Deep neural networks have been investigated in learning latent representations of medical images, yet most of the studies limit their approach in a single supervised convolutional neural network (CNN), which usually rely heavily on a large scale annotated dataset for training. To learn image representations with less supervision involved, we propose a deep Siamese CNN (SCNN) architecture that can be trained with only binary image pair information. We evaluated the learned image representations on a task of content-based medical image retrieval using a publicly available multiclass diabetic retinopathy fundus image dataset. The experimental results show that our proposed deep SCNN is comparable to the state-of-the-art single supervised CNN, and requires much less supervision for training.
In this paper, a new texture descriptor named "Fractional Local Neighborhood Intensity Pattern" (FLNIP) has been proposed for content based image retrieval (CBIR). It is an extension of the Local Neighborhood Intensity Pattern (LNIP)[1]. FLNIP calculates the relative intensity difference between a particular pixel and the center pixel of a 3x3 window by considering the relationship with adjacent neighbors. In this work, the fractional change in the local neighborhood involving the adjacent neighbors has been calculated first with respect to one of the eight neighbors of the center pixel of a 3x3 window. Next, the fractional change has been calculated with respect to the center itself. The two values of fractional change are next compared to generate a binary bit pattern. Both sign and magnitude information are encoded in a single descriptor as it deals with the relative change in magnitude in the adjacent neighborhood i.e., the comparison of the fractional change. The descriptor is applied on four multi-resolution images -- one being the raw image and the other three being filtered gaussian images obtained by applying gaussian filters of different standard deviations on the raw image to signify the importance of exploring texture information at different resolutions in an image. The four sets of distances obtained between the query and the target image are then combined with a genetic algorithm based approach to improve the retrieval performance by minimizing the distance between similar class images. The performance of the method has been tested for image retrieval on four popular databases. The precision and recall values observed on these databases have been compared with recent state-of-art local patterns. The proposed method has shown a significant improvement over many other existing methods.
Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)-based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs post-contrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available. MIL has a variety of applications such as content-based image retrieval, text categorization and medical diagnosis. Most of the previous work for MIL assume that the training bags are fully labeled. However, it is often difficult to obtain an enough number of labeled bags in practical situations, while many unlabeled bags are available. A learning framework called PU learning (positive and unlabeled learning) can address this problem. In this paper, we propose a convex PU learning method to solve an MIL problem. We experimentally show that the proposed method achieves better performance with significantly lower computational costs than an existing method for PU-MIL.
콘텐츠 기반 이미지 검색(CBIR) 시스템은 메타데이터에만 의존하지 않고 시각적 콘텐츠를 기반으로 이미지를 검색할 수 있게 해 주는 컴퓨터 비전 분야의 핵심 도구로 자리 잡았다. 본 서베이 논문은 CBIR에 대한 포괄적인 개요를 제시하며, 객체 검출(object detection)에서 CBIR이 수행하는 역할과 콘텐츠 특징을 기반으로 시각적으로 유사한 이미지를 식별하고 검색할 수 있는 잠재력을 강조한다. 의미적 격차(semantic gap)와 확장성(scalability)을 비롯해 CBIR 시스템이 직면한 과제를 잠재적 해결책과 함께 논의한다. 또한 저수준 특징과 고수준 의미 개념 사이의 차이에서 비롯되는 의미적 격차를 자세히 설명하고, 이 격차를 해소하기 위한 접근법을 탐구한다. 주목할 만한 해결책 중 하나는 관련성 피드백(relevance feedback, RF)의 통합으로, 사용자가 검색된 이미지에 대해 피드백을 제공하고 검색 결과를 반복적으로 개선할 수 있게 한다. 본 서베이는 CBIR의 정확도와 관련성을 높이기 위해 RF를 활용하는 장기 및 단기 학습 접근법을 포괄한다. 이러한 방법들은 가중치(weight) 최적화와, 분류기 학습(training)에 사용할 샘플을 선택하기 위한 능동 학습(active learning) 알고리즘의 활용에 초점을 둔다. 나아가 본 논문은 CBIR 성능을 향상시키기 위한 머신러닝 기법과 심층 학습(deep learning) 및 합성곱 신경망(convolutional neural network)의 활용을 살펴본다. 본 서베이 논문은 CBIR과 RF 기법에 대한 이해를 증진하는 데 중요한 역할을 한다. 연구자와 실무자가 기존 방법론, 과제, 잠재적 해결책을 이해하도록 안내하고, 지식 확산을 촉진하며 연구 공백을 파악하게 한다. 향후 연구 방향을 다룸으로써, 다양한 응용 분야에서 검색 정확도, 사용성, 효과성을 높일 CBIR의 발전을 위한 토대를 마련한다.