334
In e na ional Jou nal o Ad ance and Applied Resea ch
www.ijaa .co.in
ISSN – 2347-7075
Impac Fac o – 8.141
Pee Re iewed
Bi-Mon hly
Vol. 6 No. 38
Sep embe - Oc obe - 2025
Spinal Co d Ve eb ae Iden i ica ion and Segmen a ion using Machine
Lea ning Classi ica ion App oach
M . Sandeep Wa dhe
D . D Y Pa il A s, Comme ce and Science College Aku di, Pune-44
Co esponding Au ho – M . Sandeep Wa dhe
DOI - 10.5281/zenodo.17315979
Abs ac :
The ne ous sys em is a i al body phenomenon. Taking one o i s majo o gans, he spinal
co d, and desc ibing i s signi icance a e a c ucial ask. The damage in he majo hub o he
in o ma ion ansmission ne wo k can dis u b he unc ionali y o any o he i al o gan. p oposed
iden i ica ion and segmen a ion o e eb ae o spinal co d om CT scan da ase using con olu ional
neu al ne wo k, K-means algo i hm and K-NN algo i hm. The p ocess o iden i ica ion and
segmen a ion is di ided in o wo phases. In he i s phase a deep lea ning based con olu ion neu al
ne wo k is used o p o iding segmen a ion o he whole spine and he second phase has he
localiza ion and iden i ica ion o e eb ae.
Keywo ds: Spinal Co d, KNN Classi ica ion, Deep Lea ning, Machine Lea ning.
In oduc ion:
The cen al ne ous sys em is he mos
impo an p ocessing uni in human ana omy.
I manages and con ols all he essen ial o gans
om head o oe, naming eye blinking,
b ea hing, hea pumping and mo emen o
mo ion including bending and wis ing. The
cen al ne ous sys em has wo majo o gans;
he sup eme one is he b ain, and he
subsequen is he spinal co d. The s a ing
poin o he spine is he b ain s em. The spinal
co d is a delica e e ical ube-like pipe wi h a
i m ex u e ha con ains a bunch o ne es
and issues.
The spine ne es along wi h senso y
signals ansmi in o ma ion signals o o he
pa s o he body. They a e he main
communica ion sys em o he human body, as
i connec s each o gan and i s esponse o he
b ain. The b ain, being he p ocessing uni ,
ge s and supplies all he in o ma ion wi h he
help o he spinal co d. The spine helps in
mobili y o he body.
1. Ve eb ae:
Ve eb ae a e he 33 indi idual bones
ha in e lock wi h each o he o o m he
spinal column. The e eb ae a e numbe ed
and di ided in o egions: ce ical, ho acic,
lumba , sac um, and coccyx as shown in
igu e. Only he op 24 bones a e mo eable;
he e eb ae o he sac um and coccyx a e
used. The e eb ae in each egion ha e
unique ea u es ha help hem pe o m hei
main unc ions.
IJAAR Vol. 6 No. 38 ISSN – 2347-7075
M . Sandeep Wa dhe
335
Fig.1 . Spinal Co d Ve eb ae C oss Sec ion
Fig.2 Spinal Cho d
2. Spinal Pos u e De o mi ies:
The common symp oms ha indica e
spine p oblems include weakness, senses loss,
swea ing, swelling, numbness, bladde con ol,
e lex ac ion, pa alysis, and back ache. Taking
hese symp oms in o accoun , he clinical
specialis can iden i y he a ec ed. Causes
behind hese issues can be he in ec ion,
auma inju y, ascula blockage, bone
ac u e and umo .
The de o mi y o he spine is spli in o h ee
ca ego ies such as
1. Scoliosis: One o he sideways cu a u e
de o mi ies o he spine ha occu s commonly
du ing he g ow h and e up s jus be o e
pube y is called scoliosis. Mos o he ime,
cases o scoliosis a e mild bu wi h he passage
o ime, spine scoliosis de o mi ies ge se e e
as a child g ows. The se e i y o scoliosis can
lead o disabili y. Ex eme cu a u e diso de s
educe he space wi hin he ches ha causes
b ea hing p oblems as i a ec s he
unc ionali y o he lungs and hea . Ch onic
back pain and une en shoulde s, hips and
wais a e he common symp oms o his case.
2. Kyphosis: Kyphosis is he o e elabo a ed
ound-back om he ce ical egion. In simple
wo ds, i is a e eb ae wedge-shaped
de o mi y om neck o shoulde . Kyphosis
can occu a any age, e en in in an s, bu i is
mos ly common in olde women. The e a e
h ee ypes o kyphosis: pos u al,
Scheue mann and congeni al
3. Lo dosis: I he lowe lumba pel ic cu e,
which is abo e he bu ocks, a ches oo a
inwa ds, i is called Lo dosis. Lo dosis can
cause excess p essu e on he s uc u e o he
spine causing se e e pain and discom o , and
i can also a ec he subjec ’s mo emen .
IJAAR Vol. 6 No. 38 ISSN – 2347-7075
M . Sandeep Wa dhe
336
Need o A i icial In elligence in Spine
Resea ch:
One issue wi h he adi ional
diagnos ic p ocess in spine esea ch is poo
in e p e a ion and in e en ion du ing pa ien
moni o ing who su e s spinal diso de s.
Conside wo pa ien s may ha e iden ical
imaging s udies bu hey exhibi di e en
symp oms and unc ional abili ies. I will be
di icul o physicians o do in e p e a ion and
in e en ion planning. The adi ional
app oach s uggles o accu a ely apply he
weal h o collec ed pa ien da a o do pa ien
ca e. To ha e mo e p ecise in e p e a ion and
o o e be e ea men , a i icial in elligence
inspi ed applica ions a e becoming so popula .
Machine lea ning algo i hms a e capable o
seemingly s ochas ic da ase s ha a e
challenging o physicians o in e p e .
P oposed Me hodology:
The p oposed wo k consis s o s udy
and implemen a ion o obus and e icien
deep lea ning amewo k o analysis o spinal
medical da a.
Objec i e o P oposed Wo k:
● S udy, analyze and compa e a ious
exis ing machine lea ning algo i hms
● S udy, analyze and compa e a ious
pos e o- an e io (PA) and la e al
adiog aphs using machine lea ning
echniques: Two adiog aphs CT scan
and MRIs will be use o he p oposed
wo k. Techniques om supe ised and
unsupe ised machine lea ning will be
implemen ed o analyzing hese
adiog aphs. E alua ion o pe o mance
pa ame e s and compa ison o esul s o
each echnique will be p esen ed
● Implemen a ion o an e icien deep
lea ning based amewo k o spine
esea ch using a ious machine lea ning
lib a ies, models and compu e
p og amming language
● E alua ion o a ious pa ame e s ela ed
o implemen ed echnique
Resul and Discussion:
The aim o he p oposed wo k is o
implemen an e icien deep lea ning
amewo k o analysis o spine ela ed
medical da a. F amewo k will be implemen ed
o 2D pos e o-an e io and la e al adiog aphs
such as CT- scan and MRIs. Va ious
pa ame e s like con usion ma ix, accu acy,
p ecision, speci ici y, e c. ela ed o he
p oposed deep lea ning model will be
e alua ed. Quali y measu es such as Dice
Simila i y Coe icien (DSC), Recall and
P ecision alues a e used o compu e
simila i y be ween he p edic ion and he
g ound u h da a.
Epochs
DSC
Recall
P ecision
100
85.07
94.25
77.65
200
88.20
93.46
83.61
300
88.29
93.87
83.78
IJAAR Vol. 6 No. 38 ISSN – 2347-7075
M . Sandeep Wa dhe
337
Fig. 3 Segmen a ion o Spinal Cho d
Fig. 4 Iden i ica ion o Ve eb ae using Machine lea ning Classi ica ion
Conclusion:
The p oposed implemen a ion o
Machine lea ning classi ie s echniques in
iden i ica ion and classi ica ion o spinal co d
has been s udied. Fo he implemen a ion CT
Scan da ase is used and esul s a e gene a ed.
I is ound ha he CNN and KNN model
wo ks sa is ac o ily o iden i y and segmen
he e eb ae o he spinal co d.
Acknowledgmen :
I would like o exp ess my g a i ude o
D . Mohan Waman P incipal, D . D Y Pa il
A s, Comme ce and Science College Aku di
Pune o aluable guidance.
Re e ences:
1. Zami A. Me ali, E ol Colak,
Je e son R. Wilson, “Applica ion o
Machine Lea ning o Imaging o
spinal Diso de s: Cu en S a us and
Fu u e Di ec ions”, Global Spine
Jou nal, Volume 11, Issue 1, 23 Ap il
2021
2. G. Michael Mallow, Zaka iah k
.Siyaji, Fabio Galbuse a, “In elligence
based spine ca e model: New E a o
Resea ch and clinical Decision
Making”, Global Spine Jou nal,
Volume 11, issue 2, 28 No embe
2020
3. John T. Schwa z, Michael Gao, E ic
A. Geng, Kush S. Mody, Ch is ophe
M. Mikhail, Samuel K. Cho,
“Applica ions o Machine Lea ning
Using Elec onic Medical Reco ds in
Spine Su ge y”, Neu ospine, Ko ean
Spinal Neu osu ge y Socie y, 643-
653, 2019
4. Fabio Galbuse a, Glo ia Casa oli, Ti o
Bassani, “A i icial in elligence and
Machine Lea ning in spine esea ch”,
JOR Spine, Wiley Publica ions,
O hopaedic Resea ch Socie y,
Janua y 2019
IJAAR Vol. 6 No. 38 ISSN – 2347-7075
M . Sandeep Wa dhe
338
5. Michael Chang, Jose A. Camseco,
K is en J. Nicholson, Neil Pa el,
Alexande R. Vacca o, “ The ole o
Machine Lea ning in Spine Su ge y:
The Fu u e is Now”, F on ie s in
su ge y, Volume 7, A icle 4, Augus
2020
6. Hieu T. Nguyen, Hieu H. Pham,
Nghia T. Nguyen, Ha Q. Nguyen,
Thang Q. Huynh, Minh Dao, Van Vu,
“VinD Spine XR: A deep lea ning
amewo k o spinal lesions de ec ion
and classi ica ion om adiog aphs”,
a Xi :2106.12930 1, 24 June 2021
7. Weidong Liu, Caixia Qin, Kun Gao,
Heng Li, Zuen Qin, Ya ei Cao, Wen
Si, “Resea ch on Medical Da a
Fea u e Ex ac ion and In elligen
Recogni ion Technology Based on
Con olu ional Neu al Ne wo k”,
IEEE, Special Sec ion on da a Enabled
In elligence o Digi al heal h, 26
Sep embe 2019
8. Sene a h Mudalige, Don Alexis,
Chin haka Jaya ilake, Gamage
Upeksha, Ganegoda, “In ol emen o
Machine Lea ning Tools in Heal hca e
Decision Making”, Hindawi, Jou nal
o Heal hca e Enginee ing, ol. 2021,
A icle ID 6679512, 20 pages, 2021
9. A winde Dhillon, Ashima Singh,
“Machine Lea ning in Heal hca e Da a
Analysis: A Su ey”, Jou nal o
Biology and Today's Wo ld, 25 July
2019
10. N. Al ini, G. De Giosa, N. F agasso,
C. Coscia, E. Sibilano, B. P encipe,
S.M. Hussain, A. B une i, D.
Buongio n, A. Gue ie o, e al.,
“Segmen a ion and Iden i ica ion o
Ve eb ae in CT Scans Using CNN, k-
Means Clus e ing and k-NN”,
In o ma ics, 2021
