Generative Adversarial Networks based Skin Lesion Segmentation
- URL: http://arxiv.org/abs/2305.18164v2
- Date: Mon, 31 Jul 2023 16:10:03 GMT
- Title: Generative Adversarial Networks based Skin Lesion Segmentation
- Authors: Shubham Innani, Prasad Dutande, Ujjwal Baid, Venu Pokuri, Spyridon
Bakas, Sanjay Talbar, Bhakti Baheti, Sharath Chandra Guntuku
- Abstract summary: We propose a novel adversarial learning-based framework called Efficient-GAN that uses an unsupervised generative network to generate accurate lesion masks.
It outperforms the current state-of-the-art skin lesion segmentation approaches with a Dice coefficient, Jaccard similarity, and Accuracy of 90.1%, 83.6%, and 94.5%, respectively.
We also design a lightweight segmentation framework (MGAN) that achieves comparable performance as EGAN but with an order of magnitude lower number of training parameters.
- Score: 7.9234173309439715
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Skin cancer is a serious condition that requires accurate diagnosis and
treatment. One way to assist clinicians in this task is using computer-aided
diagnosis (CAD) tools that automatically segment skin lesions from dermoscopic
images. We propose a novel adversarial learning-based framework called
Efficient-GAN (EGAN) that uses an unsupervised generative network to generate
accurate lesion masks. It consists of a generator module with a top-down
squeeze excitation-based compound scaled path, an asymmetric lateral
connection-based bottom-up path, and a discriminator module that distinguishes
between original and synthetic masks. A morphology-based smoothing loss is also
implemented to encourage the network to create smooth semantic boundaries of
lesions. The framework is evaluated on the International Skin Imaging
Collaboration (ISIC) Lesion Dataset 2018. It outperforms the current
state-of-the-art skin lesion segmentation approaches with a Dice coefficient,
Jaccard similarity, and Accuracy of 90.1%, 83.6%, and 94.5%, respectively. We
also design a lightweight segmentation framework (MGAN) that achieves
comparable performance as EGAN but with an order of magnitude lower number of
training parameters, thus resulting in faster inference times for low compute
resource settings.
Related papers
- Inter-Scale Dependency Modeling for Skin Lesion Segmentation with
Transformer-based Networks [0.0]
Melanoma is a dangerous form of skin cancer caused by the abnormal growth of skin cells.
FCN approaches, including the U-Net architecture, can automatically segment skin lesions to aid diagnosis.
The symmetrical U-Net model has shown outstanding results, but its use of a convolutional operation limits its ability to capture long-range dependencies.
arXiv Detail & Related papers (2023-10-20T16:20:25Z) - Diffusion Models for Counterfactual Generation and Anomaly Detection in
Brain Images [59.85702949046042]
We present a weakly supervised method to generate a healthy version of a diseased image and then use it to obtain a pixel-wise anomaly map.
We employ a diffusion model trained on healthy samples and combine Denoising Diffusion Probabilistic Model (DDPM) and Denoising Implicit Model (DDIM) at each step of the sampling process.
We verify that when our method is applied to healthy samples, the input images are reconstructed without significant modifications.
arXiv Detail & Related papers (2023-08-03T21:56:50Z) - Self-Supervised Correction Learning for Semi-Supervised Biomedical Image
Segmentation [84.58210297703714]
We propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation.
We design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting.
Experiments on three medical image segmentation datasets for different tasks demonstrate the outstanding performance of our method.
arXiv Detail & Related papers (2023-01-12T08:19:46Z) - Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network.
We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module.
Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
arXiv Detail & Related papers (2022-12-01T07:32:56Z) - Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection
Segmentation System [69.40329819373954]
The coronavirus disease 2019 (COVID-19) continues to have a negative impact on healthcare systems around the world.
At the current stage, automatically segmenting the lung infection area from CT images is essential for the diagnosis and treatment of COVID-19.
We propose a boundary guided semantic learning network (BSNet) in this paper.
arXiv Detail & Related papers (2022-09-07T05:01:38Z) - Brain Lesion Synthesis via Progressive Adversarial Variational
Auto-Encoder [0.9954435559869312]
Region of interest (ROI) segmentation before and after laser interstitial thermal therapy (LITT) would enable automated lesion quantification.
CNNs are state-of-the-art solutions for ROI segmentation, but require large amounts of annotated data during the training.
We propose a progressive brain lesion synthesis framework (PAVAE) to expand both the quantity and diversity of the training dataset.
arXiv Detail & Related papers (2022-08-05T14:39:06Z) - Lesion Net -- Skin Lesion Segmentation Using Coordinate Convolution and
Deep Residual Units [18.908448254745473]
The accuracy of segmenting melanomas skin lesions is quite a challenging task due to less data for training, irregular shapes, unclear boundaries, and different skin colors.
Our proposed approach helps in improving the accuracy of skin lesion segmentation.
The results show that the proposed model either outperform or at par with the existing skin lesion segmentation methods.
arXiv Detail & Related papers (2020-12-28T14:43:04Z) - DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation.
Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives.
To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
arXiv Detail & Related papers (2020-08-19T06:02:46Z) - Collaborative Boundary-aware Context Encoding Networks for Error Map
Prediction [65.44752447868626]
We propose collaborative boundaryaware context encoding networks called AEP-Net for error prediction task.
Specifically, we propose a collaborative feature transformation branch for better feature fusion between images and masks, and precise localization of error regions.
The AEP-Net achieves an average DSC of 0.8358, 0.8164 for error prediction task, and shows a high Pearson correlation coefficient of 0.9873.
arXiv Detail & Related papers (2020-06-25T12:42:01Z) - Cascaded Context Enhancement Network for Automatic Skin Lesion
Segmentation [10.648218637920035]
We formulate a cascaded context enhancement neural network for automatic skin lesion segmentation.
A new context aggregation module with a gate-based information integration approach is proposed.
We evaluate our approach on four public skin dermoscopy image datasets.
arXiv Detail & Related papers (2020-04-17T08:25:17Z) - Complementary Network with Adaptive Receptive Fields for Melanoma
Segmentation [22.069817721081844]
Existing methods may suffer from the hole and shrink problems with limited segmentation performance.
We introduce a foreground network to detect melanoma lesions and a background network to mask non-melanoma regions.
Our method achieves a dice co-efficient of 86.4% and shows better performance compared with state-of-the-art melanoma segmentation methods.
arXiv Detail & Related papers (2020-01-12T09:20:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.