Gold rose to 3,354.76 USD/t.oz on July 11, 2025, up 0.92% from the previous day. Over the past month, Gold's price has fallen 0.92%, but it is still 39.14% higher than a year ago, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Gold - values, historical data, forecasts and news - updated on July of 2025.

Silver rose to 38.37 USD/t.oz on July 11, 2025, up 3.65% from the previous day. Over the past month, Silver's price has risen 5.59%, and is up 24.68% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Silver - values, historical data, forecasts and news - updated on July of 2025.

Bullion Price: Monthly Average: Mumbai: Gold: Standard data was reported at 84,995.000 INR/10 g in Feb 2025. This records an increase from the previous number of 79,079.000 INR/10 g for Jan 2025. Bullion Price: Monthly Average: Mumbai: Gold: Standard data is updated monthly, averaging 9,691.000 INR/10 g from Apr 1990 (Median) to Feb 2025, with 419 observations. The data reached an all-time high of 84,995.000 INR/10 g in Feb 2025 and a record low of 3,285.000 INR/10 g in Jul 1990. Bullion Price: Monthly Average: Mumbai: Gold: Standard data remains active status in CEIC and is reported by Reserve Bank of India. The data is categorized under Global Database’s India – Table IN.PG002: Memo Items: Bullion Price.

About this dataset

Context

The dataset tabulates the Gold Bar population over the last 20 plus years. It lists the population for each year, along with the year on year change in population, as well as the change in percentage terms for each year. The dataset can be utilized to understand the population change of Gold Bar across the last two decades. For example, using this dataset, we can identify if the population is declining or increasing. If there is a change, when the population peaked, or if it is still growing and has not reached its peak. We can also compare the trend with the overall trend of United States population over the same period of time.

Key observations

In 2023, the population of Gold Bar was 2,411, a 0.46% increase year-by-year from 2022. Previously, in 2022, Gold Bar population was 2,400, a decline of 0.37% compared to a population of 2,409 in 2021. Over the last 20 plus years, between 2000 and 2023, population of Gold Bar increased by 345. In this period, the peak population was 2,412 in the year 2020. The numbers suggest that the population has already reached its peak and is showing a trend of decline. Source: U.S. Census Bureau Population Estimates Program (PEP).

Content

When available, the data consists of estimates from the U.S. Census Bureau Population Estimates Program (PEP).

Data Coverage:

• From 2000 to 2023

Variables / Data Columns

• Year: This column displays the data year (Measured annually and for years 2000 to 2023)
• Population: The population for the specific year for the Gold Bar is shown in this column.
• Year on Year Change: This column displays the change in Gold Bar population for each year compared to the previous year.
• Change in Percent: This column displays the year on year change as a percentage. Please note that the sum of all percentages may not equal one due to rounding of values.

Good to know

Margin of Error

Data in the dataset are based on the estimates and are subject to sampling variability and thus a margin of error. Neilsberg Research recommends using caution when presening these estimates in your research.

Custom data

If you do need custom data for any of your research project, report or presentation, you can contact our research staff at research@neilsberg.com for a feasibility of a custom tabulation on a fee-for-service basis.

Inspiration

Neilsberg Research Team curates, analyze and publishes demographics and economic data from a variety of public and proprietary sources, each of which often includes multiple surveys and programs. The large majority of Neilsberg Research aggregated datasets and insights is made available for free download at https://www.neilsberg.com/research/.

Recommended for further research

This dataset is a part of the main dataset for Gold Bar Population by Year. You can refer the same here

Dataset of historical annual silver prices from 1970 to 2022, including significant events and acts that impacted silver prices.

Hong Kong Local Gold Prices data was reported at 11,422.000 HKD/Tael in Nov 2018. This records an increase from the previous number of 11,403.000 HKD/Tael for Oct 2018. Hong Kong Local Gold Prices data is updated monthly, averaging 3,611.000 HKD/Tael from Jan 1981 (Median) to Nov 2018, with 455 observations. The data reached an all-time high of 17,028.000 HKD/Tael in Aug 2011 and a record low of 2,213.000 HKD/Tael in Jun 1982. Hong Kong Local Gold Prices data remains active status in CEIC and is reported by Census and Statistics Department. The data is categorized under Global Database’s Hong Kong SAR – Table HK.P003: Gold and Silver Prices.

Rhodium traded flat at 5,700 USD/t oz. on July 11, 2025. Over the past month, Rhodium's price has risen 3.64%, and is up 23.91% compared to the same time last year, according to trading on a contract for difference (CFD) that tracks the benchmark market for this commodity. Rhodium - values, historical data, forecasts and news - updated on July of 2025.

About this dataset

Context

The dataset tabulates the Gold Beach population over the last 20 plus years. It lists the population for each year, along with the year on year change in population, as well as the change in percentage terms for each year. The dataset can be utilized to understand the population change of Gold Beach across the last two decades. For example, using this dataset, we can identify if the population is declining or increasing. If there is a change, when the population peaked, or if it is still growing and has not reached its peak. We can also compare the trend with the overall trend of United States population over the same period of time.

Key observations

In 2022, the population of Gold Beach was 2,358, a 0.46% decrease year-by-year from 2021. Previously, in 2021, Gold Beach population was 2,369, an increase of 0.85% compared to a population of 2,349 in 2020. Over the last 20 plus years, between 2000 and 2022, population of Gold Beach increased by 327. In this period, the peak population was 2,369 in the year 2021. The numbers suggest that the population has already reached its peak and is showing a trend of decline. Source: U.S. Census Bureau Population Estimates Program (PEP).

Content

When available, the data consists of estimates from the U.S. Census Bureau Population Estimates Program (PEP).

Data Coverage:

• From 2000 to 2022

Variables / Data Columns

• Year: This column displays the data year (Measured annually and for years 2000 to 2022)
• Population: The population for the specific year for the Gold Beach is shown in this column.
• Year on Year Change: This column displays the change in Gold Beach population for each year compared to the previous year.
• Change in Percent: This column displays the year on year change as a percentage. Please note that the sum of all percentages may not equal one due to rounding of values.

Good to know

Margin of Error

Data in the dataset are based on the estimates and are subject to sampling variability and thus a margin of error. Neilsberg Research recommends using caution when presening these estimates in your research.

Custom data

If you do need custom data for any of your research project, report or presentation, you can contact our research staff at research@neilsberg.com for a feasibility of a custom tabulation on a fee-for-service basis.

Inspiration

Neilsberg Research Team curates, analyze and publishes demographics and economic data from a variety of public and proprietary sources, each of which often includes multiple surveys and programs. The large majority of Neilsberg Research aggregated datasets and insights is made available for free download at https://www.neilsberg.com/research/.

Recommended for further research

This dataset is a part of the main dataset for Gold Beach Population by Year. You can refer the same here

About this dataset

Context

The dataset tabulates the Gold Hill population over the last 20 plus years. It lists the population for each year, along with the year on year change in population, as well as the change in percentage terms for each year. The dataset can be utilized to understand the population change of Gold Hill across the last two decades. For example, using this dataset, we can identify if the population is declining or increasing. If there is a change, when the population peaked, or if it is still growing and has not reached its peak. We can also compare the trend with the overall trend of United States population over the same period of time.

Key observations

In 2022, the population of Gold Hill was 1,330, a 1.41% decrease year-by-year from 2021. Previously, in 2021, Gold Hill population was 1,349, an increase of 0.90% compared to a population of 1,337 in 2020. Over the last 20 plus years, between 2000 and 2022, population of Gold Hill increased by 174. In this period, the peak population was 1,349 in the year 2021. The numbers suggest that the population has already reached its peak and is showing a trend of decline. Source: U.S. Census Bureau Population Estimates Program (PEP).

Content

When available, the data consists of estimates from the U.S. Census Bureau Population Estimates Program (PEP).

Data Coverage:

• From 2000 to 2022

Variables / Data Columns

• Year: This column displays the data year (Measured annually and for years 2000 to 2022)
• Population: The population for the specific year for the Gold Hill is shown in this column.
• Year on Year Change: This column displays the change in Gold Hill population for each year compared to the previous year.
• Change in Percent: This column displays the year on year change as a percentage. Please note that the sum of all percentages may not equal one due to rounding of values.

Good to know

Margin of Error

Data in the dataset are based on the estimates and are subject to sampling variability and thus a margin of error. Neilsberg Research recommends using caution when presening these estimates in your research.

Custom data

If you do need custom data for any of your research project, report or presentation, you can contact our research staff at research@neilsberg.com for a feasibility of a custom tabulation on a fee-for-service basis.

Inspiration

Neilsberg Research Team curates, analyze and publishes demographics and economic data from a variety of public and proprietary sources, each of which often includes multiple surveys and programs. The large majority of Neilsberg Research aggregated datasets and insights is made available for free download at https://www.neilsberg.com/research/.

Recommended for further research

This dataset is a part of the main dataset for Gold Hill Population by Year. You can refer the same here

We offer three easy-to-understand equity data packages to fit your business needs. Visit intrinio.com/pricing to compare packages.

Bronze

The Bronze package is ideal for developing your idea and prototyping your platform with high-quality EOD equity pricing data, standardized financial statement data, and supplementary fundamental datasets.

When you’re ready for launch, it’s a seamless transition to our Silver package for additional data sets, 15-minute delayed equity pricing data, expanded history, and more.

• Historical EOD equity prices & technicals (10 years history)
• Security reference data
• Standardized & as-reported financial statements (5 years history)
• 7 supplementary fundamental data sets

Bronze Benefits:

• Web API access
• 300 API calls/minute limit
• Unlimited internal users
• Unlimited internal & external display
• Built-in ticketing system
• Live chat & email support

Silver

The Silver package is ideal for startups that are in development, testing, or in the beta launch phase. Hit the ground running with 15-minute delayed and historical intraday and EOD equity prices, plus our standardized and as-reported financial statement data with nine supplementary data sets, including insider transactions and institutional ownership.

When you’re ready to scale, easily move up to the Gold package for our full range of data sets and full history, real-time equity pricing data, premium support options, and much more.

• 15-minute delayed & historical intraday equity prices
• Historical EOD equity prices & technicals (full history)
• Security reference data
• Standardized & as-reported financial statements (10 years history)
• 9 supplementary fundamental data sets

Silver Benefits:

• Web API access
• 2,000 API calls/minute limit
• Access to third-party datasets via Intrinio API (additional fees required)
• Unlimited internal users
• Unlimited internal & external display
• Built-in ticketing system
• Live chat & email support

Gold

The Gold package is ideal for funded companies that are in the growth or scaling stage, as well as institutions that are innovating within the fintech space. This full-service solution offers our complete collection of equity pricing data feeds, from real-time to historical EOD, plus standardized financial statement data and nine supplementary feeds.

You’ll also have access to our wide range of modern access methods, third-party data via Intrinio’s API with licensing assistance, support from our team of expert engineers, custom delivery architectures, and much more.

• Real-time equity prices
• Historical intraday equity prices
• Historical EOD equity prices & technicals (full history)
• Security reference data
• Standardized & as-reported financial statements (full history)
• 9 supplementary fundamental data sets

Gold Benefits:

• No exchange fees
• No user reporting or variable per-user exchange fees
• High liquidity (6%+)
• Web API & WebSocket access
• 2,000 API calls/minute limit
• Customizable access methods (Snowflake, FTP, etc.)
• Access to third-party datasets via Intrinio API (additional fees required)
• Unlimited internal users
• Unlimited internal & external display
• Built-in ticketing system
• Live chat & email support
• Access to engineering team
• Concierge customer success team
• Comarketing & promotional initiatives

Platinum

Don’t see a package that fits your needs? Our team can design premium custom packages for institutions.

Vietnam Gold Price Index: MoM: Hanoi data was reported at 0.400 % in Sep 2018. This records an increase from the previous number of -1.730 % for Aug 2018. Vietnam Gold Price Index: MoM: Hanoi data is updated monthly, averaging -0.045 % from Aug 2008 (Median) to Sep 2018, with 122 observations. The data reached an all-time high of 14.660 % in Sep 2011 and a record low of -8.090 % in Nov 2008. Vietnam Gold Price Index: MoM: Hanoi data remains active status in CEIC and is reported by Hanoi Statistical Office. The data is categorized under Global Database’s Vietnam – Table VN.T030:Table VN.I030: Gold Price Index: MoM & YoY Growth.

This dataset provides values for GOLD RESERVES reported in several countries. The data includes current values, previous releases, historical highs and record lows, release frequency, reported unit and currency.

This document contains statistical data and analysis of global gold demand and prices from 2010 to 2024, presented by Dojipedia, a website focused on Forex investment information. The data is organized quarterly and includes various categories of gold demand such as jewelry fabrication, technology use, investment, and central bank purchases. It also provides the LBMA gold price in US dollars per ounce for each quarter.The document highlights significant events that influenced gold prices and demand during this period. These events include major economic crises, geopolitical tensions, and market shifts. For instance, it mentions the European debt crisis in 2010, the U.S. credit rating downgrade in 2011, the Federal Reserve's quantitative easing tapering signals in 2013, and the COVID-19 pandemic's impact starting in 2020.The data shows how gold demand and prices often increase during times of economic uncertainty or political instability, as investors view gold as a safe-haven asset. For example, gold prices reached record highs in 2024 amid global economic and geopolitical uncertainties.Dojipedia presents itself as a platform with five years of Forex market investment experience. The site offers free educational content on technical analysis methods such as Elliott Wave, ICT Trading, and Smart Money Concept. It also mentions plans to publish free books on technical analysis.The document includes a disclaimer stating that the information provided is for general purposes only and not financial advice. It warns about the high risks associated with investing in financial markets like CFDs, Forex, cryptocurrencies, and gold. The disclaimer emphasizes that leveraged products may not be suitable for all investors due to the high risk to capital.Overall, this document serves as a comprehensive resource for those interested in gold market trends and their relationship to global economic events over the past decade and a half.

Pakistan Spot Gold Price: Karachi data was reported at 49,669.000 PKR/10 g in Sep 2018. This records an increase from the previous number of 47,387.000 PKR/10 g for Aug 2018. Pakistan Spot Gold Price: Karachi data is updated monthly, averaging 7,098.000 PKR/10 g from Sep 1988 (Median) to Sep 2018, with 361 observations. The data reached an all-time high of 53,664.000 PKR/10 g in Nov 2012 and a record low of 2,740.750 PKR/10 g in Sep 1989. Pakistan Spot Gold Price: Karachi data remains active status in CEIC and is reported by State Bank of Pakistan. The data is categorized under Global Database’s Pakistan – Table PK.P019: Spot Gold Price.

Iraq IQ: Total Reserves: Including Gold data was reported at 48.876 USD bn in 2017. This records an increase from the previous number of 44.886 USD bn for 2016. Iraq IQ: Total Reserves: Including Gold data is updated yearly, averaging 6.745 USD bn from Dec 1960 (Median) to 2017, with 58 observations. The data reached an all-time high of 77.747 USD bn in 2013 and a record low of 193.446 USD mn in 1962. Iraq IQ: Total Reserves: Including Gold data remains active status in CEIC and is reported by World Bank. The data is categorized under Global Database’s Iraq – Table IQ.World Bank.WDI: Foreign Reserves. Total reserves comprise holdings of monetary gold, special drawing rights, reserves of IMF members held by the IMF, and holdings of foreign exchange under the control of monetary authorities. The gold component of these reserves is valued at year-end (December 31) London prices. Data are in current U.S. dollars.; ; International Monetary Fund, International Financial Statistics and data files.; ;

Gold Reserves in China increased to 2292.31 Tonnes in the first quarter of 2025 from 2279.56 Tonnes in the fourth quarter of 2024. This dataset provides - China Gold Reserves - actual values, historical data, forecast, chart, statistics, economic calendar and news.

About This Dataset: Copper Prices and Market Trends

    This dataset provides **insights into copper prices**, including current rates, historical trends, and key factors affecting price fluctuations. Copper is essential in **construction**, **electronics**, and **transportation** industries. Investors, traders, and analysts use accurate copper price data to guide decisions related to **trading**, **futures**, and **commodity investments**.

    ### **Key Features of the Dataset**

    #### **Live Market Data and Updates**
    Stay updated with the latest **copper price per pound** in USD. This data is sourced from exchanges like the **London Metal Exchange (LME)** and **COMEX**. Price fluctuations result from **global supply-demand shifts**, currency changes, and geopolitical factors.

    #### **Interactive Copper Price Charts**
    Explore **dynamic charts** showcasing real-time and historical price movements. These compare copper with **gold**, **silver**, and **aluminium**, offering insights into **market trends** and inter-metal correlations.

    ### **Factors Driving Copper Prices**

    #### **1. Supply and Demand Dynamics**
    Global copper supply is driven by mining activities in regions like **Peru**, **China**, and the **United States**. Disruptions in production or policy changes can cause **supply shocks**. On the demand side, **industrial growth** in countries like **India** and **China** sustains demand for copper.

    #### **2. Economic and Industry Trends**
    Copper prices often reflect **economic trends**. The push for **renewable energy** and **electric vehicles** has boosted long-term demand. Conversely, economic downturns and **inflation** can reduce demand, lowering prices.

    #### **3. Impact of Currency and Trade Policies**
    As a globally traded commodity, copper prices are influenced by **currency fluctuations** and **tariff policies**. A strong **US dollar** typically suppresses copper prices by increasing costs for international buyers. Trade tensions can also disrupt **commodity markets**.

    ### **Applications and Benefits**

    This dataset supports **commodity investors**, **traders**, and **industry professionals**:

    - **Investors** forecast price trends and manage **investment risks**. 
    - **Analysts** perform **market research** using price data to assess **copper futures**. 
    - **Manufacturers** optimize supply chains and **cost forecasts**.

    Explore more about copper investments on **Money Metals**:

    - [**Buy Copper Products**](https://www.moneymetals.com/buy/copper) 
    - [**95% Copper Pennies (Pre-1983)**](https://www.moneymetals.com/pre-1983-95-percent-copper-pennies/4) 
    - [**Copper Buffalo Rounds**](https://www.moneymetals.com/copper-buffalo-round-1-avdp-oz-999-pure-copper/297)

    ### **Copper Price Comparisons with Other Metals**

    Copper prices often correlate with those of **industrial** and **precious metals**:

    - **Gold** and **silver** are sensitive to **inflation** and currency shifts. 
    - **Iron ore** and **aluminium** reflect changes in **global demand** within construction and manufacturing sectors.

    These correlations help traders develop **hedging strategies** and **investment models**.

    ### **Data Variables and Availability**

    Key metrics include:

    - **Copper Price Per Pound:** The current market price in USD. 
    - **Copper Futures Price:** Data from **COMEX** futures contracts. 
    - **Historical Price Trends:** Long-term movements, updated regularly. 

    Data is available in **CSV** and **JSON** formats, enabling integration with analytical tools and platforms.

    ### **Conclusion**

    Copper price data is crucial for **monitoring global commodity markets**. From **mining** to **investment strategies**, copper impacts industries worldwide. Reliable data supports **risk management**, **planning**, and **economic forecasting**.

    For more tools and data, visit the **Money Metals** [Copper Prices Page](https://www.moneymetals.com/copper-prices).

AbstractPopulation surveys are vital for wildlife management, yet traditional methods are typically effort-intensive, leading to data gaps. Modern technologies — such as drones — facilitate field surveys but increase the data analysis burden. Citizen Science (CS) can alleviate this issue by engaging non-specialists in data collection and analysis. We evaluated this approach for population monitoring using the endangered Galápagos marine iguana as a case study, assessing citizen scientists’ ability to detect and count animals in aerial images. Comparing against a Gold Standard dataset of expert counts in 4345 images, we explored optimal aggregation methods from CS inputs and evaluated the accuracy of CS counts. During three phases of our project — hosted on Zooniverse.org — over 13,000 volunteers made 1,375,201 classifications from 57,838 images; each being independently classified up to 30 times. Volunteers achieved 68% to 94% accuracy in detecting iguanas, with more false negatives than false positives. Image quality strongly influenced accuracy; by excluding data from suboptimal pilot-phase images, volunteers counted with 91% to 92% of accuracy. For detecting iguanas, the standard ‘majority vote' aggregation approach (where the answer selected is that given by the majority of individual inputs) produced less accurate results than when a minimum threshold of five (from the total independent classifications) was used. For counting iguanas, HDBSCAN clustering yielded the best results. We conclude that CS can accurately identify and count marine iguanas from drone images though there is a tendency to underestimate. CS-based data analysis is still resource-intensive, underscoring the need to develop a Machine Learning approach.MethodsWe created a citizen science project, named Iguanas from Above, in Zooniverse.org. There, we uploaded 'sliced' images from drone imagery belonging to several colonies of the Galápagos marine iguana. Citizen scientists (CS) were asked to classify the images doing two tasks: First to say yes or no for iguana presence in the image and second to count the individuals when present. Each image was classified by 20 or 30 volunteers. Once all the images, corresponding to three phases launched were classified, we downloaded the data from the Zooniverse portal and used the Panoptes Aggregation python package to extract and aggregate CS data (source code: https://github.com/cwinkelmann/iguanas-from-above-zooniverse).We ramdomly selected 5–10% of all the images to create a Gold Standard (GS) dataset. Three experts from the research team identified presence and absence of marine iguanas in the images and count them. The concensus answers are presented in this dataset and is referred as expert data. The aggregated CS data from Task 1 (a total number of yes and no answers per image) was analyzed as accepted for iguana presence when 5 or more volunteers (from the 20–30) selected yes (a minimum threshold rule), otherwise absence was accepted. Then, we compared all CS accepted answers against the expert data, as correct or incorrect, and calculated a percentage of CS accuracy regarding marine iguana detection.For Task 2, we selected all the images identied by the volunteers to have iguanas with this minimum threshold rule and aggregate (summarize) all classifications into one value (count) per image by using the statistical metrics median and mode and the spatial clustering methods DBSCAN and HDBSCAN. The rest of the images obtained 0 counts. CS data was incorporated into this dataset. We then compared total counts in this GS dataset calculated by the expert and all the aggregating methods used in terms of percentages of agreement towards the expert data. These percentages showed CS accuracy regarding marine iguana counting. We also investigated number of marine iguanas under and overestimated with all aggregating methods.Finally, by applying generalized linear models, we used this dataset to explore statistical differences among the different methods used to count marine iguanas (expert, median, mode and HDBSCAN) in the images and how the factors: phase analyzed, quality of the imges (assessed by the experts) and number of marine iguanas present in the image, could affect CS accuracy.

The Kvasir Dataset

https://media.springernature.com/m685/springer-static/image/art%3A10.1038%2Fs41597-020-00622-y/MediaObjects/41597_2020_622_Fig1_HTML.png">

Automatic detection of diseases by use of computers is an important, but still unexplored field of research. Such innovations may improve medical practice and refine health care systems all over the world. However, datasets containing medical images are hardly available, making reproducibility and comparison of approaches almost impossible. Here, we present Kvasir, a dataset containing images from inside the gastrointestinal (GI) tract. The collection of images are classified into three important anatomical landmarks and three clinically significant findings. In addition, it contains two categories of images related to endoscopic polyp removal. Sorting and annotation of the dataset is performed by medical doctors (ex- perienced endoscopists). In this respect, Kvasir is important for research on both single- and multi-disease computer aided detec- tion. By providing it, we invite and enable multimedia researcher into the medical domain of detection and retrieval.

Background

The human digestive system may be affected by several diseases. Altogether esophageal, stomach and colorectal cancer accounts for about 2.8 million new cases and 1.8 million deaths per year. Endoscopic examinations are the gold standards for investigation of the GI tract. Gastroscopy is an examination of the upper GI tract including esophagus, stomach and first part of small bowel, while colonoscopy covers the large bowel (colon) and rectum. Both these examinations are real-time video examinations of the inside of the GI tract by use of digital high definition endoscopes. Endoscopic examinations are resource demanding and requires both expensive technical equipment and trained personnel. For colorectal cancer prevention, endoscopic detection and removal of possible precancerous lesions are essential. Adenoma detection is therefore considered to be an important quality indicator in colorectal cancer screening. However, the ability to detect adenomas varies between doctors, and this may eventually affect the individuals’ risk of getting colorectal cancer. Endoscopic assessment of severity and sub-classification of different findings may also vary from one doctor to another. Accurate grading of diseases are important since it may influence decision-making on treatment and follow-up. For example, the degree of inflammation directly affects the choice of therapy in inflammatory bowel diseases (IBD). An objective and automated scoring system would therefore be highly welcomed. Automatic detection, recognition and assessment of pathological findings will probably contribute to reduce inequalities, improve quality and optimize use of scarce medical resources. Furthermore, since endoscopic examinations are real-time investigations, both normal and abnormal findings have to be recorded and documented within written reports. Automatic report generation would proba- bly contribute to reduce doctors’ time required for paperwork and thereby increase time to patient care. Reliable and careful docu- mentation with the use of minimal standard terminology (MST) may also contribute to improved patient follow-up and treatment. To our knowledge, a standardized and automatic reporting system that ensure high quality endoscopy reports does not exist. In order to make the health care system more scalable and cost effective, basic research in the intersection between computer science and medicine must go beyond traditional medical imaging by combining this area with multimedia data analysis and retrieval, artificial intelligence, and distributed processing. Next-generation medical big-data applications are a frontier for innovation, compe- tition and productivity, where there are currently large initiatives both in the EU and the US. In the area of multimedia research, people are starting to see the synergies between multimedia and medical systems. For automatic algorithmic detection of abnormalities in the GI tract, there have been many proposals from various research communities, especially for the topic of polyp detection. Hovever, the results are hard to reproduce due to lack of available medical data, i.e., the work listed above all use different and non-public data sets. Here, we therefore publish Kvasir: A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection from the Vestre Viken Health Trust (Norway) containing not only polyps, but also two other findings, two classes related to polyp removal and three anatomical landmarks in the GI tract.

Data Collection

The data is collected using endoscopic equipment at Vestre Viken Health Trust (VV) in Norway. The VV consists of 4 hospitals and provides health care to 470.000 people. One of these hospitals (the B...

AbstractPopulation surveys are vital for wildlife management, yet traditional methods often demand excessive time and resources, leading to data gaps for many species. Modern technologies such as drones can facilitate field surveys, but may also increase data analysis challenges. Citizen Science (CS) can address this issue by engaging non-specialists for data collection and analysis. We assess the applicability of CS for population monitoring using the endangered Galápagos marine iguana as a case study, analysing online volunteers' ability to detect and count animals in aerial images. Comparing against a Gold Standard dataset — comprising a consensus of expert counts in 4345 images — we investigated which aggregation methods produced optimal results from CS inputs, as well as the influence of image quality and filtering data from infrequent and anonymous participants. During three phases of our project — hosted on the Zooniverse platform — over 13,000 volunteers made 1,375,201 classifications from 57,838 aerial images; each image being independently classified 20 (phase 1 & 2) or 30 (phase 3) times. Volunteers achieved 68% to 94% accuracy in detecting iguanas, with more false negatives than false positives. Image quality strongly influenced accuracy; by excluding data from suboptimal pilot-phase images, volunteers counted with 90% to 92% of accuracy. For detecting presence or absence of iguanas, the commonly used ‘majority vote' aggregation approach (where the answer selected by the majority of individual inputs) produced less accurate results than when a minimum threshold of five (from the 20/30 independent classifications) was used. For aggregating results on iguana counts, the HDBSCAN clustering method yielded the best results. Removing inputs from anonymous and inexperienced volunteers reduced accuracy, emphasizing the importance of considering all volunteer contributions. We conclude that with sufficiently good aerial images, online volunteers can accurately identify and count marine iguanas from drone images, though a tendency to underestimate warrants further consideration. Finally, although CS-based data analysis is quicker than manual counting, it still requires significant time resources, thus we recommend the development of a Machine Learning approach to address this issue.MethodsWe created a citizen science project, named Iguanas from Above, in Zooniverse.org. There, we uploaded 'sliced' images from drone imagery belonging to several colonies of the Galápagos marine iguana. Citizen scientists (CS) were asked to classify the images doing two tasks: First to say yes or no for iguana presence in the image and second to count the individuals when present. Each image was classified by 20 or 30 volunteers. Once all the images, corresponding to three phases launched were classified, we downloaded the data from the Zooniverse portal and used the Panoptes Aggregation python package to extract and aggregate CS data.We ramdomly selected 5–10% of all the images to create a Gold Standard (GS) dataset. Three experts from the research team identified presence and absence of marine iguanas in the images and count them. The concensus answers are presented in this dataset and is referred as expert data. The aggregated CS data from Task 1 (a total number of yes and no answers per image) was analyzed as accepted for iguana presence when 5 or more volunteers (from the 20–30) selected yes (a minimum threshold rule), otherwise absence was accepted. Then, we compared all CS accepted answers against the expert data, as correct or incorrect, and calculated a percentage of CS accuracy regarding marine iguana detection.For Task 2, we selected all the images identied by the volunteers to have iguanas with this minimum threshold rule and aggregate (summarize) all classifications into one value (count) per image by using the statistical metrics median and mode and the spatial clustering methods DBSCAN and HDBSCAN. The rest of the images obtained 0 counts. CS data was incorporated into this dataset. We then compared total counts in this GS dataset calculated by the expert and all the aggregating methods used in terms of percentages of agreement towards the expert data. These percentages showed CS accuracy regarding marine iguana counting. We also investigated number of marine iguanas under and overestimated with all aggregating methods.Finally, by applying generalized linear models, we used this dataset to explore statistical differences among the different methods used to count marine iguanas (expert, median, mode and HDBSCAN) in the images and how the factors: phase analyzed, quality of the imges (assessed by the experts) and number of marine iguanas present in the image, could affect CS accuracy.