Press "Enter" to skip to content

Computer aided detection system using soft tissue technique in x-ray image

Computer aided detection system using soft tissue technique in x-ray image

Dr. R. Suresh Babu, Mr.R.Kishore

Department of ECE”,

Kamaraj College of Engineering and Technology”,

hodece@kamarajengg.edu.in and kishoreresearchscholar@gmail.com

Abstract

Lung cancer is pathological threat throughout world. Such threat needs to be detected early. To overcome situation, x-ray image need to be analyzed. Expert design computer aided detection system (CADs) which help radiologist for reliable decision and this decision sent to client through doctors. So, we recently introduce soft tissue technique. x-ray images are downloaded from JSRT database. This paper proposes soft tissue technique. Specifically, CADs system using soft tissue technique have developed from x-ray image. Support Vector Machine (SVM) layers have been used for the decision-making stage after extracting features.

Keywords: lung cancer, computer aided detection, x-ray image, soft tissue technique, JSRT Database

I. Introduction

Every year (2009), American Cancer Society announced overall lung cancer 14% curable rate having stages combined (early, middle & advanced stages) [1]. Lung cancer, starting stage, improve curable rate by 50%. In recent days, it is a challenging task when rib and clavicle feature are being overlapped with lung nodule.

A sensitive technique was needed [2]. X-ray image is being preferred because it’s cost-effective, routinely accessible plus dose-effective tool [3]. Radiologists missed 30% nodules in x ray image and that, 82-95% among missed nodules partly obscured by overlying bones such as ribs plus clavicles [4][5].

A major challenge for current CADs system is detect nodules overlapping ribs, rib crossings, plus clavicles. This leads lowering sensitivity. Nicholas J. Novak [6] detect small lung cancers using dual energy subtraction radiography method. This would increase efficiency but the hospital requires specialized equipments. Matsumoto et.al., proposed CADs system at a FP rate equals 11 per image, even though it had 80% sensitivity. But, accuracy was not improved [7].

In this work, we need to develop a CADs model using soft tissue technique to improve sensitivity with the same FP rate and simultaneously reduces FP rate by reducing improved sensitivity. Hence, accuracy need to be improved while making a good decision.

II. Materials and Methods

A. Database of X-Ray Image

154 nodules images plus 93 normal images downloaded from publicly available JSRT (Japanese Society of Radiological Technology) database [8]. nodule size ranged

15 to 24 mm. The images were digitized to yield 12-bit chest x rays (CXRs) with a resolution contains 2048 × 2048 pixels. Pixel was 0.175 × 0.175 millimeters. Missed

nodules were divided into five categories based on subtlety rating. Five categories are extremely subtle, very subtle, subtle, relatively obvious and obvious.

B. CADs System

X-ray images obtained by using single exposure technique having two detectors seperated by copper filter [3] [6]. The original image’s dimension are 1760 x 1760.The images are linearly sub-sampled to 512 x 512 dimension. This was done to facilitate experimentation as it allows for a considerable decrease in computation time. System performed lung segmentation for extracting lung boundary [9]. The various segmentation methods are rule based methods, pixel based methods, hybrid methods and deformable model based methods. After lung fields segmented, background trend correction method applied to segmented lung field. A second order bivariate polynomial function was fitted to each of the left and right lung fields where F(u”,v)= au2+bv2+cuv+du+ev+f represent polynomial function having a, b, c, d, e, f as co-efficient calculated for each parameter. Subsequently, the fitted functions for the left and right lung fields were subtracted from the original image a(u”,v). In this approach, a background trend in the lung fields as a low frequency surface was removed [10].

The pre-processed image in CADs system was applied to different types of gray level morphological open operation to form a nodule enhanced image and a nodule enhanced image is modified in the nodule likelihood map [11]. It results in nodule candidate detection based on local peaks in the map. This nodule candidate is very important to find the lung to locate boundary. Peaks within the nodule candidate region in the nodule enhanced image is used to

initialize candidate segmentation using watershed technique. With the watershed technique [12], the nodule candidate region was divided into several gray levels. The advantage of this technique is able to produce good segmentation results and it would be more useful to focus

on nodule candidates. Finally, gray level features were

extracted from nodule candidates.

The name of the gray level features are contrast, correlation, energy, homogeneity and entropy. Based on the extraction of gray level features, feature selection method based on genetic algorithm [13] is used to determine the optimal size of a feature set automatically. The optimal size of a feature set is given as input to support vector machine for classifying nodule candidates [14]. A major issue for the detection of lung cancer in CADs system is to detect lung nodules overlapping ribs and clavicles in pre-processed image. Due to this issue, radiologist miss 30% nodules. So, the sensitivity of this system is also reduced. In order to improve the sensitivity, we create a soft tissue image from x-ray for the detection of nodule candidate.

Other essay:   System

C. Creation of soft tissue image

A soft tissue technique [6] [15] [23] [24] created using x ray image. It was used in rib and clavicle suppression form. Fig 2 shows soft tissue image creation from x-ray. MTANN is non linear filter which needs to be trained using x ray image and corresponding teaching image. Here we consider the corresponding teaching image is bone.

fb(u”,v) =NN (au”,v) ———————————————-(1)

Where au”,v = {g(u-i”,v-j) |i”,j є Rs } is a input vector to MTANN which is a subregion and fb(u”,v) is an estimate for a teaching value. The MTANN is trained by using subregions together with every corresponding teaching single pixels. The training set of pairs of a sub region and a teaching pixel is represented by

{a(u-i”,v-j), T(i”,j)| u”,v є RT }

= { (a1 “,T1) (a2″,T2) (aN”,TN) }————————–(2)

Where T(i”,j) is a teaching image, RT is a training region corresponds to collection of sub region centers and N is number of pixels.. For a single MTANN, suppression of ribs containing various frequencies was difficult due to limited capability. In order to overcome this issue multiresolution decomposition/composition techniques were applied.

First”,a lower resolution image GL(u”,v) was obtained from an original higher resolution image [15] GH(2u”,2v) by performing downsampling with averaging i.e., four pixels in the original image are replaced by a mean value of four pixels represented by

GL(u”,v) = (1/4) ∑ GH(2u, 2v)—————————(3)

u”,v є R22

where R22 is a 2 x 2 pixel region. The lower resolution image is enlarged by upsampling with pixel substitution i.e., a pixel of lower resolution image is replaced by four pixels with the same pixel value, as follows:

GU(u”,v)=GL(u/2″,v/2)——————————————-(4)

[image: image1.png]

Fig 1 CADs system

[image: image2.png]

Fig 2 soft tissue image creation from x-ray

Then, we subtract enlarged lower resolution image from the

higher resolution image to get high resolution difference image, represented by

DH(u”,v) = GH(u”,v) – GU(u”,v) ——————————–(5)

These procedures are performed again and again producing

further lower resolution images. Thus, multiresolution images with various frequencies are obtained by the use of multiresolution decomposition technique. An important property of this technique is the same high resolution image GH(u”,v) that can be obtained as follows:

GH(u”,v)=GU(u”,v)+DH(u”,v) ————————————(6)

Therefore, we can choose multiresolution images for processing independently instead of processing original high resolution images directly. After training with input x ray image and the dual energy bone image, the multiresolution MTANN is able to produce bone image that are expected to be similar to the teaching bone image.

The bone image fb(u”,v) produced by the trained MTANN with the lung masking image n(u”,v) and weighting parameter wc is subtracted from the sub region of original x ray image g(u”,v) to create a soft tissue image.

f(u”,v)= g(u”,v) – wc x fb(u”,v) x n(u”,v)————————(7)

where f(u”,v) denotes the soft tissue image with different

types of rib contrast by the use of weighting parameter wc.

D. CADs system using soft tissue technique

The CADs system segments the lung for identifying sub region, create the soft tissue technique to detect nodule candidate on soft tissue image, segments the nodule candidates on soft tissue image which proceed with feature extraction and classification for the detection of lung nodules. Segmentation of nodule candidates is done by the use of clustering watershed method. Fig 3 shows the development of CADs system using soft tissue technique for detection of subtle nodules to reduce rib-induced false positives. Peaks within the nodule candidate region in the nodule enhanced image were obtained and used to initialize the clustering watershed method [12].

With the clustering watershed method, the nodule candidate regions were divided into several catchment basins. Each minimum point were surrounded by a catchment basin associated with it; there were one or more peaks, each of which were surrounded by a cluster of connected pixels that consituted a catchment basin. The features of the nodules were suppressed in soft tissue image. Detection of nodule candidate on soft tissue image may be misclassified as non-nodules. So, the segmentation step is being repeated on soft tissue and x ray image. Sixty morphologic and gray level based features were extracted from each candidate from both x ray and soft tissue image and it is given as input to feature selection method based on genetic algorithm [13]. A non linear SVM with a Gaussian kernel was employed for the classification of nodule candidates into nodules or non-nodules [14].

III. Results

In this section, we present some results to demonstrate the performance of proposed CADs system which includes the

[image: image3.png]

Fig 3 CADs system using soft tissue technique

soft tissue technique. First, we create the soft tissue technique for CADs system. Next, the sensitivity for nodule candidate detection on soft tissue image with different rib contrast was plotted to find the peak value of nodule candidate.

Other essay:   Project presentation on computer virus

A. MTANN Training

Four x rays and their corresponding bone images in a training set were used to train the MTANN. It is one of the advantages that it needs four training images. In the four images, one was a normal image and the other three contained with nodule image. In a sub region, the size of the MTANN was 9 x 9 pixels. It was sufficient to cover the width of rib in the image. Three layered MTANN were used to suppress rib where the number of input, hidden and output units were 81, 20 and 1 respectively. Fig 4 shows the bone image and the soft tissue image with different rib contrast processed by MTANN technique.

B. Nodule Candidate Detection

In fig 4, the sensitivity was highest when the rib contrast

parameter mc was set 0.4. The most nodules were obvious in the nodule candidate detection step. In this plotted graph”,

84 candidates that had max code values in the nodule likelihood map were selected as the origin point to indicate

the performance of the nodule candidate detection

C. Performance of the existing CADs system using soft tissue image

Soft tissue image was applied to replace the x-ray image in CADs system. The nodule candidates were detected from the soft tissue image by the use of two stage nodule enhancement method. Fig 5 illustrates the performance improvement of nodule candidate detection step using soft tissue image. The non-subtle nodule overlapping ribs and clavicles missed in soft tissue image but detected in x-ray image. So, the performance of CADs system using x ray image has been improved to a minimum. Then, 30 features were extracted from the soft tissue image after the segmentation of nodule candidate.

[image: image4.png]

Fig 4. Effect of the change in rib contrast on the sensitvity of the proposed CADs system

[image: image5.png]

(a) (b)

Fig 5(a) Nodule candidate detection results based on x ray image (b) Nodule candidate detection results based on soft

tissue image

[image: image6.png]

Fig 6 Sensitivity vs Number of FPs per image

Table I: Features Extracted for Proposed CADs system based on the soft tissue and x ray image

S.No

Feature Extraction

Description

1

can.u

Co-ordinates of a nodule candidate

2

can.v

Co-ordinates of a nodule candidate

3

can.Grad1

Co-ordinates of a nodule likelihood values

4

can.CV1

Calculated by using gray level values

5

can.Grad2

Co-ordinates of a nodule likelihood values

6

Can.CV2

Calculated by using gray level values

7

Shape1

Area of a segmented nodule candidate

8

Shape2

short and long axes of an ellipse fitted to the nodule candidate

9

Shape3

Area of a convex hull of the candidate

10

Shape4

distance between the centroid of the candidate and the centroid of the fitted ellipse

11

Gray1

μregion – μsurround

12

Gray2

σregion- σsurround

13

Gray3

minregion-minsurround

14

Gray4

maxregion-maxsurround

15

Gray5

Calculated using Gray1

16

Gray6

Calculated using Gray2

17

Gray7

Calculated using Gray3

18

Gray8

Calculated using Gray4

19

Grad1

7

= Gr = (1/8) ∑ Grh

k=0

Grh = [1/Nh ] ∑ cos αmn

mn є regionh

t1 ≤ Mmn ≤ t2

where Nh is the number of pixels in the segmented nodule region h

20

Grad2

7

= σ = √ ∑ (Grh- Gr )2

k=0

21

Grad3

= Gr / σ

22

Surface1

λmin

23

Surface2

λmax

24

Surface3

λmin λmax

25

Texture1

∑ [C(i”,j)2]

ij

26

Texture2

∑(i-j)2C(i”,j) ij

Where C(i”,j) ( Co-occurrence

matrix calculated over neighboring pixels and a summation range from the minimum to the maximum pixel value in the pre-processed image

27

Texture3

Calculated based on Texture1 and Texture2

28

Texture4

Calculated based on Texture1 and Texture2

29

Texture5

Calculated based on Texture1 and Texture2

30

Texture6

Calculated based on Texture1 and Texture2

31

False Positive

Lregion / Loverlap

Table II Performance comparison of several existing CAD

system which used the JSRT database

Sensitivity FPs/image Database

Wei et al. 80% 5.4 All

(123/154) (1333/247) nodule and

normal

image in

JSRT(247)

Coppini et al. 60% 4.3 All nodule

(93/154) (662/154) image in

JSRT(154)

Schilham et al. 67% 4 All nodule

(103/154) (616/154) image in

JSRT(154)

Hardie et.al. 63% 2 Nodule

(88/140) (280/140) image in

JSRT(140)

Chen et.al. 71% 2 Nodule

(100/140) (466/233) and Normal

image in

JSRT(233)

Soft tissue 87% 1.5 All nodule

based CADs (134/154) (371/247) and system normal

image in

JSRT(247)

IV. Conclusion

In a CADs system, a soft tissue technique is a technique used to suppress ribs and clavicles with the help of massive training artificial neural network. Detection of nodule candidate on soft tissue image misclassified as non-nodules due to suppression of rib feature. So, it is being developed with sensitivity value calculated as 94%=145/154 by incorporating soft tissue technique after segmentation of lung. The number of FPs per image was reduced to 1.5 by reducing values of sensitivity to 87% in CADs system.

The authors have declared that there is no conflict of interest.

Other essay:   Computer adaptive examination system

References

[1] Arnold M.R. Schilham, Bram van Ginneken, Marco Loog (2006), ”A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database”, Medical Image Analysis 10, pp 247–258.

[2] C.I. Henschke, D.I. McCauley, D.F. Yankelevitz, D.P. Naidich, G.McGuinness, O.S. Miettinen, D.M. Libby, M.W. Pasmantier, J. Koizumi, N. K. Altorki, and J. P. Smith(1999), Early lung cancer action project: Overall design and findings from baseline screening, Lancet, vol. 354, pp. 99 – 105.

[3] Chen S, Suzuki K, MacMahon H (2011), “Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification”, Medical Physics”,

Apr 38(4), pp 1844-58.

[4] J.H Austin, B. M. Romney, L.S Goldsmith (1992), Missed bronchogenic carcinoma: Radiographic findings in 27 patients with a potentially resectable leison evident in reterospect, Radiology, vol. 182, pp 115-122.

[5] P. K. Shah, J. H. Austin, C. S. White, P. Patel, L. B. Haramati, G. D. Pearson, M. C. Shiau, and Y. M. Berkmen (2003), Missed non- small cell lung cancer: Radiographic findings of potentially resectable lesions evident only in retrospect”, Radiology, vol. 226, pp. 235–241.

[6] Nicholas J. Novak (2015), Does BMI Affect Diagnostic Efficacy of Computer Aided Diagnostic Software in the Identification of Malignant Pulmonary Nodules in Dual Energy Subtracted Chest Radiographs?, Vol.11, No. 2.

[7] T. Matsumoto, K. Doi, A. Kano, H. Nakamura, T. Nakanishi(1993), Evaluation of the potential benefit of computer aided diagnosis of lung cancer screenings using photofluorography: analysis of an observer study, Nihon Igaku Hoshasen Gakkai Zasshi, vol. 53, pp 1195-1207, Oct 25.

[8] http://db.jsrt.or.jp/eng.php

[9] William M.Wells, Allan Colchester, Scott Delp (1998)”,

“Medical Image Computing and Computer Assisted Intervention”, Springer.

[10] Bram van Ginneken, Alejandro F. Frangi, Joes J. Staal, Bart M.ter Haar Romeny, Max A. Viergever, (2002), Active shape model segmentation with optimal features, IEEE Transactions on medical imaging, Vol.21, No.8.

[11] Haralick RM, Sternberg SR, Zhuang X(1987), Image analysis using mathematical morphology, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp 532-550.

[12] Chongbo Zhou, Chuancai Liu, “Co-segmentation of multiple similar images using saliency detection and region merging”, Computer Vision IET, vol. 8, no. 3, pp. 254-261, 2014

[13] Lilla Boroczky, Luyin Zhao, K.P. Lee (2005)”,Feature subset selection for improving the performance of false positive reduction

in lung nodule CAD, IEEE symposium on computer based medical

systems.

[14] Sheng Chen, Liping Yao, Bao Chen (2016) A parameterized logarithmic image processing method with Laplacian of Gaussian filtering for lung nodule enhancement in chest radiographs. Medical & Biological Engineering & Computing 54:11, pp 1793-1806.

[15] Sheng Chen, Kenji Suzuki(2013), Computerized detection of

lung nodules by means of virtual dual energy radiography, IEEE Transactions on Biomedical Engineering, vol.60, no.2.

[16] Kenji Suzuki, Hiroyuki Abe, Heber MacMahon, Kunio Doi(2006)”,Image processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network, IEEE Transactions on Medical Imaging, vol.25, no.4.

[17] Nicholas Petrick, Berkman Sahiner, Samuel G. Armato III, Alberto Bert, Loredana Correale, Silvia Delsanto, Matthew T. Freedman”,David Fryd”,David Gur, Lubomir Hadjiiski”,Zhimin Huo”,

Yulei Jiang, Lia Morra, Sophie Paquerault, Vikas Raykar, Frank Samuelson, Ronald M. Summers”,Georgia Tourassi, Hiroyuki Yoshida”,Bin Zheng, Chuan Zhou”,Heang-Ping Chan(2013), Evaluation of Computer aided detection and diagnosis systems, Am. Assoc. Phys. Med.

[18] Hayati Ture, Temel Kayikcioglu (2017), Detection and Segmentation of Nodules in Chest Radiographs Based on Lifetime Approach”,© Springer.

[19]Ali Aslantas, Dandil Emre, Murat Çakiroğlu (2017)”,”Comparison of segmentation algorithms for detection of hotspots in bone scintigraphy images and effects on CAD systems””,Biomedical Research”,vol 28, issue 2.

[20] N.S Raghava, G.Senthil Kumar(2006)”,”Image Processing for Synthesizing Lung Nodules: A Experimental Study”, Journal of Applied Sciences, pp 1238-42.

[21] Saleem Iqbal, Khalid Iqbal”,Fahim Arif, Arslan Shaukat”,Aasia Khanum(2014)”,”Potential Lung Nodules Identification for Characterization by Variable Multistep Threshold and Shape Indices from CT Images”, Computational and Mathematical Methods in Medicine”,Hindawi Publishing Corporation.

[22] Kenji Suzuki, Samuel G. Armato III”,Feng Li, Shusuke Sone”,

Kunio Doi(2002)”,”Massive training artificial neural network for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography”, Am. Assoc. Phys. Med.

[23] Bilal Ahmed, Tahir Rasheed, Mohammed A.U. Khan, Seong Jin Cho, Sungyoung Lee, Tae-Seong Kim(2006)”,”Rib Suppression for Enhancing Frontal Chest Radiographs Using Independent Component Analysis”.

[24] https://www.riveraintech.com/clearread-xray/

[25] Kenji Suzuki(2012), ”A review of computer-aided diagnosis in thoracic and colonic imaging”, pp 163-176.

[26] Suzuki K(2017), Machine Learning in Medical Imaging Before and After Introduction of Deep Learning. Journal of Medical Imaging and Information Science 34 (2): 14-24.

[27] Inyoung Song, Jeong Geun Y, Jeong Hee Park, Kyung Soo Lee, Myung Jin Chung(2016), ”Color radiography in lung nodule detection and characterization: comparison with conventional gray scale radiography””,BMC Medical Imaging, pp 1-7.

[28] https://scienceblog.com/1634/scientists-image-soft-tissues-with-new-x-ray-technique/

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *

0 Shares
Share via
Copy link

Spelling error report

The following text will be sent to our editors: