.4%) and a mammographic mass in 15/119 (12.60%). Biopsy with the 11 gauge needle was utilized in 60 patients and 59 patients with 8-G needle. Factors associated with upstaging were using a smaller 11 gauge needle and a mass on imaging, higher grade and more than four cores obtained on biopsy. There was an upstaging rate of 17/60 (28%) in patients who underwent stereotactic biopsy using a11-gauge needle versus upstaging rate of 7/59 (11.8%) in patients who underwent stereotactic biopsy using 8 gauge needle. We obtained a statistically significant p-value of 0.025. Conclusions: This is one of the few studies comparing upstaging rates from pure DCIS on STCNB using 8 and 11-gauge stereotactic vacuum assisted needles. Our results show that there is a statistically significant decrease in upstaging of pure DCIS to invasive malignancy at excision using the larger 8-gauge needle devices. The clinical implication is that SLNB need not be performed secondary to the low upstaging rate. We recommend that all stereotactic core needle biopsies be performed using the 8-gauge needle devices, and that SLNB generally be omitted for DCIS.

Sign in / Sign up

Export Citation Format

Share Document