Hasil Pencarian  ::  Simpan CSV :: Kembali

"[ABSTRAKKanker payudara adalah tumor ganas yang tumbuh akibat pertumbuhan sel-seljaringan yang tidak normal pada jaringan payudara. Kanker payudara pada wanitamerupakan penyakit yang kini paling banyak diderita dibandingkan jenis kankerlainnya. Cara yang dilakukan agar penyakit ini tidak memiliki kesempatan untukmenyebar adalah dengan mendeteksinya sedini mungkin dengan menggunakanmammografi.Pada penelitian ini penulis telah merancang suatu sistem yang menggunakankomputer untuk mendeteksi dan mengklasifikasi kanker payudara pada citramammogram. Citra mammogram yang digunakan adalah citra mammogram dariMommographic Image Analysis Society (MIAS) yang terdiri dari 322 citra.Pengolahan awal citra pada sistem ini menggunakan metode Otsu Thresholding,pendeteksian tepi dengan menggunakan metode Canny, dan metode dilasi. Ciriyang digunakan pada sistem ini adalah Gray Level Co-occurrence Matrix(GLCM) dan Discrete Wavelet Transform (DWT). Metode pengklasifikasian yangdigunakan pada penelitian ini adalah Support Vector Machine (SVM).Sistem memiliki ketahanan yang baik terhadap noise salt and pepper pada nilainoise tertentu pada tiap jenis citra mammogram yang digunakan. Tingkatkeakuratan berkisar 80% pada saat diberi noise sebesar -16dB pada citramammogram jinak dan ganas. Keakuratan sistem juga teruji cukup baik untukjumlah data latih yang hanya sebesar 70% dimana tingkat keakuratanpendeteksian dan pengklasifikasian adalah sebesar 80,6%.

---

ABSTRACTBreast cancer is a malignant tumor that grows as a result of the growth of tissuecells that are not normal in the breast tissue. Breast cancer in women is a diseasethat is now the most common cancer than other types. How that is done so that thedisease does not have a chance to spread is to detect it as early as possible byusing mammography.In this study, the authors have designed a system that uses a computer to detectand classify breast cancer on a mammogram image. Mammogram image has beentaken from Mommographic Image Analysis Society (MIAS) which consists of 322images. Initial processing images on this system using Otsu Thresholding, edgedetection using Canny method, and the method of dilation. Features used in thissystem is the Gray Level Co-occurrence Matrix (GLCM) and Discrete WaveletTransform (DWT). Claassification method was used in this study is SupportVector Machine (SVM).The system has good resistance to salt and pepper noise on certain noise value foreach type of mammogram image are used. The accuracy range was 80% whengiven the noise of -16dB on mammogram images of benign and malignant. Theaccuracy of the system was also tested well enough for the amount of training datathat only 70% where the level of detection and classification accuracy is 80,6 %.;Breast cancer is a malignant tumor that grows as a result of the growth of tissuecells that are not normal in the breast tissue. Breast cancer in women is a diseasethat is now the most common cancer than other types. How that is done so that thedisease does not have a chance to spread is to detect it as early as possible byusing mammography.In this study, the authors have designed a system that uses a computer to detectand classify breast cancer on a mammogram image. Mammogram image has beentaken from Mommographic Image Analysis Society (MIAS) which consists of 322images. Initial processing images on this system using Otsu Thresholding, edgedetection using Canny method, and the method of dilation. Features used in thissystem is the Gray Level Co-occurrence Matrix (GLCM) and Discrete WaveletTransform (DWT). Claassification method was used in this study is SupportVector Machine (SVM).The system has good resistance to salt and pepper noise on certain noise value foreach type of mammogram image are used. The accuracy range was 80% whengiven the noise of -16dB on mammogram images of benign and malignant. Theaccuracy of the system was also tested well enough for the amount of training datathat only 70% where the level of detection and classification accuracy is 80,6 %., Breast cancer is a malignant tumor that grows as a result of the growth of tissuecells that are not normal in the breast tissue. Breast cancer in women is a diseasethat is now the most common cancer than other types. How that is done so that thedisease does not have a chance to spread is to detect it as early as possible byusing mammography.In this study, the authors have designed a system that uses a computer to detectand classify breast cancer on a mammogram image. Mammogram image has beentaken from Mommographic Image Analysis Society (MIAS) which consists of 322images. Initial processing images on this system using Otsu Thresholding, edgedetection using Canny method, and the method of dilation. Features used in thissystem is the Gray Level Co-occurrence Matrix (GLCM) and Discrete WaveletTransform (DWT). Claassification method was used in this study is SupportVector Machine (SVM).The system has good resistance to salt and pepper noise on certain noise value foreach type of mammogram image are used. The accuracy range was 80% whengiven the noise of -16dB on mammogram images of benign and malignant. Theaccuracy of the system was also tested well enough for the amount of training datathat only 70% where the level of detection and classification accuracy is 80,6 %.]"

"Penampakan mikrokalsifikasi dalam citra mammography sebagai suatu indikasi terjadinya kanker payudara seringkali menjadi kendala pendiagnosisan penyakit kanker. Variasi bentuk dan ukuran kalsifikasi serta kehomogenan dengan latar belakang tekstur merupakan faktor utama yang sering menjadi masalah dalam pengamatan visual biasa.Pemanfaatan Computer Aided Diagnosis (CAD) dalam bidang pengolahan citra memungkinkan suatu citra mamography diolah dan dianalisa dalam bentuk digital untuk mengurangi kendala dalam hal pendeteksian mikrokalsifikasi.Teknik pendeteksian mikrokalsifikasi serta unjuk kerjanya dengan menggunakan transformasi wavelet, peningkatan kontras citra dan metode statistik meliputi perhitungan skewness dan kurtosis pada citra mammography digital akan diterapkan dalam tesis ini, dimana hasil pendeteksian tersebut dijadikan sebagai "second opinion" bagi ahli radiologis dalam diagnosisnya.Hasil simulasi menunjukan secara visual bahwa unjuk kerja pendeteksian mikrokalsifikasi dengan teknik yang diterapkan mempunyai tingkat keefektifan hingga 96%.

---

The presence of clustered micro-calcifications is an early sign of breast cancer, however it's difficult to detect. Variation of shape and size of calcification is the main problem for detection process, beside the homogenous texture background.Computer-aided diagnosis (CAD) schemes on image processing have the potential of substantially increasing diagnostic accuracy in mammography.Performance of wavelet transform, enhance algorithm and statistical procedure for detection method are presented in this thesis as a second opinion for radiologist's interpretation of micro-calcifications.The simulation results show visually that detecting method was applied has 96% in an effectiveness level."

"ABSTRAKKeburaman dan ketidakjelasan batas citra sangat mempengaruhi hasil pengamatan medic terutama untuk identifikasi penyakit. Karena itu meningkatkan kontras citra dan menajamkan batas citra merupakan suatu cara agar dapat memperoleh hasil citra rekonstruksi yang lebih baik.Detektor edge detection dan filterisasi Gauss adalah salah satu cara untuk menambah pencahayaan pada citra dan meningkatkan ketajaman sisi citra. Dengan menggunakan transformasi wavelet proses manipulasi piksel-piksel citra tersebut menjadi cukup mudah untuk dilaksanakan.Perhitungan nilai selisih citra dan perbandingan presentase citra dapat digunakan untuk mengukur seberapa jauh tingkat pencahayaan dari citra rekonstruksi. Semakin tinggi nilai selisih dan presentase maka semakin baik citra rekonstruksi.

---

ABSTRACT

Blurring image is a fundamental problem for mammogram images. In case this trouble always takes some difficulty for medical purposes. So, edge detection of images and increase their contrast is one way to solve this problem.

Edge detector and gaussian's filter are manipulated to enhance an original image. Some of manipulation of pixels can be easily done by wavelet transform to get reconstruction images. Difference analysis and percentage analysis are used to determine the criteria of resulting image."

"ABSTRAKLatar belakang: Mamografi merupakan pemeriksaan baku emas dan merupakan modalitas satu-satunya untuk skrining payudara perempuan. Namun efektivitas mamografi menurun terutama pada payudara berdensitas padat. Handheld ultrasonography (HHUS) sering diperlukan sebagai pelengkap mamografi dan dapat meningkatkan sensitivitas dan spesifisitas untuk deteksi kanker payudara berdensitas padat. Automated breast ultrasound (ABUS) merupakan modalitas relatif baru dengan beberapa kelebihan dibandingkan dengan HHUS antara lain reproducible, variabilitas yang rendah, waktu akuisisi lebih singkat dan konsisten, serta ukuran transduser yang lebar sehingga mencakup payudara lebih menyeluruh dan dapat melakukan karakterisasi lesi yang ukurannya melebihi lebar transduser HHUS dengan lebih baik. Saat ini penggunaan ABUS belum merata di rumah sakit di Indonesia, dan penelitian mengenai ABUS masih terbatas, sehingga perlu dilakukan penelitian mengenai ABUS dibandingkan dengan modalitas lain secara lebih obyektif. Tujuan : Penelitian ini bertujuan untuk mengetahui kesesuaian temuan, morfologis, dan lokasi lesi di payudara berdasarkan densitas mamografi dan HHUS dengan densitas mamografi dan ABUS. Metode: Dilakukan pemeriksaan payudara menggunakan mamografi, HHUS GE tipe Logic S8 dengan transduser linear 7-12 MHz, dan ABUS GE Invenia dengan transduser konkaf linear 6-12 MHz. Seluruh pemeriksaan HHUS dan ABUS dilakukan sendiri oleh peneliti di Departemen Radiologi RSCM, dan dikonfirmasi oleh Dokter Spesialis Radiologi konsultan payudara bersertifikasi ABUS untuk menentukan ada atau tidaknya lesi, morfologis, dan lokasi lesi. Kesesuaian hasil pemeriksaan mamografi-ABUS dan mamografi HHUS dianalisis menggunakan uji Mc Nemar. Hasil: Terdapat 30 subyek penelitian dan diperoleh 48 sampel payudara, dengan rentang usia 36-66 tahun (rerata ± SD 51,4 ± 8,5 tahun). Dalam menentukan ada tidaknya lesi, pemeriksaan mamografi-HHUS dan mamografi-ABUS memiliki kesesuaian dengan level sedang (moderate agreement), nilai Kappa 0,43 dan 0,49 (p 0,002 dan p 0,001); dalam menentukan morfologis lesi memiliki kesesuaian dengan level sedang (moderate agreement) dengan nilai Kappa 0,51 dan 0,43 (p 0,000 dan 0,000); serta dalam menentukan lokasi lesi memiliki kesesuaian dengan level fair agreement dengan nilai Kappa 0,37 dan 0,36 (p 0,000 dan 0,000). Simpulan: Kombinasi mamografi-HHUS memiliki kesesuaian dengan level relatif setara dalam menentukan ada tidaknya lesi dan lokasi lesi, namun sedikit lebih tinggi dalam menilai morfologis lesi dibandingkan dengan kombinasi mamografi-ABUS.

---

ABSTRACTBackground: Mammography is the gold standard and well known to be a powerful screening tool in the detection of breast cancer. However its sensitivity is reduced in women with dense breasts. Additionally, women with dense breasts have an increased risk of developing breast cancer while mammography has a lower sensitivity.Handheld ultrasonography (HHUS) is often needed as a adjunction to mammography, can increase sensitivity and specificity for detection of cancer in dense breast breasts. Automated breast ultrasound (ABUS) is a relative new modality with several advantages compared to HHUS including reproducible, low variability, shorter and consistent acquisition time, and a wide transducer size that covers the breast more thoroughly and can characterize lesions whose size exceeds the width of the transducer HHUS better. At present the use of ABUS is not evenly distributed in hospitals in Indonesia, and research on ABUS is still limited, so it is necessary to conduct research on ABUS compared to other modalities more objectively. Objective : This study aims to determine the alternative selection of HHUS and ABUS examination to detect abnormalities in the breast based on mammographic density. Method: Breast examination using mammography, HHUS GE Logic S8 with 7-12 MHz linear transducer, and GE Invenia ABUS with 6-12 MHz linear concave transducer. All HHUS and ABUS examinations are carried out solely by researchers in the Radiology Department of the RSCM, and are confirmed by an ABUS certified breast consultant radiologist to determine the presence, morphology, and location of the lesion. The suitability of ABUS mammography and HHUS mammography results were analyzed using the Mc Nemar test. Result: There were 30 subjects and 48 breast samples were obtained, with an age range of 36-66 years (mean ± SD 51.4 ± 8.5 years). In determining the presence or absence of lesions, examination of mammography-HHUS and mammography-ABUS is in accordance with moderate agreement and Kappa values 0.43 and 0.49 (p 0.002 and p 0.001); in determining the morphology of the lesion is in accordance with moderate agreement and Kappa value 0.51 and 0.43 (p 0,000 and 0,000); and in determining the location of the lesion is in accordance with fair agreement and Kappa values ​​of 0.37 and 0.36 (p 0,000 and 0,000). Conclusion : The mammographic-HHUS combination is compatible with a relatively equal level in determining the presence or absence of the lesion and location of the lesion, but is slightly higher in assessing the morphology of the lesion compared with the mammographic-ABUS combination."

"Breast cancer can be detected using digital mammograms. In this research study, a system is designed to classify digital mammograms into two classes, namely normal and abnormal, using the k-Nearest Neighbor (kNN) method. Prior to classification, the region of interest (ROI) of a mammogram is cropped, and the feature is extracted using the wavelet transformation method. Energy, mean, and standard deviation from wavelet decomposition coefficients are used as input for the classification. Optimal accuracy is obtained when wavelet decomposition level 3 is used with the feature combination of mean and standard deviation. The highest accuracy, sensitivity, and specificity of this method are 96.8%, 100%, and 95%, respectively."

"Sistem mamografi terus mengalami perkembangan. Teknologi terbaru yang muncul, seperti detektor pencacah foton tentu menjadi harapan semakin baiknya performa pencitraan yang dihasilkan, baik ditinjau dari segi kualitas citra maupun dosis. Oleh karena itu, dibutuhkan sebuah evaluasi kualitas citra dan dosimetri agar keluaran yang dihasilkan adalah citra dengan kualitas terbaik dan dosis yang masih aman diterima pasien sesuai dengan prinsip As Low As Reasonably Achieveble (ALARA). Penelitian ini dilakukan menggunakan 5 unit pesawat mamografi dengan detektor pencacah foton. Mean glandular dose (MGD) dihitung menggunakan persamaan yang dipublikasikan oleh IAEA Human Series No.17 - Quality Assurance Programme For Digital Mammography, pada ketebalan PMMA 20-70 mm. Kualitas citra dievaluasi secara otomatis menggunakan perangkat lunak Erica2 berbasis CDCOM. European Reference Organisation for Quality Assured Breast Screening and Diagnostic Services (EUREF) digunakan untuk mendapatkan nilai batas yang „dapat diterima‟ dan „dapat dicapai‟ untuk MGD dan nilai ketebalan ambang disk. Hasilnya dibandingkan dengan kinerja pesawat mamografi dengan detektor flat-panel. Nilai MGD pada pesawat dengan detektor pencacah foton menunjukan nilai yang lebih rendah pada ketebalan 40 hingga 70 mm PMMA dibanding detektor flat-panel. Nilai ketebalan ambang disk pada detektor pencacah foton juga menunjukkan angka yang lebih rendah dibanding detektor flat-panel pada seluruh diameter.

---

The mammography system is constantly evolving. The latest emerging technologies, such as photon counting detector, certainly will be a hope for better imaging performance, both in terms of image quality and dose. Therefore, an evaluation of image quality and dosimetry is needed, so the produced output will be an image with the best quality and dose that is still safe for patients according to the As Low As Reasonably Achievable (ALARA). This research was conducted using 5 units of mammography with photon counting detector. The mean glandular dose (MGD) was calculated using the equation published by the IAEA Human Series No. 17 - Quality Assurance Programme For Digital Mammography, at a PMMA thickness of 20-70 mm. Image quality is evaluated automatically using the CDCOM-based Erica2 software. The European Reference Organization for Quality Assured Breast Screening and Diagnostic Services (EUREF) was used to obtain 'acceptable' and 'achievable' values for the MGD and threshold gold thickness values. The result was compared with the performance of a mammography systems with a flat-panel detector. The MGD on a mammography systems with a photon counting detector shows a lower value at a thickness of 40 to 70 mm PMMA compared to a flat- panel detector. The threshold gold thickness values on the photon counting detector also shows a lower number than the flat-panel detector in all diameters."