Abstract
| Language | English |
|---|---|
| Title of host publication | Medical Imaging 2019: Digital Pathology |
| Editors | John E. Tomaszewski, Aaron D. Ward |
| Publisher | SPIE |
| Number of pages | 8 |
| DOIs | |
| State | Published - 18 Mar 2019 |
| Event | SPIE Medical Imaging: Digital Pathology - San Diego, United States Duration: 16 Feb 2019 → 21 Feb 2019 Conference number: 10956 https://spie.org/MI/conferencedetails/digital-pathology |
Publication series
| Name | Proceedings of SPIE |
|---|---|
| Volume | 10956 |
Conference
| Conference | SPIE Medical Imaging |
|---|---|
| Country | United States |
| City | San Diego |
| Period | 16/02/19 → 21/02/19 |
| Internet address |
Fingerprint
Cite this
}
Cancer detection in mass spectrometry imaging data by dilated convolutional neural networks. / van Kersbergen, Jannis; Ghazvinian Zanjani, F.; Zinger, Svitlana; van der Sommen, Fons; Balluff, Benjamin; Vos, D.R.N. ; Ellis, S.R. ; Heeren, Ron M.A.; Lucas, M. ; Marquering, H.A. ; Jansen, I.; Savci-Heijink, Cemile Dilara; de Bruin, D.M.; de With, P.H.N.
Medical Imaging 2019: Digital Pathology. ed. / John E. Tomaszewski; Aaron D. Ward. SPIE, 2019. 1095601 (Proceedings of SPIE; Vol. 10956).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Cancer detection in mass spectrometry imaging data by dilated convolutional neural networks
AU - van Kersbergen,Jannis
AU - Ghazvinian Zanjani,F.
AU - Zinger,Svitlana
AU - van der Sommen,Fons
AU - Balluff,Benjamin
AU - Vos,D.R.N.
AU - Ellis,S.R.
AU - Heeren,Ron M.A.
AU - Lucas,M.
AU - Marquering,H.A.
AU - Jansen,I.
AU - Savci-Heijink,Cemile Dilara
AU - de Bruin,D.M.
AU - de With,P.H.N.
PY - 2019/3/18
Y1 - 2019/3/18
N2 - Imaging mass spectrometry (IMS) is a novel molecular imaging technique to investigate how molecules are distributed between tumors and within tumor region in order to shed light into tumor biology or find potential biomarkers. Convolutional neural networks (CNNs) have proven to be very potent classifiers often outperforming other machine learning algorithms, especially in computational pathology. To overcome the challenge of complexity and high-dimensionality of the IMS data, the proposed CNNs are either very deep or use large kernels, which results in large amount of parameters and therefore a high computational complexity. An alternative is down-sampling the data, which inherently leads to a loss of information. In this paper, we propose using dilated CNNs as a possible solution to this challenge, since it allows for an increase of the receptive field size, neither by increasing the network parameters nor by decreasing the input signal resolution. Since the mass signature of cancer biomarkers are distributed over the whole mass spectrum, both locally- and globally-distributed patterns need to be captured to correctly classify the spectrum. By experiment, we show that employing dilated convolutions in the architecture of a CNN leads to a higher performance in tumor classification. Our proposed model outperforms the state-of-the-art for tumor classification in both clinical lung and bladder datasets by 1-3%.
AB - Imaging mass spectrometry (IMS) is a novel molecular imaging technique to investigate how molecules are distributed between tumors and within tumor region in order to shed light into tumor biology or find potential biomarkers. Convolutional neural networks (CNNs) have proven to be very potent classifiers often outperforming other machine learning algorithms, especially in computational pathology. To overcome the challenge of complexity and high-dimensionality of the IMS data, the proposed CNNs are either very deep or use large kernels, which results in large amount of parameters and therefore a high computational complexity. An alternative is down-sampling the data, which inherently leads to a loss of information. In this paper, we propose using dilated CNNs as a possible solution to this challenge, since it allows for an increase of the receptive field size, neither by increasing the network parameters nor by decreasing the input signal resolution. Since the mass signature of cancer biomarkers are distributed over the whole mass spectrum, both locally- and globally-distributed patterns need to be captured to correctly classify the spectrum. By experiment, we show that employing dilated convolutions in the architecture of a CNN leads to a higher performance in tumor classification. Our proposed model outperforms the state-of-the-art for tumor classification in both clinical lung and bladder datasets by 1-3%.
U2 - 10.1117/12.2512360
DO - 10.1117/12.2512360
M3 - Conference contribution
T3 - Proceedings of SPIE
BT - Medical Imaging 2019: Digital Pathology
PB - SPIE
ER -