Back

Virtual Spectral Decomposition with Dendritic Binary Gating Detects Pancreatic Cancer Tissue Transformation on Standard CT: Multi-Institutional Validation Across Three Independent Datasets with a 3.8-Year Pre-Diagnostic Detection Window

Chandra, S.

2026-04-12 oncology
10.64898/2026.04.08.26350418 medRxiv
Show abstract

Background. Pancreatic ductal adenocarcinoma (PDAC) has a five-year survival rate of approximately 12%, largely because it is typically diagnosed at an advanced stage. CT-based computational methods for early detection exist but rely on black-box deep learning or large texture feature sets without tissue-specific interpretability. Methods. We developed Virtual Spectral Decomposition (VSD), which applies six parameterized sigmoid functions S(HU) = 1/(1+exp(-alpha x (HU - mu))) to standard portal-venous CT, decomposing each pixel into tissue-specific response channels for fat (mu=-60), fluid (mu=10), parenchyma (mu=45), stroma (mu=75), vascular (mu=130), and calcification (mu=250). Dendritic Binary Gating identifies structural content per channel using morphological filtering, enabling co-firing analysis and lone firer identification. A 25-feature signature was extracted per patient. Three independent datasets were analyzed: NIH Pancreas-CT (n=78 healthy), Medical Segmentation Decathlon Task07 (n=281 PDAC, paired tumor/adjacent tissue), and CPTAC-PDA from The Cancer Imaging Archive (n=82, multi-institutional, with DICOM time point tags). The same six sigmoid parameters were used across all datasets without retraining. Results. VSD achieved AUC 0.943 for field effect detection (healthy vs cancer-adjacent parenchyma) and AUC 0.931 for patient-stratified tumor specification on MSD. On CPTAC-PDA, VSD achieved AUC 0.961 (6 features) and 0.979 (25 features) for distinguishing healthy from cancer-bearing pancreas on scans obtained prior to pathological diagnosis. All significant features replicated across datasets in the same direction: z_fat (d=-2.10, p=3.5e-27), z_fluid (d=-2.76, p=2.4e-38), fire_fat (d=+2.18, p=1.2e-28). Critically, VSD severity did not correlate with days-from-diagnosis (r=-0.008, p=0.944) across a range of day -1394 to day +249. Patient C3N-01375, scanned 3.8 years before pathological diagnosis, had VSD severity 1.87, well above the healthy mean of 0.94 +/- 0.33. The tissue transformation signature was temporally stable, indicating an early, persistent tissue state rather than a progressively worsening process. Conclusions. VSD with Dendritic Binary Gating detects a stable pancreatic tissue composition signature on standard CT that is present years before clinical diagnosis, validated across three independent datasets without parameter adjustment. The six sigmoid channels map to biologically meaningful tissue components through a fully transparent interpretability chain. The temporal stability of the signal implies a detection window of 3-7 years, consistent with known PanIN-3 microenvironment transformation timelines. VSD functions as a single-scan screening tool applicable to any abdominal CT performed during the pre-clinical window.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

1
Clinical Cancer Research
58 papers in training set
Top 0.1%
15.2%
2
Scientific Reports
3102 papers in training set
Top 5%
10.4%
3
Nature Communications
4913 papers in training set
Top 21%
8.7%
4
eLife
5422 papers in training set
Top 12%
6.5%
5
Medical Physics
14 papers in training set
Top 0.2%
3.7%
6
International Journal of Radiation Oncology*Biology*Physics
21 papers in training set
Top 0.2%
2.1%
7
npj Digital Medicine
97 papers in training set
Top 2%
2.0%
8
PLOS ONE
4510 papers in training set
Top 50%
2.0%
50% of probability mass above
9
JAMA Network Open
127 papers in training set
Top 2%
1.8%
10
IEEE Transactions on Medical Imaging
18 papers in training set
Top 0.2%
1.8%
11
PLOS Computational Biology
1633 papers in training set
Top 15%
1.8%
12
eBioMedicine
130 papers in training set
Top 2%
1.4%
13
Diagnostics
48 papers in training set
Top 1%
1.3%
14
Frontiers in Oncology
95 papers in training set
Top 3%
1.1%
15
BMJ Open
554 papers in training set
Top 11%
1.0%
16
Journal of Translational Medicine
46 papers in training set
Top 2%
1.0%
17
NeuroImage
813 papers in training set
Top 5%
0.9%
18
npj Precision Oncology
48 papers in training set
Top 1.0%
0.9%
19
Cancer Research
116 papers in training set
Top 3%
0.9%
20
Science Advances
1098 papers in training set
Top 27%
0.8%
21
Breast Cancer Research
32 papers in training set
Top 0.4%
0.8%
22
PeerJ
261 papers in training set
Top 13%
0.8%
23
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 42%
0.8%
24
JNCI Cancer Spectrum
10 papers in training set
Top 0.4%
0.8%
25
Cancers
200 papers in training set
Top 4%
0.8%
26
Science Translational Medicine
111 papers in training set
Top 6%
0.8%
27
Cancer Discovery
61 papers in training set
Top 2%
0.8%
28
Interface Focus
14 papers in training set
Top 0.3%
0.8%
29
Communications Biology
886 papers in training set
Top 22%
0.8%
30
Cancer Research Communications
46 papers in training set
Top 1%
0.8%