Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation

Murugesan, Balamurali; Sarveswaran, Kaushik; Shankaranarayana, Sharath M; Ram, Keerthi; Joseph, Jayaraj; Sivaprakasam, Mohanasankar

doi:10.1109/embc.2019.8857339

Cited by 122 publications

(51 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Endoscopy is an invasive imaging procedure in which the imaging device is inserted into an organ or cavity to take pictures. U-net has been applied to endoscopy images for segmentation of polyps in the gastrointestinal tract [97], [274], [301], [334], colon objects [59], detection of laryngeal leukoplakia [65], and detection of surgical instruments [335]. On electron microscopy images, applications include the detection of neuronal structures [161], [336], cell contour [161], [201], [232], and viruses [337].…”

Section: H Other Modalitiesmentioning

confidence: 99%

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to Xrays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net's potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

show abstract

Section: H Other Modalitiesmentioning

confidence: 99%

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Finally, in order to further adjust the category imbalance, we assign a specific weight to each type of label, the background label weight is assigned a value of 0.1, and the ET, WT, TC area label weight is assigned a value of 1.0. For the loss function of the distance transform encoder, we refer to the practice of Balamurali M. et al (29), using the mean square error loss. The loss function of the distance transform decoder is shown in (5),…”

Section: Loss Functionmentioning

confidence: 99%

A Deep Multi-Task Learning Framework for Brain Tumor Segmentation

et al. 2021

View full text Add to dashboard Cite

Glioma is the most common primary central nervous system tumor, accounting for about half of all intracranial primary tumors. As a non-invasive examination method, MRI has an extremely important guiding role in the clinical intervention of tumors. However, manually segmenting brain tumors from MRI requires a lot of time and energy for doctors, which affects the implementation of follow-up diagnosis and treatment plans. With the development of deep learning, medical image segmentation is gradually automated. However, brain tumors are easily confused with strokes and serious imbalances between classes make brain tumor segmentation one of the most difficult tasks in MRI segmentation. In order to solve these problems, we propose a deep multi-task learning framework and integrate a multi-depth fusion module in the framework to accurately segment brain tumors. In this framework, we have added a distance transform decoder based on the V-Net, which can make the segmentation contour generated by the mask decoder more accurate and reduce the generation of rough boundaries. In order to combine the different tasks of the two decoders, we weighted and added their corresponding loss functions, where the distance map prediction regularized the mask prediction. At the same time, the multi-depth fusion module in the encoder can enhance the ability of the network to extract features. The accuracy of the model will be evaluated online using the multispectral MRI records of the BraTS 2018, BraTS 2019, and BraTS 2020 datasets. This method obtains high-quality segmentation results, and the average Dice is as high as 78%. The experimental results show that this model has great potential in segmenting brain tumors automatically and accurately.

show abstract

“…The multitask UNet model is a network of encoder-decoder structures. On the left is the contracting encoder path, which uses a typical CNN architecture, and on the right, there are two deconvolutional decoder paths (23). The encoder path includes four repeated layers with two successive 3 × 3 convolutions, nonlinear activation, and max pooling operations that halve the size of the feature map after each convolutional layer.…”

Section: Vessel Segmentationmentioning

confidence: 99%

Automated Quantitative Analysis of Blood Flow in Extracranial–Intracranial Arterial Bypass Based on Indocyanine Green Angiography

Jiang

Zhang

et al. 2021

Front. Surg.

View full text Add to dashboard Cite

Microvascular imaging based on indocyanine green is an important tool for surgeons who carry out extracranial–intracranial arterial bypass surgery. In terms of blood perfusion, indocyanine green images contain abundant information, which cannot be effectively interpreted by humans or currently available commercial software. In this paper, an automatic processing framework for perfusion assessments based on indocyanine green videos is proposed and consists of three stages, namely, vessel segmentation based on the UNet deep neural network, preoperative and postoperative image registrations based on scale-invariant transform features, and blood flow evaluation based on the Horn–Schunck optical flow method. This automatic processing flow can reveal the blood flow direction and intensity curve of any vessel, as well as the blood perfusion changes before and after an operation. Commercial software embedded in a microscope is used as a reference to evaluate the effectiveness of the algorithm in this study. A total of 120 patients from multiple centers were sampled for the study. For blood vessel segmentation, a Dice coefficient of 0.80 and a Jaccard coefficient of 0.73 were obtained. For image registration, the success rate was 81%. In preoperative and postoperative video processing, the coincidence rates between the automatic processing method and commercial software were 89 and 87%, respectively. The proposed framework not only achieves blood perfusion analysis similar to that of commercial software but also automatically detects and matches blood vessels before and after an operation, thus quantifying the flow direction and enabling surgeons to intuitively evaluate the perfusion changes caused by bypass surgery.

show abstract

Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation

Cited by 122 publications

References 6 publications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

A Deep Multi-Task Learning Framework for Brain Tumor Segmentation

Automated Quantitative Analysis of Blood Flow in Extracranial–Intracranial Arterial Bypass Based on Indocyanine Green Angiography

Contact Info

Product

Resources

About