SEGMENTASI DAN PEMISAHAN CITRA PAP SMEAR OVERLAPPING DENGAN METODE DEEP LEARNING DAN WATERSHED

• MUH. JAMIL
• 14002631

---

ABSTRAK

 

ABSTRAK Nama : Muh. Jamil NIM : 14002631 Fakultas : Teknologi Informasi Program Studi : Magister Ilmu Komputer Jenjang : Strata Dua (S2) Konsentrasi : Image Processing Judul : Segmentasi dan Pemisahan Citra Pap smear Overlapping Dengan Metode Deep learning dan Watershed Kanker serviks merupakan penyakit yang menjadi penyebab kematian ribuan wanita di seluruh dunia pada setiap tahunnya. Sehingga menjadikan penyakit ini sebagai kanker tertinggi ke empat yang diderita oleh wanita. Salah satu cara untuk mewaspadai penyakit ini adalah dengan melakukan pemeriksaan dini yang disebut dengan Pap smear tes yang telah diperkenalkan oleh Dr.Georges
Papanicolou pada tahun 1940. Pemeriksaan ini membutuhkan waktu yang cukup lama dan rawan kesalahan, sehingga pemeriksaan otomatis dengan bantuan komputer sangat dibutuhkan. Segmentasi citra Pap smear merupakan salah satu langkah penting untuk dapat mengidentifikasi objek sel yang ada pada citra Pap
smear. Penelitian ini mengusulkan sebuah metode segmentasi untuk dapat memisahkan 2 sel overlap pada dataset RepomedUNM. Dari dataset tersebut dilakukan rekayasa pembuatan citra Pap smear sintetis beserta dengan citra ground
truth dalam bentuk overlap dan tunggal. Metode segmentasi yang diusulkan adalah metode berbasis deep learning untuk dapat mengenali 2 sel overlap pada area sel dan area overlap sel dengan skor mean IoU sebesar 0,9061. Selanjutnya hasil segmentasi dengan deep learning dapat dibagi keseluruhan areanya dengan menggunakan metode watershed segmentation sehingga pada hasil akhir sel
overlap berhasil dipisahkan dengan melakukan pengubahan nilai piksel pada objek sel dengan rata-rata skor jaccard berada pada angka 0,945 ketika dibadingkan dengan citra ground truth tunggalnya.
Kata kunci : Pap smear, Segmentasi, U-Net,Watershed segmentation.
 

KATA KUNCI

Segmentasi Pemisahan Citra,Deep Learning,Watershed

---

DAFTAR PUSTAKA

 

DAFTAR PUSTAKA [1] S. Rio, E. Sri, and T. Suci, “Persepsi tentang Kanker Serviks dan Upaya Prevensinya pada Perempuan yang Memiliki Keluarga dengan Riwayat Kanker,” J. Kesehat. Reproduksi, vol. 4, no. 3, pp. 159–169, 2017, doi: 10.22146/jkr.36511. [2] N. I. Nonik Ayu Wartini, “Deteksi Dini Kanker Serviks dengan Inspeksi Visual Asam Asetat (IVA),” J. Ners dan Kebidanan, vol. 6, no. 1, pp. 27– 34, 2016, doi: 10.26699/jnk.v6i1.ART.p027. [3] D. Riana, A. N. Hidayanto, and Fitriyani, “Integration of Bagging and greedy forward selection on image pap smear classification using Naïve Bayes,”
2017 5th Int. Conf. Cyber IT Serv. Manag. CITSM 2017, 2017, doi: 10.1109/CITSM.2017.8089320. [4] T. Hidayatulloh, A. Herliana, and T. Arifin, “Klasifikasi Sel Tunggal Pap Smear Berdasarkan Analisis Fitur Berbasis Naïve Bayes Classifier Dan Particle Swarm Optimization,” ., vol. 4, no. 2, pp. 186–193, 2016. [5] Y. P. Pasrun, C. Fatichah, and N. Suciati, “Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear,” J. Buana Inform., vol. 7, no. 1, pp. 11 –20, 2016, doi: 10.24002/jbi.v7i1.479. [6] N. P. Husain and C. Fatichah, “Segmentasi Citra Sel Tunggal Smear Serviks Menggunakan Radiating Component Normalized Generalized GVFS,” J.
Nas. Tek. Elektro dan Teknol. Inf., vol. 6, no. 1, pp. 107–114, 2017, [Online]. Available: http://repository.its.ac.id/1936/. [7] M. Zhao et al., “SEENS: Nuclei segmentation in Pap smear images with selective edge enhancement,” Futur. Gener. Comput. Syst. , vol. 114, pp. 185–194, 2021, doi: 10.1016/j.future.2020.07.045. [8] D. Riana, D. E. O. Dewi, D. H. Widyantoro, and T. L. R. Mengko, “Segmentasi Luas Nukleus Sel Normal Superfisial PAP SMEAR Menggunakan Operasi Kanal Warna dan Deteksi Tepi,” Semin. Nas. Inov.
59
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri
dan Teknol., vol. 1, no. January, pp. 275–280, 2012, [Online]. Available: https://repository.nusamandiri.ac.id/index.php/unduh/item/221329/Ticom2 _1,-segmentasi-sel-nukleus.pdf. [9] S. Hadianti and D. Riana, “Segmentation and analysis of Pap smear microscopic images using the K-means and J48 algorithms,” J. Teknol. dan
Sist. Komput., vol. 9, no. 2, pp. 113–119, 2021, doi: 10.14710/jtsiskom.2021.13943. [10] N. Merlina, E. Noersasongko, P. Nurtantio, M. A. Soeleman, D. Riana, and S. Hadianti, “Detecting theWidth of Pap Smear Cytoplasm Image Based on GLCM Feature,” Smart Trends Comput. Commun. Proc. SmartCom 2020, vol. 182, p. 231, 2020, doi: 10.1007/978-981-15-5224-3. [11] A. Taneja, P. Ranjan, and A. Ujlayan, “Multi-cell nuclei segmentation in cervical cancer images by integrated feature vectors,” Multimed. Tools Appl. , vol. 77, no. 8, pp. 9271 –9290, 2018, doi: 10.1007/s11042-017-4864-x. [12] J. Zhao, Q. Li, X. Li, H. Li, and L. Zhang, “Automated Segmentation Of Cervical Nuclei In Pap Smear Images Using Deformable Multi-Path Ensemble Model,” no. Isbi, pp. 1514–1518, 2019. [13] E. Braz and R. Lotufo, “Nuclei Detection Using Deep Learning,” pp. 1059– 1063, 2017, doi: 10.14209/sbrt.2017.48. [14] S. Gautam, A. Bhavsar, A. K. Sao, and H. K.K., “CNN based segmentation of nuclei in PAP-smear images with selective pre-processing,” no. March, p. 32, 2018, doi: 10.1117/12.2293526. [15] B. Harangi, J. Toth, G. Bogacsovics, D. Kupas, L. Kovacs, and A. Hajdu, “Cell detection on digitized Pap smear images using ensemble of conventional image processing and deep learning techniques,” Int. Symp.
Image Signal Process. Anal. ISPA, vol. 2019-Septe, pp. 38–42, 2019, doi: 10.1109/ISPA.2019.8868683. [16] F. H. D. Araújo et al., “Deep learning for cell image segmentation and ranking,” Comput. Med. Imaging Graph., vol. 72, pp. 13–21, 2019, doi:
60
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri 10.1016/j.compmedimag.2019.01.003. [17] N. Ibtehaz and M. S. Rahman, “MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation,” Neural
Networks, vol. 121, pp. 74–87, 2020, doi: 10.1016/j.neunet.2019.08.025. [18] V. Iglovikov and A. Shvets, “TernausNet: U-Net with VGG11 Encoder PreTrained on ImageNet for Image Segmentation,” 2018, [Online]. Available: http://arxiv.org/abs/1801.05746. [19] J. Zhao et al., “PGU-net+: progressive growing of U-net+ for automated cervical nuclei segmentation,” Lect. Notes Comput. Sci. (including Subser.
Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11977 LNCS, pp. 51–58, 2020, doi: 10.1007/978-3-030-37969-8_7. [20] T. L. Mahyari and R. M. Dansereau, “Deep learning methods for image decomposition of cervical cells,” Eur. Signal Process. Conf., vol. 2021- Janua, pp. 1110–1114, 2021, doi: 10.23919/Eusipco47968.2020.9287435. [21] D. Cheng and E. Y. Lam, “Transfer Learning U-Net Deep Learning for Lung Ultrasound Segmentation,” pp. 1 –14, 2021, [Online]. Available: http://arxiv.org/abs/2110.02196. [22] A. A. Pravitasari et al., “UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation,” Telkomnika (Telecommunication Comput.
Electron. Control., vol. 18, no. 3, pp. 1310–1318, 2020, doi: 10.12928/TELKOMNIKA.v18i3.14753. [23] B. Cui, X. Chen, and Y. Lu, “Semantic Segmentation of Remote Sensing Images Using Transfer Learning and Deep Convolutional Neural Network with Dense Connection,” IEEE Access, vol. 8, pp. 116744–116755, 2020, doi: 10.1109/ACCESS.2020.3003914. [24] R. Raj, N. D. Londhe, and R. Sonawane, “Automated psoriasis lesion segmentation from unconstrained environment using residual U-Net with transfer learning,” Comput. Methods Programs Biomed. , vol. 206, p. 106123, 2021, doi: 10.1016/j.cmpb.2021.106123.
61
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [25] Zohan Nazarudin, Izzati Muhimmah, and Ika Fidianingsih, “Segmentasi Citra untuk Menentukan Skor Kerusakan Hati secara Histologi,” Semin. Nas.
Inform. Medis VIII, vol. 15, pp. 15–21, 2017. [26] D. Kupas and B. Harangi, “Solving the problem of imbalanced dataset with synthetic image generation for cell classification using deep learning,” Proc.
Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2021 -Janua, pp. 2981–2984, 2021, doi: 10.1109/EMBC46164.2021.9631065. [27] P. Sachan, M. Singh, M. Patel, and R. Sachan, “A Study on Cervical Cancer Screening Using Pap Smear Test and Clinical Correlation,” Asia-Pacific J.
Oncol. Nurs., vol. 5, no. 3, pp. 337–341, 2018, doi: 10.4103/apjon.apjon_15_18. [28] U. N. Mandiri, “Repository Medical Imaging Citra Pap Smear Untuk Deteksi Dini Cervical Cancer,” Universitas Nusa Mandiri, 2021. http://repomed.nusamandiri.ac.id/ (accessed Mar. 05, 2022). [29] D. Riana, S. Hadianti, and S. Rahayu, “RepoMedUNM?: A New Dataset for Extraction Feature and Train Deep Learning Network to Classify of Pap Smear Images.” [30] V. Ariesandi, I. B. Hidayat, P. Ir, and S. Darana, “Estimasi Bobot Karkas Sapi Berdasarkan Metode Gabor Wavelet dan Klasifikasi Support Vector Machine Multiclass,” vol. 4, no. 2, pp. 2084–2091, 2017. [31] M. Orisa and T. Hidayat, “Analisis Teknik Segmentasi Pada Pengolahan Citra,” J. Mnemon., vol. 2, no. 2, pp. 9–13, 2019, doi: 10.36040/mnemonic.v2i2.84. [32] O. Ronnerberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” IEEE Access, vol. 9, pp. 16591 – 16603, 2021, doi: 10.1109/ACCESS.2021.3053408. [33] ArcGIS Developers, “How U-net works?” https://developers.arcgis.com/python/guide/how-unet-works/ (accessed Sep. 14, 2022).
62
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [34] G. Du, X. Cao, J. Liang, X. Chen, and Y. Zhan, “Medical image segmentation based on U-Net: A review,” J. Imaging Sci. Technol. , vol. 64, no. 2, pp. 1 –12, 2020, doi: 10.2352/J.ImagingSci.Technol.2020.64.2.020508. [35] M. Z. Alom, C. Yakopcic, M. Hasan, T. m Taha, and V. k Asari, “Recurrent residual U-Net for medical image segmentation,” J. of Medical Imaging, 2019. [36] S. Cai, Y. Tian, H. Lui, H. Zeng, Y. Wu, and G. Chen, “Dense-unet: A novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network,” Quant. Imaging Med. Surg., vol. 10, no. 6, pp. 1275–1285, 2020, doi: 10.21037/QIMS-19-1090. [37] Z. Zhang, Q. Liu, Y. Wang, and S. Member, “Road Extraction by Deep Residual U-Net,” pp. 1–5, 2018. [38] R. Li et al., “DeepUNet: A Deep Fully Convolutional Network for PixelLevel Sea-Land Segmentation,” IEEE J. Sel. Top. Appl. Earth Obs. Remote
Sens., vol. 11, no. 11, pp. 3954–3962, 2018, doi: 10.1109/JSTARS.2018.2833382. [39] J. H. Jang, T. Y. Kim, and D. Yoon, “Effectiveness of transfer learning for deep learning-based electrocardiogram analysis,” Healthc. Inform. Res., vol. 27, no. 1, pp. 19–28, 2021, doi: 10.4258/hir.2021.27.1.19. [40] Keras-team, “Keras Applications.” https://keras.io/api/applications/ (accessed Feb. 25, 2022). [41] E. Rezende, G. Ruppert, T. Carvalho, A. Theophilo, F. Ramos, and P. de Geus, “Malicious Software Classification Using VGG16 Deep Neural Network’s Bottleneck Features,” Adv. Intell. Syst. Comput., vol. 738, pp. 51 – 59, 2018, doi: 10.1007/978-3-319-77028-4_9. [42] M. To?açar, Z. Cömert, and B. Ergen, “Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks,” Chaos,
Solitons and Fractals, vol. 144, p. 110714, 2021, doi:
63
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri 10.1016/j.chaos.2021.110714. [43] M. V. L. Branch and A. S. Carvalho, “Polyp Segmentation in Colonoscopy Images using U-Net-MobileNetV2,” arXiv Prepr. arXiv2103.15715, pp. 2– 5, 2021. [44] A. G. Taylor, C. Mielke, and J. Mongan, “Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study,” PLoS Med., vol. 15, no. 11, pp. 1 – 15, 2018, doi: 10.1371/journal.pmed.1002697. [45] S. Jegou, M. Drozdzal, D. Vazquez, A. Romero, and Y. Bengio, “The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
Work., vol. 2017-July, pp. 1175–1183, 2017, doi: 10.1109/CVPRW.2017.156. [46] O. Rochmawanti and F. Utaminingrum, “Chest X-Ray Image to Classify Lung diseases in Different Resolution Size using DenseNet-121 Architectures,” ACM Int. Conf. Proceeding Ser. , pp. 327–331, 2021, doi: 10.1145/3479645.3479667. [47] X. Li, H. Chen, X. Qi, Q. Dou, C. W. Fu, and P. A. Heng, “H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes,” IEEE Trans. Med. Imaging, vol. 37, no. 12, pp. 2663–2674, 2018, doi: 10.1109/TMI.2018.2845918. [48] Z. Wei, H. Song, L. Chen, Q. Li, and G. Han, “Attention-based denseunet network with adversarial training for skin lesion segmentation,” IEEE
Access, vol. 7, pp. 136616–136629, 2019, doi: 10.1109/ACCESS.2019.2940794. [49] B. Preim and C. Botha, Image Analysis for Medical Visualization. 2014. [50] A. S. Kornilov and I. V. Safonov, “An overview of watershed algorithm implementations in open source libraries,” J. Imaging, vol. 4, no. 10, 2018, doi: 10.3390/jimaging4100123.
64
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [51] Y. Song et al., “A deep learning based framework for accurate segmentation of cervical cytoplasm and nuclei,” 2014 36th Annu. Int. Conf. IEEE Eng.
Med. Biol. Soc. EMBC 2014, pp. 2903–2906, 2014, doi: 10.1109/EMBC.2014.6944230. [52] Y. Song, L. Zhang, S. Chen, D. Ni, B. Lei, and T. Wang, “Accurate segmentation of cervical cytoplasm and nuclei based on multiscale convolutional network and graph partitioning,” IEEE Trans. Biomed. Eng., vol. 62, no. 10, pp. 2421 –2433, 2015, doi: 10.1109/TBME.2015.2430895. [53] B. Sharma and K. K. Mangat, “An improved nucleus segmentation for cervical cell images using FCM clustering and BPNN,” 2016 Int. Conf. Adv.
Comput. Commun. Informatics, ICACCI 2016, pp. 1924–1929, 2016, doi: 10.1109/ICACCI.2016.7732332. [54] Y. Song et al., “Accurate cervical cell segmentation from overlapping clumps in pap smear images,” IEEE Trans. Med. Imaging, vol. 36, no. 1, pp. 288–300, 2017, doi: 10.1109/TMI.2016.2606380. [55] A. Tareef et al., “Optimizing the cervix cytological examination based on deep learning and dynamic shape modeling,” Neurocomputing, vol. 248, pp. 28–40, 2017, doi: 10.1016/j.neucom.2017.01.093. [56] Y. Zhou, H. Chen, J. Xu, Q. Dou, and P. A. Heng, “IRNet: Instance relation network for overlapping cervical cell segmentation,” Lect. Notes Comput.
Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11764 LNCS, no. August, pp. 640–648, 2019, doi: 10.1007/978-3-030- 32239-7_71. [57] W. Wang et al., “Learn to segment single cells with deep distance estimator and deep cell detector,” Comput. Biol. Med., vol. 108, no. October 2018, pp. 133–141, 2019, doi: 10.1016/j.compbiomed.2019.04.006. [58] P. Wang et al., “Understanding Convolution for Semantic Segmentation,”
Proc. - 2018 IEEE Winter Conf. Appl. Comput. Vision, WACV 2018, vol. 2018-Janua, pp. 1451–1460, 2018, doi: 10.1109/WACV.2018.00163.
65
Program Studi Ilmu Komputer (S2) Universitas Nusa Mandiri [59] S. N. Rahmawati, E. W. Hidayat, and H. Mubarok, “Implementasi Deep Learning Pada Pengenalan Aksara Sunda Menggunakan Metode Convolutional Neural Network,” Inser. Inf. Syst. Emerg. Technol. J., vol. 2, no. 1, p. 46, 2021, doi: 10.23887/insert.v2i1.37405. [60] S. Ghosh, A. Chaki, and K. Santosh, “Improved U-Net architecture with VGG-16 for brain tumor segmentation,” Phys. Eng. Sci. Med., vol. 44, no. 3, pp. 703–712, 2021, doi: 10.1007/s13246-021-01019-w. [61] T. Laibacher, T. Weyde, and S. Jalali, “M2U-net: Effective and efficient retinal vessel segmentation for real-world applications,” IEEE Comput. Soc.
Conf. Comput. Vis. Pattern Recognit. Work. , vol. 2019-June, pp. 115–124, 2019, doi: 10.1109/CVPRW.2019.00020. [62] J. Stawiaski, “A Pretrained DenseNet Encoder for Brain Tumor Segmentation Jean,” vol. 2, pp. 380–392, 2019, doi: 10.1007/978-3-030- 11726-9. [63] A. Fathan Hidayatullah, M. Rifqi Ma, and arif Program Studi Manajemen Informatika STMIK Jenderal Achmad Yani Yogyakarta Jl Ringroad Barat, “Penerapan Text Mining dalam Klasifikasi Judul Skripsi,” Semin. Nas. Apl.
Teknol. Inf. Agustus, pp. 1907–5022, 2016. [64] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. , vol. 2019-June, pp. 658–666, 2019, doi: 10.1109/CVPR.2019.00075. [65] R. Arora, I. Saini, and N. Sood, “Multi-label segmentation and detection of COVID-19 abnormalities from chest radiographs using deep learning,”
Optik (Stuttg)., vol. 246, no. June, p. 167780, 2021, doi: 10.1016/j.ijleo.2021.167780.