StackBC: Deep learning and transfer learning techniques based stacking approach for accurate Invasive Ductal Carcinoma classification using histology images

Artificial intelligence (AI) based computer-aided diagnostic (CAD) systems can effectively diagnose critical disease. AI-based detection of breast cancer (BC) through images data is more efficient and accurate than professional radiologists. However, the existing AI-based BC diagnosis methods have complexity in low prediction accuracy and high computation time. Due to these reasons, medical professionals are not employing the current proposed techniques in E-Healthcare to effectively diagnose the BC. To diagnose the breast cancer effectively need to incorporate advanced AI techniques based methods in diagnosis process. In this work, we proposed a deep learning based diagnosis method (StackBC) to detect breast cancer in the early stage for effective treatment and recovery. In particular, we have incorporated deep learning models including Convolutional neural network (CNN), Long short term memory (LSTM), and Gated recurrent unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, data augmentation and transfer learning techniques have been incorporated for data set balancing and for effective training the model. To further improve the predictive performance of model we used stacking technique. Among the three base classifiers (CNN, LSTM, GRU) the predictive performance of GRU are better as compared to individual model. The GRU is selected as a meta classifier to distinguish between Non-IDC and IDC breast images. The method Hold-Out has been incorporated and the data set is split into 90% and 10% for training and testing of the model, respectively. Model evaluation metrics have been computed for model performance evaluation. To analyze the efficacy of the model, we have used breast histology images data set. Our experimental results demonstrated that the proposed StackBC method achieved improved performance by gaining 99.02% accuracy and 100% area under the receiver operating characteristics curve (AUC-ROC) compared to state-of-the-art methods. Due to the high performance of the proposed method, we recommend it for early recognition of breast cancer in E-Healthcare.

Classification and enhancement of invasive ductal carcinoma samples using convolutional neural networks

In the medical area, the detection of invasive ductal carcinoma is the most common sub-type of all breast cancers; about 80% of all breast cancers are invasive ductal carcinomas. Detection of this type of cancer shows a great challenge for specialist doctors since the digital images of the sample must be analyzed by sections because the spatial dimensions of this kind of image are above 50k × 50k pixels; doing this operation manually takes long time to determine if the patient suffers this type of cancer. Time is essential for the patient because this cancer can invade quickly other parts of the body. Its name reaffirms this characteristic, with the term "invasive" forming part of its name. With the purpose of solving this task, we propose an automatic methodology consisting in improving the performance of a convolutional neural network that classifies images containing invasive ductal carcinoma cells by highlighting cancer cells using several preprocessing methods such as histogram stretching and contrast enhancement. In this way, characteristics of the sub-images are extracted from the panoramic sample and it is possible to learn to classify them in a better way.

Hematotoxicity and functional impacts related to chemotherapy with doxorubicin and cyclophosphamide for invasive ductal breast carcinoma: a study in clinical records

Objective: To evaluate the occurrence of hematological and functional toxicities during chemotherapy with doxorubicin and cyclophosphamide in women with breast invasive ductal carcinoma. Methods: This was a descriptive, cross-sectional and quantitative study, involving the data collection in clinical records of 119 women undergoing chemotherapy for breast invasive ductal carcinoma in an oncology outpatient clinic, carried out between February 2014 and February 2015. Results: The investigated toxicities and their respectively occurrences in patients exposed to doxorubicin and cyclophosphamide were hemoglobinemia (26,5%), leukopenia (21,6%), neutropenia (10,8%), thrombocytopenia (none) and reduced hematocrit (28,4%), in addition to fatigue (93,1%), fever (20,6%), gain (35,3%) and weight loss (22,5%). In these variables, there were no significant differences between the exposed and not exposed patients. The association with taxanes showed a significant reduction in hematocrit values (p=0.019) and the toxicities distributed by age group were not significant within the exposed group. Conclusions: Exposure to doxorubicin and cyclophosphamide was not associated with an increase in the occurrence of hematotoxicities and functional impacts in women with breast ductal invasive carcinoma, except when associated with taxane agents.

The incidence of discordant clinical and genomic risk in patients with invasive lobular or ductal carcinoma of the breast: a National Cancer Database Study

When molecular testing classifies breast tumors as low risk but clinical risk is high, the optimal management strategy is unknown. One group of patients who may be more likely to have such discordant risk are those with invasive lobular carcinoma of the breast. We sought to examine whether patients with invasive lobular carcinoma are more likely to have clinical high/genomic low-risk tumors compared to those with invasive ductal carcinoma, and to evaluate the impact on receipt of chemotherapy and overall survival. We conducted a cohort study using the National Cancer Database from 2010–2016. Patients with hormone receptor positive, HER2 negative, stage I-III breast cancer who underwent 70-gene signature testing were included. We evaluated the proportion of patients with discordant clinical and genomic risk by histology using Kaplan-Meier plots, log-rank tests, and Cox proportional hazards models with and without propensity score matching. A total of 7399 patients (1497 with invasive lobular carcinoma [20.2%]) were identified. Patients with invasive lobular carcinoma were significantly more likely to fall into a discordant risk category compared to those with invasive ductal carcinoma (46.8% versus 37.1%, p < 0.001), especially in the clinical high/genomic low risk subgroup (35.6% versus 19.2%, p < 0.001). In unadjusted analysis of the clinical high/genomic low-risk cohort who received chemotherapy, invasive ductal carcinoma patients had significantly improved overall survival compared to those with invasive lobular carcinoma (p = 0.02). These findings suggest that current tools for stratifying clinical and genomic risk could be improved for those with invasive lobular carcinoma to better tailor treatment selection.

Trastuzumab in the Treatment of Invasive Ductal Carcinoma of the Breast Induces Severe Edema: A Case Report

BackgroundTrastuzumab, a monoclonal antibody which binds to the extracellular domain of HER2, is the first biological drug approved for the treatment of HER2-positive breast cancer. However, trastuzumab exhibits a series of adverse reactions in clinic, including cardiac toxicity, nerve damage, mild edema, abnormal liver function, thrombocytopenia, etc.Case presentationWe reported an invasive ductal carcinoma of the breast patient with single dose trastuzumab treatment developed a rare severe edema in patient’s neck, face, chest, abdomen, and both upper limbs. One month after trastuzumab administration, the patient was given methylprednisone (80 mg/day) for 5 days. The edema in patient’s neck, face and both upper limbs was mildly reduced compared with before, but patient’s CT image showed no significant reduction of edema.ConclusionTrastuzumab has an adverse reaction of edema, but this severe edema is extremely rare. It is important to increase awareness of serious adverse reactions among oncologist, and treat such serious adverse reactions at an early stage may reduce further damage.

Invasive Lobular Carcinoma Has Worse Outcome Compared with Invasive Ductal Carcinoma in Stage IV Breast Cancer with Bone-Only Metastasis

Background: Invasive lobular carcinoma (ILC) is more likely to be bone metastasis than invasive ductal carcinoma (IDC). However, the prognosis for bone metastasis in ILC and IDC is barely known. So, the aim of this study was to investigate the difference of prognosis between ILC and IDC accompany by bone metastasis. Methods: We evaluated the women with bone-only metastasis of defined IDC or ILC, reported to the Surveillance, Epidemiology and End Results program from 2010 to 2016. Pearson's chi-squared test was used to compare the difference of clinicopathologic factors between IDC and ILC. Univariate and multivariate analyses were performed to verify the effects of histological types (IDC and ILC) and other clinicopathologic factors on the overall survival (OS) and cancer-special survival (CSS). Results: Overall, 3647 patients with IDC and 945 patients with ILC met the inclusion criteria and were analyzed in our study. The patients with ILC were more likely to be older, lower histological grade and higher proportion of HR+/HER2- subtype. But less treatment was applied to ILC than IDC, such as surgery of the breast, radiation and chemotherapy. Compared patients with IDC, the patients with ILC showed worse OS (median OS 36 and 42 months respectively, p<0.001) and CSS (median CSS 39 and 45 months respectively, p<0.001), especially in subgroups with HR+/HER2- subtype [OS (Hazard ration: 1.501, 95% CI [1.270-1.773], p<0.001); CSS (Hazard ration: 1.529, 95% CI [1.281-1.825], p<0.001)], lower histological grade (Ⅰ-Ⅱ) [OS (Hazard ration: 1.411, 95% CI [1.184-1.683], p<0.001); CSS (Hazard ration: 1.488, 95% CI [1.235-1.791], p<0.001)] or tumor burden, such as T0-2 [OS (Hazard ration: 1.693, 95% CI [1.368-2.096], p<0.001); CSS (Hazard ration: 1.76, 95% CI [1.405-2.205], p<0.001)] and N1-2 [OS (Hazard ration: 1.451, 95% CI [1.171-1.799], p=0.001); CSS (Hazard ration: 1.488, 95% CI [1.187-1.865], p=0.001)]. Furthermore, older age, black race, unmarried status, higher tumor burden (T3-4 and N3), triple-negative subtype and higher histological grade were independent risk factors for both OS and CSS. Surgery of the breast and chemotherapy could significantly improve the prognosis for patients. Conclusion: The patients with ILC have worse outcomes compared with that of IDC when bone-only metastasis occurred to them, especially in subgroups with lower histological grade or tumor burden. More effective treatment measures may be needed for ILC, such as cyclin-dependent kinase 4/6 inhibitors (CDKs), new targeted drugs, etc.

Synchronous Invasive Breast Carcinoma, Endometrial Cancer and Small Lymphocytic Lymphoma in a 49 Year-old Female Libyan Patient: Case Report and Literature Review

Although breast cancer and endometrial cancer are two frequent female cancers, finding synchronous primary cancers in the same patient is a comparatively uncommon occurrence. We present the case of a Libyan woman who developed synchronous breast cancer, endometrial cancer, and small lymphocytic lymphoma. For the previous six months, a 49-year-old female patient had a right breast mass. An ultrasound scan revealed an uneven doubtful growth in the right breast as well as swollen of the axillary lymph nodes. After a wide local excision, histopathology revealed that the patient had invasive ductal carcinoma of the breast with a positive resection margin, and he was admitted to the Surgery Department. No distal metastasis was seen on a computed tomography (CT) scan of the chest, abdomen, or pelvis, so the patient had a right mastectomy and axillary clearance. Residual invasive ductal carcinoma was found on histopathology and immunohistochemistry with positivity for the estrogen receptor and the progesterone receptor. Small lymphocytic lymphoma (SLL) affected the axillary lymph nodes, affirmed by immunohistochemical staining positive for CD20, CD5, CD23 and BCL-2 while negative for CD3 and Cyclin D1. Resection margins were free. Second cancers are characterized by being linked to SCL, and some researchers have described that the risk of second cancers is elevated in SCL patients. We represent a combined case of synchronous primary SCL with breast cancer and endometrial cancer in a woman which is a rare occurrence.