In recent years of history, AI has achieved one of the greatest places towards the development of Mankind. They have contributed so much that nowadays we can not imagine a Technical Project and not take AI under consideration. The most amazing field that AI has contributed in is the Medical Field (strictly according to my opinion, no discrepancies). In recent discovery is a prototype named "SMILE" (Software with Machine Intelligence for Life Enhancement) developed by an amazing company Nirmai Health Analytix (for further info refer to https://www.niramai.com/).
This prototype uses Deep Learning (https://en.wikipedia.org/wiki/Deep_learning) and Neural Networks (https://en.wikipedia.org/wiki/Neural_network) for its functioning.
This prototype is used for the detection of Breast Cancer at an early and curable stage and if detected at a later stage , to provide with specific treatment procedures, which are much less pain full than Chemotherapy (https://www.webmd.com/cancer/chemotherapy-what-to-expect) and with almost no side-effects.
SMILE (Software with Machine Intelligence for Life Enhancement) is a web interface for the NIRAMAI certified technician to upload demography information about the patient along with her thermal images. The information is processed using our patented technology, Thermalytix to analyze the patient’s breast health condition.
SMILE, has been tested on more than 4000 women in 12 hospitals/diagnostic center as well as screening camps. 3 clinical trials, comparing Thermalytix with current standard of care, have been published in peer reviewed conference/journals. The results from these clinical trials indicate very high accuracy of Thermalytix that is comparable and sometimes better that Mammography.
Below is a summary of the results from trials done so far:
· Over 90% sensitivity in all trials
· 27% higher accuracy than Mammography (most of the additional cancers detected were in dense breasts)
· 70% higher positive predictive value than Visual interpretation of Thermography (results from traditional thermography are very subjective and error prone)
Now coming to another prospect of the Working principles of SMILE : NEURAL NETWORKS.
Based on nature, neural networks are the usual representation we make of the brain : neurons interconnected to other neurons which forms a network. A simple information transits in a lot of them before becoming an actual thing, like “move the hand to pick up this pencil”.
The operation of a complete neural network is straightforward : one enter variables as inputs (for example an image if the neural network is supposed to tell what is on an image), and after some calculations, an output is returned (following the first example, giving an image of a cat should return the word “cat”).
So, shall I give a glimpse of code snippet, on the working of Neural Network using Python?
import numpy, random, os
lr = 1 #learning rate
bias = 1 #value of bias
weights = [random.random(),random.random(),random.random()] #weights generated in a list (3 weights in total for 2 neurons and the bias)
def Perceptron(input1, input2, output) :
outputP = input1*weights[0]+input2*weights[1]+bias*weights[2]
if outputP > 0 : #activation function (here Heaviside)
outputP = 1
else :
outputP = 0
error = output – outputP
weights[0] += error * input1 * lr
weights[1] += error * input2 * lr
weights[2] += error * bias * lr Just a small glimpse, do you want to learn more here's your key https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6
A fig. showing basic neural network
Stay tuned for further interesting feeds.
Awesome blog😇😇
Nice One