TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing

• URL: http://arxiv.org/abs/2303.07428v1
• Date: Mon, 13 Mar 2023 19:11:17 GMT
• Title: TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing
• Authors: Debesh Jha, Nikhil Kumar Tomar, Vanshali Sharma, Ulas Bagci
• Abstract summary: We propose a novel real-time deep learning based architecture, Transformer based Residual network (TransNetR) for colon polyp segmentation. TransNetR is an encoder-decoder network that consists of a pre-trained ResNet50 as the encoder, three decoder blocks, and an upsampling layer at the end of the network. It obtains a high dice coefficient of 0.8706 and a mean Intersection over union of 0.8016 and retains a real-time processing speed of 54.60 on the Kvasir-SEG dataset.
• Score: 2.3293678240472517
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Colonoscopy is considered the most effective screening test to detect colorectal cancer (CRC) and its precursor lesions, i.e., polyps. However, the procedure experiences high miss rates due to polyp heterogeneity and inter-observer dependency. Hence, several deep learning powered systems have been proposed considering the criticality of polyp detection and segmentation in clinical practices. Despite achieving improved outcomes, the existing automated approaches are inefficient in attaining real-time processing speed. Moreover, they suffer from a significant performance drop when evaluated on inter-patient data, especially those collected from different centers. Therefore, we intend to develop a novel real-time deep learning based architecture, Transformer based Residual network (TransNetR), for colon polyp segmentation and evaluate its diagnostic performance. The proposed architecture, TransNetR, is an encoder-decoder network that consists of a pre-trained ResNet50 as the encoder, three decoder blocks, and an upsampling layer at the end of the network. TransNetR obtains a high dice coefficient of 0.8706 and a mean Intersection over union of 0.8016 and retains a real-time processing speed of 54.60 on the Kvasir-SEG dataset. Apart from this, the major contribution of the work lies in exploring the generalizability of the TransNetR by testing the proposed algorithm on the out-of-distribution (test distribution is unknown and different from training distribution) dataset. As a use case, we tested our proposed algorithm on the PolypGen (6 unique centers) dataset and two other popular polyp segmentation benchmarking datasets. We obtained state-of-the-art performance on all three datasets during out-of-distribution testing. The source code of TransNetR will be made publicly available at https://github.com/DebeshJha.

Related papers

• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• TransRUPNet for Improved Polyp Segmentation [1.2498887792836635]
  We develop an advanced deep learning-based architecture, Transformer based Residual Upsampling Network (TransRUPNet) for automatic and real-time polyp segmentation. With the image size of $256times256$, the proposed method achieves an excellent real-time operation speed of 47.07 frames per second.
  arXiv  Detail & Related papers  (2023-06-03T19:06:06Z)
• Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network [3.1374864575817214]
  In this study, we introduce a novel deep learning architecture, named textbfMKDCNet, for automatic polyp segmentation. Experiments on four publicly available polyp datasets and cell nuclei dataset show that the proposed MKDCNet outperforms the state-of-the-art methods. MKDCNet can be a strong benchmark for building real-time systems for clinical colonoscopies.
  arXiv  Detail & Related papers  (2022-06-13T15:47:38Z)
• GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation [12.086664133486144]
  Colonoscopy is a gold standard procedure but is highly operator-dependent. Efforts have been made to automate the detection and segmentation of polyps, a precancerous precursor, to effectively minimize missed rate. Computer-aided polyp segmentation systems actuated by encoder-decoder have achieved high performance in terms of accuracy.
  arXiv  Detail & Related papers  (2021-11-20T15:41:59Z)
• DBSegment: Fast and robust segmentation of deep brain structures -- Evaluation of transportability across acquisition domains [0.18472148461613155]
  This paper uses deep learning to provide a robust and efficient deep brain segmentation solution. We trained the network to segment 30 deep brain structures, as well as a brain mask, using labels generated from a registration-based approach. Our proposed method is fast, robust, and generalizes with high reliability.
  arXiv  Detail & Related papers  (2021-10-18T17:15:39Z)
• MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection [80.83725644958633]
  Current deepfake generation methods leave discriminative artifacts in the frequency spectrum of fake images and videos. We present a novel approach, termed as MD-CSDNetwork, for combining the features in the spatial and frequency domains to mine a shared discriminative representation.
  arXiv  Detail & Related papers  (2021-09-15T14:11:53Z)
• Automatic Polyp Segmentation via Multi-scale Subtraction Network [100.94922587360871]
  In clinical practice, precise polyp segmentation provides important information in the early detection of colorectal cancer. Most existing methods are based on U-shape structure and use element-wise addition or concatenation to fuse different level features progressively in decoder. We propose a multi-scale subtraction network (MSNet) to segment polyp from colonoscopy image.
  arXiv  Detail & Related papers  (2021-08-11T07:54:07Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation [0.3734402152170273]
  We propose a novel architecture called DDANet'' based on a dual decoder attention network. Experiments demonstrate that the model trained on the Kvasir-SEG dataset and tested on an unseen dataset achieves a dice coefficient of 0.7874, mIoU of 0.7010, recall of 0.7987, and a precision of 0.8577.
  arXiv  Detail & Related papers  (2020-12-30T17:52:35Z)
• Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection [121.28769542994664]
  Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance. In this paper, we are the first to reveal that the region proposal network (RPN) and region proposal classifier(RPC) demonstrate significantly different transferability when facing large domain gap.
  arXiv  Detail & Related papers  (2020-09-17T07:39:52Z)
• DC-NAS: Divide-and-Conquer Neural Architecture Search [108.57785531758076]
  We present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures. We achieve a $75.1%$ top-1 accuracy on the ImageNet dataset, which is higher than that of state-of-the-art methods using the same search space.
  arXiv  Detail & Related papers  (2020-05-29T09:02:16Z)

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.