2. A.N.N.C.R.I.P.S The Artificial Neural Networks for Cancer Research in Prediction & Survival A CSI – VESIT PRESENTATION Presented By Karan Kamdar Amit Mathapati Arpan Nanavati © 2003 – The A.N.N.C.R.I.P.S

3. Why A.N.N.C.R.I.P.S ? Prostate Cancer – Most common form among men Prostate Cancer – Most common form among men Screening – Carried out through blood tests & presence of high PSA (can indicate cancer risk) Screening – Carried out through blood tests & presence of high PSA (can indicate cancer risk) Drawbacks – Initial screenings lead to high percentage Drawbacks – Initial screenings lead to high percentage of false positive test results (FPTRs) of false positive test results (FPTRs) Scope for improvement – FPTRs can be reduced by Scope for improvement – FPTRs can be reduced by employing intelligent Artificial Neural Networks employing intelligent Artificial Neural Networks Implementation at all levels – ANN models can be used at every stage of Cancer analysis Implementation at all levels – ANN models can be used at every stage of Cancer analysis Advantage – Non-required trial and error methods reduced. Hence early cancer diagnosis and treatment Advantage – Non-required trial and error methods reduced. Hence early cancer diagnosis and treatment

4. Project Overview Voluntary effort started by the core members of this group and our colleagues Voluntary effort started by the core members of this group and our colleagues Objective – Build a mathematical model to improve prostate cancer detection and staging systems Objective – Build a mathematical model to improve prostate cancer detection and staging systems Basis – Mathematical model revolves around the concept of Artificial Neural Networks (ANNs) Basis – Mathematical model revolves around the concept of Artificial Neural Networks (ANNs) Development & Implementation – Programming the ANN model to develop a standalone application which can be deployed across medical organizations Development & Implementation – Programming the ANN model to develop a standalone application which can be deployed across medical organizations

5. Introduction to ANNs Information processing paradigm inspired by the way biological nervous systems eg. brain process information ANNs adopt this interconnected neuron network to perform complex computations

6. Basic ANN model

7. Overview of Prostate Cancer Prostate – Male sex gland producing the semen – Prostate Cancer – Cancer beginning in prostate which may remain in the prostate gland or spread – Screening & Diagnosis – If symptoms occur, DRE & blood tests are undertaken to measure level of PSA – Staging – After initial diagnosis, further staging such as TNM undertaken Our ANN model employed to improve cancer risk estimation of screening & staging systems

8. Linking ANNs to PCa Analysis Finding % tPSA – Current method of PCa detection Faults – 1. Only Cancer confined to the prostate detected 2. Additional info requires more tissue samplings 2. Additional info requires more tissue samplings Possible Soln. – Finding % free PSA (fPSA) to suggest spread of Cancer to other parts. spread of Cancer to other parts. Core Drawbacks – Both systems not intelligent. a) Cannot predict on individual basis a) Cannot predict on individual basis b) Inability to learn and associate b) Inability to learn and associate c) Moderate Accuracy c) Moderate Accuracy The A.N.N.C.R.I.P.S model – Take the best of both and include other role playing variables to build an intelligent, reliable cancer detection and prediction system

9. Building the ANN model Building the ANN model  Based on the concept of MultiLayer Perceptron (MLP)  Consists of a network of processing elements or nodes arranged in layers  Principle - Input pattern presented at the input layer causes network nodes to perform calculations in the successive layers until an output value is computed at each of the output nodes from which the most significant is selected  Working – Input to node j :  Output of node j :  This continues through all the layers of the network until output layer is reached and output vector is computed  The function f denotes activation function of each node. A sigmoid function is generally used

10. Extending the MLP methodology Extending the MLP methodology  Our neural network model used is a multilayer perceptron (MLP) network composed of one input layer with four primary preprocessed variables (tPSA, fPSA, prostate volume, DRE)  One hidden layer with two neurons, and one output layer with one neuron giving the output value that is a measure of the probability of cancer.  13 parameters (weights) to be optimized. Activation function used in the hidden and output layers is hyperbolic tangent sigmoid function. Output values are between -1 to 1 [a= tanh(s) = (e^s – e^ -s) / (e^s + e^ -s)]  Formula for whole network : a1 = tanh (IW1,1*X1 + IW2,1*X2 + IW3,1*X3 + IW4,1*X4 + IB1) a2 = tanh (IW1,2*X1 + IW2,2*X2 + IW3,2*X3 + IW4,2*X4 + IB2) aout = tanh (LW1*a1 + LW2*a2 + LB)  After model build-up, initialize weights and enter inputs. Inputs are actual data of patients suffering from prostate cancer  Network now trained using Levenberg-Marquardt & Bayesian optimization techniques to recognize and associate patterns of input with desired outputs indicating the correct cancer risk.  Internal processing in network takes place and resultant output takes the form between 0 (low PCa risk) and 1 (high PCa risk). In some cases, the value is 1 which is not relevant  Intelligent learning is the key to ANN success. E.g. if the network has been trained for person having high PSA level due to non-cancerous cells then it wont indicate any cancer risk for persons falling into the same characteristic group

11. Training Procedure Training Procedure

12. 5 Steps to Implement the ANN Step 1 – Obtaining the Input Data Set Step 2 – Adjusting Initial Weights i) model fitted on 75% and tested on 25% of patients in each training set. ii) randomization, fitting and testing sessions repeated 5 – 6 times and the weights producing smallest sum of squared errors on the initial test set are selected as initial weights for the final training of the MLP. Step 3 – Train Network Step 4 – Test Network Step 5 – Validating & Generalizing Network Efficiency Actual Training of Network begins with estimation & validation samples If validation objective is acquired, network trained again till best performance parameter values are obtained

13. Results of the ANN on a comparative basis  Sensitivity : Ability of the model to detect prostate cancer early  Accuracy : Proportion of subjects with a correct test result  Specificity : Efficiency of avoiding repeated tissue samplings  ROC Curve : ANN model occupies greater area under curve as compared to FP & TP models

14. Here comes our Final Product !

15. Conclusion Prostate cancer is the most common form of cancer among men in the industrialized world Screening is a very rough estimate for cancer risk Further staging systems such as A,B,C,D, TNM lack required efficiency Our model developed to aid or substitute the current diagnosis and prognosis methods Our model developed to aid or substitute the current diagnosis and prognosis methods Studies have shown that these highly accurate ANNs can detect prostate cancer early & reduce unnecessary tissue samplings Studies have shown that these highly accurate ANNs can detect prostate cancer early & reduce unnecessary tissue samplings Influencing factors : a) Larger no. of input variables b) Establishing interconnecting relationships b) Establishing interconnecting relationships between them between them c) Ability of network to be trained time and again c) Ability of network to be trained time and again thereby increasing accuracy each time thereby increasing accuracy each time Result : Our proposed ANN model is far more efficient in predicting prostate cancer risk and reduce the no. of false positive test results

16. © 2003 – The A.N.N.C.R.I.P.S Join us to save a million lives www.anncrips.com