Cue Integration for Medical Image Annotation

Tommasi, Tatiana; Orabona, Francesco; Caputo, Barbara

doi:10.1007/978-3-540-85760-0_72

Cited by 3 publications

(3 citation statements)

References 12 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, for deciding upon a dictionary size to be used for a specific application, one should identify the optimum tradeoffs of accuracy and computational efficiency. Even though a higher dictionary size provides better results in most applications on natural image classification1820, the size of a dictionary was found not to be particularly important in a medical image classification task44. Caicedo et al36 also report that their SIFT-based codebook required fewer codeblocks to express all different patterns in the histo-pathological image collection that they have tested, and claim their results to be consistent with the rotation and scale invariance properties of the SIFT descriptor.…”

Section: Resultsmentioning

confidence: 98%

Experimenting Liver Fibrosis Diagnostic by Two Photon Excitation Microscopy and Bag-of-Features Image Classification

Stanciu

Xu²,

Qian

et al. 2014

Sci Rep

View full text Add to dashboard Cite

The accurate staging of liver fibrosis is of paramount importance to determine the state of disease progression, therapy responses, and to optimize disease treatment strategies. Non-linear optical microscopy techniques such as two-photon excitation fluorescence (TPEF) and second harmonic generation (SHG) can image the endogenous signals of tissue structures and can be used for fibrosis assessment on non-stained tissue samples. While image analysis of collagen in SHG images was consistently addressed until now, cellular and tissue information included in TPEF images, such as inflammatory and hepatic cell damage, equally important as collagen deposition imaged by SHG, remain poorly exploited to date. We address this situation by experimenting liver fibrosis quantification and scoring using a combined approach based on TPEF liver surface imaging on a Thioacetamide-induced rat model and a gradient based Bag-of-Features (BoF) image classification strategy. We report the assessed performance results and discuss the influence of specific BoF parameters to the performance of the fibrosis scoring framework.

show abstract

Section: Resultsmentioning

confidence: 98%

Experimenting Liver Fibrosis Diagnostic by Two Photon Excitation Microscopy and Bag-of-Features Image Classification

Stanciu

Xu²,

Qian

et al. 2014

Sci Rep

View full text Add to dashboard Cite

show abstract

“…On top of this, one should remember that the problem presents a high inter-class vs intra-class variability, which also pushes for storing a large percentage of training data as support vectors. For a more detailed discussion of the results, we refer the reader to Tommasi et al (2007).…”

Section: Resultsmentioning

confidence: 99%

Discriminative cue integration for medical image annotation

Tommasi

Orabona

Caputo

2008

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

a b s t r a c tAutomatic annotation of medical images is an increasingly important tool for physicians in their daily activity. Hospitals nowadays produce an increasing amount of data. Manual annotation is very costly and prone to human mistakes. This paper proposes a multi-cue approach to automatic medical image annotation. We represent images using global and local features. These cues are then combined using three alternative approaches, all based on the support vector machine algorithm. We tested our methods on the IRMA database, and with two of the three approaches proposed here we participated in the 2007 ImageCLEFmed benchmark evaluation, in the medical image annotation track. These algorithms ranked first and fifth, respectively among all submission. Experiments using the third approach also confirm the power of cue integration for this task.

show abstract

“…In order to generate a codebook, K ‐means clustering algorithm is used and all the local features are clustered together independently using K = 500. Here K indicates the size of dictionary/codebook, however, codebook size is not significant in medical images [32]. An average of 32,770 vectors was identified for all lesions as well as for normal features to form 500 clusters.…”

Section: Methodsmentioning

confidence: 99%

Detection of severity level of diabetic retinopathy using Bag of features model

Leeza¹,

Farooq²

2019

IET Computer Vision

View full text Add to dashboard Cite

Diabetic retinopathy is a vascular disease caused by uncontrolled diabetes. Its early detection can save diabetic patients from blindness. However, the detection of its severity level is a challenge for ophthalmologists since last few decades. Several efforts have been made for the identification of its limited stages by using pre-and post-processing methods, which require extensive domain knowledge. This study proposes an improved automated system for severity detection of diabetic retinopathy which is a dictionary-based approach and does not include pre-and post-processing steps. This approach integrates pathological explicit image representation into a learning outline. To create the dictionary of visual features, points of interest are detected to compute the descriptive features from retinal images through speed up robust features algorithm and histogram of oriented gradients. These features are clustered to generate a dictionary, then coding and pooling are applied for compact representation of features. Radial basis kernel support vector machine and neural network are used to classify the images into five classes namely normal, mild, moderate, severe non-proliferative diabetic retinopathy, and proliferative diabetic retinopathy. The proposed system exhibits improved results of 95.92% sensitivity and 98.90% specificity in relation to the reported state of the art methods.

show abstract

Cue Integration for Medical Image Annotation

Cited by 3 publications

References 12 publications

Experimenting Liver Fibrosis Diagnostic by Two Photon Excitation Microscopy and Bag-of-Features Image Classification

Experimenting Liver Fibrosis Diagnostic by Two Photon Excitation Microscopy and Bag-of-Features Image Classification

Discriminative cue integration for medical image annotation

Detection of severity level of diabetic retinopathy using Bag of features model

Contact Info

Product

Resources

About