Acetowhite region segmentation in uterine cervix images using a registered ratio image

Automatic Acetowhite Lesion Segmentation via Specular Reflection Removal and Deep Attention Network

Automatic acetowhite lesion segmentation in colposcopy images (cervigrams) is essential in assisting gynecologists for the diagnosis of cervical intraepithelial neoplasia grades and cervical cancer. It can also help gynecologists determine the correct lesion areas for further pathological examination. Existing computer-aided diagnosis algorithms show poor segmentation performance because of specular reflections, insufficient training data and the inability to focus on semantically meaningful lesion parts. In this paper, a novel computer-aided diagnosis algorithm is proposed to segment acetowhite lesions in cervigrams automatically. To reduce the interference of specularities on segmentation performance, a specular reflection removal mechanism is presented to detect and inpaint these areas with precision. Moreover, we design a cervigram image classification network to classify pathology results and generate lesion attention maps, which are subsequently leveraged to guide a more accurate lesion segmentation task by the proposed lesion-aware convolutional neural network. We conducted comprehensive experiments to evaluate the proposed approaches on 3045 clinical cervigrams. Our results show that our method outperforms state-of-the-art approaches and achieves better Dice similarity coefficient and Hausdorff Distance values in acetowhite legion segmentation.

Segmentation of acetowhite region in uterine cervical image based on deep learning

BACKGROUND

Acetowhite (AW) region is a critical physiological phenomenon of precancerous lesions of cervical cancer. An accurate segmentation of the AW region can provide a useful diagnostic tool for gynecologic oncologists in screening cervical cancers. Traditional approaches for the segmentation of AW regions relied heavily on manual or semi-automatic methods.

OBJECTIVE

To automatically segment the AW regions from colposcope images.

METHODS

First, the cervical region was extracted from the original colposcope images by k-means clustering algorithm. Second, a deep learning-based image semantic segmentation model named DeepLab V3+ was used to segment the AW region from the cervical image.

RESULTS

The results showed that, compared to the fuzzy clustering segmentation algorithm and the level set segmentation algorithm, the new method proposed in this study achieved a mean Jaccard Index (JI) accuracy of 63.6% (improved by 27.9% and 27.5% respectively), a mean specificity of 94.9% (improved by 55.8% and 32.3% respectively) and a mean accuracy of 91.2% (improved by 38.6% and 26.4% respectively). A mean sensitivity of 78.2% was achieved by the proposed method, which was 17.4% and 10.1% lower respectively. Compared to the image semantic segmentation models U-Net and PSPNet, the proposed method yielded a higher mean JI accuracy, mean sensitivity and mean accuracy.

CONCLUSION

The improved segmentation performance suggested that the proposed method may serve as a useful complimentary tool in screening cervical cancer.

Evaluation of the active contour and topographic watershed segmentation "assessment of the systolic ejection fraction in the left ventricular for medical assistance in 5D short axis cine MRI"

A comparative study has been depicted between the contour and topographic watershed segmentation approach for short-axis 5D cardiac sequences with MRI for medical decision. The fifth dimension has been defined as the excitation of pixels based on the gray scale around the myocardium without consideration of the morphological structure of the heart in 3D and fourth dimension (time). Three patients were performed the first is healthy, the second has a genetic disease, and the third had a heart failure syndrome for a dimension ROI = 150mm, average age is 54 years old, and mean of weight = 86 kg. A contouring and watershed segmentation algorithm for a sample of 63 Cine Fiesta MRI sequences for short-axis cuts with Matlab and its in-box toolbox complements was implemented. For a healthy patient 13.4% tolerance rate for the estimation of the stroke fraction, 6.4% for a patient with genetic disease, 8.7% error rate for a patient with heart failure symptom. The results show that the regurgitation fraction by the contour approach for a patient case with symptom of the presence of a genetic disease is 0.0335% for an aortic valve, 0.248% for a mitral valve, an error rate 0.16% for estimating this parameter for the aortic orifice with the watershed segmentation approach. In return, for a patient with suspected heart failure (stenosis or regurgitation) the regurgitation fraction is estimated by 0% for aortic valve, 1.49 e + 03% for a mitral valve, an error rate 11.76% compared to the watershed segmentation approach. The results are validated clinically. The Optimization of the topographic watershed approach with mutual information was simulated for the extraction of measurements (ejection fraction, regurgitation rate) within the left ventricle for three patient types (healthy, genetic pathology and heart failure). The results are considered interesting compared to the clinical assessment.

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

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 Mask^X 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.