scholarly journals End-to-End Deep Learning for Detecting Metastatic Breast Cancer in Axillary Lymph Node from Digital Pathology Images

2021 ◽  
pp. 343-353
Author(s):  
Turki Turki ◽  
Anmar Al-Sharif ◽  
Y-h. Taguchi
2021 ◽  
Author(s):  
Turki Turki ◽  
Anmar Al-Sharif ◽  
Y-h. Taguchi

Metastatic breast cancer is one of the attributed leading causes of women deaths worldwide. Accurate diagnosis to the spread of breast cancer to axillary lymph nodes (ALNs) is done by breast pathologist, utilizing the microscope to inspect and then providing the biopsy report. Because such a diagnosis process requires special expertise, there is a need for artificial intelligence-based tools to assist breast pathologists to automatically detect breast cancer metastases. This study aims to detect breast cancer metastasized to ALN with end-to-end deep learning (DL). Also, we utilize several DL architectures, including DenseNet121, ResNet50, VGG16, Xception as well as a customized lightweight convolutional neural network. We evaluate the DL models on NVIDIA GeForce RTX 2080Ti GPU using 114 processed microscopic images pertaining to ALN metastases in breast cancer patients. Compared to all DL models employed in this study, experimental results show that DenseNet121 generates the highest performance results (64-68%) based on AUC and accuracy.


2015 ◽  
Vol 34 (6) ◽  
pp. 1131-1137 ◽  
Author(s):  
Tomoyuki Ohta ◽  
Makiko Nishioka ◽  
Norio Nakata ◽  
Kunihiko Fukuda ◽  
Kumiko Kato

2021 ◽  
pp. 1608-1615
Author(s):  
Ana S. Acostamadiedo Marx ◽  
Camilo Andrés Avendaño-Capriles ◽  
Julio A. Lemos ◽  
Eric Gorman ◽  
Jose M. Acostamadiedo

To our knowledge, this is the first case reported in the English literature of simultaneous occult male metastatic breast cancer presenting as pulmonary nodules and right axillary lymph node metastasis in a chronic lymphocytic leukemia (CLL) patient and is the second case of simultaneous male breast cancer and CLL reported. The first case was reported by Dubashi et al. [Curr Oncol. 2011;18(2):e101–2] in 2011. This unique clinical and pathological entity presents various challenges in its management, including early detection, screening, and treatment.


2018 ◽  
Vol 64 (1) ◽  
pp. 45-53
Author(s):  
Juliana Cunha e Silva Ominelli De Souza ◽  
Andrew Sá Nunes ◽  
Jesse Lopes Da Silva ◽  
Aline Coelho Gonçalves ◽  
Suzanne Crocamo Ventilari Da Costa

Introduction: Breast cancer is the leading cause of cancer-related deaths in women aged 20-59 years. Younger women usually have more aggressive tumors and more advanced disease with larger size and axillary lymph node involvement. There have been few studies assessing the characteristics of breast cancer in very young women. Objective: Evaluate the epidemiological and clinical profile of non-metastatic very young patients with breast cancer. Method: We performed a retrospective analysis to evaluate the epidemiological and clinical profile of non-metastatic breast cancer in patients ≤ 30 years of age treated between 1993 and 2011 at the Brazilian National Cancer Institute José Alencar Gomes da Silva. We evaluated relapse-free survival (RFS) and overall survival (OS). Results: Of the 196 patients evaluated, 181 (90%) had ductal carcinoma, 79 (40%) had high-grade tumors, and 102 (52%) had hormone receptor-positive tumors. 117 patients(60%) had stage III disease at diagnosis. The median age was 29 years (range, 17-30 years). Of 185 patients who underwent surgery, 156 (84.3%) underwent total mastectomy and 171 (92%) underwent axillary lymph node dissection. 119 patients received neoadjuvant chemotherapy, and 14 patients (9.3%) underwent neoadjuvant radiotherapy. After a median follow-up of 81.5 months, 109 patients (55%) had relapsed and 81 (41%) had died. The median RFS and OS were 49.5 months and 134 months, respectively. Lymph node involvement and neoadjuvant chemotherapy were associated with shorter RFS and OS. Conclusion: Breast cancer is uncommon in young patients, especially in those ≤ 30 years of age. We found a predominance of locally advanced disease and worse prognostic pathological characteristics. Despite the aggressive treatment, our patients had worse outcomes than those reported by other authors.


Sign in / Sign up

Export Citation Format

Share Document