CHEST X-RAY IMAGE SEGMENTATION USING MODIFIED DEEPLABV3+ METHOD

Abstract

English

COVID-19 is a disease that affects the human respiratory system. The latest developments in September 2022 the number of confirmed cases of COVID-19 worldwide reached 608,328,548 with 6,501,469 patients who died. While in Indonesia confirmed COVID-19 reached 6,408,806 with 157,892 patients who died. Reserve Transcription Polymerase Chain Reaction (RT-PCR) is the most widely used tool. However, the latest RT-PCR test report shows that the RT-PCR test is inadequate. As an alternative, radiographic images such as chest x-rays and CT scans can help detect this. Radiographic images, especially x-rays, need processing to be able to make a diagnosis. Computer Aided Diagnosis (CAD) is a computer assisted diagnosis system that can be used as supporting information in making a diagnosis. To make it easier to make a diagnosis, we need a deep learning model that can help with this. DeepLabV3+ is a method that can carry out the segmentation process. DeepLabV3+ which is an extension of DeepLabV3 with the aim of improving the segmentation results. DeepLabV3+ uses a modified Xception as the backbone. In this study, 1,500 chest x-ray image data were used which were then divided into 80% for training data and 20% for testing data. There are 4 test scenarios in this study, namely with a learning rate of 0.01 without CLAHE, a learning rate of 0,01 and using CLAHE, a learning rate of 0,0001 without CLAHE, and a learning rate of 0,0001 using CLAHE. Of the 4 scenarios the learning rate scenario is 0,01 and using CLAHE gets the highest evaluation results using the Dice Similarity Coefficient (DSC) of 96.91%.

Bahasa Indonesia

COVID-19 merupakan penyakit yang mengganggu sistem pernapasan manusia. Perkembangan terbaru September 2022 jumlah kasus COVID-19 di seluruh dunia terkonfirmasi mencapai 608.328.548 dengan pasien yang meninggal berjumlah 6.501.469. Sedangkan di Indonesia yang terkonfirmasi COVID-19 mencapai 6.408.806 dengan pasien yang meninggal sebanyak 157.892. Reserve Transcription Polymerase Chain Reaction (RT-PCR) merupakan alat yang paling banyak digunakan untuk mendeteksi COVID-19. Namun, laporan terakhir uji RT-PCR menunjukkan bahwa uji RT-PCR tersebut kurang memadai. Sebagai alternatifnya, citra radiografi seperti x-ray dan CT-Scan dada dapat membantu dalam mendeteksi penyakit ini. Citra radiografi khususnya x-ray perlu dilakukan pengolahan untuk dapat melakukan diagnosis. Computer Aided Diagnosis (CAD) adalah sistem diagnosis berbantuan komputer yang bisa digunakan sebagai informasi pendukung dalam melakukan diagnosis. Untuk mempermudah dalam melakukan diagnosis diperlukan suatu model deep learning yang dapat membantu hal tersebut. DeepLabV3+ merupakan salah satu metode yang dapat melakukan proses segmentasi. DeepLabV3+ merupakan perluasan pada DeepLabV3 dengan tujuan supaya bisa menyempurnakan hasil segmentasi. DeepLabV3+ menggunakan Xception yang dimodifikasi sebagai backbone. Dalam penelitian ini menggunakan 1.500 data citra x-ray dada yang kemudian data tersebut dibagi menjadi 80% untuk data pelatihan dan 20% untuk data pengujian. Terdapat 4 skenario uji coba dalam penelitian ini yaitu dengan learning rate 0,01 tanpa CLAHE, learning rate 0,01 dan menggunakan CLAHE, learning rate 0,0001 tanpa CLAHE, serta learning rate 0,0001 menggunakan CLAHE. Dari 4 skenario tersebut skenario learning rate 0,01 dan menggunakan CLAHE mendapatkan hasil evaluasi tertinggi dengan menggunakan Dice Similarity Coefficient (DSC) sebesar 96,91%. AbstractCOVID-19 is a disease that affects the human respiratory system. The latest developments in September 2022 the number of confirmed cases of COVID-19 worldwide reached 608,328,548 with 6,501,469 patients who died. While in Indonesia confirmed COVID-19 reached 6,408,806 with 157,892 patients who died. Reserve Transcription Polymerase Chain Reaction (RT-PCR) is the most widely used tool. However, the latest RT-PCR test report shows that the RT-PCR test is inadequate. As an alternative, radiographic images such as chest x-rays and CT scans can help detect this. Radiographic images, especially x-rays, need processing to be able to make a diagnosis. Computer Aided Diagnosis (CAD) is a computer assisted diagnosis system that can be used as supporting information in making a diagnosis. To make it easier to make a diagnosis, we need a deep learning model that can help with this. DeepLabV3+ is a method that can carry out the segmentation process. DeepLabV3+ which is an extension of DeepLabV3 with the aim of improving the segmentation results. DeepLabV3+ uses a modified Xception as the backbone. In this study, 1,500 chest x-ray image data were used which were then divided into 80% for training data and 20% for testing data. There are 4 test scenarios in this study, namely with a learning rate of 0,01 without CLAHE, a learning rate of 0,01 and using CLAHE, a learning rate of 0,0001 without CLAHE, and a learning rate of 0,0001 using CLAHE. Of the 4 scenarios the learning rate scenario is 0,01 and using CLAHE gets the highest evaluation results using the Dice Similarity Coefficient (DSC) of 96,91%.