Differentiation of COVID-19 conditions in planar chest radiographs using optimized convolutional neural networks

Govindarajan, S.; Swaminathan, Ramakrishnan

doi:10.1007/s10489-020-01941-8

Cited by 9 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This should be considered when planning similar studies. The occlusion-based explanations pointing to critical structures represent a useful tool for fine-tuning and optimization of neural networks in histopathology, and potentially for identification of previously unrecognized morphological features related to histopathological diagnosis, prognosis, and prediction [23, 24]. Finally, unravelling the large quantity of features within the network and exposing the key elements will help to promote trust in these and similar AI-based methods in pathology, enhancing the opportunities for incorporation into clinical use.…”

Section: Discussionmentioning

confidence: 99%

Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability

Krajňanský

Gallo

Nenutil

et al. 2022

Preprint

View full text Add to dashboard Cite

Diagnostic histopathology is facing increasing demands due to aging populations and expanding healthcare programs. Semi-automated diagnostic systems employing deep learning methods are one approach to alleviate this pressure, with promising results for many routine diagnostic procedures. However, one major issue with deep learning approaches is their lack of interpretability - after adequate training they perform their assigned tasks admirably, but do not explain how they reach their conclusions. Knowledge of how a given method performs its task with high sensitivity and specificity would be advantageous to understand the key features responsible for diagnosis, and should in turn allow fine-tuning of deep learning approaches. This paper presents a deep learning-based system for carcinoma detection in whole slide images of prostate core biopsies, achieving state-of-the-art performance; 100% area under curve and sensitivity of 0.978 for 8 detected false positives on average per slide. Furthermore, we investigated various methods to extract the key features used by the neural network for classification. Of these, the technique called occlusion, adapted to whole slide images, analyzes the sensitivity of the detection system to changes in the input images. This technique produces heatmaps indicating which parts of the image have the strongest impact on the system's output that a histopathologist can examine to identify the network's reasoning behind a given classification. Reassuringly, the heatmaps identified several prevailing histomorphological features characterizing carcinoma, e.g. single-layered epithelium, presence of small lumina, and hyperchromatic nuclei with halos. A convincing finding was the recognition of their mimickers in non-neoplastic tissue. The results show that the neural network approach to recognize prostatic cancer is similar to that taken by a human pathologist at medium optical resolution. The use of explainability heatmaps provides added value for automated digital pathology to analyze and fine-tune deep learning systems, and improves trust in computer-based decisions.

show abstract

Section: Discussionmentioning

confidence: 99%

Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability

Krajňanský

Gallo

Nenutil

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The results showed that better values of different metrics are achieved in binary classification. S. Govindarajan and R. Swaminathan [18] acquired critical image features using CNN with several different hyper-parameter settings and cross-validation methods. They visualized them using occlusion sensitivity maps.…”

Section: Related Workmentioning

confidence: 99%

Hyper-parameter optimization of convolutional neural networks for classifying COVID-19 X-ray images

Vrbacic

Pečnik

Podgorelec

2022

ComSIS

View full text Add to dashboard Cite

For more than a year the COVID-19 epidemic is threatening people all over the world. Numerous researchers are looking for all possible insights into the new corona virus SARS-CoV-2. One of the possibilities is an in-depth analysis of X-ray images from COVID-19 patients, commonly conducted by a radiologist, which are due to high demand facing with overload. With the latest achievements in the field of deep learning, the approaches using transfer learning proved to be successful when tackling such problem. However, when utilizing deep learning methods, we are commonly facing the problem of hyper-parameter settings. In this research, we adapted and generalized transfer learning based classification method for detecting COVID-19 from X-ray images and employed different optimization algorithms for solving the task of hyper-parameter settings. Utilizing different optimization algorithms our method was evaluated on a dataset of 1446 X-ray images, with the overall accuracy of 84.44%, outperforming both conventional CNN method as well as the compared baseline transfer learning method. Besides quantitative analysis, we also conducted a qualitative in-depth analysis using the local interpretable modelagnostic explanations method and gain some in-depth view of COVID-19 characteristics and the predictive model perception.

show abstract

“…The Reverse Transcription - Polymerase Chain Reaction (RT-PCR) is a gold standard for detecting the presence of coronavirus [ 9 ]. It can reliably detect a virus in the early days of infection [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

COVID-19 prediction based on hybrid Inception V3 with VGG16 using chest X-ray images

Srinivas

Rahayu

Pravallika³

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

The Corona Virus was first started in the Wuhan city, China in December of 2019. It belongs to the Coronaviridae family, which can infect both animals and humans. The diagnosis of coronavirus disease-2019 (COVID-19) is typically detected by Serology, Genetic Real-Time reverse transcription–Polymerase Chain Reaction (RT-PCR), and Antigen testing. These testing methods have limitations like limited sensitivity, high cost, and long turn-around time. It is necessary to develop an automatic detection system for COVID-19 prediction. Chest X-ray is a lower-cost process in comparison to chest Computed tomography (CT). Deep learning is the best fruitful technique of machine learning, which provides useful investigation for learning and screening a large amount of chest X-ray images with COVID-19 and normal. There are many deep learning methods for prediction, but these methods have a few limitations like overfitting, misclassification, and false predictions for poor-quality chest X-rays. In order to overcome these limitations, the novel hybrid model called “Inception V3 with VGG16 (Visual Geometry Group)” is proposed for the prediction of COVID-19 using chest X-rays. It is a combination of two deep learning models, Inception V3 and VGG16 (IV3-VGG). To build the hybrid model, collected 243 images from the COVID-19 Radiography Database. Out of 243 X-rays, 121 are COVID-19 positive and 122 are normal images. The hybrid model is divided into two modules namely pre-processing and the IV3-VGG. In the dataset, some of the images with different sizes and different color intensities are identified and pre-processed. The second module i.e., IV3-VGG consists of four blocks. The first block is considered for VGG-16 and blocks 2 and 3 are considered for Inception V3 networks and final block 4 consists of four layers namely Avg pooling, dropout, fully connected, and Softmax layers. The experimental results show that the IV3-VGG model achieves the highest accuracy of 98% compared to the existing five prominent deep learning models such as Inception V3, VGG16, ResNet50, DenseNet121, and MobileNet.

show abstract

Differentiation of COVID-19 conditions in planar chest radiographs using optimized convolutional neural networks

Cited by 9 publications

References 33 publications

Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability

Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability

Hyper-parameter optimization of convolutional neural networks for classifying COVID-19 X-ray images

COVID-19 prediction based on hybrid Inception V3 with VGG16 using chest X-ray images

Contact Info

Product

Resources

About