International Journal of Reconfigurable and Embedded Systems (IJRES)

Vol. 13, No. 2, July 2024, pp. 262~270

ISSN: 2089-4864, DOI: 10.11591/ijres.v13.i2.pp262-270  262

A novel compression methodology for medical images using

deep learning for high-speed transmission

Shyamala Navaneethakrishnan1, Geetha Shanmugam2

1
Department of Computer Science, Government Arts College, Udumalpet, India
2
Department of Computer Science, Government Arts and Science College for Women, Puliakulam, India

Article Info ABSTRACT

Article history: Medical imaging is a rapidly growing field having a high impact on the early
detection, diagnosis and surgical planning of diseases. Several imaging
Received Jan 9, 2023 techniques such as computed tomography (CT), magnetic resonance imaging
Revised Sep 4, 2023 (MRI) and ultrasound (US) imaging generate a higher volume of data,
Accepted Sep 17, 2023 necessitating additional storage and communication requirements. Hence,
image compression is utilized in medical field to reduce redundancy and
alleviate memory and bandwidth issues. This paper presents a novel deep
Keywords: learning-based compression method to reduce the size of medical images.
This method employs a deep convolutional neural network for learning
Compact form compact representations of medical images, then coded by a Huffman
Deep convolutional neural encoder. The compression process is reversed to reconstruct the original
network image. Several tests are conducted to compare the results with other well-
Deep learning known compression methods. The proposed model achieved a mean peak
Medical image compression signal-to-noise ratio (PSNR) of 42.82 dB with storage space saving (SSS) of
Storage space-saving 96.15% for CT, 43.88 dB with SSS of 96.25% for MRI, 46.29 dB with SSS
Telemedicine of 96.07% for US and 43.51 dB with SSS of 96.95% for X-ray images. The
findings showed that the proposed compression technique could greatly
compress the image size, saving storage space, facilitating better
transmission and preserving critical diagnostic information.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Shyamala Navaneethakrishnan
Department of Computer Science, Government Arts College
Udumalpet, Tamil Nadu, India
Email: [email protected]

1. INTRODUCTION
Medical imaging techniques are becoming a crucial component of the diagnostic procedure in
healthcare practices. The importance of medical imaging has increased significantly as a result of
advancements in screening technologies. The improvements have led to great accuracy in medical imaging
with better quality and improved image resolution [1]. Furthermore, a huge amount of data is generated by
various imaging techniques such as magnetic resonance imaging (MRI), computed tomography (CT) and
ultrasound (US). However, the development has caused an exponential rise in the amount of data that needs
to be processed and stored in a local memory or transmitted over the network [2]. Therefore, image
compression methods have become crucial in processing medical images.
A number of image compression methods have been designed so far to compress medical images
and reduce the amount of bandwidth needed for transmission. Image compression methods are grouped into
lossy and lossless compression. Lossless compression is preferable for medical image compression due to its
characteristics of restoring the image to its original quality without loss of any data and quality. In general,
traditional compression methods can be utilized to minimize medical image size, JPEG and their upgraded

Journal homepage: http://ijres.iaescore.com

Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  263

versions. It can be observed that these conventional methods do not appropriately handle diagnostic
information and instead focus primarily on maintaining the quality of the image which may not be largely
helpful. These characteristics must be taken into account while designing a compression system for medical
images. Recently, deep learning networks have been used to compress images which achieved better
compression rates. Furthermore, the use of deep learning models offers better flexibility in terms of the types
of objects in the compressed images [3]–[6]. The compression method just has to be trained to new features
because these networks do not rely on hand-crafted features. This paper builds a novel compression method
to reduce the size of medical images while preserving diagnostic information and reducing the amount of
bandwidth needed for transmission. The core contributions of this paper are given: i) two deep convolutional
neural networks (DCNNs) are connected together in order to design an efficient compression method, ii) a
novel compact-DCNN (C-DNN) is proposed to learn the compact representation of medical images
containing diagnostic data, iii) a reconstruct-DCNN (R-DCNN) is designed to recover the compressed image
with increased quality, iv) the performance of the developed system is analyzed utilizing different imaging
techniques such as CT, MRI, US and X-ray, and v) extensive experiments are conducted and the outcomes
are compared with traditional methods.
The article is outlined as section 2 discusses the review of previous works and provides a brief
survey of earlier methods. Section 3 enumerates the introduced medical image compression system and
describes the functioning of the method. Section 4 discusses the numerical outcomes and discussion with
considerations on the obtained results. Section 5 summarizes the article.

2. REVIEW OF PAST APPROACHES

This section gives a brief overview of various existing techniques for compressing medical images.
Ahilan et al. [7] designed a method for compressing the size of medical images. Particle swarm optimization
(PSO) along with multilevel thresholding is used to select the optimal value to compress the image. This
method archived better results in terms of peak signal-to-noise ratio (PSNR). However, the PSO needs more
training to obtain good results.
As per Ammah and Owusu [8] discrete wavelet transform (DWT) and vector quantization were
adapted to compress medical images. Input images were filtered using a median filter and then divided into
many subbands using DWT. Then, the obtained coefficients were quantized and encoded. This approach
failed to attain high PSNR due to floating point error.
A fusion method by combining burrows-wheeler transform (BWT) and move to front transform
(MTF) was presented by Devadoss and Sankaragomathi [9]. The input image was divided into region of
interest (ROI) and non-ROI with morphological operations. BWT-MTF and quasi fractal (QF) were adopted
to compress ROI and non-ROI respectively since the block division was done in the ROI to reduce BWT
time. Storage space saving (SSS) is reduced by increasing the block size.
Maheswari and Raghavan [10] designed a compression algorithm for medical images. In this work,
tetrolet was applied to divide an image into multiple sub-images. The sub-images were divided into
4×4 pixels and then compressed. The performance of this method was validated on MRI and CT images. This
work requires more time for reconstruction.
A hybrid method by integrating the quasi fractal and oscillation method (QFOM) was presented by
Magar and Sridharan [11]. A bandpass filter was used to isolate the ROI region from its background. The
ROI was compressed using QF whereas non-ROI was compressed with OM. A neural network-based
compression method was proposed by Sabbavarapu et al. [12]. In this work, DWT and optimized recurrent
neural network (RNN) were utilized for compressing ROI and non-ROI respectively. This method attained
better compression ratio (CR) and PSNR.
Salih and Kadhim [13] presented a medical compression method based on set partitioning in
hierarchical trees-binary array technique (SPIHT-BAT) algorithm. Reddy et al. [14] used discrete cosine
transform (DCT), singular value decomposition (SVD) and SPIHT. Initially, DCT was applied over the input
image and then SVD was followed by SPIHT. This method may lose some information. Rahman and
Hamada [15] presented a detailed survey of image compression techniques.

3. PROPOSED IMAGE COMPRESSION METHOD

The proposed method consists of two DCNNs, C-DCNN, R-DCNN, huffman encoding (HE) [16]
and decoding. During compression, the input image is represented compactly to preserve salient information
of the medical image. Whereas during decompression, another R-DCNN is used to improve the recovered
image quality. Figure 1 depicts the phases of the presented compression method.

A novel compression methodology for medical images using deep … (Shyamala Navaneethakrishnan)
264  ISSN: 2089-4864

Figure 1. The structure of the designed compression technique

3.1. C-DCNN in compression

The C-DNN consists of three convolutional (Conv) layers [17], [18] as depicted in Figure 2. The
integration of conv and rectified linear unit (ReLU) [19] is used at the first and second layers. The first Conv
layer extracts the relevant information that eliminates the region that may overlap in the input image. The
ReLU activation function and a total of 64 3×3 filters are employed to create 64 feature maps. The following
layer performs two processes such as downsampling and enhancement employing convolution. The filters of
size 3×3×64 and ReLU are utilized. The filters of 3×3×64 are used to create a compact representation in the
last layer.

Figure 2. Process of C-DCNN and R-DCNN

3.2. R-CNN in decompression

The R-CNN has many layers including Conv+ReLU, Conv+ReLU+batch normalization (BN) [20]
and Conv. Feature maps are created in the first layer using 64 filters of size 3×3, then ReLU. In the
subsequent layers, 64 filters with a 3×3 size are used and BN is added with Conv and ReLU. The filters of
size 3×3×64 are used in the last layer to reconstruct the image. The BN is used to improve results. The
bicubic interpolation method will upscale the compressed image to the size of the input image.

Int J Reconfigurable & Embedded Syst, Vol. 13, No. 2, July 2024: 262-270
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  265

3.3. Learning algorithm and loss function

The developed compression method intends to reduce medical image size and reconstruct the image
with better quality. The optimization goal can be expressed as,
2
(𝜃̂𝑥 , 𝜃̂𝑦 ) = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥,𝜃𝑦 ‖𝑅 (𝜃𝑦, 𝐻𝐸(𝐶(𝜃𝑥 , 𝑋))) − 𝑋‖ (1)

where X is the input image, HE is the Huffman encoder, C is the compression, R is the reconstruction, C(.) is
C-DCNN and R(.) is R-DCNN. In (1) shows that the image X is given on the phases of compression,
including C-DNN, HE and R-DCNN for decoding and the result of the reconstructed image 𝑋̂. In (1) utilizes
a rounding function that is non-differentiable when executing the backpropagation algorithm. To fix the
issue, an iterative optimization training algorithm is proposed. Initially, by fixing 𝜃𝑦 , it is obtained as,

2
𝜃̂𝑥 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 ‖𝑅 (𝜃𝑦, 𝐻𝐸(𝐶(𝜃𝑥 , 𝑋))) − 𝑋‖ (2)

by setting 𝜃𝑥 , it is obtained as,

2
𝜃̂𝑦 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑦 ‖𝑅 (𝜃𝑦, 𝐻𝐸(𝐶(𝜃𝑥 , 𝑋))) − 𝑋‖ (3)

let 𝑋̂𝑟 is the compact form and it can be defined as,

𝑋̂𝑟 = 𝐻𝐸 (𝐶(𝜃̂𝑥 , 𝑋)) (4)

to update 𝜃𝑦 , (3) and (4) are combined and are written as,

2
𝜃̂𝑦 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑦 ‖𝑅(𝜃𝑦 , 𝑋̂𝑟 ) − 𝑋‖ (5)

2
𝑋̂𝑟′ = 𝑎𝑟𝑔𝑚𝑖𝑛𝑥̂𝑟 ‖𝑅(𝜃̂𝑦 , 𝑋̂𝑟 ) − 𝑋‖ (6)

2 2
it is assumed that 𝐷(𝜃̂𝑟 , . ) is monotonic concerning 𝑋̂𝑟′ and is denoted as, ‖𝜏 − 𝑋̂𝑟′ ‖ ≥ ‖𝜑 − 𝑋̂𝑟′ ‖ , if and
only if,
2 2
‖𝑅(𝜃̂𝑦 , 𝜏) − 𝑋‖ ≥ ‖𝑅(𝜃̂𝑦 , 𝜑) − 𝑋‖ (7)

2
let 𝜃̃𝑥 - solution of ‖𝐻𝐸(𝐶((𝜃, 𝑋) − 𝑋̂𝑟 ‖ , for any probable 𝜃𝑥∗ , it fulfills,

2 2
‖𝐻𝐸(𝐶(𝜃𝑥∗ , 𝑋)) − 𝑋̂𝑟′ ‖ ≥ ‖𝐻𝐸 (𝐶(𝜃̃𝑥 , 𝑋)) − 𝑋̂𝑟′ ‖ (8)

2 2
‖𝑅 (𝜃̂𝑦 , 𝐻𝐸(𝐶(𝜃𝑥∗ , 𝑋))) − 𝑋‖ ≥ ‖𝑅 (𝜃̂𝑦 , 𝐻𝐸(𝐶(𝜃𝑥∗ , 𝑋))) − 𝑋‖ (9)

2
𝜃̃𝑥 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 𝜃̃𝑥 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 ‖𝑅 (𝜃̂𝑦, 𝐻𝐸(𝐶(𝜃𝑥 , 𝑋))) − 𝑋‖ (10)

𝜃̂𝑥 = 𝜃̃𝑦

2
𝜃̂𝑥 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 ‖𝐻𝐸(𝐶(𝜃𝑥 , 𝑋)) − 𝑋̂𝑟′ ‖ (11)

HE is a coding function, (11) becomes,

2
𝜃̂𝑥 ≈ 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 ‖𝐶(𝜃𝑥 , 𝑋) − 𝑋̂𝑟′ ‖ (12)

combining (7) and (12),

A novel compression methodology for medical images using deep … (Shyamala Navaneethakrishnan)
266  ISSN: 2089-4864

2
𝜃̂𝑥 = 𝑎𝑟𝑔𝑚𝑖𝑛𝜃𝑥 ‖𝑅 (𝜃̂𝑦, 𝐶(𝜃𝑥 , 𝑋)) − 𝑋‖ (13)

in (13) is employed to train the model.

Let X and 𝜃𝑗 be the collection of input images and trained variables, mean square error (MSE) is used
as the loss function to train C-DCNN and it is represented as:

1 2
𝐿𝑜𝑠𝑠𝑥 (𝜃𝑥 ) = ∑𝑀 ̂
𝑝=1 ‖𝑅 (𝜃𝑦 , 𝐶(𝜃𝑥 , 𝑋𝑝 )) − 𝑋𝑝 ‖ (14)
2𝑀

similarly, with a collection of compact form 𝑋̂𝑟 from C-DCNN and input images X, MSE is used as the loss
function to train R-DCNN.
2
1
𝐿𝑜𝑠𝑠𝑦 (𝜃𝑦 ) = ∑𝑀 ̂ ̂
𝑝=1 ‖𝑟𝑒𝑠 (𝐻𝐸 (𝜃𝑥 , 𝑋𝑟𝑝 , 𝜃𝑦 )) − (𝐻𝐸 (𝑋𝑟𝑝 ) − 𝑋𝑝 )‖ (15)
2𝑀

4. NUMERICAL RESULTS AND DISCUSSION

4.1. Details of the dataset
In this research work, a robust method is proposed for compressing medical images without losing
image quality. The proposed method has been implemented and verified in MATLAB-2019a, executed in
Intel core i5-processor @ 3.60 GHZ, 16 GB RAM. The proposed method is validated on various medical
images of Medpix [21] and Kaggle [22] databases. A total of 600 images are randomly chosen for training, as
given in Table 1. The remaining images are employed to validate the presented method. Figure 3 shows the
original images.

Table 1. Data source information

Sl. No. Image type Number of images
1. CT 200
2. MRI 200
3. US 200
4. X-ray 200

CT MRI US X-ray

Figure 3. Sample medical images

4.2. Performance metrics

The effectiveness of the presented compression technique is assessed based on PSNR [23],
CR, mean structural similarity index (SSIM) [24] and SSS [25]. In summary, higher PSNR and SSIM
indicate that the recovered images, R are identical to the original images, O. The definition of these metrics
as (16)-(21).
1
𝑀𝑆𝐸 = ∑𝑀 𝑁
𝑖=1 ∑𝑗=1[𝑂(𝑖, 𝑗) − 𝑅(𝑖, 𝑗)]
2
(16)
𝑀𝑁

2
𝑃𝑆𝑁𝑅 = 10 ∗ 𝑙𝑜𝑔10 (255 ⁄𝑀𝑆𝐸 ) 𝑑𝐵 (17)

Int J Reconfigurable & Embedded Syst, Vol. 13, No. 2, July 2024: 262-270
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  267

(2𝜇𝑂 𝜇𝑅 +𝑐1 )+(2𝜎𝑂𝑅 +𝑐2 )

𝑆𝑆𝐼 = 2 𝜇 2 +𝑐 )(𝜎 2 𝜎 2 +𝑐 ) (18)
(𝜇𝑂 𝑅 1 𝑂 𝑅 2

1
𝑆𝑆𝐼𝑀 = ∑𝑁
𝑖=1 𝑆𝑆𝐼𝑖 (19)
𝑁

𝑆𝑖𝑧𝑒 𝑜𝑓 𝑜𝑟𝑖𝑔𝑖𝑛𝑎𝑙 𝑖𝑚𝑎𝑔𝑒

𝐶𝑅 = (20)
𝑆𝑖𝑧𝑒 𝑜𝑓 𝑐𝑜𝑚𝑝𝑟𝑒𝑠𝑠𝑒𝑑 𝑏𝑖𝑡𝑠𝑡𝑟𝑒𝑎𝑚

𝑆𝑖𝑧𝑒 𝑜𝑓 𝑐𝑜𝑚𝑝𝑟𝑒𝑠𝑠𝑒𝑑 𝑖𝑚𝑎𝑔𝑒

𝑆𝑆𝑆 = 1 − 𝑋 100 (21)
𝑆𝑖𝑧𝑒 𝑜𝑓 𝑜𝑟𝑖𝑔𝑖𝑛𝑎𝑙 𝑖𝑚𝑎𝑔𝑒

4.3. Experimental study

4.3.1. Performance evaluation of CT images
The prime target of this method is to obtain medical images with high CR, SSIM, and PSNR.
Table 2 summarizes the efficiency of the presented compression technique over CT images. There are five
different CT images taken to compute metrics which are furnished in Table 2. The presented method yielded
mean PSNR, CR, SSIM and SSS values of CT images as 42.82 dB, 26.14, 0.95 and 96.15% respectively.
Figure 4 displays the input and reconstructed CT images.

Table 2. Effectiveness of the compression method on CT images

Image no. PSNR (dB) CR SSIM SSS (%)
1 41.72 23.91 0.930 95.82
2 43.16 26.95 0.960 96.29
3 43.34 23.38 0.909 95.72
4 43.18 28.88 0.986 96.54
5 42.69 27.57 0.971 96.37
Mean 42.82 26.14 0.95 96.15

Input images

Reconstructed images

Figure 4. Samples of the input and recovered images employing the proposed technique

4.3.2. Performance evaluation of MRI images

In this sub-section, the performance of the proposed compression method is analyzed using MRI
images. There are five MRI images considered to estimate the PSNR, CR, SSIM and SSS. Table 3 lists the
effectiveness of the suggested strategy when applied to MRI images. The suggested technique achieved mean
values of 43.88 dB, 26.81, 0.96 and 96.25% for PSNR, CR, SSIM and SSS, respectively. Figure 4 displays
the input and reconstructed MRI images.

A novel compression methodology for medical images using deep … (Shyamala Navaneethakrishnan)
268  ISSN: 2089-4864

Table 3. Effectiveness of the compression method on MRI images

Image no. PSNR (dB) CR SSIM SSS (%)
1 43.88 29.15 0.998 96.57
2 43.40 27.18 0.964 96.32
3 43.11 28.63 0.972 96.51
4 44.78 25.73 0.956 96.11
5 44.24 23.35 0.907 95.72
Mean 43.88 26.81 0.96 96.25

4.3.3. Performance evaluation of ultrasound images

The introduced compression technique is targeted to enhance the CR, PSNR, SSIM and SSS of the
medical image without losing significant information. Table 4 displays how well the proposed method
performs compression over US images. To evaluate the effectiveness of the suggested strategy, five US
images are used. A mean PSNR of 46.29 dB, CR of 25.76, SSIM of 0.98 and SSS of 96.07% were all
attained using the suggested approach. Figure 4 displays the original and recovered US images.

Table 4. Effectiveness of the compression method on US images

Image no. PSNR (dB) CR SSIM SSS (%)
1 46.45 28.40 0.982 96.48
2 45.12 21.40 0.965 95.33
3 47.25 25.98 0.992 96.15
4 46.52 24.24 0.988 95.88
5 46.11 28.78 0.959 96.53
Mean 46.29 25.76 0.98 96.07

4.3.4. Performance evaluation of X-ray images

The efficacy of the introduced technique is examined using the X-ray image in this sub-section. Five
X-ray images are employed. The outcomes of this method are applied to the X-ray images and summarized in
Table 5. The presented method achieved the mean PSNR, CR, SSIM, and SSS values as 43.51 dB, 29.97,
0.98 and 96.95% respectively. Figure 4 displays the input and reconstructed X-ray images.

Table 5. Effectiveness of the compression method on X-ray images

Image no. PSNR (dB) CR SSIM SSS (%)
1 44.39 34.68 0.987 97.12
2 44.92 27.94 0.973 96.42
3 43.30 27.39 0.969 96.35
4 41.05 30.04 0.983 96.67
5 43.90 29.79 0.979 98.21
Mean 43.51 29.97 0.98 96.95

4.4. Discussions on the results

To demonstrate the proposed compression method’s superiority, its efficiency is compared with
other well-known techniques in light of PSNR, CR and SSS. The previous methods considered for
comparison are PSO-based thresholding BWT-MTF [9] tetrolet [10] QFOM [11] optimized RNN [12] and
SPIHT-BAT [13] because all the previous models process the MRI images. Ahilan et al. [7] used multilevel
thresholding of PSO to extract ROI. The computed ROI and non-ROI regions are compressed using the
blending method. As per Devadoss and Sankaragomathi [9] morphological operations are used to distinguish
the ROI from non-ROI areas. The ROI is reduced with quadtree and non-ROI is compressed with the fusion
BWT-MTF. After compression, the data is encoded with HE. Maheswari and Raghavan [10] used the tetrolet
method to compress medical images. Magar and Sridharan [11] compressed the ROI region using quasi-
fractal and non-ROI with OM. In the study by Sabbavarapu et al. [12] the ROI region is compressed using
DWT and the non-ROI region is compressed using optimized RNN. In this method, a hybrid gravitational
search algorithm-PSO (GSA-PSO) is adopted to optimize the RNN’s parameters.
A comparison of the proposed strategy with earlier methods is shown in Table 6. A pictorial
representation of CR and PSNR with previous methods is shown in Table 6. It is quite clear from the
comparative study that the introduced technique achieves high CR while keeping decent PSNR in contrast to
the prior methods used for comparison.

Int J Reconfigurable & Embedded Syst, Vol. 13, No. 2, July 2024: 262-270
Int J Reconfigurable & Embedded Syst ISSN: 2089-4864  269

The PSO method has low CR and PSNR because it uses thresholding and blending methods to
compress an image. The PSNR and CR of the developed method are higher than PSO, QFOM, RNN and
BWT-MTF. It demonstrates that the proposed method recovers images with good quality, also the results
proved that the efficiency of the proposed method is enhanced in light of PSNR, CR and SSS. The proposed
method produces better CR, PSNR and SS than the earlier methods, because of the usage of the deep learning
network in medical image compression.

Table 6. Comparative outcomes of the proposed method with previous approaches

Contributors Method PSNR (dB) CR SSS (%)
Ahilan et al. [7] PSO 22.7 2.13 -
Devadoss and Sankaragomathi [9] BWT-MTF 34.6 4.63 78.42
Maheswari and Raghavan [10] TETROLET 19.65 4.12 -
Magar and Sridharan [11] QFOM 33.5 24.61 -
Sabbavarapu et al. [12] RNN 35.2 23.34 95.71
Salih and Kadhim [13] SPIHT-BAT 36.71 21.41 95.07
Proposed DCNN-MRI 43.88 26.81 96.25
DCNN-CT 42.82 26.14 96.15
DCNN-US 46.29 25.76 96.07
DCNN-X-ray 43.51 29.97 96.95

5. CONCLUSION AND FUTURE WORKS

This paper presents image compression using the CNN for medical images. To achieve a better
tradeoff between compression rate and image quality, two CNNs are connected to design an efficient
compression method. The proposed method employed deep learning for learning the compact demonstration
of the input image and then coded by HE. Finally, the encoded image is recovered with higher quality.
The outcomes showed the power of the proposed technique, achieving mean PSNR of 42.82 dB, 43.88 dB,
46.29 dB and 43.51 dB for CT, MRI, US and X-ray images. In the future, this method shall be implemented
in real-time applications and be used for other emerging applications. Likewise, the performance of this
method can be improved by optimizing the hyperparameters of the CNN model.

REFERENCES
[1] H. Kasban and S. Hashima, “Adaptive radiographic image compression technique using hierarchical vector quantization and
huffman encoding,” Journal of Ambient Intelligence and Humanized Computing, vol. 10, no. 7, pp. 2855–2867, Jul. 2019, doi:
10.1007/s12652-018-1016-8.
[2] G. U. V. Selvi and R. Nadarajan, “CT and MRI image compression using wavelet-based contourlet transform and binary array
technique,” Journal of Real-Time Image Processing, vol. 13, no. 2, pp. 261–272, Jun. 2017, doi: 10.1007/s11554-014-0400-7.
[3] S. N. Kumar, A. L. Fred, H. A. Kumar, and P. S. Varghese, “Lossless compression of CT images by an improved prediction
scheme using least square algorithm,” Circuits, Systems, and Signal Processing, vol. 39, no. 2, pp. 522–542, Feb. 2020, doi:
10.1007/s00034-019-01152-8.
[4] N. A. Awad and A. Mahmoud, “Improving reconstructed image quality via hybrid compression techniques,” Computers,
Materials & Continua, vol. 66, no. 3, pp. 3151–3160, 2021, doi: 10.32604/cmc.2021.014426.
[5] B. Sujitha, V. S. Parvathy, E. L. Lydia, P. Rani, Z. Polkowski, and K. Shankar, “Optimal deep learning based image compression
technique for data transmission on industrial internet of things applications,” Transactions on Emerging Telecommunications
Technologies, vol. 32, no. 7, Jul. 2021, doi: 10.1002/ett.3976.
[6] N. Krishnaraj, M. Elhoseny, M. Thenmozhi, M. M. Selim, and K. Shankar, “Deep learning model for real-time image
compression in internet of underwater things (IoUT),” Journal of Real-Time Image Processing, vol. 17, no. 6, pp. 2097–2111,
Dec. 2020, doi: 10.1007/s11554-019-00879-6.
[7] A. Ahilan et al., “Segmentation by fractional order darwinian particle swarm optimization based multilevel thresholding and
improved lossless prediction based compression algorithm for medical images,” IEEE Access, vol. 7, pp. 89570–89580, 2019, doi:
10.1109/ACCESS.2019.2891632.
[8] P. N. T. Ammah and E. Owusu, “Robust medical image compression based on wavelet transform and vector quantization,”
Informatics in Medicine Unlocked, vol. 15, p. 100183, 2019, doi: 10.1016/j.imu.2019.100183.
[9] C. P. Devadoss and B. Sankaragomathi, “Near lossless medical image compression using block BWT–MTF and hybrid fractal
compression techniques,” Cluster Computing, vol. 22, no. S5, pp. 12929–12937, Sep. 2019, doi: 10.1007/s10586-018-1801-3.
[10] S. Saravanan and S. Juliet, “A metaheuristic approach for tetrolet-based medical image compression,” Journal of Cases on
Information Technology, vol. 24, no. 2, pp. 1–14, Jul. 2021, doi: 10.4018/jcit.20220401.oa3.
[11] S. S. Magar and B. Sridharan, “Hybrid image compression technique using oscillation concept quasi fractal,” Health and
Technology, vol. 10, no. 1, pp. 313–320, Jan. 2020, doi: 10.1007/s12553-018-00282-4.
[12] S. S. Yadav and S. M. Jadhav, “Deep convolutional neural network based medical image classification for disease diagnosis,”
Journal of Big Data, vol. 6, no. 113, pp. 1–18, Dec. 2019, doi: 10.1186/s40537-019-0276-2.
[13] H. M. Salih and A. M. Kadhim, “Medical image compression based on SPIHT-BAT algorithms,” IOP Conference Series:
Materials Science and Engineering, vol. 1076, no. 1, p. 012037, Feb. 2021, doi: 10.1088/1757-899X/1076/1/012037.
[14] M. R. Reddy, K. S. Ravichandran, B. Venkatraman, K. R. Sekar, and R. Manikandan, “Improved pharma education system in the
field of medical images using compression techniques,” Cluster Computing, vol. 22, no. S6, pp. 15049–15057, Nov. 2019, doi:
10.1007/s10586-018-2496-1.

A novel compression methodology for medical images using deep … (Shyamala Navaneethakrishnan)
270  ISSN: 2089-4864

[15] M. A. Rahman and M. Hamada, “Lossless image compression techniques: a state-of-the-art survey,” Symmetry, vol. 11, no. 10,
Oct. 2019, doi: 10.3390/sym11101274.
[16] E. Erdal and A. Ergüzen, “An efficient encoding algorithm using local path on huffman encoding algorithm for compression,”
Applied Sciences, vol. 9, no. 4, Feb. 2019, doi: 10.3390/app9040782.
[17] E. Jalilian, H. Hofbauer, and A. Uhl, “Iris image compression using deep convolutional neural networks,” Sensors, vol. 22, no. 7,
Mar. 2022, doi: 10.3390/s22072698.
[18] S. K. Lakshmanaprabu, N. M. Sachi, K. Shankar, N. Arunkumar, and R. Gustavo, “Optimal deep learning model for classification
of lung cancer on CT images,” Future Generation Computer Systems, vol. 92, pp. 374–382, Mar. 2019, doi:
10.1016/j.future.2018.10.009.
[19] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classifcation with deep convolutional neural networks,” Advances in
neural information processing systems, vol. 25, 2012.
[20] S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in
Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 448–456.
[21] “MedPix.” Accessed: Sept. 21, 2022. [Online]. Available: https://medpix.nlm.nih.gov.
[22] “Kaggle.” Accessed: Sept. 13, 2022. [Online]. Available: https://kaggle.com.
[23] K. Dimililer, “DCT-based medical image compression using machine learning,” Signal, Image and Video Processing, vol. 16,
no. 1, pp. 55–62, Feb. 2022, doi: 10.1007/s11760-021-01951-0.
[24] Q. Min, X. Wang, B. Huang, and Z. Zhou, “Lossless medical image compression based on anatomical information and deep
neural networks,” Biomedical Signal Processing and Control, vol. 74, Apr. 2022, doi: 10.1016/j.bspc.2022.103499.
[25] Y. Pourasad and F. Cavallaro, “A Novel image processing approach to enhancement and compression of X-ray images,”
International Journal of Environmental Research and Public Health, vol. 18, no. 13, Jun. 2021, doi: 10.3390/ijerph18136724.

BIOGRAPHIES OF AUTHORS

Shyamala Navaneethakrishnan worked as an assistant professor at Nallamuthu

Gounder Mahalingam College, Pollachi. She completed her M.Phil. in 2015 and pursuing her
Ph.D. under the guidance of Dr. S. Geetha, Department of Computer Science, Government
Arts and Science College for Women, Puliakulam, Coimbatore. She is having nearly 12 years
of teaching experience and published nearly 10 papers in national and international journals.
Her area of research is data mining, image processing and machine learning. She can be
contacted at email: [email protected].

Dr. Geetha Shanmugam is working as an assistant professor in the Department

of Computer Science in Government Arts and Science College for Women, Puliakulam,
Coimbatore, Tamil Nadu. She completed her Ph.D. at Anna University. She is having 20 years
of teaching and research experience. Her area of research is soft computing. She has published
more than 20 papers in various national and international journals. She delivered lectures in
many colleges and chaired many conferences. She organized many seminars, workshops,
conferences and received funds from agencies like UGC, CSIR and TEQIP. She can be
contacted at email: [email protected].

Int J Reconfigurable & Embedded Syst, Vol. 13, No. 2, July 2024: 262-270