Medical Image Colorization for Better Visualization and Segmentation

Khan, Muhammad Usman Ghani; Gotoh, Yoshihiko; Nida, Nudrat

doi:10.1007/978-3-319-60964-5_50

Cited by 19 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It not only carries a plethora of clinically significant markers, but also it also serves as one of the most significant image of one's parenthood as well as for the child to get a surprise by looking back. Although, colorization of digital-images [8], [9] has been in practice for a long time [10], but it is critically important for medical images to be color-schematized without information-loss for enhanced visual clarity as well as enhancement of aesthetics. Adding clarity and aesthetics to fetal-USG imaging without information-loss to augment naturally grainy images is the main theme of this work.…”

Section: Introductionmentioning

confidence: 99%

Aestheticization of Ultrasound Images

Pal¹,

Vago²,

Ghosh³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div> <div> <div> <p>Ultrasound imaging is one of the most versatile imaging method in order to observe inner workings of human- body. Due to its simplicity, cost-effectiveness, easy availability and portability, a diverse set of applications are influenced by this very popular imaging modality. Despite its popularity as one of the most widely used imaging techniques, it has some serious limitations including lack of image clarity as well as complete absence of any visual aesthetics. Although, commonplace data filters can potentially make ultrasound images smoother looking, however, there is a significant loss of information introduced by the smoothing filters. In this article, we developed a method to enhance the image clarity as well as a protocol for enhancing image aesthetics for ultrasound modality using modern data-curation tool SOCKS. We performed few case studies using various color schemas applied on a publicly available fetal ultrasound image. The outlined technique can be easily generalized to any other kind of ultrasound images. We hypothesize that, our method would not only provide us with enhanced scientific accuracy, visual clarity of ultrasound images but also add additional layers of visual clarity coupled with artistic and aesthetic values. Our method calls for an complete rethinking of how we present ultrasound images </p> </div> </div> </div>

show abstract

Section: Introductionmentioning

confidence: 99%

Aestheticization of Ultrasound Images

Pal¹,

Vago²,

Ghosh³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Among them, medical image coloring is a common medical image processing direction. The color medical image has broad application prospects in the fields of image reconstruction, simulation, segmentation [2], virtual biopsy, virtual surgery and clinical image diagnosis reference, which can enhance the sense of visual reality and assist diagnosis. For example, Virtual Endoscopy(VE) which based on medical imaging and scientific visualization is to provide trusty means for medical diagnoses by noninvasive demonstration anatomical structures and human's lesions.…”

Section: Introductionmentioning

confidence: 99%

“…The color medical image can simulate the visual efferent of optical endoscope, and increase the intuitive feeling of virtual observation, which is conducive to the correct judgment of observation [3]. It has been proved by clinical practice practice that pseudo-color images can highlight the details of organs and tissues better comparing with gray images [4], which can help doctors make correct judgment and avoid misjudgment [5], and also help for medical image segmentation [2], such as the color medical image in Fig. 1 can easily distinguish to the chest and lungs, glioma center, brain and bone.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Medical Image Deep Color Perception Algorithm

Zeng

Tong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The existing medical imaging technologies have little consideration on color information, thus most of medical images are gray. Classical hand-craft features-based methods have obtained unsatisfactory results in colorizing medical images. Moreover, these methods ignore the deep feature of medical images that represent pathology and color information. In this paper, we propose a novel method that iteratively colorizes grayscale medical images under preserving content in fine-tuned deep neural network. To the best of our knowledge, there is no currently work that attempts to colorize the medical image by using deep neural network. Specifically, we propose Y-loss which is defined as nonlinear combination of 1 and 2 norm to preserve content invariance between target and colorized medical image. Then, adaptive reference image search algorithm is introduced to code reference and target medical image with D-hash and search reference image in hash code automatically, which free the manual selection of the reference image. Extensive experiment results show that the proposed method can generate higher quality colored medical image than recent state-of-the-art methods, and can be approved by the doctor. The objective evaluation (PSNR and SSIM) outperform an average increment 24% and 47% than baseline method, respectively. Our code is available at: https://github.com/Tongshiyue/Adaptive-medical-image-deep-color-perception-algorithm. INDEX TERMS Medical images enhance, color images, color transfer, deep neural network, automatic search.

show abstract

“…In this strategy, Hue is set to the same value of Intensity (2). That makes the shades vary from red to magenta for the gray shades from black to white respectively.…”

Section: A Equal To Intensity (Ei)mentioning

confidence: 99%

“…X-ray, CT, MRI, Ultrasound, Mammogram, Nuclear Medicine, PET, Ultrasound, and Thermal imaging are some of the famous imaging technologies [1,2]. Each of which has its suitable applications and features and exports gray shades images which usually come in low contrast intensities.…”

Section: Introductionmentioning

confidence: 99%