scholarly journals Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images

2020 ◽  
Vol 10 (21) ◽  
pp. 7761
Author(s):  
Zaneta Swiderska-Chadaj ◽  
Jaime Gallego ◽  
Lucia Gonzalez-Lopez ◽  
Gloria Bueno
Keyword(s):  
Breast Cancer ◽  
Mutual Information ◽  
Invasive Breast Cancer ◽  
Hot Spots ◽  
Cellular Proliferation ◽  
Hot Spot ◽  
Predictive Biomarker ◽  
Spot Detection ◽  
Color Deconvolution ◽  
Whole Slide Images

Ki67 hot-spot detection and its evaluation in invasive breast cancer regions play a significant role in routine medical practice. The quantification of cellular proliferation assessed by Ki67 immunohistochemistry is an established prognostic and predictive biomarker that determines the choice of therapeutic protocols. In this paper, we present three deep learning-based approaches to automatically detect and quantify Ki67 hot-spot areas by means of the Ki67 labeling index. To this end, a dataset composed of 100 whole slide images (WSIs) belonging to 50 breast cancer cases (Ki67 and H&E WSI pairs) was used. Three methods based on CNN classification were proposed and compared to create the tumor proliferation map. The best results were obtained by applying the CNN to the mutual information acquired from the color deconvolution of both the Ki67 marker and the H&E WSIs. The overall accuracy of this approach was 95%. The agreement between the automatic Ki67 scoring and the manual analysis is promising with a Spearman’s ρ correlation of 0.92. The results illustrate the suitability of this CNN-based approach for detecting hot-spots areas of invasive breast cancer in WSI.

scholarly journals Fully automated microvessel counting and hot spot selection by image processing of whole tumour sections in invasive breast cancer

1999 ◽  
Vol 52 (3) ◽  
pp. 184-192 ◽  
Author(s):  
J. A. Belien ◽  
S. Somi ◽  
J. S. de Jong ◽  
P. J. van Diest ◽  
J. P. Baak
Keyword(s):  
Breast Cancer ◽  
Image Processing ◽  
Invasive Breast Cancer ◽  
Hot Spot

Improving Earth hot-spot detection from MODIS data using MODVOLC algorithm

2020 ◽  
Author(s):  
Andrea Gabrieli ◽  
Robert Wright ◽  
Harold Garbeil ◽  
Eric Pilger
Keyword(s):  
Hot Spots ◽  
Thermal Emission ◽  
Hot Spot ◽  
Image Data ◽  
Anthropogenic Heat ◽  
Heat Sources ◽  
Lower Intensity ◽  
New Approach ◽  
Spot Detection ◽  
Modis Image

<p>Space-borne hot-spot detection on the Earth surface is key to monitoring and studying volcanic activity, wildfires and anthropogenic heat sources from space. Lower intensity thermal emission hot-spots, which often represent the onset of volcanic eruptions and large wildfires, are difficult to detect. We are improving the MODVOLC algorithm, which monitors Earth’s surface for hot-spots by analyzing Moderate Resolution Imaging Spectroradiometer (MODIS) data every 48 hours, to allow lower intensity thermal emission detection. Improving the existing MODVOLC algorithm for hot-spot detection from MODIS image data is not trivial. A new approach, which we refer it to as the Maximum Radiance Algorithm for MODIS, has been explored. The new approach requires a MODIS 4 µm and accompanying 12 µm global radiance time-series at ~1 km grid spacing. This reference data set describes the maximum radiance that has been measured from each square km of Earth’s surface over a ten year period (having first excluded high natural and anthropogenic heat sources from the time-series, using the existing MODVOLC approach). For each new geolocated MODIS image data, the observed radiance for each pixel is compared with this reference, and if its radiance exceeds the historical maximum, it can be considered a potential hot-spot. A dynamic tolerance is used to then confirm if the potential hot-spot is an actual hot-spot. We show that this new approach for hot-spot detection offers significant advantage over existing techniques for lower intensity thermal emission hot-spot detection during both day and nighttime conditions.</p>

scholarly journals Breast cancer mortality hot spots among Black women with de novo metastatic breast cancer

2020 ◽  
Author(s):  
Yunan Han ◽  
Marvin Langston ◽  
Lindsay Fuzzell ◽  
Saira Khan ◽  
Marquita W Lewis-Thames ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Metastatic Breast Cancer ◽  
Black Women ◽  
Cancer Mortality ◽  
Hot Spots ◽  
De Novo ◽  
Hot Spot ◽  
Breast Cancer Mortality ◽  
Metastatic Breast ◽  
The Us

Abstract Background Black women living in southern states have the highest breast cancer mortality rate in the US. The prognosis of de novo metastatic breast cancer is poor. Given these mortality rates, we are the first to link nationally representative data on breast cancer mortality hot spots (counties with high breast cancer mortality rates) with cancer mortality data in the US and investigate the association of geographic breast cancer mortality hot spots with de novo metastatic breast cancer mortality among Black women. Methods We identified 7,292 Black women diagnosed with de novo metastatic breast cancer in SEER. The county-level characteristics were obtained from 2014 County Health Rankings and linked to SEER. We used Cox proportional hazards models to calculate adjusted hazard ratios (aHRs) and 95% confidence interval (CIs) for mortality between hot spot and non-hot spot counties. Results Among 7,292 patients, 393 (5.4%) resided in breast cancer mortality hot spots. Women residing in hot spots had similar risks of breast cancer-specific mortality (aHR = 0.99; 95% CI = 0.85-1.15) and all-cause mortality (aHR = 0.97; 95% CI = 0.84-1.11) as women in non-hot spots after adjusting for individual and tumor-level factors, and treatments. Additional adjustment for county-level characteristics did not impact mortality. Conclusion Living in a breast cancer mortality hot spot was not associated with de novo metastatic breast cancer mortality among Black women. Future research should begin to examine variation in both individual and population-level determinants, as well in molecular and genetic determinants that underlie the aggressive nature of de novo metastatic breast cancer.

scholarly journals Comparison of the Manual, Semiautomatic, and Automatic Selection and Leveling of Hot Spots in Whole Slide Images for Ki-67 Quantification in Meningiomas

2015 ◽  
Vol 2015 ◽  
pp. 1-15 ◽  
Author(s):  
Zaneta Swiderska ◽  
Anna Korzynska ◽  
Tomasz Markiewicz ◽  
Malgorzata Lorent ◽  
Jakub Zak ◽  
...  
Keyword(s):  
Hot Spots ◽  
Interobserver Agreement ◽  
Hot Spot ◽  
Proliferation Index ◽  
Scoring Methods ◽  
Ki 67 ◽  
Tissue Sections ◽  
Automatic Methods ◽  
Whole Slide Images ◽  
Mib 1

Background. This paper presents the study concerning hot-spot selection in the assessment of whole slide images of tissue sections collected from meningioma patients. The samples were immunohistochemically stained to determine the Ki-67/MIB-1 proliferation index used for prognosis and treatment planning.Objective. The observer performance was examined by comparing results of the proposed method of automatic hot-spot selection in whole slide images, results of traditional scoring under a microscope, and results of a pathologist’s manual hot-spot selection.Methods. The results of scoring the Ki-67 index using optical scoring under a microscope, software for Ki-67 index quantification based on hot spots selected by two pathologists (resp., once and three times), and the same software but on hot spots selected by proposed automatic methods were compared using Kendall’s tau-b statistics.Results. Results show intra- and interobserver agreement. The agreement between Ki-67 scoring with manual and automatic hot-spot selection is high, while agreement between Ki-67 index scoring results in whole slide images and traditional microscopic examination is lower.Conclusions. The agreement observed for the three scoring methods shows that automation of area selection is an effective tool in supporting physicians and in increasing the reliability of Ki-67 scoring in meningioma.

scholarly journals RSTVOLC implementation on MODIS data for monitoring of thermal volcanic activity

2011 ◽  
Vol 54 (5) ◽  
Author(s):  
Teodosio Lacava ◽  
Francesco Marchese ◽  
Nicola Pergola ◽  
Valerio Tramutoli ◽  
Irina Coviello ◽  
...  
Keyword(s):  
Volcanic Activity ◽  
Hot Spots ◽  
Hot Spot ◽  
Mount Etna ◽  
Satellite Monitoring ◽  
Modis Data ◽  
Spot Detection ◽  
Moderate Resolution ◽  
Resolution Imaging ◽  
Moderate Resolution Imaging Spectroradiometer

An optimized configuration of the Robust Satellite Technique (RST) approach was developed within the framework of the ‘LAVA’ project. This project is funded by the Italian Department of Civil Protection and the Italian Istituto Nazionale di Geofisica e Vulcanologia, with the aim to improve the effectiveness of satellite monitoring of thermal volcanic activity. This improved RST configuration, named RSTVOLC, has recently been implemented in an automatic processing chain that was developed to detect hot-spots in near real-time for Italian volcanoes. This study presents the results obtained for the Mount Etna eruption of July 14-24, 2006, using the Moderate Resolution Imaging Spectroradiometer (MODIS) data. To better assess the operational performance, the RSTVOLC results are also discussed in comparison with those obtained by MODVOLC, a well-established, MODIS-based algorithm for hot-spot detection that is used worldwide.

scholarly journals Potential Application of Hough Transform to Extract Hot Spot Delineated Boundaries using Landsat-8 Satellite Images

2020 ◽  
Vol 9 (3) ◽  
pp. 3550-3557
Keyword(s):  
Hough Transform ◽  
Hot Spots ◽  
Large Scale ◽  
Hot Spot ◽  
Satellite Image ◽  
Detection Algorithm ◽  
Landsat 8 ◽  
Spot Detection ◽  
Canny Edge ◽  
Satellite Image Analysis

Coal fires, also known as subsurface fires or hot spots are all-inclusive issues in coal mines everywhere throughout the globe. Aimless mining over a period of past 100 years has prompted large scale damages to the ecosystem of the earth. For example, debasement in nature of water, soil, air, vegetation dissemination and variations in land topography have caused degradation. Research is needed to be more attentive on developing the prospective use of the satellite image analysis for hot spot detection because ground-based hot spots monitoring is time-taking, complex, cumbrous and very expensive. In this paper, a two-stage model has been developed to extract the hot spot delineated boundaries in Jharia coal field (JCF) region. In the first stage, contextual thresholding (CT) technique has been used to classify the hot spot and non-hot spot regions. After thorough processing, hot spots regions have been retrieved and for performance evaluation sensitivity and specificity are calculated, which suggest that hot spots were detected accurately in successful and efficient way. In second stage, the Canny edge detection algorithm is applied to detect the edges of the hot spot regions and then the binary image is generated, which is later converted into a vector image. Finally Hough transform is implemented on the obtained vector images for delineating hot spot boundaries. In future, delineated hot spot boundaries may be used to obtain the expansion or shrinking information of hot spot regions and it can be used for area estimation also.

Sign in / Sign up

Export Citation Format

Share Document