PyTorchKR Papers

최신 논문

총 413편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1511.06348

How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?

The use of Convolutional Neural Networks (CNN) in natural image classification systems has produced very impressive results. Combined with the inherent nature of medical images that make them ideal for deep-learning, further application of such systems to medical image classification holds much promise. However, the usefulness and potential impact of such a system can be completely negated if it does not reach a target accuracy. In this paper, we present a study on determining the optimum size of the training data set necessary to achieve high classification accuracy with low variance in medical image classification systems. The CNN was applied to classify axial Computed Tomography (CT) images into six anatomical classes. We trained the CNN using six different sizes of training data set (5, 10, 20, 50, 100, and 200) and then tested the resulting system with a total of 6000 CT images. All images were acquired from the Massachusetts General Hospital (MGH) Picture Archiving and Communication System (PACS). Using this data, we employ the learning curve approach to predict classification accuracy at a given training sample size. Our research will present a general methodology for determining the training data set size necessary to achieve a certain target classification accuracy that can be easily applied to other problems within such systems.

arXiv:1602.03409

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and the revival of deep CNN. CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

arXiv:1706.09092

Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning

The Classification of medical images and illustrations in the literature aims to label a medical image according to the modality it was produced or label an illustration according to its production attributes. It is an essential and challenging research hotspot in the area of automated literature review, retrieval and mining. The significant intra-class variation and inter-class similarity caused by the diverse imaging modalities and various illustration types brings a great deal of difficulties to the problem. In this paper, we propose a synergic deep learning (SDL) model to address this issue. Specifically, a dual deep convolutional neural network with a synergic signal system is designed to mutually learn image representation. The synergic signal is used to verify whether the input image pair belongs to the same category and to give the corrective feedback if a synergic error exists. Our SDL model can be trained 'end to end'. In the test phase, the class label of an input can be predicted by averaging the likelihood probabilities obtained by two convolutional neural network components. Experimental results on the ImageCLEF2016 Subfigure Classification Challenge suggest that our proposed SDL model achieves the state-of-the art performance in this medical image classification problem and its accuracy is higher than that of the first place solution on the Challenge leader board so far.

arXiv:1708.03111

Modality-bridge Transfer Learning for Medical Image Classification

This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target data, we propose a modality-bridge transfer learning which employs the bridge database in the same medical imaging acquisition modality as target database. By learning the projection function from source to bridge and from bridge to target, the domain difference between source (e.g., natural images) and target (e.g., X-ray images) can be mitigated. Experimental results show that the proposed method can achieve a high classification performance even for a small number of labeled target medical images, compared to various transfer learning approaches.

arXiv:1709.01872

Synthetic Medical Images from Dual Generative Adversarial Networks

Currently there is strong interest in data-driven approaches to medical image classification. However, medical imaging data is scarce, expensive, and fraught with legal concerns regarding patient privacy. Typical consent forms only allow for patient data to be used in medical journals or education, meaning the majority of medical data is inaccessible for general public research. We propose a novel, two-stage pipeline for generating synthetic medical images from a pair of generative adversarial networks, tested in practice on retinal fundi images. We develop a hierarchical generation process to divide the complex image generation task into two parts: geometry and photorealism. We hope researchers will use our pipeline to bring private medical data into the public domain, sparking growth in imaging tasks that have previously relied on the hand-tuning of models. We have begun this initiative through the development of SynthMed, an online repository for synthetic medical images.

arXiv:1608.06993공식 코드 · Papers with Code

Densely Connected Convolutional Networks

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet .

arXiv:1803.01229

GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification

Deep learning methods, and in particular convolutional neural networks (CNNs), have led to an enormous breakthrough in a wide range of computer vision tasks, primarily by using large-scale annotated datasets. However, obtaining such datasets in the medical domain remains a challenge. In this paper, we present methods for generating synthetic medical images using recently presented deep learning Generative Adversarial Networks (GANs). Furthermore, we show that generated medical images can be used for synthetic data augmentation, and improve the performance of CNN for medical image classification. Our novel method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). We first exploit GAN architectures for synthesizing high quality liver lesion ROIs. Then we present a novel scheme for liver lesion classification using CNN. Finally, we train the CNN using classic data augmentation and our synthetic data augmentation and compare performance. In addition, we explore the quality of our synthesized examples using visualization and expert assessment. The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results increased to 85.7% sensitivity and 92.4% specificity. We believe that this approach to synthetic data augmentation can generalize to other medical classification applications and thus support radiologists' efforts to improve diagnosis.

arXiv:1802.06955

Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation

Deep learning (DL) based semantic segmentation methods have been providing state-of-the-art performance in the last few years. More specifically, these techniques have been successfully applied to medical image classification, segmentation, and detection tasks. One deep learning technique, U-Net, has become one of the most popular for these applications. In this paper, we propose a Recurrent Convolutional Neural Network (RCNN) based on U-Net as well as a Recurrent Residual Convolutional Neural Network (RRCNN) based on U-Net models, which are named RU-Net and R2U-Net respectively. The proposed models utilize the power of U-Net, Residual Network, as well as RCNN. There are several advantages of these proposed architectures for segmentation tasks. First, a residual unit helps when training deep architecture. Second, feature accumulation with recurrent residual convolutional layers ensures better feature representation for segmentation tasks. Third, it allows us to design better U-Net architecture with same number of network parameters with better performance for medical image segmentation. The proposed models are tested on three benchmark datasets such as blood vessel segmentation in retina images, skin cancer segmentation, and lung lesion segmentation. The experimental results show superior performance on segmentation tasks compared to equivalent models including U-Net and residual U-Net (ResU-Net).

arXiv:1805.11837

Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels

Medical image classification involves thresholding of labels that represent malignancy risk levels. Usually, a task defines a single threshold, and when developing computer-aided diagnosis tools, a single network is trained per such threshold, e.g. as screening out healthy (very low risk) patients to leave possibly sick ones for further analysis (low threshold), or trying to find malignant cases among those marked as non-risk by the radiologist ("second reading", high threshold). We propose a way to rephrase the classification problem in a manner that yields several problems (corresponding to different thresholds) to be solved simultaneously. This allows the use of Multiple Task Learning (MTL) methods, significantly improving the performance of the original classifier, by facilitating effective extraction of information from existing data.

arXiv:1806.05473

Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples and add to the training data. We use conditional generative adversarial networks (cGANs) to generate realistic chest xray images with different disease characteristics by conditioning its generation on a real image sample. Informative samples to add to the training set are identified using a Bayesian neural network. Experiments show our proposed AL framework is able to achieve state of the art performance by using about 35% of the full dataset, thus saving significant time and effort over conventional methods.

arXiv:2607.10851v1cs.CV

집중 학습: 의료 이미지 분류를 위한 해부학 유도 어텐션 정규화

Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification

의료 이미지 분류 모델은 예측 시 진단적으로 관련된 영역을 식별하는 것이 이상적으로 기대되지만, 표준 분류 손실은 공간적 감독을 거의 제공하지 않는다. 과제 관련 해부학의 분할 마스크와 같은 해부학적 형태 정보를 통한 명시적 감독은 네트워크를 목표 예측에 관련된 영역으로 유도하는 것으로 나타났다. 그러나 이러한 마스크를 획득하는 데는 상당한 수동 어노테이션 노력과 계산 오버헤드가 수반된다. 다양한 영상 모달리티에서 해부학적 구조를 강력하게 위치 파악하는 분할 파운데이션 모델의 등장으로, 우리는 전용 분할 모델을 학습하는 부담 없이 해부학적 형태 사전 정보를 추출하기 위해 이 능력을 활용한다. 본 논문에서는 사전학습된 분할 파운데이션 모델을 활용하여 다양한 영상 모달리티에서 분류기의 어텐션을 진단적으로 의미 있는 해부학적 구조로 유도하는 해부학적 어텐션 정규화 프레임워크인 Locus를 제안한다. 파운데이션 모델에서 도출된 마스크와의 픽셀 단위 정렬을 강제하는 대신, 해부학적(전경) 영역과 배경 영역 사이의 어텐션을 적응적으로 균형 조정하는 정규화 항을 도입하여 배경 어텐션이 지배적일 때 분류기에 페널티를 부여한다. 우리는 피부경검사, X선, 조직병리학, 심장 MRI를 포괄하는 8개의 다양한 의료 영상 데이터셋에서 Locus를 검증하여, 향상된 해부학적 근거 어텐션과 함께 분류 성능의 일관된 향상을 보여준다.

arXiv:2607.03797v1cs.CV

의료 이미지 분류에서의 확률적 강건성

Probabilistic Robustness in Medical Image Classification

심층 학습(DL)은 의료 이미지 분류에서 강력한 성능을 보여왔으나, 예측 오류가 심각한 결과를 초래할 수 있는 안전 필수 임상 환경에서의 신뢰할 수 있는 배포는 여전히 어려운 과제이다. 기존 연구들은 주로 최악의 경우 관점에서 적대적 강건성(AR)에 초점을 맞추고 있으나, 이러한 설정은 실제 의료 응용을 충분히 반영하지 못할 수 있다. 본 연구에서는 모델 신뢰성의 보다 실용적인 측도로서 확률적 강건성(PR)을 조사한다. 이를 위해 의료 이미지 분류를 위한 자연 손상(natural corruption) 설정 집합을 구성하고, MedMNIST v2 데이터셋에서 일반적으로 사용되는 DL 모델을 체계적으로 평가한다. 본 연구는 DL 모델의 신뢰성 평가에 대한 통계적으로 근거 있는 관점을 제공함으로써, 의료 영상 응용에서 보다 신뢰할 수 있는 배포를 지원한다.

arXiv:2607.02591v1cs.CV

CPR: 거친-것에서-세밀한 의료 이미지 분류를 위한 연쇄 지각 정제

CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification

고해상도 의료 이미지에는 진단에 필수적인 세밀하고 공간적으로 희소한 단서가 포함되어 있으나, 전체 해상도를 유지하면 상당한 연산 및 메모리 비용이 발생한다. 대부분의 딥러닝 모델은 이미지를 균일하게 처리하므로, 다운샘플링 시 불필요한 연산이 발생하거나 진단적 세부 정보가 손실된다. 본 논문에서는 의료 이미지 분석을 순차적인 전역-에서-지역 의사결정 과정으로 정식화하는 거친-것에서-세밀한 프레임워크인 연쇄 지각 정제(CPR, Chained Perceptual Refinement)를 제안한다. 저해상도 전역 뷰에서 시작하여, CPR은 정제 영역의 위치와 공간적 범위를 동적으로 예측하고, 원본 이미지에서 고해상도 증거를 추출하며, 이를 전역 컨텍스트와 점진적으로 통합한다. 지각 필드를 축소하면서 백본 입력 크기를 고정함으로써, CPR은 일정한 최대 GPU 메모리로 진단적 충실도를 보존한다. 5개의 의료 이미지 데이터셋과 다수의 백본 아키텍처에 대한 광범위한 실험을 통해, CPR이 고정 해상도 및 다중 스케일 최신 기법 베이스라인 모두를 지속적으로 능가하며, 두 번째 최고 방법 대비 최대 2.27 퍼센트 포인트의 성능 향상을 달성함을 입증한다. 또한 동일한 정확도에서 GFLOPs를 최대 19.6배 감소시켜, 고해상도 의료 이미지 분석에서 우수한 정확도-효율성 트레이드오프를 확립한다. 코드는 GitHub에서 공개되어 있다.