FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

• URL: http://arxiv.org/abs/2003.09108v1
• Date: Fri, 20 Mar 2020 05:12:31 GMT
• Title: FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
• Authors: Dong Wang, Yuan Zhang, Kexin Zhang, Liwei Wang
• Abstract summary: We propose a novel method, called FocalMix, which is the first to leverage recent advances in semi-supervised learning (SSL) for 3D medical image detection. Results show that our proposed SSL methods can achieve a substantial improvement of up to 17.3% over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.
• Score: 24.058713299186845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Applying artificial intelligence techniques in medical imaging is one of the most promising areas in medicine. However, most of the recent success in this area highly relies on large amounts of carefully annotated data, whereas annotating medical images is a costly process. In this paper, we propose a novel method, called FocalMix, which, to the best of our knowledge, is the first to leverage recent advances in semi-supervised learning (SSL) for 3D medical image detection. We conducted extensive experiments on two widely used datasets for lung nodule detection, LUNA16 and NLST. Results show that our proposed SSL methods can achieve a substantial improvement of up to 17.3% over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.

Related papers

• Towards Scalable Language-Image Pre-training for 3D Medical Imaging [49.18894445671976]
  We introduce Hierarchical attention for Language-Image Pre-training (HLIP), a scalable pre-training framework for 3D medical imaging.<n>HLIP adopts a lightweight hierarchical attention mechanism inspired by the natural hierarchy of radiology data: slice, scan, and study.<n>Trained on 220K patients with 3.13 million scans for brain MRI and 240K patients with 1.44 million scans for head CT, HLIP achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-28T01:16:34Z)
• The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound [60.80780313225093]
  This study systematically investigated the impact of data augmentation and preprocessing strategies in self-supervised learning for lung ultrasound. Three data augmentation pipelines were assessed: a baseline pipeline commonly used across imaging domains, a novel semantic-preserving pipeline designed for ultrasound, and a distilled set of the most effective transformations from both pipelines.
  arXiv  Detail & Related papers  (2025-04-10T16:26:47Z)
• Enhancing Retinal Disease Classification from OCTA Images via Active Learning Techniques [0.8035416719640156]
  Eye diseases are common in older Americans and can lead to decreased vision and blindness. Recent advancements in imaging technologies allow clinicians to capture high-quality images of the retinal blood vessels via Optical Coherence Tomography Angiography ( OCTA) OCTA provides detailed vascular imaging as compared to the solely structural information obtained by common OCT imaging.
  arXiv  Detail & Related papers  (2024-07-21T23:24:49Z)
• Medical Image Retrieval Using Pretrained Embeddings [0.6827423171182154]
  We show that medical image retrieval is feasible using pretrained networks without any additional training or fine-tuning steps. Using pretrained embeddings, we achieved a recall of 1 for various tasks at modality, body region, and organ level.
  arXiv  Detail & Related papers  (2023-11-22T17:42:33Z)
• Monsters in the Dark: Sanitizing Hidden Threats with Diffusion Models [4.443677138272269]
  Steganography is the art of hiding information in plain sight. Current image steganography defenses rely upon steganalysis, or the detection of hidden messages. Recent work has focused on a defense mechanism known as sanitization, which eliminates hidden information from images.
  arXiv  Detail & Related papers  (2023-10-10T19:15:11Z)
• PCDAL: A Perturbation Consistency-Driven Active Learning Approach for Medical Image Segmentation and Classification [12.560273908522714]
  Supervised learning deeply relies on large-scale annotated data, which is expensive, time-consuming, and impractical to acquire in medical imaging applications. Active Learning (AL) methods have been widely applied in natural image classification tasks to reduce annotation costs. We propose an AL-based method that can be simultaneously applied to 2D medical image classification, segmentation, and 3D medical image segmentation tasks.
  arXiv  Detail & Related papers  (2023-06-29T13:11:46Z)
• Multi-View Attention Learning for Residual Disease Prediction of Ovarian Cancer [8.697258566996126]
  We propose a novel Multi-View Attention Learning (MuVAL) method for residual disease prediction. Our method focuses on the comprehensive learning of 3D Computed Tomography (CT) images in a multi-view manner. Experiments on a dataset of 111 patients show that our method outperforms existing deep-learning methods.
  arXiv  Detail & Related papers  (2023-06-26T12:31:08Z)
• RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images [49.24576562557866]
  We propose a novel method called region-guided masked image modeling (RGMIM) for learning meaningful representations from X-ray images. RGMIM significantly improved performance in small data volumes, such as 5% and 10% of the training set compared to other methods.
  arXiv  Detail & Related papers  (2022-11-01T07:41:03Z)
• Dissecting Self-Supervised Learning Methods for Surgical Computer Vision [51.370873913181605]
  Self-Supervised Learning (SSL) methods have begun to gain traction in the general computer vision community. The effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection.
  arXiv  Detail & Related papers  (2022-07-01T14:17:11Z)
• Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis [68.5287824124996]
  We present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. We apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-29T08:41:17Z)
• Which images to label for few-shot medical landmark detection? [27.23114378514831]
  We propose a novel Sample Choosing Policy ( SCP) to select "the most worthy" images for annotation. SCP consists of three parts: 1) Self-supervised training for building a pre-trained deep model to extract features from radiological images, 2) Key Point Proposal for localizing informative patches, and 3) Representative Score Estimation for searching the most representative samples or templates. For one-shot medical landmark detection, its use reduces the mean radial errors on Cephalometric and HandXray datasets by 14.2% and 35.5%, respectively.
  arXiv  Detail & Related papers  (2021-12-07T07:46:18Z)
• Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning [62.13520959168732]
  We propose a semi-supervised learning framework for instrument segmentation in 3D US. To achieve the SSL learning, a Dual-UNet is proposed to segment the instrument. Our proposed method achieves Dice score of about 68.6%-69.1% and the inference time of about 1 sec. per volume.
  arXiv  Detail & Related papers  (2021-07-30T07:59:45Z)
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis [49.3704402041314]
  We propose a multi-stage attentive transfer learning framework for improving COVID-19 diagnosis. Our proposed framework consists of three stages to train accurate diagnosis models through learning knowledge from multiple source tasks and data of different domains. Importantly, we propose a novel self-supervised learning method to learn multi-scale representations for lung CT images.
  arXiv  Detail & Related papers  (2021-01-14T01:39:19Z)
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet [74.22397862400177]
  We propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation. With the detected catheter, patch-based Dual-UNet is applied to segment the catheter in 3D volumetric data.
  arXiv  Detail & Related papers  (2020-06-25T21:10:04Z)

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.