Dataset Information

Performance analysis of seven Convolutional Neural Networks (CNNs) with transfer learning for Invasive Ductal Carcinoma (IDC) grading in breast histopathological images.

ABSTRACT: Computer-aided Invasive Ductal Carcinoma (IDC) grading classification systems based on deep learning have shown that deep learning may achieve reliable accuracy in IDC grade classification using histopathology images. However, there is a dearth of comprehensive performance comparisons of Convolutional Neural Network (CNN) designs on IDC in the literature. As such, we would like to conduct a comparison analysis of the performance of seven selected CNN models: EfficientNetB0, EfficientNetV2B0, EfficientNetV2B0-21k, ResNetV1-50, ResNetV2-50, MobileNetV1, and MobileNetV2 with transfer learning. To implement each pre-trained CNN architecture, we deployed the corresponded feature vector available from the TensorFlowHub, integrating it with dropout and dense layers to form a complete CNN model. Our findings indicated that the EfficientNetV2B0-21k (0.72B Floating-Point Operations and 7.1 M parameters) outperformed other CNN models in the IDC grading task. Nevertheless, we discovered that practically all selected CNN models perform well in the IDC grading task, with an average balanced accuracy of 0.936 ± 0.0189 on the cross-validation set and 0.9308 ± 0.0211on the test set.

SUBMITTER: Voon W

PROVIDER: S-EPMC9649772 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Performance analysis of seven Convolutional Neural Networks (CNNs) with transfer learning for Invasive Ductal Carcinoma (IDC) grading in breast histopathological images.

Voon Wingates W Hum Yan Chai YC Tee Yee Kai YK Yap Wun-She WS Salim Maheza Irna Mohamad MIM Tan Tian Swee TS Mokayed Hamam H Lai Khin Wee KW

Scientific reports 20221110 1

Computer-aided Invasive Ductal Carcinoma (IDC) grading classification systems based on deep learning have shown that deep learning may achieve reliable accuracy in IDC grade classification using histopathology images. However, there is a dearth of comprehensive performance comparisons of Convolutional Neural Network (CNN) designs on IDC in the literature. As such, we would like to conduct a comparison analysis of the performance of seven selected CNN models: EfficientNetB0, EfficientNetV2B0, Eff ...[more]

PMID: 36357456

Similar Datasets

Project description:BackgroundInvasive ductal carcinoma (IDC) is the most common form of breast cancer which accounts for 85% of all breast cancer diagnoses. Non-invasive and early stages have a better prognosis than late-stage invasive cancer that has spread to lymph nodes. The involvement of microRNAs (miRNAs) in the initiation and progression of breast cancer holds great promise for the development of molecular tools for early diagnosis and prognosis. Therefore, developing a cost effective, quick and robust early detection protocol using miRNAs for breast cancer diagnosis is an imminent need that could strengthen the health care system to tackle this disease around the world.MethodsWe have analyzed putative miRNAs signatures in 100 breast cancer samples using two independent high fidelity array systems. Unique and common miRNA signatures from both array systems were validated using stringent double-blind individual TaqMan assays and their expression pattern was confirmed with tissue microarrays and northern analysis. In silico analysis were carried out to find miRNA targets and were validated with q-PCR and immunoblotting. In addition, functional validation using antibody arrays was also carried out to confirm the oncotargets and their networking in different pathways. Similar profiling was carried out in Brca2/p53 double knock out mice models using rodent miRNA microarrays that revealed common signatures with human arrays which could be used for future in vivo functional validation.ResultsExpression profile revealed 85% downregulated and 15% upregulated microRNAs in the patient samples of IDC. Among them, 439 miRNAs were associated with breast cancer, out of which 107 miRNAs qualified to be potential biomarkers for the stratification of different types, grades and stages of IDC after stringent validation. Functional validation of their putative targets revealed extensive miRNA network in different oncogenic pathways thus contributing to epithelial-mesenchymal transition (EMT) and cellular plasticity.ConclusionThis study revealed potential biomarkers for the robust classification as well as rapid, cost effective and early detection of IDC of breast cancer. It not only confirmed the role of these miRNAs in cancer development but also revealed the oncogenic pathways involved in different progressive grades and stages thus suggesting a role in EMT and cellular plasticity during breast tumorigenesis per se and IDC in particular. Thus, our findings have provided newer insights into the miRNA signatures for the classification and early detection of IDC.

Project description:Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen's kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.

Project description:Histopathological images contain rich phenotypic descriptions of the molecular processes underlying disease progression. Convolutional neural networks, state-of-the-art image analysis techniques in computer vision, automatically learn representative features from such images which can be useful for disease diagnosis, prognosis, and subtyping. Hepatocellular carcinoma (HCC) is the sixth most common type of primary liver malignancy. Despite the high mortality rate of HCC, little previous work has made use of CNN models to explore the use of histopathological images for prognosis and clinical survival prediction of HCC. We applied three pre-trained CNN models-VGG 16, Inception V3 and ResNet 50-to extract features from HCC histopathological images. Sample visualization and classification analyses based on these features showed a very clear separation between cancer and normal samples. In a univariate Cox regression analysis, 21.4% and 16% of image features on average were significantly associated with overall survival (OS) and disease-free survival (DFS), respectively. We also observed significant correlations between these features and integrated biological pathways derived from gene expression and copy number variation. Using an elastic net regularized Cox Proportional Hazards model of OS constructed from Inception image features, we obtained a concordance index (C-index) of 0.789 and a significant log-rank test (p = 7.6E-18). We also performed unsupervised classification to identify HCC subgroups from image features. The optimal two subgroups discovered using Inception model image features showed significant differences in both overall (C-index = 0.628 and p = 7.39E-07) and DFS (C-index = 0.558 and p = 0.012). Our work demonstrates the utility of extracting image features using pre-trained models by using them to build accurate prognostic models of HCC as well as highlight significant correlations between these features, clinical survival, and relevant biological pathways. Image features extracted from HCC histopathological images using the pre-trained CNN models VGG 16, Inception V3 and ResNet 50 can accurately distinguish normal and cancer samples. Furthermore, these image features are significantly correlated with survival and relevant biological pathways.

Dataset Information

Performance analysis of seven Convolutional Neural Networks (CNNs) with transfer learning for Invasive Ductal Carcinoma (IDC) grading in breast histopathological images.

Publications

Performance analysis of seven Convolutional Neural Networks (CNNs) with transfer learning for Invasive Ductal Carcinoma (IDC) grading in breast histopathological images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets