Thresholding for Medical Image Segmentation for Cancer using Fuzzy Entropy with Level Set Algorithm

Toward Intraoperative Margin Assessment Using a Deep Learning-Based Approach for Automatic Tumor Segmentation in Breast Lumpectomy Ultrasound Images

There is an unmet clinical need for an accurate, rapid and reliable tool for margin assessment during breast-conserving surgeries. Ultrasound offers the potential for a rapid, reproducible, and non-invasive method to assess margins. However, it is challenged by certain drawbacks, including a low signal-to-noise ratio, artifacts, and the need for experience with the acquirement and interpretation of images. A possible solution might be computer-aided ultrasound evaluation. In this study, we have developed new ensemble approaches for automated breast tumor segmentation. The ensemble approaches to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm) in the ultrasound images were based on 8 pre-trained deep neural networks. The best optimum ensemble approach for segmentation attained a median Dice score of 0.88 on our data set. Furthermore, utilizing the segmentation results we were able to achieve a sensitivity of 96% and a specificity of 76% for predicting a close margin when compared to histology results. The promising results demonstrate the capability of AI-based ultrasound imaging as an intraoperative surgical margin assessment tool during breast-conserving surgery.

Quantifying Liver Heterogeneity via R2*-MRI with Super-Paramagnetic Iron Oxide Nanoparticles (SPION) to Characterize Liver Function and Tumor

Simple Summary

Super-paramagnetic iron oxide nanoparticles (SPIONs) are phagocytized by the hepatic Kupffer cells (KC) in the liver and shorten MRI signals within the volume of functional liver parenchyma (FLP) where KCs are found. However, malignant tumors lacking KCs exhibit minimal signal change, resulting in increasing liver heterogeneity. This study investigates whether SPIONs improve liver heterogeneity on R2*-MRI to characterize FLP and non-FLP (i.e., tumor, hepatic vessels, liver fibrosis and scarring associated with hepatic cirrhosis, prior liver-directed therapies or hepatic resection). By using SPIONs, liver heterogeneity was improved across two MRI sessions with and without an intravenous SPION injection, and the volume of FLP was identified in our auto-contouring tool. This is a desirable technique for achieving more accurate characterizations of liver function and tumors during radiation treatment planning.

Abstract

The use of super-paramagnetic iron oxide nanoparticles (SPIONs) as an MRI contrast agent (SPION-CA) can safely label hepatic macrophages and be localized within hepatic parenchyma for T2*- and R2*-MRI of the liver. To date, no study has utilized the R2*-MRI with SPIONs for quantifying liver heterogeneity to characterize functional liver parenchyma (FLP) and hepatic tumors. This study investigates whether SPIONs enhance liver heterogeneity for an auto-contouring tool to identify the voxel-wise functional liver parenchyma volume (FLPV). This was the first study to directly evaluate the impact of SPIONs on the FLPV in R2*-MRI for 12 liver cancer patients. By using SPIONs, liver heterogeneity was improved across pre- and post-SPION MRI sessions. On average, 60% of the liver [range 40–78%] was identified as the FLPV in our auto-contouring tool with a pre-determined threshold of the mean R2* of the tumor and liver. This method performed well in 10 out of 12 liver cancer patients; the remaining 2 needed a longer echo time. These results demonstrate that our contouring tool with SPIONs can facilitate the heterogeneous R2* of the liver to automatically characterize FLP. This is a desirable technique for achieving more accurate FLPV contouring during liver radiation treatment planning.

An adaptive multilevel thresholding method with chaotically-enhanced Rao algorithm

Multilevel image thresholding is a well-known technique for image segmentation. Recently, various metaheuristic methods have been proposed for the determination of the thresholds for multilevel image segmentation. These methods are mainly based on metaphors and they have high complexity and their convergences are comparably slow. In this paper, a multilevel image thresholding approach is proposed that simplifies the thresholding problem by using a simple optimization technique instead of metaphor-based algorithms. More specifically, in this paper, Chaotic enhanced Rao (CER) algorithms are developed where eight chaotic maps namely Logistic, Sine, Sinusoidal, Gauss, Circle, Chebyshev, Singer, and Tent are used. Besides, in the developed CER algorithm, the number of thresholds is determined automatically, instead of manual determination. The performances of the developed CER algorithms are evaluated based on different statistical analysis metrics namely BDE, PRI, VOI, GCE, SSIM, FSIM, RMSE, PSNR, NK, AD, SC, MD, and NAE. The experimental works and the related evaluations are carried out on the BSDS300 dataset. The obtained experimental results demonstrate that the proposed CER algorithm outperforms the compared methods based on PRI, SSIM, FSIM, PSNR, RMSE, AD, and NAE metrics. In addition, the proposed method provides better convergence regarding speed and accuracy.

Grayscale medical image segmentation method based on 2D&3D object detection with deep learning

Background

Grayscale medical image segmentation is the key step in clinical computer-aided diagnosis. Model-driven and data-driven image segmentation methods are widely used for their less computational complexity and more accurate feature extraction. However, model-driven methods like thresholding usually suffer from wrong segmentation and noises regions because different grayscale images have distinct intensity distribution property thus pre-processing is always demanded. While data-driven methods with deep learning like encoder-decoder networks always are always accompanied by complex architectures which require amounts of training data.

Methods

Combining thresholding method and deep learning, this paper presents a novel method by using 2D&3D object detection technologies. First, interest regions contain segmented object are determined with fine-tuning 2D object detection network. Then, pixels in cropped images are turned as point cloud according to their positions and grayscale values. Finally, 3D object detection network is applied to obtain bounding boxes with target points and boxes’ bottoms and tops represent thresholding values for segmentation. After projecting to 2D images, these target points could composite the segmented object.

Results

Three groups of grayscale medical images are used to evaluate the proposed image segmentation method. We obtain the IoU (DSC) scores of 0.92 (0.96), 0.88 (0.94) and 0.94 (0.94) for segmentation accuracy on different datasets respectively. Also, compared with five state of the arts and clinically performed well models, our method achieves higher scores and better performance.

Conclusions

The prominent segmentation results demonstrate that the built method based on 2D&3D object detection with deep learning is workable and promising for segmentation task of grayscale medical images.

Semantic Segmentation- A systematic analysis from State-of-the-Art Techniques to Advance Deep Networks

Semantic segmentation was traditionally performed using primitive methods however, in recent times a significant growth in the advancement of deep learning techniques for the same is observed. In this paper, an extensive study and review of the existing deep learning (DL) based techniques used for the purpose of semantic segmentation is carried out; along with a summary of the datasets and evaluation metrics used for the same. The paper begins with a general and broader focus on semantic segmentation as a problem and further narrows its focus on existing DL-based approaches for this task. In addition to this, a summary of the traditional methods used for semantic segmentation is also presented towards the beginning. Since the problem of scene understanding is being vastly explored in the computer vision community, especially with the help of semantic segmentation, we believe that this paper will benefit active researchers in reviewing and studying the existing state-of-the-art as well as advanced methods for the same.

Methods for the segmentation and classification of breast ultrasound images: a review

PURPOSE

Breast ultrasound (BUS) is one of the imaging modalities for the diagnosis and treatment of breast cancer. However, the segmentation and classification of BUS images is a challenging task. In recent years, several methods for segmenting and classifying BUS images have been studied. These methods use BUS datasets for evaluation. In addition, semantic segmentation algorithms have gained prominence for segmenting medical images.

METHODS

In this paper, we examined different methods for segmenting and classifying BUS images. Popular datasets used to evaluate BUS images and semantic segmentation algorithms were examined. Several segmentation and classification papers were selected for analysis and review. Both conventional and semantic methods for BUS segmentation were reviewed.

RESULTS

Commonly used methods for BUS segmentation were depicted in a graphical representation, while other conventional methods for segmentation were equally elucidated.

CONCLUSIONS

We presented a review of the segmentation and classification methods for tumours detected in BUS images. This review paper selected old and recent studies on segmenting and classifying tumours in BUS images.

Intelligent Segmentation Algorithm for Diagnosis of Meniere's Disease in the Inner Auditory Canal Using MRI Images with Three-Dimensional Level Set

This paper aimed to explore segmentation effects of the magnetic resonance imaging (MRI) images of the inner auditory canal of patients with Meniere's disease under the intelligent segmentation method of the inner ear based on three-dimensional (3D) level set (IS3DLS). The statistical shape model and the level set segmentation algorithm were combined to propose the IS3DLS. First, the shape training samples of the inner ear model were determined, and the results were manually segmented to further obtain region of interest (ROI) of the inner ear. The IS3DLS was employed to accurately segment MRI images of the inner auditory canal of patients with Meniere's disease. The segmentation performance of IS3DLS was compared with the expert manual segmentation method and the region growth level set-based segmentation algorithm. Results showed that Matthews correlation coefficient (MCC), Dice similarity coefficient (DSC), false positive rate (FPR), and false negative rate (FNR) of this algorithm were 0.9599, 0.9594, 0.0325, and 0.03655, respectively. Therefore, the IS3DLS could achieve good segmentation effect in MRI images of the inner auditory canal of patients with Meniere's disease, which was helpful for diagnosis and subsequent treatment of Meniere's disease.

Pyramid graph cut: Integrating intensity and gradient information for grayscale medical image segmentation

Segmentation of grayscale medical images is challenging because of the similarity of pixel intensities and poor gradient strength between adjacent regions. The existing image segmentation approaches based on either intensity or gradient information alone often fail to produce accurate segmentation results. Previous approaches in the literature have approached the problem by embedded or sequential integration of different information types to improve the performance of the image segmentation on specific tasks. However, an effective combination or integration of such information is difficult to implement and not sufficiently generic for closely related tasks. Integration of the two information sources in a single graph structure is a potentially more effective way to solve the problem. In this paper we introduce a novel technique for grayscale medical image segmentation called pyramid graph cut, which combines intensity and gradient sources of information in a pyramid-shaped graph structure using a single source node and multiple sink nodes. The source node, which is the top of the pyramid graph, embeds intensity information into its linked edges. The sink nodes, which are the base of the pyramid graph, embed gradient information into their linked edges. The min-cut uses intensity information and gradient information, depending on which one is more useful or has a higher influence in each cutting location of each iteration. The experimental results demonstrate the effectiveness of the proposed method over intensity-based segmentation alone (i.e. Gaussian mixture model) and gradient-based segmentation alone (i.e. distance regularized level set evolution) on grayscale medical image datasets, including the public 3DIRCADb-01 dataset. The proposed method archives excellent segmentation results on the sample CT of abdominal aortic aneurysm, MRI of liver tumor and US of liver tumor, with dice scores of 90.49±5.23%, 88.86±11.77%, 90.68±2.45%, respectively.

Dermoscopy in China: current status and future prospective

OBJECTIVE

Dermoscopy is a useful technique for improving the diagnostic accuracy of various types of skin disorders. In China, dermoscopy has been widely accepted, and domestic researchers have made tremendous progress in the field of dermoscopy. The main purpose of this review is to summarize the current status of dermoscopy in China and identify its future directions.

DATA SOURCES

Articles included in this review were obtained by searching the following databases: Wanfang, China National Knowledge Infrastructure, PubMed, and the Web of Science. We focused on research published before 2019 with keywords including dermoscopy, dermoscopic, dermoscope and trichoscopy.

STUDY SELECTION

A total of 50 studies were selected. Of these studies, 20 studies were in Chinese and 30 in English, research samples of all the studies were collected from Chinese populations.

RESULTS

Since 2000, more than 380 articles about dermoscopy have been published in domestic or foreign journals. Dermoscopy can improve the diagnostic accuracy of neoplastic diseases, evaluating the therapeutic effect of treatment, and determining the treatment endpoint, and it can also assist in the differential diagnosis of inflammatory diseases and in the assessment of the severity of the disease. In addition, researches about the applications of dermoscopy during surgical treatment have been published. Training courses aiming to improve the diagnostic ability of dermatologists, either face-to-face or online, have been offered. The Chinese Skin Image Database, launched in 2017 as a work platform for dermatologists, has promoted the development of dermoscopy in China. Computer-aided diagnostic systems based on the Chinese population are ready for use. In the future, cooperation, resource sharing, talent development, image management, and computer-aided diagnosis will be important directions for the development of dermoscopy in China.

CONCLUSION

Dermoscopy has been widely used and developed in China, however, it still needs to address more challenges in the future.