**8. Conclusions**

110 Liver Tumors

Fig. 7. (a) the original image (Data set 4). The tumor detection result obtained (b) using the method based on [6], (c) the proposed method, and (d) by the application of a shape filter to the image in (c). (In (b)–(d), the detected regions are white and the arrows indicate the

Fig. 8 show the results of the experiments for Data set 3. We used four methods: EM with and without preprocessing (contrast enhancement) and EM/MPM with and without preprocessing. As we used different pre-processing for EM and EM/MPM, it may affect the result a little. However, Figures 8(c)–(f) are the images obtained after morphology operations. Figures 8(c), (d) demonstrate the effectiveness of our histogram transformation. Comparing

Figs. 8(c), (e) with Figs. 8(d), (f), we find that using EM/MPM improves performance.

locations of the detected tumors.)

EM/MPM with preprocessing

(a) (b) (c) (d)

(a) (b) (c)

(d) (e) (f)

Fig. 8. Results after morphology (white lines) (a) Smoothed original image (b) answer (c) EM without preprocessing (d) EM with preprocessing (e) EM/MPM without preprocessing (f)

Next, we quantitatively evaluate the tumor segmentation performance in terms of the metrics proposed in the MICCAI Liver Tumor Segmentation Challenge 2008 [11]. The metrics are the volumetric overlap error (Overlap Error), absolute relative volume difference (Vol. dif.), average symmetric surface distance (Ave. Dist.), RMS symmetric surface distance (RMS Dist.), and maximum surface distance (Max. Dist.). For ideal segmentation, all metrics should be zero. Table 3 shows the results obtained for one slice of a segmented region in a tumor by the metrics given in [11]. For Data set 1, regions in which tumors are detected are not solely represented by dark regions but also by bright voxels around them. Our proposed method can detect dark tumor regions; however, it cannot detect the bright tumor regions. Therefore, we We have proposed a new method to detect tumors automatically in CT image. By using contrast enhancement with PDFs of different tissue classes in a newly devised histogram transformation method, we can enhance the image contrast. Moreover, by using the EM/MPM algorithm, we can detect tumors more accurately. We plan to improve our work to handle the large morphology variation of tumors.
