The winner of the Google Science Fair this year was a 17 year old girl who built a cloud-based service that helps doctors detect malignant breast cancer tumors 99% of the time. 
Medical usage demands neural networks achieve accuracy with their diagnosis and reduce malignant false negatives. Building on data collected by the University of Wisconsin in the early 1990s, this project first evaluates three modern commercial neural network implementations. Information regarding potential indicators of breast cancer is quantified in the dataset; specifically, clump thickness, single epithelial cell size, bare nuclei, mitoses, and five other attributes. Each network accepts this input to optimize its hidden nodes and is tested with ten trials. With each trial, a randomly selected 10% of the dataset is used to assess the predictive power of the constructed neural network. These commercially created neural networks serve as a control group.
Development of a custom neural network weights malignant false negatives and allows for the identification of inconclusive samples (capacities not available in commercial products.) Additionally, more samples are needed to improve the predictive capability of the network; therefore, the network has been published in the cloud, allowing for global submissions and benefit. The cloud service is hosted in the Google App Engine.
The successfully implemented custom network is tested with 6,800 trials. To assure maximum training, each sample is run through ten trials evaluated by different networks trained against all other samples. The custom neural network achieved predictive success of 97.4% with 99.1% sensitivity to malignancy – substantially better than the evaluated commercial products. Out of the commercial products, two experienced consistent success while the third experienced erratic success. The sensitivity to malignancy for the custom network was 5% higher than the best commercial network’s sensitivity. This experiment demonstrates modern neural networks can handle outliers and work with unmodified datasets to identify patterns. In addition, when all data is used for training, the custom network achieves 100% success with only 4 inconclusive samples, proving the network is more effective with more samples. Additionally, 7.6 million trials were run using different training sample sizes to demonstrate the sensitivity and predictive success improves as the network receives more training samples.
The Global Neural Network Cloud Service for Breast Cancer may be ready to diagnose actual patients – more global participation is required to confirm the findings and increase the predictive success on blind samples.
(Editor’s note: I weep with joy knowing that the world’s problems are being tackled and solved by increasingly younger minds.)
-
fannywhanny reblogged this from youmightfindyourself
-
mattciaglia likes this
-
newfashionedgal reblogged this from enchanted-dystopia and added:
WHAT AM I DOING WITH MY LIFE??
-
criada reblogged this from rori5000
-
criada likes this
-
allisonhu likes this
-
rori5000 reblogged this from the-keegsta and added:
So…what have you done with your life thus far Tony? …I play with clay sometimes.
-
captainofalltheships reblogged this from enchanted-dystopia
-
otoubat likes this
-
purrsikat reblogged this from thisfemaleform and added:
The future. It’s amazing.
-
the-keegsta reblogged this from thisfemaleform
-
the-keegsta likes this
-
huggs-boson likes this
-
deskofmahogany likes this
-
tinypiecesofpizza likes this
-
vv20 reblogged this from enchanted-dystopia
-
larissa011 likes this
-
frogfern likes this
-
enchanted-dystopia reblogged this from thisfemaleform
-
enchanted-dystopia likes this
-
inmi likes this
-
monkeyfrog likes this
-
onepieceswimmer reblogged this from thisfemaleform
-
onepieceswimmer likes this
-
offmysteez likes this
-
king-deluxe likes this
-
willwork4theatre likes this
-
edskee likes this
-
allicese7en likes this
-
thisfemaleform reblogged this from youmightfindyourself
-
tophatzzt likes this
-
thelonliestmonk reblogged this from youmightfindyourself
-
meopat likes this
-
amlacula likes this
-
twistedragons reblogged this from youmightfindyourself and added:
Last year, there was a middle school kid (i think, or even elementary school, can’t remember. definitely younger than...
-
kit-kat-attack reblogged this from youmightfindyourself
-
beryllinthranox reblogged this from youmightfindyourself
-
delacroix likes this
-
jyoungblood reblogged this from youmightfindyourself and added:
welp,
-
caxigalines likes this
-
goldalceste likes this
-
laughing-baubo likes this
-
airyairy reblogged this from youmightfindyourself
-
airyairy likes this
-
rob-anybody likes this
-
thebeautyoflanguage reblogged this from youmightfindyourself
-
c0me0n-baby reblogged this from youmightfindyourself
-
rofleo likes this
-
killakeish reblogged this from youmightfindyourself
- Show more notes




