Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning

Kanavati, Fahdi

doi:10.3390/cancers13215368

Cited by 21 publications

(15 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows an overview of the training method. The training methodology that we used in the present study was the same as reported in our previous studies Kanavati and Tsuneki (2021a); Tsuneki and Kanavati (2021); Tsuneki et al (2022). For completeness we repeat the methodology here.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

“…In the field of computational pathology as a computer-aided detection (CADe) or computer-aided diagnosis (CADx), deep learning models have been widely applied in histopathological cancer classification on whole-slide images (WSIs), cancer cell detection and segmentation, and the stratification of patient clinical outcomes Yu et al (2016); Hou et al (2016); Madabhushi and Lee (2016); Litjens et al (2016); Kraus et al (2016); Korbar et al (2017); Luo et al (2017); Coudray et al (2018); Wei et al (2019); Gertych et al (2019); Bejnordi et al (2017); Saltz et al (2018); Campanella et al (2019); Iizuka et al (2020). Previous studies have looked into applying deep learning models for ADC classification in stomach Iizuka et al (2020); Kanavati and Tsuneki (2021b); Kanavati et al (2021a), colon Iizuka et al (2020); Tsuneki and Kanavati (2021), lung Kanavati and Tsuneki (2021b); Kanavati et al (2021b), breast Kanavati and Tsuneki (2021a); Kanavati et al (2022), and prostate Tsuneki et al (2022) histopathological specimen WSIs. As for the gastric poorly differentiated ADC classification on WSIs, we have developed deep learning models based on endoscopic biopsy specimens Kanavati and Tsuneki (2021b); Kanavati et al (2021a).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Ichihara

Kanavati²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The endoscopic submucosal dissection (ESD) is the preferred technique for treating early gastric cancers including poorly differentiated adenocarcinoma without ulcerative findings. The histopathological classification of poorly differentiated adenocarcinoma including signet ring cell carcinoma is of pivotal importance for determining further optimum cancer treatment(s) and clinical outcomes. Because conventional diagnosis by pathologists using microscopes is time-consuming and limited in terms of human resources, it is very important to develop computer-aided techniques that can rapidly and accurately inspect large numbers of histopathological specimen whole-slide images (WSIs). Computational pathology applications which can assist pathologists in detecting and classifying gastric poorly differentiated adenocarcinoma from ESD WSIs would be of great benefit for routine histopathological diagnostic workflow. In this study, we trained the deep learning model to classify poorly differentiated adenocarcinoma in ESD WSIs by transfer and weakly supervised learning approaches. We evaluated the model on ESD, endoscopic biopsy, and surgical specimen WSI test sets, achieving and ROC-AUC up to 0.975 in gastric ESD test sets for poorly differentiated adenocarcinoma. The deep learning model developed in this study demonstrates the high promising potential of deployment in a routine practical gastric ESD histopathological diagnostic workflow as a computer-aided diagnosis system

show abstract

Section: Deep Learning Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Ichihara

Kanavati²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, there is a shortage of experienced pathologists, who require years of training and examination, which creates challenges for cancer centers [ 5 ]. In the automatic analysis of WSIs, glass slides are digitized to produce on-screen WSIs, and artificial intelligence, in particular deep learning technology, is applied [ 6 , 7 , 8 ]. The emergence of digital WSIs has made it possible to introduce deep learning.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, Das et al [ 28 ] adopted a multi-instance network to exclude input disturbance and acquire cancer features. Kanavati et al [ 7 ]. used the EfficientNet-B1 to detect breast invasive ductal carcinoma, with loose annotation.…”

Section: Introductionmentioning

confidence: 99%

BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images

et al. 2022

View full text Add to dashboard Cite

Breast cancer is one of the most common types of cancer and is the leading cause of cancer-related death. Diagnosis of breast cancer is based on the evaluation of pathology slides. In the era of digital pathology, these slides can be converted into digital whole slide images (WSIs) for further analysis. However, due to their sheer size, digital WSIs diagnoses are time consuming and challenging. In this study, we present a lightweight architecture that consists of a bilinear structure and MobileNet-V3 network, bilinear MobileNet-V3 (BM-Net), to analyze breast cancer WSIs. We utilized the WSI dataset from the ICIAR2018 Grand Challenge on Breast Cancer Histology Images (BACH) competition, which contains four classes: normal, benign, in situ carcinoma, and invasive carcinoma. We adopted data augmentation techniques to increase diversity and utilized focal loss to remove class imbalance. We achieved high performance, with 0.88 accuracy in patch classification and an average 0.71 score, which surpassed state-of-the-art models. Our BM-Net shows great potential in detecting cancer in WSIs and is a promising clinical tool.

show abstract

“…The process, however, involves manual feature engineering by expert pathologists who must carefully observe and examine the glass slide of biopsy specimens. Capturing these specimens into images makes them available for use in computer-aided detection/diagnosis [ 14 ]. Approaches such as machine learning (ML) and, more specifically, deep learning (DL), have been explored in recent years due to their successes in aiding in the prognosis and diagnosis of other medical conditions [ 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 ].…”

Section: Introductionmentioning

confidence: 99%

Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images

Agbley

Hossin

et al. 2022

Diagnostics

View full text Add to dashboard Cite

Invasive carcinoma of no special type (IC-NST) is known to be one of the most prevalent kinds of breast cancer, hence the growing research interest in studying automated systems that can detect the presence of breast tumors and appropriately classify them into subtypes. Machine learning (ML) and, more specifically, deep learning (DL) techniques have been used to approach this problem. However, such techniques usually require massive amounts of data to obtain competitive results. This requirement makes their application in specific areas such as health problematic as privacy concerns regarding the release of patients’ data publicly result in a limited number of publicly available datasets for the research community. This paper proposes an approach that leverages federated learning (FL) to securely train mathematical models over multiple clients with local IC-NST images partitioned from the breast histopathology image (BHI) dataset to obtain a global model. First, we used residual neural networks for automatic feature extraction. Then, we proposed a second network consisting of Gabor kernels to extract another set of features from the IC-NST dataset. After that, we performed a late fusion of the two sets of features and passed the output through a custom classifier. Experiments were conducted for the federated learning (FL) and centralized learning (CL) scenarios, and the results were compared. Competitive results were obtained, indicating the positive prospects of adopting FL for IC-NST detection. Additionally, fusing the Gabor features with the residual neural network features resulted in the best performance in terms of accuracy, F1 score, and area under the receiver operation curve (AUC-ROC). The models show good generalization by performing well on another domain dataset, the breast cancer histopathological (BreakHis) image dataset. Our method also outperformed other methods from the literature.

show abstract

Breast Invasive Ductal Carcinoma Classification on Whole Slide Images with Weakly-Supervised and Transfer Learning

Cited by 21 publications

References 35 publications

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

Weakly supervised learning for poorly differentiated adenocarcinoma classification in gastric endoscopic submucosal dissection whole slide images

BM-Net: CNN-Based MobileNet-V3 and Bilinear Structure for Breast Cancer Detection in Whole Slide Images

Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images

Contact Info

Product

Resources

About