Detection of Bone Fracture using Image Processing

Methods

INTRODUCTION:
Bio-medical image analysis is an interdisciplinary field which includes: biology,
physics, medicine and engineering. It deals with application of image processing
techniques to biological or medical problems. Medical images to be analyzed contain
a lot of information regarding the anatomical structure under investigation to reveal
valid diagnosis and thereby helping doctors to choose adequate therapy. Doctors
usually analyse these medical images manually through visual interpretation.
Abnormality detection
Diseases and injuries to the bone are the major contributing factors in causing
abnormalities in bones. Now, what happens is, whenever there is an injury to the
bone, the physician asks you to do an X-Ray, thus when such hundreds of patients
visit hospitals everyday there are massive number of X-rays done on regular basis. To
be specific with the stats, Musculoskeletal conditions affect more than 1.7 billion
people worldwide, and are the most common cause of severe, long-term pain and
disability, with 30 million emergency department visits annually and increasing. So,
in order to reduce the error rate of the Radiologist and to do the analysis much faster,
an AI solution should suffice the purpose.
Bones are the solid organs in the human body protecting many important organs such
as brain, heart, lungs and other internal organs. The human body has 206 bones with
various shapes,size and structures. The largest bones are the femur bones, and
the smallest bones are the auditory ossicles. Bone fracture is a common problem in
human beings.

DATASET USED:
there was this Deep Learning competition hosted by Stanford last year which
expected the participants to detect the bone abnormalities. The dataset is widely
known as MURA. MURA is a dataset of musculoskeletal radiographs consisting of
14,863 studies from 12,173 patients, with a total of 40,561 multi-view radiographic
images. Each belongs to one of seven standard upper extremity radiographic study
types: elbow, finger, forearm, hand, humerus, shoulder, and wrist.

FEASIBILITY STUDY:

METHODOLOGY/PLANNING OF WORK:
 Detection of Bone Fracture using Image Processing
Methods

 Learning rate schedulers

The learning rate is a hyper parameter that controls how much to change the model in
response to the estimated error each time the model weights are updated. Choosing
the learning rate is challenging, as a value too small may result in a long training
process that could get stuck, whereas a value too large may result in learning a sub-
optimal set of weights too fast or an unstable training process.
So what becomes necessary is to find the optimal learning rate. Although, libraries
like fastai have built-in functions to find the ideal learning rate, here we use the
traditional ones The two techniques I used were:
1. Step decay: This technique involves reducing the learning rate after certain
predefined number of epochs. You can write your implementation of it. Mine was as
follows:
def step_decay(epoch):
initial_lrate = 0.0001
drop = 0.1
epochs_drop = 10.0
lrate = initial_lrate*
math.pow(drop,math.floor((1+epoch)/epochs_drop))
return lrate

This function basically reduces the learning rate to 1/10th of its initial value after
every 10 epochs.
It can be included in the callbacks as follows:
lrate = LearningRateScheduler(step_decay)
callbacks = [lrate]

2. Loss based decay: This technique reduces the learning rate after a patience of
certain predefined epochs once the model stops improving. Keras has a built-in
module named ReduceLRonPlateau which is shown in the code below.
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=10, min_delta=0.0001, verbose=1,
min_lr=0.0000001)
callbacks = [reduce_lr]

The above function monitors the validation loss and once it stops decreasing for a
patience of 10 epochs it reduces the learning rate by a factor of 0.1. Here, my model
 Detection of Bone Fracture using Image Processing
Methods
had an initial learning rate of 0.001 and through this function I could take it to a value
min_lr which is 10–6.
For me the later technique proved to be more effective.

 Class weights penalisation

This is one of the techniques I came across while reading about optimizing model’s
performance when you have a class imbalance. Although, when the class imbalance
is not too high, it’s not that useful. But in my case, the positive cases were
approximately 2/3rd that of the negative ones. So, I used this technique to train the
model. There are two ways you could do this:
1. Set the class weights manually for each of the classes by calculating the
imbalance in the training set.
class_weight = {0: 1, 1: 1.5}model.fit(X_train, Y_train,
nb_epoch=50, batch_size=32, class_weight=class_weight)

2. The other method involves using Scikitlearn, which comes with a function which
automatically computes the class weights from the training data which is as follows:
from sklearn.utils import class_weightclass_weights =
class_weight.compute_class_weight('balanced',
np.unique(y_train), y_train)model.fit(X_train, y_train,
class_weight=class_weights)

 Data Augmentation
This technique is used when the dataset consists of less number of samples or the
images have varied orientations. Here, the task at hand asked us to build a binary
classifier to determine if the bone had some abnormality or was normal. Although,
the dataset had around 1000–2000 samples of each bone for the positive class, still
the orientation differed. Following are the sample image from Hand data.

 Various optimizers
You can use different optimizers as a part of hyperparameter tuning. You can change
it to SGD, Adam. I have always used ‘rmsprop’ as a part of training but the Stanford
team has used ‘Adam’ with some specific parameters changed. Although, I haven’t
found luck in improving the model’s performance by changing the optimizers
 Detection of Bone Fracture using Image Processing
Methods

 Ensembling
Ensembling is a technique which allows you to make decisions by aggregating the
predictions from your different models. The reasons ensembling works better than
single models is because every model learns different features as per its architecture.
So, in this case, you could ensemble all your best performing models to get better
results.
There are two different ways of ensembling, one is Averaging out predictions from
the models and the other is to take the majority vote. The former method solely
depends on the probabilities or the confidence with which the class is being predicted
whereas the later one depends on the predicted class by most number of models in the
ensemble.

3.6 Classification
Classification is a step of data analysis to study a set of data
and categorize them into a number of categories. Each
category has its own characteristics and the data that belong to
such category have the same properties of this category. In
proposed method, different types of classifier are used such as
decision tree (DT) and neural network (NN) and meta-
classifier. Based on the GLCM textural features, classifiers
classify the given image into fractured and non-fractured
image. not ragged.

MODULE AND TEAM WISE DISTRIBUTION OF WORK

 Detection of Bone Fracture using Image Processing
Methods

INNOVATION:

SOFTWARE AND HARDWARE REQUIREMENTS:

BIBLIOGRAPHY:
[1] Vijaykumar, V., Vanathi, P., Kanagasabapathy, P.
(2010). Fast and efficient algorithm to remove gaussian
noise in digital images. IAENG International Journal of
Computer Science, 37(1).

[2] Al-Khaffaf, H., Talib, A. Z., Salam, R. A. (2008).

Removing salt-and-pepper noise from binary images of
engineering drawings. In: Pattern Recognition. ICPR.
19th International Conference on, p. 1–4. IEEE.

[3] Zain, M. L. M., Elamvazuthi, I., Begam, M. (2009).

Enhancement of bone fracture image using filtering techniques. The International
Journal of Video and
Image Processing and Network Security, 9 (10).

[4] Chan, K.-P., Fu, A. W.-C. (1999). Efficient time series

matching by wavelets. Data Engineering. In:
Proceedings, 15th International Conference on, p. 126–
 Detection of Bone Fracture using Image Processing
Methods
133. IEEE.

[5] Tian, T. (2002). Detection of femur fractures in x-ray

images. Master’s thesis, National University of
Singapore, Singapore.

[6] Lim, S. E., Xing, Y., Chen, Y., Leow, W. K., Howe, T.
S., Png, M. A. (2004). Detection of femur and radius
fractures in x-ray images. In: Proc. 2nd Int. Conf. on
Advances in Medical Signal and Info. Proc.

[7] Yap, D. W.-H., Chen, Y., Leow, W. K., Howe, T. S.,

Png, M. A. (2004). Detecting femur fractures by texture
analysis of trabeculae. In Pattern Recognition. ICPR. In:
Proceedings of the 17th International Conference on, 3,
p. 730–733. IEEE.