Shape-Aware Semi-supervised 3D Semantic Segmentation for Medical Images

Li, Shuailin; Zhang, Chuyu; He, Xuming

doi:10.1007/978-3-030-59710-8_54

Cited by 214 publications

(201 citation statements)

References 12 publications

Supporting

Mentioning

189

Contrasting

Order By: Relevance

“…Although SSL can improve the accuracy of natural images, its performance on medical images is unclear. Recently, some studies were proposed to determine whether SSL based on a small amount of labeled data and a large amount of unlabeled data can improve medical image analysis [28][29][30] , such as object detection 31 , data augmentation 32 , image segmentation 33,34 . However, only a very limited few studies have investigated if SSL can be applied to achieve satisfactory accuracy in pathological images 35 , where on a small data set of 115 WSIs, an SSL method of CRC recognition can achieve the best accuracy of 0.938 only at 7180 patches of 50 WSIs from one data center, suggesting the potential of SSL for pathological diagnosis on patch-level.…”

mentioning

confidence: 99%

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Sun

et al. 2021

Nat Commun

View full text Add to dashboard Cite

Machine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

show abstract

mentioning

confidence: 99%

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Sun

et al. 2021

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Recently, methods requiring less labeled data have gained attention, such as SSL (29)(30)(31)(32). Some studies have proven that when labeled data is limited, SSL can achieve good results in some medical images (29)(30)(31)(32). However, this conclusion has not been evaluated on a large scale, especially for medical images with large amounts of noise, artifacts, and low contrast, for example, breast ultrasound.…”

Section: Discussionmentioning

confidence: 99%

“…If semi-supervised learning is as accurate as supervised learning in the medical domain, then medical AI trained by semi-supervised learning may be more economical and faster in development by reducing the amount of data annotations needed. Further exploration is needed to determine whether semi-supervised learning using a small number of labeled images and a large number of unlabeled images can achieve satisfactory performance in medical image analysis, such as based on semi-supervised detection (28), magnetic resonance imaging image segmentation (29,30), data augmentation (31), and histology image classification (32).…”

Section: Original Articlementioning

confidence: 99%

Detection and recognition of ultrasound breast nodules based on semi-supervised deep learning: a powerful alternative strategy

Gao¹,

Liu²,

Zhu³

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The successful recognition of benign and malignant breast nodules using ultrasound images is based mainly on supervised learning that requires a large number of labeled images. However, because high-quality labeling is expensive and time-consuming, we hypothesized that semi-supervised learning could provide a low-cost and powerful alternative approach. This study aimed to develop an accurate semisupervised recognition method and compared its performance with supervised methods and sonographers.Methods: The faster region-based convolutional neural network was used for nodule detection from ultrasound images. A semi-supervised classifier based on the mean teacher model was proposed to recognize benign and malignant nodule images. The general performance of the proposed method on two datasets (8,966 nodules) was reported.Results: The detection accuracy was 0.88±0.03 and 0.86±0.02, respectively, on two testing sets (1,350 and 2,220 nodules). When 800 labeled training nodules were available, the proposed semi-supervised model plus 4,396 unlabeled nodules performed better than the supervised learning model (area under the curve (AUC): 0.934±0.026 vs. 0.83±0.050; 0.916±0.022 vs. 0.815±0.049). The performance of the semi-supervised model trained on 800 labeled and 4,396 unlabeled nodules was close to that of the supervised learning model trained on a massive number of labeled nodules (n=5,196) (AUC: 0.934±0.026 vs. 0.952±0.027; 0.916±0.022 vs. 0.918±0.017). Moreover, the semi-supervised model was better than the average accuracy of five human sonographers (AUC: 0.922 vs. 0.889). Conclusions:The semi-supervised model can achieve excellent performance for nodule recognition and be useful for medical sciences. The method reduced the number of labeled images required for training, thus significantly alleviating the difficulty in data preparation of medical artificial intelligence.

show abstract

“…Using unlabeled data, in such a way, implicitly extracts relevant features for the primary segmentation task. Li et al [14] proposed the prediction of surface distance maps to capture more effectively shape-aware features. Kervadec et al [12] predicted the size of the target segmentation as an intermediate task.…”

Section: Introductionmentioning

confidence: 99%

POPCORN: Progressive Pseudo-Labeling with Consistency Regularization and Neighboring

Kamraoui

Papadakis

et al. 2021

Medical Image Computing and Computer Assisted Intervention – MICCAI 2021

View full text Add to dashboard Cite

Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks. In this work, we propose POPCORN, a novel method combining consistency regularization and pseudo-labeling designed for image segmentation. The proposed framework uses high-level regularization to constrain our segmentation model to use similar latent features for images with similar segmentations. POPCORN estimates a proximity graph to select data from easiest ones to more difficult ones, in order to ensure accurate pseudo-labeling and to limit confirmation bias. Applied to multiple sclerosis lesion segmentation, our method demonstrates competitive results compared to other state-of-the-art SSL strategies.

show abstract

Shape-Aware Semi-supervised 3D Semantic Segmentation for Medical Images

Cited by 214 publications

References 12 publications

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Detection and recognition of ultrasound breast nodules based on semi-supervised deep learning: a powerful alternative strategy

POPCORN: Progressive Pseudo-Labeling with Consistency Regularization and Neighboring

Contact Info

Product

Resources

About