Rudy Gunawan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rudy Gunawan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Hung Tan Nguyen
New Mexico State University
3 shared publications - Jinchuan Zheng
Swinburne University of Technology, Melbourne, Australia
3 shared publications - Rifai Chai
Department of Engineering Technologies, School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Australia
3 shared publications - Yvonne Tran
Macquarie University Hearing Research Centre
3 shared publications Alison Church
Research & Development GlaxoSmithKline Research Triangle Park North Carolina USA
1 shared publication- Ann Carrigan
The University of Sydney, Australia
1 shared publication
Latest Publications
- Open Access
Optimizing Natural Image Quality Evaluators for Quality Measurement in CT Scan Denoising
Evaluating the results of image denoising algorithms in Computed Tomography (CT) scans typically involves several key metrics to assess noise reduction while preserving essential details. Full Reference (FR) quality evaluators are popular for evaluating image quality in denoising CT scans. There is limited information about using Blind/No Reference (NR) quality evaluators in the medical image area. This paper shows the previously utilized Natural Image Quality Evaluator (NIQE) in CT scans; this NIQE is commonly used as a photolike image evaluator and provides an extensive assessment of the optimum NIQE setting. The result was obtained using the library of good images. Most are also part of the Convolutional Neural Network (CNN) training dataset against the testing dataset, and a new dataset shows an optimum patch size and contrast levels suitable for the task. This evidence indicates a possibility of using the NIQE as a new option in evaluating denoised quality to find improvement or compare the quality between CNN models.
Open AccessOptimizing Natural Image Quality Evaluators for Quality Measurement in CT Scan Denoising
Evaluating the results of image denoising algorithms in Computed Tomography (CT) scans typically involves several key metrics to assess noise reduction while preserving essential details. Full Reference (FR) quality evaluators are popular for evaluating image quality in denoising CT scans. There is limited information about using Blind/No Reference (NR) quality evaluators in the medical image area. This paper shows the previously utilized Natural Image Quality Evaluator (NIQE) in CT scans; this NIQE is commonly used as a photolike image evaluator and provides an extensive assessment of the optimum NIQE setting. The result was obtained using the library of good images. Most are also part of the Convolutional Neural Network (CNN) training dataset against the testing dataset, and a new dataset shows an optimum patch size and contrast levels suitable for the task. This evidence indicates a possibility of using the NIQE as a new option in evaluating denoised quality to find improvement or compare the quality between CNN models.
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5519-5527
Combining Multistaged Filters and Modified Segmentation Network for Improving Lung Nodules Classification
Advancements in computational technology have led to a shift towards automated detection processes in lung cancer screening, particularly through nodule segmentation techniques. These techniques employ thresholding to distinguish between soft and firm tissues, including cancerous nodules. The challenge of accurately detecting nodules close to critical lung structures such as blood vessels, bronchi, and the pleura highlights the necessity for more sophisticated methods to enhance diagnostic accuracy. This paper proposed combined processing filters for data preparation before using one of the modified Convolutional Neural Networks (CNN) as the classifier. With refined filters, the nodule targets are solid, semi-solid, and ground glass, ranging from low-stage cancer (cancer screening data) to high-stage cancer. Furthermore, two additional works were added to address juxta-pleural nodules while the pre-processing end and classification are done in a 3-dimensional domain in opposition to the usual image classification. The accuracy output indicates that even using a simple Segmentation Network if modified correctly, can improve the classification result compared to the other eight models. The proposed sequence total accuracy reached 99.7%, with 99.71% cancer class accuracy and 99.82% non-cancer accuracy, much higher than any previous research, which can improve the detection efforts of the radiologist.
- 28 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (9) , 5519-5527
Combining Multistaged Filters and Modified Segmentation Network for Improving Lung Nodules Classification
Advancements in computational technology have led to a shift towards automated detection processes in lung cancer screening, particularly through nodule segmentation techniques. These techniques employ thresholding to distinguish between soft and firm tissues, including cancerous nodules. The challenge of accurately detecting nodules close to critical lung structures such as blood vessels, bronchi, and the pleura highlights the necessity for more sophisticated methods to enhance diagnostic accuracy. This paper proposed combined processing filters for data preparation before using one of the modified Convolutional Neural Networks (CNN) as the classifier. With refined filters, the nodule targets are solid, semi-solid, and ground glass, ranging from low-stage cancer (cancer screening data) to high-stage cancer. Furthermore, two additional works were added to address juxta-pleural nodules while the pre-processing end and classification are done in a 3-dimensional domain in opposition to the usual image classification. The accuracy output indicates that even using a simple Segmentation Network if modified correctly, can improve the classification result compared to the other eight models. The proposed sequence total accuracy reached 99.7%, with 99.71% cancer class accuracy and 99.82% non-cancer accuracy, much higher than any previous research, which can improve the detection efforts of the radiologist.
- Open Access
Image Recovery from Synthetic Noise Artifacts in CT Scans Using Modified U-Net
Computed Tomography (CT) is commonly used for cancer screening as it utilizes low radiation for the scan. One problem with low-dose scans is the noise artifacts associated with low photon count that can lead to a reduced success rate of cancer detection during radiologist assessment. The noise had to be removed to restore detail clarity. We propose a noise removal method using a new model Convolutional Neural Network (CNN). Even though the network training time is long, the result is better than other CNN models in quality score and visual observation. The proposed CNN model uses a stacked modified U-Net with a specific number of feature maps per layer to improve the image quality, observable on an average PSNR quality score improvement out of 174 images. The next best model has 0.54 points lower in the average score. The score difference is less than 1 point, but the image result is closer to the full-dose scan image. We used separate testing data to clarify that the model can handle different noise densities. Besides comparing the CNN configuration, we discuss the denoising quality of CNN compared to classical denoising in which the noise characteristics affect quality.
Open AccessImage Recovery from Synthetic Noise Artifacts in CT Scans Using Modified U-Net
Computed Tomography (CT) is commonly used for cancer screening as it utilizes low radiation for the scan. One problem with low-dose scans is the noise artifacts associated with low photon count that can lead to a reduced success rate of cancer detection during radiologist assessment. The noise had to be removed to restore detail clarity. We propose a noise removal method using a new model Convolutional Neural Network (CNN). Even though the network training time is long, the result is better than other CNN models in quality score and visual observation. The proposed CNN model uses a stacked modified U-Net with a specific number of feature maps per layer to improve the image quality, observable on an average PSNR quality score improvement out of 174 images. The next best model has 0.54 points lower in the average score. The score difference is less than 1 point, but the image result is closer to the full-dose scan image. We used separate testing data to clarify that the model can handle different noise densities. Besides comparing the CNN configuration, we discuss the denoising quality of CNN compared to classical denoising in which the noise characteristics affect quality.
- Open Access
- 6 August 2022
- Published by Wiley in CPT: Pharmacometrics & Systems Pharmacology
- Vol. 11 (10) , 1358-1370
Population pharmacokinetic analysis for tisotumab vedotin in patients with locally advanced and/or metastatic solid tumors
Tisotumab vedotin is an investigational antibody–drug conjugate (ADC) for treatment of solid tumors expressing tissue factor with accelerated approval from the US Food and Drug Administration for treatment of recurrent or metastatic cervical cancer with disease progression during or after chemotherapy. This study describes development of a population pharmacokinetic (PK) model to assess the PK profile of tisotumab vedotin and microtubule‐disrupting agent monomethyl auristatin E (MMAE) using data from 399 patients with solid tumors across four phase I/II trials. The ADC–MMAE model describes ADC and MMAE concentrations following intravenous administration of tisotumab vedotin. This four‐compartment model comprises a two‐compartment ADC model with parallel linear and Michaelis–Menten elimination, a delay compartment, and a one‐compartment MMAE model. Nonspecific linear clearance of ADC was 1.42 L/day, central volume of distribution (Vc) was 3.10 L, and median terminal half‐life of ADC was 4.04 days. Apparent clearance of MMAE was 42.8 L/day, and apparent volume of distribution was 2.09 L. Terminal slope of the MMAE concentration–time curve was defined by the delay compartment rate with a half‐life of 2.56 days. Patients with higher body weight and lower albumin concentration had faster ADC clearance. Male patients and those with higher body weight and lower albumin concentration had higher Vc. Body weight was the most influential covariate influencing distribution and elimination of ADC and MMAE, thus supporting weight‐based dosing of tisotumab vedotin. Presence of antidrug antibodies (detected in 3.3% of patients) did not affect key PK parameters or exposures for ADC and MMAE.
- 6 August 2022
- Published by Wiley in CPT: Pharmacometrics & Systems Pharmacology
- Vol. 11 (10) , 1358-1370
Open AccessPopulation pharmacokinetic analysis for tisotumab vedotin in patients with locally advanced and/or metastatic solid tumors
Tisotumab vedotin is an investigational antibody–drug conjugate (ADC) for treatment of solid tumors expressing tissue factor with accelerated approval from the US Food and Drug Administration for treatment of recurrent or metastatic cervical cancer with disease progression during or after chemotherapy. This study describes development of a population pharmacokinetic (PK) model to assess the PK profile of tisotumab vedotin and microtubule‐disrupting agent monomethyl auristatin E (MMAE) using data from 399 patients with solid tumors across four phase I/II trials. The ADC–MMAE model describes ADC and MMAE concentrations following intravenous administration of tisotumab vedotin. This four‐compartment model comprises a two‐compartment ADC model with parallel linear and Michaelis–Menten elimination, a delay compartment, and a one‐compartment MMAE model. Nonspecific linear clearance of ADC was 1.42 L/day, central volume of distribution (Vc) was 3.10 L, and median terminal half‐life of ADC was 4.04 days. Apparent clearance of MMAE was 42.8 L/day, and apparent volume of distribution was 2.09 L. Terminal slope of the MMAE concentration–time curve was defined by the delay compartment rate with a half‐life of 2.56 days. Patients with higher body weight and lower albumin concentration had faster ADC clearance. Male patients and those with higher body weight and lower albumin concentration had higher Vc. Body weight was the most influential covariate influencing distribution and elimination of ADC and MMAE, thus supporting weight‐based dosing of tisotumab vedotin. Presence of antidrug antibodies (detected in 3.3% of patients) did not affect key PK parameters or exposures for ADC and MMAE.
- 24 June 2014
- Published by Wiley in The Journal of Clinical Pharmacology
- Vol. 54 (11) , 1214-1220
Dose response of umeclidinium administered once or twice daily in patients with COPD: A pooled analysis of two randomized, double‐blind, placebo‐controlled studies
Umeclidinium (UMEC) is an inhaled long‐acting muscarinic antagonist approved in the US and EU for the once‐daily (QD) treatment of chronic obstructive pulmonary disease (COPD); it is not indicated for the treatment of asthma. To fully characterize the dose–response relationship of UMEC in patients with COPD, a pooled analysis of data from two randomized, placebo‐controlled, cross‐over, dose‐ranging studies was performed, evaluating UMEC at doses of 15.6–1000 mcg QD and 15.6–250 mcg twice daily (BID). The primary endpoint was trough forced expiratory volume in one second (FEV1) at the end of each study's treatment period (Day 8/Day 15). A population model‐based analysis using total daily UMEC dose was used for the primary analysis comparing QD and BID dosing. A physiological effect (Emax) model was optimal in defining the relationship between UMEC dose and the primary endpoint, demonstrating a clear monotonic dose response over QD and BID dosing regimens. UMEC doses ≥62.5 mcg QD were differentiated from lower doses and BID dosing did not provide benefit over QD dosing. The potency (ED50) estimate was 33 mcg with QD dosing. These data indicate that UMEC 62.5 mcg and 125 mcg QD provide lung function benefits that warrant further investigation for the treatment of COPD.
- 24 June 2014
- Published by Wiley in The Journal of Clinical Pharmacology
- Vol. 54 (11) , 1214-1220
Dose response of umeclidinium administered once or twice daily in patients with COPD: A pooled analysis of two randomized, double‐blind, placebo‐controlled studies
Umeclidinium (UMEC) is an inhaled long‐acting muscarinic antagonist approved in the US and EU for the once‐daily (QD) treatment of chronic obstructive pulmonary disease (COPD); it is not indicated for the treatment of asthma. To fully characterize the dose–response relationship of UMEC in patients with COPD, a pooled analysis of data from two randomized, placebo‐controlled, cross‐over, dose‐ranging studies was performed, evaluating UMEC at doses of 15.6–1000 mcg QD and 15.6–250 mcg twice daily (BID). The primary endpoint was trough forced expiratory volume in one second (FEV1) at the end of each study's treatment period (Day 8/Day 15). A population model‐based analysis using total daily UMEC dose was used for the primary analysis comparing QD and BID dosing. A physiological effect (Emax) model was optimal in defining the relationship between UMEC dose and the primary endpoint, demonstrating a clear monotonic dose response over QD and BID dosing regimens. UMEC doses ≥62.5 mcg QD were differentiated from lower doses and BID dosing did not provide benefit over QD dosing. The potency (ED50) estimate was 33 mcg with QD dosing. These data indicate that UMEC 62.5 mcg and 125 mcg QD provide lung function benefits that warrant further investigation for the treatment of COPD.