Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUsing Top-Hat and Bottom-Hat Transforms for Contrast Enhancement of Mammograms
استخدام تحويلي TOP-HAT و BOTTOM-HAT لتحسين تباين صور الماموغرام
1521
1 30
0
(
0
)
Added by
Tishreen University ورقة بحثية
Publication date
2016
fields
Medical Device Engineering
and research's language is
العربية
Created by
Shamra Editor
Ask ChatGPT about the research
التصوير الشعاعي للثدي (الماموغرام) هو تقنية تستخدم على نطاق واسع للكشف عن سرطان الثدي، فبالرغم من وجود تقنيات أخرى مختلفة للكشف عن سرطان الثدي إلا أن التصوير الشعاعي للثدي هو الأسلوب الأكثر موثوقية و فعالية في الكشف المبكر عن سرطان الثدي. إن الصور التي يتم الحصول عليها عن طريق التصوير الشعاعي للثدي هي ذات تباين منخفض و هذا ما يسبب مشكلة لأطباء الأشعة لتشخيص المرض من هذه الصور، إذاً، تستخدم تقنيات معالجة الصورة في الحصول على صور ذات جودة عالية، بهدف استخلاص أي نوع من المعلومات منها، لذلك وضعت العديد من الخوارزميات لتحسين تباين الصورة خلال السنوات الماضية. في هذا العمل، اُقْتُرِحَتْ طريقة لتحسين تباين التكلسات في صور الماموغرام، تعتمد هذه الطريقة على تطبيق تحويلي القبعة العليا Top-Hat و القبعة السفلى Bottom –Hat و التي تعتمد على العمليات المورفولوجية الرياضية. اختبرت الطريقة على مجموعة صور ذات أنماط مختلفة من نسج الثدي من قاعدة بيانات معيارية mini-Mias . لتقييم أداء خوارزمية التحسين استخدم معيار تحسين التباين CII، و معيار نسبة ذروة الاشارة الى الضجيج PSNR بعد كل تحسين. تشير النتائج التجريبية أن الخوارزمية المقترحة لديها القدرة على تحسين نظام التشخيص بمساعدة الحاسب (CAD) و خاصة لنسج الثدي الكثيفة.
Mammography is widely used technique for breast cancer screening. There are various other techniques for breast cancer screening but mammography is the most reliable and effective technique. The images obtained through mammography are of low contrast which causes problem for the radiologists to interpret. Hence, a high quality image is mandatory for the processing of the image for extracting any kind of information. Many contrast enhancement algorithms have been developed over the years. This work presents a method to enhancement Microcalcifications in digitized mammograms. The method is based Mainly on the combination of Image Processing. The top-Hat and bottom–hat transforms are a techniques based on Mathematical morphology operations. This algorithm has been tested on mini-Mias database which have three types of breast tissues . For evaluation of performance of image enhancement algorithm, the Contrast Improvement Index (CII) and Peak Signal to Noise Ratio (PSNR) have been used. Experimental results suggest that algorithm can be improve significantly overall detection of the Computer-Aided Diagnosis (CAD) system especially for dense breast.
References used
BORING,C.C., SQUIRES, T.S. and TONG, T.; "Cancer statistics, 1992, CA", A Cancer Journal for Clinicians, Vol. 42, No. 1, pp. 19-38, 1992
JOHNS .P.C., YAFFE .M.J.,“X-ray characterization of normal and neoplastic breast tissues,” Physics Medical and Biology, Vol.32, no. 6, 1987, 675-695
THANGAVEL .K., KARAN .M., SIVAKUMAR .R., KAJA MOHIDEEN.A., “Automatic detection of microcalcification in mammograms: a review,” ICGST-GVIP Journal, Volume (5), Issue (5), May 2005
rate research
Read More
A mammogram is the best option for early detection of breast cancer,
Computer Aided Diagnostic systems(CADs) developed in order to
improve the diagnosis of mammograms. This paper presents a proposed
method to automatic images segmentation dependin
g on the Otsu's
method in order to detect microcalcifications and mass lesions in
mammogram images. The proposed technique is based on three steps:
(a) region of interest (ROI), (b) 2D wavelet transformation, and (c) OTSU
thresholding application on ROI. The method tested on standard mini-
MIAS database. It implemented within MATLAB software environment.
Experimental results and performance evaluate results show that the
proposed detection algorithm is a tool to help improve the diagnostic
performance, and has the possibility and the ability to detect the breast
lesions.
Breast cancer is the most widespread types of cancer among women. An efficient
diagnosis in its early stage can give women a better chance of full recovery. Calcification
is the important sign for early breast cancer detection. Mammography is the m
ost effective
method for breast cancer early detection using low radiation doses. The studies improved
the sensitivity of mammogram from 15% to 30% based on Computer Auto-Detection CAD
systems, which are used as a “second opinion” to alert the radiologist to structures that,
otherwise, might be overlooked. This article summarizes the various methods adopted for
micro-calcification cluster detection and compares their performance. Moreover, reasons
for the adoption of a common public image database as a test bench for CAD systems,
motivations for further CAD tool improvements, and the effectiveness of various CAD
systems in a clinical environment are given.
Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient, it is not
possible to directly use them with popular pre-trained language models trained using vanilla attention, without an expensive corrective pre-training stage. In this work, we propose a simple yet highly accurate approximation for vanilla attention. We process the queries in chunks, and for each query, compute the top-*k* scores with respect to the keys. Our approach offers several advantages: (a) its memory usage is linear in the input size, similar to linear attention variants, such as Performer and RFA (b) it is a drop-in replacement for vanilla attention that does not require any corrective pre-training, and (c) it can also lead to significant memory savings in the feed-forward layers after casting them into the familiar query-key-value framework. We evaluate the quality of top-*k* approximation for multi-head attention layers on the Long Range Arena Benchmark, and for feed-forward layers of T5 and UnifiedQA on multiple QA datasets. We show our approach leads to accuracy that is nearly-identical to vanilla attention in multiple setups including training from scratch, fine-tuning, and zero-shot inference.
This research gives a new type of encryption, using vectors give me a private
encryption key, which generates a triangular matrices from the top (bottom),
and check conditions matrix Hill.
These matrices resulting from private vectors constitute a relatively
preliminary numbers of size n = 256
The encryption process produces by multiplying the original matrix
encryption keys.
In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of the retrieval system and ho
w they complement each other. We propose a multi-stage framework comprising of pre-training with synthetic data, fine-tuning with labeled data, and negative sampling at both stages. We study six negative sampling strategies and apply them to the fine-tuning stage and, as a noteworthy novelty, to the synthetic data that we use for pre-training. Also, we explore fusion methods that combine negatives from different strategies. We evaluate our system using two passage retrieval tasks for open-domain QA and using MS MARCO. Our experiments show that augmenting the negative contrast in both stages is effective to improve passage retrieval accuracy and, importantly, they also show that synthetic data generation and negative sampling have additive benefits. Moreover, using the fusion of different kinds allows us to reach performance that establishes a new state-of-the-art level in two of the tasks we evaluated.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
