Classification of breast cancer types, sub-types and grade from histopathological images using deep learning technique

AbstractBreast cancer is an invasive tumor that develops in the breast tissue. It is the most common cancer and also the leading cause of cancer mortality among women worldwide. Survival from breast cancer can be increased through advances in screening methods and early diagnosis. Clinical examination, screening using imaging modalities and pathological assessment (biopsy test) are common methods of breast cancer diagnosis. Among these, pathological assessment is a gold standard due to its potential in identifying the cancer type, sub-type and stage. However, current diagnosis using this pathological assessment technique is commonly done through visual inspection microscopic images. This procedure is time consuming, tedious and subjective which may lead to misdiagnosis. In this paper, a multi-class classification system for breast cancer type, sub-type and grade is proposed based on deep learning technique. The system was trained and validated using histopathological images acquired from Jimma University Medical Center (JUMC) using digital camera (Optikam PRO5) mounted on Optika microscope by four levels of magnification (40x, 100x, 200x, 400x), and also from ‘BreakHis’ and ‘zendo’ online datasets. All images were pre-processed and enhanced prior to feeding to the ResNet 50 pre-trained model. The developed system is capable of classifying breast cancer into binary classes (benign and malignant) and multi-classes (sub-types). Identification of can cer g...
Source: Health and Technology - Category: Information Technology Source Type: research

Related Links:

J Oncol. 2021 Oct 8;2021:9657071. doi: 10.1155/2021/9657071. eCollection 2021.ABSTRACTBreast cancer is a heterogeneous disease in which genetic factors are involved in disease worsening and higher mortality. Epidemiological and clinical research revealed that breast cancer incidence continues to rise. 100 histopathologically confirmed untreated newly diagnosed cases of invasive ductal carcinoma (IDC) of breast and 100 healthy subjects were involved and blood samples were collected in non-EDTA plain vials. Serum was separated by centrifugation, total RNA was extracted from serum, and cDNA synthesis was done to study the miR...
Source: Journal of Oncology - Category: Cancer & Oncology Authors: Source Type: research
Bull Cancer. 2021 Oct 13:S0007-4551(21)00363-5. doi: 10.1016/j.bulcan.2021.06.017. Online ahead of print.ABSTRACTThe surgical management of breast cancer has been marked by a therapeutic de-escalation from radical surgery to breast conservation and from axillary curage to sentinel lymph node sampling. With regard to breast surgery, the de-escalation of treatment has been largely due to organized screening, which has made it possible to diagnose tumors of smaller volume or at an earlier stage. The indications for conservative surgery have been broadened by the addition of radiotherapy on one hand, and the introduction of ad...
Source: Bulletin du Cancer - Category: Cancer & Oncology Authors: Source Type: research
CONCLUSION: RSL is rapidly replacing WGL as the preoperative localization technique in breast surgery. This large nationwide registry study found no association between the type of localization technique and the odds of having a reoperation, thus confirming the results of previous prospective cohort studies.PMID:34642736 | DOI:10.1093/bjs/znab339
Source: The British Journal of Surgery - Category: Surgery Authors: Source Type: research
CONCLUSION: Several imaging features were shown to be independent variables predicting molecular subtypes of BC. Knowledge of such correlations could help clinicians stratify BC patients, possibly enabling earlier treatment or aiding in therapeutic decisions in countries where receptor testing is not readily available.PMID:34631444 | PMC:PMC8479344 | DOI:10.5306/wjco.v12.i9.808
Source: Clinical Breast Cancer - Category: Cancer & Oncology Authors: Source Type: research
Conclusions: This study proposed an integrative approach for the identification of candidate genes for risk assessment of overall survival in these patients through typical survival analysis methods. The 14 candidate genes selected are particularly involved in cell-cycle processes, deoxyribonucleic acid repair, and drug resistance; their mutations were found to be generally associated with disease progression or therapeutic resistance, which is commonly associated with poor overall survival outcomes in IDC.Public Health Genomics
Source: Public Health Genomics - Category: Genetics & Stem Cells Source Type: research
Int J Clin Oncol. 2021 Oct 7. doi: 10.1007/s10147-021-02036-1. Online ahead of print.ABSTRACTPURPOSE: Trials for DCIS have not explored whether outcomes for patients with large disease burden requiring mastectomy are comparable to those of patients with lumpectomy-amenable disease. We aim to identify whether patients with DCIS larger than 5 cm and diffuse-type DCIS differ in breast cancer mortality (BCM) from patients with disease less than 5 cm.METHODS: Patients diagnosed with DCIS in the SEER program were assessed to identify factors prognostic of breast-cancer-specific survival using competing risks regression.RESULTS: ...
Source: Clinical Breast Cancer - Category: Cancer & Oncology Authors: Source Type: research
AbstractPurposeTrials for  DCIS have not explored whether outcomes for patients with large disease burden requiring mastectomy are comparable to those of patients with lumpectomy-amenable disease. We aim to identify whether patients with DCIS larger than 5 cm and diffuse-type DCIS differ in breast cancer mortality (BCM)  from patients with disease less than 5 cm.MethodsPatients diagnosed with DCIS in the SEER program were assessed to identify factors prognostic of breast-cancer-specific survival using competing risks regression.Results44,849 patients met criteria for the cumulative incidence e...
Source: International Journal of Clinical Oncology - Category: Cancer & Oncology Source Type: research
J Clin Oncol. 2021 Oct 6:JCO2101896. doi: 10.1200/JCO.21.01896. Online ahead of print.ABSTRACTThe Oncology Grand Rounds series is designed to place original reports published in the Journal into clinical context. A case presentation is followed by a description of diagnostic and management challenges, a review of the relevant literature, and a summary of the authors' suggested management approaches. The goal of this series is to help readers better understand how to apply the results of key studies, including those published in Journal of Clinical Oncology, to patients seen in their own clinical practice.PMID:34613792 | DO...
Source: Clinical Breast Cancer - Category: Cancer & Oncology Authors: Source Type: research
ConclusionThe ability of mammography and breast ultrasound to accurately measure residual tumor size following neoadjuvant chemotherapy compared to Breast MRI measurement of the residual tumor demonstrated sensitivity of 94.12 % and specificity of 83.33% with high accuracy value reaching to 91.30 %. Even that the MRI is proved to be of high accuracy in detecting residual tumor, sonomammographic imaging isa cost-effective imaging modality than the MRI with sensitivity and specificity near to that of MRI.
Source: QJM - Category: Internal Medicine Source Type: research
ConclusionUltrasoundelastography has significant complementray role beside conventional mammogram and ultrasound in characterization of solid breast lesions.
Source: QJM - Category: Internal Medicine Source Type: research
More News: Breast Cancer | Breast Carcinoma | Cancer | Cancer & Oncology | Carcinoma | Ductal Carcinoma | Information Technology | Learning | Universities & Medical Training | Women