Fuzzy logic and how it is curing cancer
It is everything that is not crisp/solid. A science that gives no 100% accurate answer, but the more adequate thing is that it does not require a 100% clear input.
A simple example is a program that predicts the age of a person from their photo. It studies multiple features in the photo such as hair color, skin texture, wrinkles, etc. and estimates their age.
Input: A photo that might not be of high-resolution/a side view photo.
Output: A number that is -supposedly- close to this person’s age.
Soft computing is based on fuzzy logic, which will be explained later.
Hard computing is the traditional computing method which most of you are probably already familiar with. An example is a program that adds 2 numbers. Definite input and an absolute answer.
A great free book that would give you a good kickstart on both soft computing and fuzzy logic is Introduction to Soft Computing by Eva Volná.
Traditional ways would classify a cup of coffee into two sets only, either cold or hot. A warm-near-hot cup would fall into the hot category. In the fuzzy world, this warm cup would have a degree of membership to the hot set of 70% and 30% to the cold one.
Fuzzy logic is an approach to computing based on the degrees of truth rather than the usual true or false. Such that for every element, it has a degree of membership to every set that is contained within the problem.
This sort of computations is really useful in our daily lives. For example, a school is auditioning basketball players for the school team, they announced that they need people who are 5’5″+. Will this disqualify a very good player who is 5’4″? Or will he be auditioned because it’s not really a big difference? What if a 5’3″ person applied. He’s only an inch shorter than the last one who was admitted. And it goes like this forever. This is why a more suitable application would have a score in the height field, where relatively shorter people would have a lesser grade (a degree of membership to the tall-people-set < 100%) and taller people would get the full mark (completely belong to the-tall-people-set).
Nature itself is not crisp, when you see a rainbow you see red followed by orange. You stare at a point and you could swear that it’s red, 100% red. Also, you see it getting lighter and lighter until it smoothly turns to orange. You can’t tell at which point exactly did it stop being red and started being orange. It is not a stroke of solid red followed by a stroke of solid orange, instead, it’s a decreasing percentage of red starting from 100% to 0% and an increasing percentage of orange starting from 0% to 100%.
There are 3 flaws in the literature (previous/current papers/researches about detecting tumors):
On the beach, you don’t see the sea water ending in a perfectly straight line. Instead, the depth of the sea gradually decreases. From shoulder length to knee length to wet toes then moist sand and finally fully dry sand. It’s the same with tumors, when you examine an MRI scan, you see a cancerous bulk (water) and the cancerous cells keep fading gradually until you reach the part of the organ that’s completely healthy (sand). Literature doesn’t account for that. They don’t take the intrinsic tumor fuzziness into consideration. Biological systems in general and cancerous tumors in particular, do not exhibit sharp boundaries. Thus, the intrinsic gradation must be taken into account for a precise description of the tumor to both evaluate the initial tumor structure and trace the therapeutic progress. The fuzzy parts where some cells might contain just 40% of cancerous tissues would be considered to be 100% cancerous cells. This overestimates the patient’s conditions and might result in an unnecessary heavy healing process.
Another big mistake in the literature with cancer detection is that they assume that the tumor is of a regular spherical shape that has the diameter of the longest line in the tumor itself. This could lead to terribly erroneous sizing especially with the cases where the tumor is of irregular shape or when the difference between the longest and shortest dimensions is large. Volume estimation based on the longest diameter as typically done leads to a much larger volume size than the reality of the case. This measurement technique can be accurate only for perfect or near perfect spherical lesions.
Cancer staging is used to describe and rank cancer severity. From stage 0 to IV. where IV is the most severe. Stage IV means that the disease has already spread to other organs. The fuzzy nature of biological systems was realized since the early inception of fuzzy set theory by Lotfy Zadeh himself, Since then, The gradation of biological phenomena has been emphasized and applied extensively. For example, if a stage falls between the values of tumor diameters 2 cm and 4 cm as lower and upper bounds respectively, what about the values 1.99 and 4.01? Should we shift the whole treatment plan or drug design from one stage to another for such a minor deviation from the boundaries? If we do not, then at what index value should we set the limit? This is a typical example of the paradox for which fuzzy set theory was invented.
A lot of what I wrote here, I learned from this Tumor volume fuzzification for intelligent cancer staging paper.
Fuzzy logic and how it is curing cancer
Research & References of Fuzzy logic and how it is curing cancer|A&C Accounting And Tax Services