Computer aided detection
Dotaz
Zobrazit nápovědu
International Congress Series ; 1182
1st Ed. xii, 563 s. : il.
- Klíčová slova
- diagnostika, zobrazovací metody, zobrazovací diagnostika, počítačová diagnostika,
- Konspekt
- Lékařské vědy. Lékařství
- NLK Obory
- diagnostika
- lékařská informatika
Cílem studie je ukázat, že nově vyvinutá metoda automatické analýzy EEG dokáže rozpoznat abnormální fenomény novorozeneckého EEG a je schopna závažnost odchylky zhodnotit kvantitativně. Analyzovány byly digitální EEG záznamy 36 novorozenců, u nichž bylo EEG vyšetření indikováno z klinických důvodů. Pětiminutové vzorky EEG aktivity ze standardizovaného behaviorálního stavu byly za použití počítačem podporované čtyřstupňové analýzy popsány 312 číselnými položkami, informujícími o amplitudě, výkonu v pěti frekvenčních pásmech, o tvaru signálu a o jeho stálosti či proměnlivosti. Každá z těchto položek byla automaticky porovnána s normativním údajem, získaným vyšetřením 21 zdravých donosených novorozenců, a testována, liší-li se od normy o jednu či o dvě směrodatné odchylky. Počet pacientových položek lišících se od normy byl úměrný závažnosti jeho abnormality. Orientační porovnání výsledků automatické a vizuální analýzy pacientských elektroencefalogramů osvědčilo dobrou shodu. Metoda je příslibem pro klinickou praxi, neboť může významně přispět jak ke zrychlení, tak i k objektivizaci hodnocení novorozeneckého EEG.
The study aims to demonstrate that the newly developed method of automated EEG analysis can detect abnormal phenomena in the neonatal EEG and can quantify the severity of the deviation from the norm. EEG records from 36 neonates with clinically indicated EEG examination were analyzed. Five-minutes samples of EEG activity during a standardized behavioral state were processed using a computer-supported four-stage analysis and described with 312 numerical items, providing the information on amplitude, power in five frequency bands, on signal shape and its stability or variability. Each of these items was automatically compared to normative data acquired from the examination of 21 healthy, full term neonates and tested whether it differs by one or two standard deviations from the norm. The number of patient's items differing from the norm was proportional to the severity of their abnormality. A cursory comparison of the results of automatic and visual analyses of patienť EEG records showed good agreement. The method shows promise for the clinical practice, where it can significantly contribute to both acceleration and greater objectivity of neonatal EEG assessment.
Background: Breast cancer is one of the leading cancers in woman worldwide both in developed and developing nations as per the records from World Health Organization. Many studies have shown that mammography is very effective tool for the breast cancer diagnosis. Mass segmentation plays an important step for the cancer detection. Objective: The objective of the proposed method is to segment the mass and to classify the mass with high accuracy. Methods: The segmentation includes two main steps. First, a rough initial segmentation through iterative thresholding, and second, an active contour based segmentation. The relevant statistical features are extracted and the classification is done by using Adaptive Neuro Fuzzy Inference System (ANFIS). Results: The proposed mass detection scheme achieves sensitivity of 87.5% and specificity of 100% for a set of twenty two images. The overall segmentation accuracy obtained is 91.30%. Conclusions: This work appears to be of high clinical significance since the mass detection plays an important role in diagnosis of breast cancer.
BACKGROUND AND PURPOSE: MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting. MATERIALS AND METHODS: Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used. RESULTS: For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity. CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.
- MeSH
- algoritmy * MeSH
- diagnóza počítačová metody MeSH
- intrakraniální aneurysma radiografie MeSH
- lidé MeSH
- magnetická rezonanční angiografie metody MeSH
- retrospektivní studie MeSH
- Check Tag
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Cíl. Zhodnotit praktický přínos sofwaru pro automatickou detekci malých plicních uzlů. Metoda. Dva radiologové s různou délkou praxe (R1 ? 1,5 roku, R2 ? 10 let) hodnotili počet uzlů a vyšetřovací časy u 14 CT vyšetření nemocných s vícečetnými plicními metastázami. V první fázi studie bylo provedeno hodnocení běžným způsobem. Ve druhé fázi byl použit systém pro automatickou detekci (CAD) plicních uzlů Syngo Lung CAD (Siemens, Forchheim, SRN). Výsledky. Při použití CAD došlo v obou případech ke zvýšení počtu detekovaných uzlů. Rozdíl v jejich celkovém počtu byl statisticky nevýznamný (R1 o 10,8 %, p = 0,077; R2 o 3,8 %, p = 0,66). U méně zkušeného radiologa (R1) byl ale zjištěn statisticky významný rozdíl v počtu uzlů velikosti do 8 mm (zvýšení počtu o 12 % ve skupině velikosti do 4 mm, p = 0,006 a o 10,7 % ve skupině o velikosti 5?8 mm, p = 0,001) a u zkušenějšího radiologa (R2) u uzlů velikosti do 4 mm (zvýšení počtu o 6,2 %, p = 0,008). V obou případech bylo zaznamenáno statisticky významné zkrácení časů potřebných pro hodnocení (u R1 o 62 %, p < 0,001; u R2 o 32 %, p < 0,001). Závěr. Systém CAD zvýšil počet detekovaných malých plicních uzlů a zkrátil čas potřebný pro hodnocení. Přínosnější byl pro radiologa s kratší praxí.
Aim. To evaluate the feasibility of sofware for computer-aided detection (CAD) of small pumonary nodules. Method. Two radiologists with different experience (R1 ? 1.5 year, R2 ? 10 years) assessed the number of nodules and the evaluation times in 14 CT examinations of patients with multiple pulmonary metastases. In the first instance, they performed the evaluation in an accustomed way. Tey performed repeated evaluation with CAD system Syngo Lung CAD (Siemens, Forchheim, FRG) afer 14 days. Results. Te applicaton of CAD system increased the number of detected nodules. Te difference in their total number was not significant (R1 +10.8%, p = 0.77; R2 +3.8%, p = 0.66). But in the less experienced radiologist (R1) was found significant difference in the number of nodules with size up to 8 mm (+12 % in the group of nodules up to 4 mm, p = 0.006 and +10.7 % in the group with size 5?8 mm, p = 0.001). In the more experienced radiologist (R2) was found significant increase of the number of nodules in the group with size up to 4 mm (+6.2 %, p = 0.008). In both cases was achieved significant shortening of evaluation times (R1 -62%, p < 0.001; R2 -32 %, p < 0.001). Conclusion. Te application of CAD sofware increased the number of detected lung nodules and decreased evaluation time. It looks more helpful for less experienced radiologist.
- MeSH
- diagnóza počítačová metody přístrojové vybavení využití MeSH
- financování organizované MeSH
- interpretace statistických dat MeSH
- metastázy nádorů diagnóza MeSH
- počítačová rentgenová tomografie metody využití MeSH
- software normy trendy MeSH
- solitární plicní uzel diagnóza patologie MeSH
- tomografie spirální počítačová metody využití MeSH
- zobrazování trojrozměrné metody přístrojové vybavení využití MeSH
The aim of this study was a comparison of sperm concentration and motility (percentage of WHO A+B group) by standard spermiogram evaluation with computer-aided sperm analysis (CASA) for testing of their possible clinical impact. Methods: We have analyzed 105 ejaculate samples. The standard spermiogram evaluation was performed by bright field microscopy in the Makler chamber without heated stage. CASA was done with negative phase contrast in the Makler chamber with stage heated at 37 °C using the medeaLAB CASA software (MTG Medical Technology Vertriebs GmbH) with analog camera. Differences between both methods were evaluated by MS Excel software. Results: Average value of sperm concentration was 68 mil./ml by standard counting and 87,7 mil./ml by CASA. Median value of sperm concentration was 57 mil./ml by standard counting and 71,5 mil./ml by CASA. Average difference between the concentrations by the two methods was 46 mil./ml. Median difference between the concentrations by the two methods was 33,5 mil./ml. Correlation coefficient between the results of the two methods was 0,44. Average value of sperm motility was 50,9% by standard counting and 50,9% by CASA. Median value of sperm motility was 50% by standard counting and 50% by CASA. Average difference between the motility percentages by the two methods was 15,2%, median difference was 12,1%. The correlation coefficient between the results of the two methods was 0,71. Conclusion: The differences can be explained by difficulty of detection of moving sperm and sperm crossing of the chamber fields borders by human eye, by rather low frequency/resolution and higher sensitivity to focusing and lighting irregularities of the camera, by negative phase contrast and microscope stage heating used for CASA. Computer-aided sperm analysis (CASA) offers more objective sperm evaluation than analysis by human eye.
Využití umělé inteligence jako asistenční detekční metody v endoskopii se v uplynulých letech těší zvyšujícímu se zájmu. Algoritmy strojového učení slibují zefektivnění detekce polypů, a dokonce optickou lokalizaci nálezů, to vše s minimálním zaškolením endoskopisty. Praktickým cílem této studie je analýza CAD softwaru (computer-aided diagnosis) Carebot pro detekci kolorektálních polypů s využitím konvoluční neuronové sítě. Navržený binární klasifikátor pro detekci polypů dosahuje přesnosti až 98 %, specificity 0,99 a preciznosti 0,96. Současně je diskutována nezbytnost dostupnosti rozsáhlých klinických dat pro vývoj modelů na bázi umělé inteligence pro automatickou detekci adenomů a benigních neoplastických lézí.
The use of artificial intelligence as an assistive detection method in endoscopy has attracted increasing interest in recent years. Machine learning algorithms promise to improve the efficiency of polyp detection and even optical localization of findings, all with minimal training of the endoscopist. The practical goal of this study is to analyse the CAD software (computer-aided diagnosis) Carebot for colorectal polyp detection using a convolutional neural network. The proposed binary classifier for polyp detection achieves accuracy of up to 98%, specificity of 0.99 and precision of 0.96. At the same time, the need for the availability of large-scale clinical data for the development of artificial--intelligence-based models for the automatic detection of adenomas and benign neoplastic lesions is discussed.
- Klíčová slova
- prostorová lokalizace,
- MeSH
- diagnóza počítačová * MeSH
- lidé MeSH
- neuronové sítě MeSH
- polypy střeva * diagnóza MeSH
- umělá inteligence MeSH
- Check Tag
- lidé MeSH
... Proteomic strategies for the early detection of lung cancer 117 -- Pierre P Massion, Pinar ? ... ... New directions in spiral CT image processing and computer-aided diagnosis 205 -- Anthony P Reeves, Andinet ... ... Diagnostic workup of screen-detected lesions 223 -- David E Midthun, Stephen J Swensen, James R Jett ... ... The pathology of screen-detected lesions 245 -- Keith M Kerr, Masayuki Noguchi -- 16. ... ... Surgical approaches to screen-detected lesions and tissue acquisition for translational research 269 ...
First published xii, 396 stran : ilustrováno ; 26 cm
- MeSH
- časná detekce nádoru MeSH
- diagnostické techniky dýchacího ústrojí MeSH
- nádory plic * diagnóza prevence a kontrola MeSH
- Publikační typ
- učebnice MeSH
- Konspekt
- Patologie. Klinická medicína
- NLK Obory
- pneumologie a ftizeologie
- onkologie
- NLK Publikační typ
- kolektivní monografie
Wireless capsule endoscopy (WCE) is one of the most efficient methods for the examination of gastrointestinal tracts. Computer-aided intelligent diagnostic tools alleviate the challenges faced during manual inspection of long WCE videos. Several approaches have been proposed in the literature for the automatic detection and localization of anomalies in WCE images. Some of them focus on specific anomalies such as bleeding, polyp, lesion, etc. However, relatively fewer generic methods have been proposed to detect all those common anomalies simultaneously. In this paper, a deep convolutional neural network (CNN) based model 'WCENet' is proposed for anomaly detection and localization in WCE images. The model works in two phases. In the first phase, a simple and efficient attention-based CNN classifies an image into one of the four categories: polyp, vascular, inflammatory, or normal. If the image is classified in one of the abnormal categories, it is processed in the second phase for the anomaly localization. Fusion of Grad-CAM++ and a custom SegNet is used for anomalous region segmentation in the abnormal image. WCENet classifier attains accuracy and area under receiver operating characteristic of 98% and 99%. The WCENet segmentation model obtains a frequency weighted intersection over union of 81%, and an average dice score of 56% on the KID dataset. WCENet outperforms nine different state-of-the-art conventional machine learning and deep learning models on the KID dataset. The proposed model demonstrates potential for clinical applications.
PURPOSE: Medium vessel occlusions (MeVOs) can be challenging to detect on imaging. Multiphase computed tomography angiography (mCTA) has been shown to improve large vessel occlusion (LVO) detection and endovascular treatment (EVT) selection. The aims of this study were to determine if mCTA-derived tissue maps can (1) accurately detect MeVOs and (2) predict infarction on 24-h follow-up imaging with comparable accuracy to CT perfusion (CTP). METHODS: Two readers assessed mCTA tissue maps of 116 ischemic stroke patients (58 MeVOs, 58 non-MeVOs) and determined by consensus: (1) MeVO (yes/no) and (2) occlusion site, blinded to clinical or imaging data. Sensitivity, specificity, and area under the curve (AUC) for MeVO detection were estimated in comparison to reference standards of (1) expert readings of baseline mCTA and (2) CTP maps. Volumetric and spatial agreement between mCTA- and CTP-predicted infarcts was assessed using concordance/intraclass correlation and Dice coefficients. Interrater agreement for MeVO detection on mCTA tissue maps was estimated with Cohen's kappa. RESULTS: MeVO detection from mCTA-derived tissue maps had a sensitivity of 91% (95% CI: 80-97), specificity of 82% (95% CI: 70-90), and AUC of 0.87 (95% CI: 0.80-0.93) compared to expert reads of baseline mCTA. Interrater reliability was good (0.72, 95% CI: 0.60-0.85). Compared to CTP maps, sensitivity was 87% (95% CI: 75-95), specificity was 78% (95%CI: 65-88), and AUC was 0.83 (95% CI: 0.76-0.90). The mean difference between mCTA- and CTP-predicted final infarct volume was 4.8 mL (limits of agreement: - 58.5 to 68.1) with a Dice coefficient of 33.5%. CONCLUSION: mCTA tissue maps can be used to reliably detect MeVO stroke and predict tissue fate.
- MeSH
- cévní mozková příhoda * diagnostické zobrazování terapie MeSH
- CT angiografie metody MeSH
- cytidintrifosfát MeSH
- ischemie mozku * terapie MeSH
- lidé MeSH
- mozková angiografie metody MeSH
- počítačová rentgenová tomografie metody MeSH
- reprodukovatelnost výsledků MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH