Dr. Janne J. Näppi Profile

Dr. Janne J. Näppi

Associate Investigator at Massachusetts General Hospital

SPIE Involvement:

Conference Program Committee | Author

Area of Expertise:

computer-aided detection , computer-assisted diagnosis , machine learning , CT colonography , radiomics , breast imaging

Publications (31)

PROCEEDINGS ARTICLE | March 6, 2018

Radiomic texture-curvature (RTC) features for precision medicine of patients with rheumatoid arthritis-associated interstitial lung disease

Proc. SPIE. 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications

KEYWORDS: Chest, Feature extraction, Lung, Computed tomography, Pulmonary function tests

Read Abstract

PROCEEDINGS ARTICLE | February 28, 2018

Deep radiomic prediction with clinical predictors of the survival in patients with rheumatoid arthritis-associated interstitial lung diseases

Proc. SPIE. 10575, Medical Imaging 2018: Computer-Aided Diagnosis

KEYWORDS: Convolutional neural networks, Feature extraction, Lung, Computed tomography, Performance modeling, Pulmonary function tests

Read Abstract

We developed and evaluated the effect of our deep-learning-derived radiomic features, called deep radiomic features (DRFs), together with their combination with clinical predictors, on the prediction of the overall survival of patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD). We retrospectively identified 70 RA-ILD patients with thin-section lung CT and pulmonary function tests. An experienced observer delineated regions of interest (ROIs) from the lung regions on the CT images, and labeled them into one of four ILD patterns (ground-class opacity, reticulation, consolidation, and honeycombing) or a normal pattern. Small image patches centered at individual pixels on these ROIs were extracted and labeled with the class of the ROI to which the patch belonged. A deep convolutional neural network (DCNN), which consists of a series of convolutional layers for feature extraction and a series of fully connected layers, was trained and validated with 5-fold cross-validation for classifying the image patches into one of the above five patterns. A DRF vector for each patch was identified as the output of the last convolutional layer of the DCNN. Statistical moments of each element of the DRF vectors were computed to derive a DRF vector that characterizes the patient. The DRF vector was subjected to a Cox proportional hazards model with elastic-net penalty for predicting the survival of the patient. Evaluation was performed by use of bootstrapping with 2,000 replications, where concordance index (C-index) was used as a comparative performance metric. Preliminary results on clinical predictors, DRFs, and their combinations thereof showed (a) Gender and Age: C-index 64.8% [95% confidence interval (CI): 51.7, 77.9]; (b) gender, age, and physiology (GAP index): C-index: 78.5% [CI: 70.50 86.51], P < 0.0001 in comparison with (a); (c) DRFs: C-index 85.5% [CI: 73.4, 99.6], P < 0.0001 in comparison with (b); and (d) DRF and GAP: C-index 91.0% [CI: 84.6, 97.2], P < 0.0001 in comparison with (c). Kaplan-Meier survival curves of patients stratified to low- and high-risk groups based on the DRFs showed a statistically significant (P < 0.0001) difference. The DRFs outperform the clinical predictors in predicting patient survival, and a combination of the DRFs and GAP index outperforms either one of these predictors. Our results indicate that the DRFs and their combination with clinical predictors provide an accurate prognostic biomarker for patients with RA-ILD.

PROCEEDINGS ARTICLE | February 27, 2018

Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy

Proc. SPIE. 10575, Medical Imaging 2018: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Cancer, Data modeling, Computing systems, Neural networks, Colorectal cancer, Colon, Network architectures, Computer-aided diagnosis, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 10, 2017

Enhancement of weakly tagged fecal materials in dual-energy CT colonography using spectral-driven iterative reconstruction technique

Proc. SPIE. 10132, Medical Imaging 2017: Physics of Medical Imaging

KEYWORDS: Computer aided diagnosis and therapy, CT reconstruction, Visualization, Tissues, Iodine, Image enhancement, Computed tomography, Reconstruction algorithms, Computer aided design, Virtual colonoscopy

Read Abstract

Dual-energy computed tomography is used increasingly in CT colonography (CTC). The combination of computer-aided detection (CAD) and dual-energy CTC has a high clinical value because it can automatically detect clinically significant colonic lesions in CTC images with higher accuracy than does single-energy CTC. While CAD has demonstrated its ability to detect small polyps, its performance is highly dependent on the quality of the input images. The presence of artifacts such as beam hardening and image noise in ultra-low-dose CTC may severely degrade detection performance for small polyps. A further limitation to the effectiveness of CAD are the weakly tagged fecal materials in the colon that may cause false-positive detections. In this work, we developed a dual-energy method for enhancing the appearance of weakly tagged fecal materials in CTC images. The proposed method consists of two stages: 1) the detection of weakly tagged fecal materials by use of sinogram-based image decomposition and 2) the enhancement of the detected tagged fecal materials in the images using an iterative reconstruction method. In the first stage, the ultra-low-dose dual-energy projection data obtained from a CT scanner are decomposed into two basis materials – soft tissue and fecal-tagged material (iodine). Virtual monochromatic projection data are calculated from the material decomposition at a pre-determined energy. The iodine-decomposed sinogram and the virtual monochromatic projection data are then used as input to an iterative reconstruction method. In the second stage, virtual monochromatic images are reconstructed iteratively while the intensity of weakly tagged iodine in the images is enhanced. The performance of the proposed method was assessed qualitatively and quantitatively. Preliminary results show that our method effectively enhances the visual appearance of weakly tagged fecal materials in the reconstructed CT images while reducing noise and improving the overall quality of the reconstructed images.

PROCEEDINGS ARTICLE | March 3, 2017

Deep learning of contrast-coated serrated polyps for computer-aided detection in CT colonography

Proc. SPIE. 10134, Medical Imaging 2017: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Cancer, Convolutional neural networks, Coating, Feature extraction, Neural networks, Colorectal cancer, Machine learning, Colon, Error control coding, Barium, Computer-aided diagnosis, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 3, 2017

Deep multi-spectral ensemble learning for electronic cleansing in dual-energy CT colonography

Proc. SPIE. 10134, Medical Imaging 2017: Computer-Aided Diagnosis

KEYWORDS: Endoscopy, Image compression, Tissues, Image segmentation, Medical imaging, Multispectral imaging, Neural networks, Computed tomography, Image classification, Colon, RGB color model, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 3, 2017

Electronic cleansing for CT colonography using spectral-driven iterative reconstruction

Proc. SPIE. 10134, Medical Imaging 2017: Computer-Aided Diagnosis

KEYWORDS: X-ray computed tomography, Computer aided diagnosis and therapy, CT reconstruction, Image quality, Computed tomography, Reconstruction algorithms, Colon, Computer-aided diagnosis, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 3, 2017

Deep ensemble learning of virtual endoluminal views for polyp detection in CT colonography

Proc. SPIE. 10134, Medical Imaging 2017: Computer-Aided Diagnosis

KEYWORDS: Cancer, Convolutional neural networks, Detection and tracking algorithms, Neural networks, Colorectal cancer, Machine learning, Colon, Algorithm development, Computer-aided diagnosis, 3D image processing, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 24, 2016

Deep learning for electronic cleansing in dual-energy CT colonography

Proc. SPIE. 9785, Medical Imaging 2016: Computer-Aided Diagnosis

KEYWORDS: Image compression, Convolutional neural networks, Tissues, Medical imaging, Iodine, Colorectal cancer, Colon, Forward error correction, Natural surfaces, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 24, 2016

Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography

Proc. SPIE. 9785, Medical Imaging 2016: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Cancer, Convolutional neural networks, Data modeling, Computing systems, Feature extraction, Colorectal cancer, Colon, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 24, 2016

Performance evaluation of multi-material electronic cleansing for ultra-low-dose dual-energy CT colonography

Proc. SPIE. 9785, Medical Imaging 2016: Computer-Aided Diagnosis

KEYWORDS: Cancer, Medical research, Iodine, Colorectal cancer, Machine learning, Computed tomography

Read Abstract

PROCEEDINGS ARTICLE | March 20, 2015

Electronic cleansing for dual-energy CT colonography based on material decomposition and virtual monochromatic imaging

Proc. SPIE. 9414, Medical Imaging 2015: Computer-Aided Diagnosis

KEYWORDS: Endoscopy, Visualization, Tissues, Signal attenuation, Iodine, Colorectal cancer, Machine learning, Colon, Forward error correction, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 20, 2015

Context-specific method for detection of soft-tissue lesions in non-cathartic low-dose dual-energy CT colonography

Proc. SPIE. 9414, Medical Imaging 2015: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Cancer, Visualization, Tissues, Colorectal cancer, Computed tomography, Colon, Radiation effects, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 18, 2015

A comparison of material decomposition techniques for dual-energy CT colonography

Proc. SPIE. 9412, Medical Imaging 2015: Physics of Medical Imaging

KEYWORDS: Computer aided diagnosis and therapy, Signal attenuation, Image segmentation, Diagnostics, Bone, Iodine, Computed tomography, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 20, 2014

Progressive region-based colon extraction for computer-aided detection and quantitative imaging in cathartic and non-cathartic CT colonography

Proc. SPIE. 9035, Medical Imaging 2014: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Detection and tracking algorithms, Image segmentation, Interfaces, Feature extraction, Colon, Algorithm development, Lawrencium, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | February 28, 2013

Volumetric detection of flat lesions for minimal-preparation dual-energy CT colonography

Proc. SPIE. 8670, Medical Imaging 2013: Computer-Aided Diagnosis

KEYWORDS: Target detection, 3D acquisition, Computer aided diagnosis and therapy, Computing systems, Tomography, Iodine, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | February 23, 2012

Automated detection of colorectal lesions with dual-energy CT colonography

Proc. SPIE. 8315, Medical Imaging 2012: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Tissues, Interfaces, Feature extraction, Iodine, Computed tomography, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 9, 2011

Computer-aided detection of small bowel strictures in CT enterography

Proc. SPIE. 7963, Medical Imaging 2011: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Sensors, Diagnostics, Image analysis, Image enhancement, Computed tomography, Computer aided design, Radiology, 3D image processing

Read Abstract

PROCEEDINGS ARTICLE | March 5, 2011

Probabilistic method for context-sensitive detection of polyps in CT colonography

Proc. SPIE. 7963, Medical Imaging 2011: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Computing systems, Neural networks, Computed tomography, Colon, Computer aided design, CAD systems, Solid modeling, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 29, 2007

Pseudo-enhancement correction for computer-aided detection in fecal-tagging CT colonography

Proc. SPIE. 6514, Medical Imaging 2007: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Visualization, Signal attenuation, Image segmentation, Computed tomography, Colon, Computer aided design, CAD systems, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 29, 2007

Delineation of tagged region by use of local iso-surface roughness in electronic cleansing for CT colonography

Proc. SPIE. 6514, Medical Imaging 2007: Computer-Aided Diagnosis

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Colorectal cancer, Image enhancement, Computed tomography, Image classification, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 16, 2006

Centerline-based colon segmentation for CAD of CT colonography

Proc. SPIE. 6144, Medical Imaging 2006: Image Processing

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Computed tomography, Colon, Computer aided design, Algorithm development, Rectum, Binary data, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | March 10, 2006

Digital bowel cleansing for computer-aided detection of polyps in fecal-tagging CT colonography

Proc. SPIE. 6144, Medical Imaging 2006: Image Processing

KEYWORDS: Magnesium, X-ray computed tomography, Computer aided diagnosis and therapy, Image segmentation, Integration, Computed tomography, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | April 14, 2005

Ranking of polyp candidates for CAD in CT colonography

Proc. SPIE. 5746, Medical Imaging 2005: Physiology, Function, and Structure from Medical Images

KEYWORDS: Computer aided diagnosis and therapy, Cancer, Image segmentation, Feature extraction, Colorectal cancer, Computed tomography, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 12, 2004

New high-performance CAD scheme for the detection of polyps in CT colonography

Proc. SPIE. 5370, Medical Imaging 2004: Image Processing

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Diagnostics, Neural networks, Colorectal cancer, Computed tomography, Colon, Computer aided design, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 15, 2003

Computer-aided detection of polyps and masses for CT colonography

Proc. SPIE. 5032, Medical Imaging 2003: Image Processing

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Diagnostics, Colorectal cancer, Computed tomography, Colon, Computer aided design, Stomach, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 2, 2003

Fast and robust method to compute colon centerline in CT colonography

Proc. SPIE. 5031, Medical Imaging 2003: Physiology and Function: Methods, Systems, and Applications

KEYWORDS: Endoscopy, Image segmentation, Lung, Optical inspection, Distance measurement, Colorectal cancer, Computed tomography, Colon, Stomach, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 9, 2002

Computer-aided diagnosis in CT colonography: detection of polyps based on geometric and texture features

Proc. SPIE. 4684, Medical Imaging 2002: Image Processing

KEYWORDS: Statistical analysis, Computer aided diagnosis and therapy, Image segmentation, Colorectal cancer, Computed tomography, Colon, Computer aided design, Fuzzy logic, Virtual colonoscopy, Data analysis

Read Abstract

PROCEEDINGS ARTICLE | April 24, 2002

Effect of knowledge-guided colon segmentation in automated detection of polyps in CT colonography

Proc. SPIE. 4683, Medical Imaging 2002: Physiology and Function from Multidimensional Images

KEYWORDS: Computer aided diagnosis and therapy, Image segmentation, Lung, Computed tomography, Colon, Computer aided design, Stomach, Rectum, Virtual colonoscopy

Read Abstract

PROCEEDINGS ARTICLE | May 21, 1999

Computerized diagnosis of breast calcifications using specimen radiography and simulated calcifications

Proc. SPIE. 3661, Medical Imaging 1999: Image Processing

KEYWORDS: Breast, Imaging systems, Image segmentation, Particles, Radiography, Computing systems, Computer simulations, Image quality, Mammography, Spatial resolution

Read Abstract

PROCEEDINGS ARTICLE | April 25, 1997

Mammographic feature generator for evaluation of image analysis algorithms

Proc. SPIE. 3034, Medical Imaging 1997: Image Processing

KEYWORDS: Modeling, Visualization, Tissues, Image segmentation, Computing systems, Feature extraction, Image analysis, Mammography, Digital mammography, Plasma

Read Abstract