Deep Convolutional Neural Networks for Detecting Cellular Changes Due to Malignancy

Forslid, Gustav; Wieslander, Håkan; Bengtsson, Ewert; Wählby, Carolina; Hirsch, Jan‐Michaél; Stark, Christina; Sadanandan, Sajith Kecheril

doi:10.1109/iccvw.2017.18

Cited by 32 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the contributors utilize CNN to extract the deep features and then manage classifiers like SVM to analyze the cell images. The author in [81] compares the results obtained from ResNet and VGGNet and verify that ResNet is more suitable for the classification of the cervical cytology images. Most of the researchers achieve accuracies over 80%.…”

Section: B Methods Analysismentioning

confidence: 80%

“…AlexNet, VGG-16, and ResNet are found to be the most frequently used network architecture for the segmentation and classification tasks for cervical cancer. The work of [81] finds that ResNet is the preferable network for the classification problem compared with the VGG network. In this subsection, we will give a brief description of AlexNet, VGGNet, ResNet and Inception Net with their network architecture.…”

Section: B Popular Cnn Architecture That Are Used In Cervical Cytopamentioning

confidence: 99%

“…To automatically detect the morphology and chromatinassociated changes of the cervical cell nucleus, a CNN based approach has been developed in [81]. VGG16 and ResNet architecture is used as CNN.…”

Section: A Reference Reviewmentioning

confidence: 99%

See 2 more Smart Citations

A Survey for Cervical Cytopathology Image Analysis Using Deep Learning

Rahaman

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Cervical cancer is one of the most common and deadliest cancers among women. Despite that, this cancer is entirely treatable if it is detected at a precancerous stage. Pap smear test is the most extensively performed screening method for early detection of cervical cancer. However, this hand-operated screening approach suffers from a high false-positive result because of human errors. To improve the accuracy and manual screening practice, computer-aided diagnosis methods based on deep learning is developed widely to segment and classify the cervical cytology images automatically. In this survey, we provide a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images. Firstly, we introduce deep learning and its simplified architectures that have been used in this field. Secondly, we discuss the publicly available cervical cytopathology datasets and evaluation metrics for segmentation and classification tasks. Then, a thorough review of the recent development of deep learning for the segmentation and classification of cervical cytology images is presented. Finally, we investigate the existing methodology along with the most suitable techniques for the analysis of pap smear cells.

show abstract

Section: B Methods Analysismentioning

confidence: 80%

Section: B Popular Cnn Architecture That Are Used In Cervical Cytopamentioning

confidence: 99%

See 1 more Smart Citation

A Survey for Cervical Cytopathology Image Analysis Using Deep Learning

Rahaman

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Traditionally, supervised learning based image analysis combines feature extraction with classical machine learning methods [16]. Convolutional Neural Network (CNN) is an alternative and recent trend for image classification that has been proven to produce high accuracy in image classification tasks [17] without requiring any task-specific feature engineering [18]. It is considered the most successful machine learning model in recent years [19] and the most eminent method in computer vision [20], in part because it consists of a powerful image features extractor [21].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Object Classification in Thermal Images using Convolutional Neural Networks for Search and Rescue Missions with Unmanned Aerial Systems

Rodin

Lima

Andrade

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

In recent years, the use of Unmanned Aerial Systems (UAS) has become commonplace in a wide variety of tasks due to their relatively low cost and ease of operation. In this paper, we explore the use of UAS in maritime Search And Rescue (SAR) missions by using experimental data to detect and classify objects at the sea surface. The objects are chosen as common objects present in maritime SAR missions: a boat, a pallet, a human, and a buoy. The data consists of thermal images and Gaussian Mixture Model (GMM) is used to discriminate foreground objects from the background. Then, bounding boxes containing the object are defined and used to train a Convolutional Neural Network (CNN). The CNN achieves the average accuracy of 92.5% when evaluating a testing dataset.

show abstract

“…Algorithms plays a major role in the artifacts filtering, segmentation, feature extraction and classification, which will expedite the disease diagnosis. In the recent two decades, deep learning algorithms played a vital role in the medical image processing with improved performance than the conventional machine learning algorithms, such advanced algorithms that show greater accuracy in the classification of cancer cells, lesions, organ segmentation and medical image enhancement with an average accuracy ranges of 96% to 98% [3]. In the mere future, advanced computational and learning approaches like Deep learning and hybrid deep learning approaches will play a vital role in the field of diagnostic imaging with most substantial clinical impact on medical imaging examinations to provide improved decision support in medical image interpretation and analysis [4 -10].…”

mentioning

confidence: 99%