Cervical Cancer Diagnosis using CervixNet - A Deep Learning Approach

Gorantla, Rohan; Singh, Rajeev Kumar; Pandey, Rohan; Jain, Mayank

doi:10.1109/bibe.2019.00078

Cited by 30 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [23][24][25], a convolutional neural network (CNN) model is implemented over a cervix dataset collected by MobileODT (Kaggle Dataset); the reported average Dice score is 0.67. Very recently, one research group applied Mask R-CNN on cervix segmentation tasks, the obtained (Dice, IoU) score is (0.8711, 0.765) on "Kaggle Dataset" as reported in [26]. We use the same dataset in our study and compare our results with these techniques.…”

Section: Deep Learning-based Techniquesmentioning

confidence: 98%

Cross-Dataset Evaluation of Deep Learning Networks for Uterine Cervix Segmentation

2020

View full text Add to dashboard Cite

Evidence from recent research shows that automatic visual evaluation (AVE) of photographic images of the uterine cervix using deep learning-based algorithms presents a viable solution for improving cervical cancer screening by visual inspection with acetic acid (VIA). However, a significant performance determinant in AVE is the photographic image quality. While this includes image sharpness and focus, an important criterion is the localization of the cervix region. Deep learning networks have been successfully applied for object localization and segmentation in images, providing impetus for studying their use for fine contour segmentation of the cervix. In this paper, we present an evaluation of two state-of-the-art deep learning-based object localization and segmentation methods, viz., Mask R-convolutional neural network (CNN) and MaskX R-CNN, for automatic cervix segmentation using three datasets. We carried out extensive experimental tests and algorithm comparisons on each individual dataset and across datasets, and achieved performance either notably higher than, or comparable to, that reported in the literature. The highest Dice and intersection-over-union (IoU) scores that we obtained using Mask R-CNN were 0.947 and 0.901, respectively.

show abstract

Section: Deep Learning-based Techniquesmentioning

confidence: 98%

Cross-Dataset Evaluation of Deep Learning Networks for Uterine Cervix Segmentation

2020

View full text Add to dashboard Cite

show abstract

“…Several studies have been conducted to diagnose cervical cancer [5,14,15,26,27]; however, colposcopy based cervical images classification using deep learning is quite limited. Generally, most of the published studies used microscopic data as inputs for their systems [5,25].…”

Section: A Models Comparison With Earlier Workmentioning

confidence: 99%

“…Generally, all proposed residual networks (18,50,101, and 152 layers) use a non-saturating rectified linear unit (ReLU) as an activation function that allows complex relationships to be learned by the network [11,12]. This function has been verified to a great outcome in many works [13,14,15]; however, researchers found that it can be associated with a problem called "dying ReLU," i.e., it outputs zeros for the negative input values it receives [16]. This, therefore, badly affects the learning of the network.…”

Section: Introductionmentioning

confidence: 99%

Cervical Cancer Diagnosis Using Very Deep Networks Over Different Activation Functions

Adweb¹,

Çavuş²,

Şekeroğlu³

2021

IEEE Access

View full text Add to dashboard Cite

Cancer prevention is mainly achieved by screening the transformation zones. Cervical precancerous stages can be seen in three different types, and all can transform into cancer. Thus, it is crucial to intelligently screen cervical abnormality and have a robust system for detecting whether a cervix is in normal (healthy) or at a pre-cancerous stage. Deep learning showed great potentials when applied to biomedical problems, including medical image analysis, disease prediction, and image segmentation. Hence, in this paper, very deep residual learning based networks are designed in order to perform cervical cancer screening. Moreover, in this work, we highlight the importance of the activation functions on a residual network (ResNet)'s performance. Thus, three residual networks of the same structure are built with different activation functions. The employed models are trained and tested using a dataset of colposcopy cervical images, and the experimental results showed that designed residual networks with leaky and parametric rectified linear unit (Leaky-RELU and PRELU) activation functions performed almost equally in terms of accuracy where they reached accuracies of 90.2 and 100%, respectively. This achieved high accuracy was compared to other related works' results, and it showed an outperformance in screening the pre-cancerous and healthy colposcopy cervical images. Such an earlier and accurate diagnosis may help in preventing cervical cancer transformation.

show abstract

“…In the last few years, deep learning has grown exponentially and in the medical imaging world, the potential of automated disease discovery framework has been highlighted by many scientists [13,25,40,47,66,76]. Considering the success and potential of AI and deep learning in the medical imaging field, many computer scientists are exploring the possibility of automatic detection of COVID-19 using chest X-rays.…”

Section: Introductionmentioning

confidence: 99%

COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays

Singh

Pandey

Babu

2021

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

COVID-19 has emerged as a global crisis with unprecedented socioeconomic challenges, jeopardizing our lives and livelihoods for years to come. The unavailability of vaccines for COVID-19 has rendered rapid testing of the population instrumental in order to contain the exponential rise in cases of infection. Shortage of RT-PCR test kits and delays in obtaining test results calls for alternative methods of rapid and reliable diagnosis. In this article, we propose a novel deep learning-based solution using chest X-rays which can help in rapid triaging of COVID-19 patients. The proposed solution uses image enhancement, image segmentation, and employs a modified stacked ensemble model consisting of four CNN base-learners along with Naive Bayes as meta-learner to classify chest X-rays into three classes viz. COVID-19, pneumonia, and normal. An effective pruning strategy as introduced in the proposed framework results in increased model performance, generalizability, and decreased model complexity. We incorporate explainability in our article by using Grad-CAM visualization in order to establish trust in the medical AI system. Furthermore, we evaluate multiple state-ofthe-art GAN architectures and their ability to generate realistic synthetic samples of COVID-19 chest X-rays to deal with limited numbers of training samples. The proposed solution significantly outperforms existing methods, with 98.67% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98 for COVID-19, normal, and pneumonia classes, respectively, on standard datasets. The proposed solution can be used as one element of patient evaluation along with goldstandard clinical and laboratory testing.

show abstract

Cervical Cancer Diagnosis using CervixNet - A Deep Learning Approach

Cited by 30 publications

References 33 publications

Cross-Dataset Evaluation of Deep Learning Networks for Uterine Cervix Segmentation

Cross-Dataset Evaluation of Deep Learning Networks for Uterine Cervix Segmentation

Cervical Cancer Diagnosis Using Very Deep Networks Over Different Activation Functions

COVIDScreen: explainable deep learning framework for differential diagnosis of COVID-19 using chest X-rays

Contact Info

Product

Resources

About