Nisanard Pisuchpen
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
Nisanard Pisuchpen has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Avinash Kambadakone
Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
4 shared publications - Aileen O'SHea
Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts
2 shared publications - Jinjin Cao
From the Department of Radiology, Division of Abdominal Radiology (S.S.R., N.U.B., J.C., O.A.C., J.A.B., A.R.K.) and Department of Surgery (J.C.C.), Massachusetts General Hospital, Harvard Medical School, 55 Fruit St, White 270, Boston, MA 02114-2696; and Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, Mass (O.A.C.).
2 shared publications - Kulyada Eurboonyanun
Department of Radiology, Faculty of Medicine, Khon Kaen University, Khon Kaen, Thailand
2 shared publications - Mukesh G. Harisinghani
Department of Radiology, Massachusetts General Hospital, Boston, USA
2 shared publications - Abbas Rezaei
Abdominal Radiology Division, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, United States
1 shared publication
Latest Publications
- Open Access
- 1 April 2026
- Published by AME Publishing Company in Translational Andrology and Urology
- Vol. 15 (4) , 125
Prostate imaging reporting and data system version 2.1 as a predictor of clinically significant and aggressive prostate cancer: a radical prostatectomy-validated study
Original Article Prostate imaging reporting and data system version 2.1 as a predictor of clinically significant and aggressive prostate cancer: a radical prostatectomy-validated study Nisanard Pisuchpen, Kulyada Eurboonyanun, Aileen O’Shea, Rita Maria Lahoud, Isha D. Atre, Mukesh Harisinghani
- 1 April 2026
- Published by AME Publishing Company in Translational Andrology and Urology
- Vol. 15 (4) , 125
Open AccessProstate imaging reporting and data system version 2.1 as a predictor of clinically significant and aggressive prostate cancer: a radical prostatectomy-validated study
Original Article Prostate imaging reporting and data system version 2.1 as a predictor of clinically significant and aggressive prostate cancer: a radical prostatectomy-validated study Nisanard Pisuchpen, Kulyada Eurboonyanun, Aileen O’Shea, Rita Maria Lahoud, Isha D. Atre, Mukesh Harisinghani
- 16 June 2025
- Published by Springer Nature in Abdominal Radiology
- Vol. 51 (1) , 424-445
Artificial intelligence (AI) and CT in abdominal imaging: image reconstruction and beyond
Computed tomography (CT) is a cornerstone of abdominal imaging, playing a vital role in accurate diagnosis, appropriate treatment planning, and disease monitoring. The evolution of artificial intelligence (AI) in imaging has introduced deep learning-based reconstruction (DLR) techniques that enhance image quality, reduce radiation dose, and improve workflow efficiency. Traditional image reconstruction methods, including filtered back projection (FBP) and iterative reconstruction (IR), have limitations such as high noise levels and artificial image texture. DLR overcomes these challenges by leveraging convolutional neural networks to generate high-fidelity images while preserving anatomical details. Recent advances in vendor-specific and vendor-agnostic DLR algorithms, such as TrueFidelity, AiCE, and Precise Image, have demonstrated significant improvements in contrast-to-noise ratio, lesion detection, and diagnostic confidence across various abdominal organs, including the liver, pancreas, and kidneys. Furthermore, AI extends beyond image reconstruction to applications such as low contrast lesion detection, quantitative imaging, and workflow optimization, augmenting radiologists’ efficiency and diagnostic accuracy. However, challenges remain in clinical validation, standardization, and widespread adoption. This review explores the principles, advancements, and future directions of AI-driven CT image reconstruction and its expanding role in abdominal imaging.
- 16 June 2025
- Published by Springer Nature in Abdominal Radiology
- Vol. 51 (1) , 424-445
Artificial intelligence (AI) and CT in abdominal imaging: image reconstruction and beyond
Computed tomography (CT) is a cornerstone of abdominal imaging, playing a vital role in accurate diagnosis, appropriate treatment planning, and disease monitoring. The evolution of artificial intelligence (AI) in imaging has introduced deep learning-based reconstruction (DLR) techniques that enhance image quality, reduce radiation dose, and improve workflow efficiency. Traditional image reconstruction methods, including filtered back projection (FBP) and iterative reconstruction (IR), have limitations such as high noise levels and artificial image texture. DLR overcomes these challenges by leveraging convolutional neural networks to generate high-fidelity images while preserving anatomical details. Recent advances in vendor-specific and vendor-agnostic DLR algorithms, such as TrueFidelity, AiCE, and Precise Image, have demonstrated significant improvements in contrast-to-noise ratio, lesion detection, and diagnostic confidence across various abdominal organs, including the liver, pancreas, and kidneys. Furthermore, AI extends beyond image reconstruction to applications such as low contrast lesion detection, quantitative imaging, and workflow optimization, augmenting radiologists’ efficiency and diagnostic accuracy. However, challenges remain in clinical validation, standardization, and widespread adoption. This review explores the principles, advancements, and future directions of AI-driven CT image reconstruction and its expanding role in abdominal imaging.
- 1 October 2024
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 313 (1) , e232749
Detectability of Hypoattenuating Liver Lesions with Deep Learning CT Reconstruction: A Phantom and Patient Study
There were no differences in radiologist performance for detecting hypoattenuating liver lesions at abdominal CT between adaptive statistical iterative reconstruction-V at 40% strength and deep learning image reconstruction with different strengths.
- 1 October 2024
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 313 (1) , e232749
Detectability of Hypoattenuating Liver Lesions with Deep Learning CT Reconstruction: A Phantom and Patient Study
There were no differences in radiologist performance for detecting hypoattenuating liver lesions at abdominal CT between adaptive statistical iterative reconstruction-V at 40% strength and deep learning image reconstruction with different strengths.
- 9 November 2022
- Published by Springer Nature in European Radiology
- Vol. 33 (4) , 2439-2449
CT image quality evaluation in the age of deep learning: trade-off between functionality and fidelity
Objective To quantitatively compare DLIR and ASiR-V with realistic anatomical images. Methods CT scans of an anthropomorphic phantom were acquired using three routine protocols (brain, chest, and abdomen) at four dose levels, with images reconstructed at five levels of ASiR-V and three levels of DLIR. Noise power spectrum (NPS) was estimated using a difference image by subtracting two matching images from repeated scans. Using the max-dose FBP reconstruction as the ground truth, the structure similarity index (SSIM) and gradient magnitude (GM) of difference images were evaluated. Image noise magnitude (σ), frequency location of the NPS peak (fpeak), mean SSIM (MSSIM), and mean GM (MGM) were used as quantitative metrics to compare image quality, for each anatomical region, protocol, algorithm, dose level, and slice thickness. Results Image noise had a strong (R2 > 0.99) power law relationship with dose for all algorithms. For the abdomen and chest, fpeak shifted from 0.3 (FBP) down to 0.15 mm-1 (ASiR-V 100%) with increasing ASiR-V strength but remained 0.3 mm-1 for all DLIR levels. fpeak shifted down for the brain protocol with increasing DLIR levels. Three levels of DLIR produced similar image noise levels as ASiR-V 40%, 80%, and 100%, respectively. DLIR had lower MSSIM but higher MGM than ASiR-V while matching imaging noise. Conclusion Compared to ASiR-V, DLIR presents trade-offs between functionality and fidelity: it has a noise texture closer to FBP and more edge enhancement, but reduced structure similarity. These trade-offs and unique protocol-dependent behaviors of DLIR should be considered during clinical implementation and deployment. Key Points • DLIR reconstructed images demonstrate closer noise texture and lower structure similarity to FBP while producing equivalent noise levels comparable to ASiR-V. • DLIR has additional edge enhancement as compared to ASiR-V. • DLIR has unique protocol-dependent behaviors that should be considered for clinical implementation.
- 9 November 2022
- Published by Springer Nature in European Radiology
- Vol. 33 (4) , 2439-2449
CT image quality evaluation in the age of deep learning: trade-off between functionality and fidelity
Objective To quantitatively compare DLIR and ASiR-V with realistic anatomical images. Methods CT scans of an anthropomorphic phantom were acquired using three routine protocols (brain, chest, and abdomen) at four dose levels, with images reconstructed at five levels of ASiR-V and three levels of DLIR. Noise power spectrum (NPS) was estimated using a difference image by subtracting two matching images from repeated scans. Using the max-dose FBP reconstruction as the ground truth, the structure similarity index (SSIM) and gradient magnitude (GM) of difference images were evaluated. Image noise magnitude (σ), frequency location of the NPS peak (fpeak), mean SSIM (MSSIM), and mean GM (MGM) were used as quantitative metrics to compare image quality, for each anatomical region, protocol, algorithm, dose level, and slice thickness. Results Image noise had a strong (R2 > 0.99) power law relationship with dose for all algorithms. For the abdomen and chest, fpeak shifted from 0.3 (FBP) down to 0.15 mm-1 (ASiR-V 100%) with increasing ASiR-V strength but remained 0.3 mm-1 for all DLIR levels. fpeak shifted down for the brain protocol with increasing DLIR levels. Three levels of DLIR produced similar image noise levels as ASiR-V 40%, 80%, and 100%, respectively. DLIR had lower MSSIM but higher MGM than ASiR-V while matching imaging noise. Conclusion Compared to ASiR-V, DLIR presents trade-offs between functionality and fidelity: it has a noise texture closer to FBP and more edge enhancement, but reduced structure similarity. These trade-offs and unique protocol-dependent behaviors of DLIR should be considered during clinical implementation and deployment. Key Points • DLIR reconstructed images demonstrate closer noise texture and lower structure similarity to FBP while producing equivalent noise levels comparable to ASiR-V. • DLIR has additional edge enhancement as compared to ASiR-V. • DLIR has unique protocol-dependent behaviors that should be considered for clinical implementation.
- 8 August 2022
- Published by Elsevier in Pancreatology
- Vol. 22 (7) , 951-958
Concordance of EUS and MRI/MRCP findings among high-risk individuals undergoing pancreatic cancer screening
- 8 August 2022
- Published by Elsevier in Pancreatology
- Vol. 22 (7) , 951-958
Concordance of EUS and MRI/MRCP findings among high-risk individuals undergoing pancreatic cancer screening
- 26 March 2021
- Published by Springer Nature in Abdominal Radiology
- Vol. 46 (8) , 4014-4024
The absolute tumor-capsule contact length in the diagnosis of extraprostatic extension of prostate cancer
Background Extraprostatic extension (EPE) of prostate cancer is associated with a poor prognosis. The broad-based capsule-tumor interface has been recognized as one of the worrisome imaging features in multiparametric prostate MRI (mpMRI). However, there was significant heterogeneity among the measurement method used in prior studies. Objectives This study’s objectives were to investigate and compare the accuracy between the curvilinear and linear measurement, find the optimal cut-off contact surface threshold for the diagnosis of EPE, and assess the benefit of the additional contact surface measurement versus visual assessment alone. Methods The status of EPE in mpMRI and the overall PI-RADS were assessed. The tumor’s dimensions, the actual tumor-capsule contact length (ACTCL), and the absolute tumor-capsule contact length (ABTCL) were measured. The parameters were analyzed and correlated with the EPE status from prostatectomy specimens. Results Ninety-five patients who underwent mpMRI followed by prostatectomy were included in the study. High Gleason score (score 8–9), radiologist’s impression of EPE, and PI-RADS 5 were significantly correlated with EPE in surgical specimens (p = 0.014, p < 0.001, and p < 0.001, respectively). Both ACTCL and ABTCL of patients with EPE were significantly higher than those without EPE in all imaging sequences (p < 0.001 to p = 0.003). The ABTCL has higher accuracy than the ACTCL. Dynamic contrast enhancement (DCE) was the most accurate sequence to measure the contact interface. The recommended cut-off value of ABTCL was 15.0 mm, which had a sensitivity and specificity of 75.86% and 72.09%. Multivariable analysis revealed that the ABTCL > 15 mm and the radiologist’s impression on visual assessment were the only two independent predictors for the prediction of EPE (p = 0.048 and p = 0.016, respectively). Improvement of diagnostic performance was achieved when the two factors were combined. Conclusion The ABTCL has better accuracy than the curvilinear measurement in the prediction of EPE. The optimum sequence for the measurement of the contact surface is the DCE. We recommended using 15.0 mm as a cut-off point. Clinical impact The addition of the ABTCL measurement showed an increase in diagnostic performance. We encourage radiologists to use the capsular contact measurement in addition to their visual assessment to detect EPE in pre-operative MRI.
- 26 March 2021
- Published by Springer Nature in Abdominal Radiology
- Vol. 46 (8) , 4014-4024
The absolute tumor-capsule contact length in the diagnosis of extraprostatic extension of prostate cancer
Background Extraprostatic extension (EPE) of prostate cancer is associated with a poor prognosis. The broad-based capsule-tumor interface has been recognized as one of the worrisome imaging features in multiparametric prostate MRI (mpMRI). However, there was significant heterogeneity among the measurement method used in prior studies. Objectives This study’s objectives were to investigate and compare the accuracy between the curvilinear and linear measurement, find the optimal cut-off contact surface threshold for the diagnosis of EPE, and assess the benefit of the additional contact surface measurement versus visual assessment alone. Methods The status of EPE in mpMRI and the overall PI-RADS were assessed. The tumor’s dimensions, the actual tumor-capsule contact length (ACTCL), and the absolute tumor-capsule contact length (ABTCL) were measured. The parameters were analyzed and correlated with the EPE status from prostatectomy specimens. Results Ninety-five patients who underwent mpMRI followed by prostatectomy were included in the study. High Gleason score (score 8–9), radiologist’s impression of EPE, and PI-RADS 5 were significantly correlated with EPE in surgical specimens (p = 0.014, p < 0.001, and p < 0.001, respectively). Both ACTCL and ABTCL of patients with EPE were significantly higher than those without EPE in all imaging sequences (p < 0.001 to p = 0.003). The ABTCL has higher accuracy than the ACTCL. Dynamic contrast enhancement (DCE) was the most accurate sequence to measure the contact interface. The recommended cut-off value of ABTCL was 15.0 mm, which had a sensitivity and specificity of 75.86% and 72.09%. Multivariable analysis revealed that the ABTCL > 15 mm and the radiologist’s impression on visual assessment were the only two independent predictors for the prediction of EPE (p = 0.048 and p = 0.016, respectively). Improvement of diagnostic performance was achieved when the two factors were combined. Conclusion The ABTCL has better accuracy than the curvilinear measurement in the prediction of EPE. The optimum sequence for the measurement of the contact surface is the DCE. We recommended using 15.0 mm as a cut-off point. Clinical impact The addition of the ABTCL measurement showed an increase in diagnostic performance. We encourage radiologists to use the capsular contact measurement in addition to their visual assessment to detect EPE in pre-operative MRI.