Advanced Deep Convolutional Neural Network Approaches for Digital Pathology Image Analysis: a comprehensive evaluation with different use cases

Alom, Zahangir; Aspiras, Theus; Taha, Tarek M.; Asari, Vijayan K.; Bowen, T. J.; Billiter, Dave; Simon, Arkell,

doi:10.48550/arxiv.1904.09075

Cited by 9 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also focused on a different problem of prostate histopathological image classification instead of cribriform pattern classification. On similar lines, various DL architectures have been deployed for prostate histopathological images' tasks [14,22,33,48,49]. Generally, DL architectures require a preferably large dataset for training and evaluation purposes due to their huge parameter space.…”

Section: Related Workmentioning

confidence: 99%

“…These hand-crafted nuclei features are designed to incorporate relevant nuclei texture and spatial information for cribriform pattern detection. The DL architectures used in our method have been chosen and/or modified according to their performance in similar histopathological tasks as suggested in literature [16][17][18][19][20][21][22]. Recently, various deep models like ResNet [23], VGG16 [24], VGG19 [24], Inception-v3 (GoogLeNet) [25,26], and DenseNet [27] have achieved top performance in the ImageNet [28] challenge.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cribriform pattern detection in prostate histopathological images using deep learning models

Singh¹,

Kalaw²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Architecture, size, and shape of glands are most important patterns used by pathologists for assessment of cancer malignancy in prostate histopathological tissue slides. Varying structures of glands along with cumbersome manual observations may result in subjective and inconsistent assessment. Cribriform gland with irregular border is an important feature in Gleason pattern 4. We propose using deep neural networks for cribriform pattern classification in prostate histopathological images. 163708 Hematoxylin and Eosin (H&E) stained images were extracted from histopathologic tissue slides of 19 patients with prostate cancer and annotated for cribriform patterns. Our automated image classification system analyses the H&E images to classify them as either 'Cribriform' or 'Non-cribriform'. Our system uses various deep learning approaches and hand-crafted image pixel intensity-based features. We present our results for cribriform pattern detection across various parameters and configuration allowed by our system. The combination of fine-tuned deep learning models outperformed the state-of-art nuclei feature based methods. Our image classification system achieved the testing accuracy of 85.93 ± 7.54 (cross-validated) and 88.04 ± 5.63 ( additional unseen test set) across three folds. In this paper, we present an annotated cribriform dataset along with analysis of deep learning models and hand-crafted features for cribriform pattern detection in prostate histopathological images.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Cribriform pattern detection in prostate histopathological images using deep learning models

Singh¹,

Kalaw²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…[9][10][11] Notably, convolutional neural networks (CNNs) outperform manual feature engineering on a variety of digital pathology tasks. 8,[11][12][13][14] However, training these models typically requires thousands of training examples, while annotated data is highly limited, especially for rare entities like pediatric brain tumors. A common approach to overcome limited data in digital pathology is transfer learning.…”

Section: Introductionmentioning

confidence: 99%

Medulloblastoma tumor classification using deep transfer learning with multi-scale EfficientNets

Bengs

Bockmayr

Schüller

et al. 2021

Medical Imaging 2021: Digital Pathology

View full text Add to dashboard Cite

Medulloblastoma (MB) is the most common malignant brain tumor in childhood. The diagnosis is generally based on the microscopic evaluation of histopathological tissue slides. However, visual-only assessment of histopathological patterns is a tedious and time-consuming task and is also affected by observer variability. Hence, automated MB tumor classification could assist pathologists by promoting consistency and robust quantification. Recently, convolutional neural networks (CNNs) have been proposed for this task, while transfer learning has shown promising results. In this work, we propose an end-to-end MB tumor classification and explore transfer learning with various input sizes and matching network dimensions. We focus on differentiating between the histological subtypes classic and desmoplastic/nodular. For this purpose, we systematically evaluate recently proposed Effi-cientNets, which uniformly scale all dimensions of a CNN. Using a data set with 161 cases, we demonstrate that pre-trained EfficientNets with larger input resolutions lead to significant performance improvements compared to commonly used pre-trained CNN architectures. Also, we highlight the importance of transfer learning, when using such large architectures. Overall, our best performing method achieves an F1-Score of 80.1%.

show abstract

“…Although this approach allows for promising results, manual feature extraction is task-dependent and requires strong domain expertise. In contrast to that, Convolutional Neural Networks (CNNs) provide a more general approach and it has been demonstrated recently that CNNs outperform conventional methods in various pathological image analysis tasks [1,16]. While CNNs provide a general approach with superior performance in many learning tasks, they require a large number of training examples.…”

Section: Introductionmentioning

confidence: 99%

“…224 × 224 pixels [18], which conflicts with the high-resolution WSIs. Hence, WSIs are typically divided into several thousand tiles [1,7], which are processed with a deep learning approach afterwards. Here, the question arises which tile size to choose.…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

Bengs¹,

Pant²,

Bockmayr³

et al. 2021

Preprint

View full text Add to dashboard Cite

Medulloblastoma (MB) is a primary central nervous system tumor and the most common malignant brain cancer among children. Neuropathologists perform microscopic inspection of histopathological tissue slides under a microscope to assess the severity of the tumor. This is a time-consuming task and often infused with observer variability. Recently, pre-trained convolutional neural networks (CNN) have shown promising results for MB subtype classification. Typically, highresolution images are divided into smaller tiles for classification, while the size of the tiles has not been systematically evaluated. We study the impact of tile size and input strategy and classify the two major histopathological subtypes-Classic and Demoplastic/Nodular. To this end, we use recently proposed Effi-cientNets and evaluate tiles with increasing size combined with various downsampling scales. Our results demonstrate using large input tiles pixels followed by intermediate downsampling and patch cropping significantly improves MB classification performance. Our top-performing method achieves the AUC-ROC value of 90.90% compared to 84.53% using the previous approach with smaller input tiles.

show abstract

Advanced Deep Convolutional Neural Network Approaches for Digital Pathology Image Analysis: a comprehensive evaluation with different use cases

Cited by 9 publications

References 0 publications

Cribriform pattern detection in prostate histopathological images using deep learning models

Cribriform pattern detection in prostate histopathological images using deep learning models

Medulloblastoma tumor classification using deep transfer learning with multi-scale EfficientNets

Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

Contact Info

Product

Resources

About