AI and Cancer Research ── Lung ── 2026-11-01

Journals covered and how papers are chosen: see the index

Lung cancer: treatment, trials and AI

• Machine learning stratification of LUAD-to-SCLC transformation states and drug-response signatures
  npj Systems Biology and Applications · 2026-10-30 · Evidence: Retrospective observational (reanalysis of existing mouse and human datasets; hypothesis-generating)
  Abstract

  Histologic transformation from lung adenocarcinoma (LUAD) to small cell lung cancer (SCLC) is a clinically important mechanism of acquired resistance to EGFR tyrosine kinase inhibitors, but the regulatory programs associated with this lineage transition remain incompletely characterized. We reanalyzed mouse and human single-cell and bulk transcriptomic datasets to define a 13-regulon Histologic Transformation Regulon Signature (HTRS) and developed TransRiskML, a machine-learning framework that stratifies LUAD samples into low-, medium-, and high-HTRS molecular states. Across independent cohorts, high-HTRS tumors showed poorer survival, stronger SCLC-like transcriptional features, distinct genomic features, and transcriptome-inferred drug-response patterns. HTRS captured transformation-associated molecular states that were largely independent of general proliferative activity across cohorts, although proliferation contributed substantially to the prognostic signal in advanced-stage NSCLC, where adjustment attenuated the association. A simplified 15-gene surrogate score was developed for downstream analyses, and exploratory pathology suggested a trend toward higher tumor-cell nuclear HDAC2 staining in pre-transformation LUAD and transformed SCLC specimens. These findings provide a systems-level framework for transformation-associated molecular-state stratification and prioritize candidate regulatory features for prospective investigation of LUAD-to-SCLC lineage plasticity. The framework is intended for hypothesis generation; prospective studies with documented transformation outcomes are required to determine its clinical utility.

  Journal IF-equivalent: 5.1 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)
  Reference: Tang M, Yang J, Zhang X, Zhang B, Jiang L, Bao J, et al. Machine learning stratification of LUAD-to-SCLC transformation states and drug-response signatures. npj Syst Biol Appl. 2026 Oct 30 [Epub ahead of print]. doi:10.1038/s41540-026-00845-6.
  Checked: Abstract only
• An uncertainty-aware deep learning-based registration model for adaptive lung cancer radiotherapy
  Physics in Medicine and Biology · 2026-10-30 · Evidence: Model development and validation on imaging datasets
  Abstract

  Objective: To develop a deep learning (DL) based probabilistic 3D deformable image registration framework for uncertainty-aware dose accumulation in magnetic resonance imaging-guided radiotherapy (MRgRT) of lung cancer. Approach: We propose TransMorph-prob (TM-prob), a variational Bayesian model that predicts the voxel-wise mean and variance of dense displacement fields (DDFs). Two TM-prob models were trained on an internal CT dataset (725 patients) and a low-field MR-linac dataset (102 patients), and benchmarked against Monte Carlo dropout TransMorph (TM-MCD) and DIRUncertainty with B-spline initialization (ASDIR) on the DIRLAB 4DCT dataset (10 patients, 3000 landmarks), and an annotated MR-linac dataset (16 patients, 107 image pairs, 227 landmarks) with target and seven organ-at-risk (OAR) contours. Both datasets contained an additional 1239/13,289 algorithm-generated landmarks. Performance was evaluated using target registration error (TRE), Dice similarity coefficient (DSC), landmark- and voxel-wise expected calibration errors (LECE/ECE), and dose distributions derived from 2000 DDF samples per patient. Main results: On the DIRLAB dataset, TM-prob achieved a median TRE of \qty{1.8}{\mm}/\qty{2.8}{\mm} on manual/algorithm-generated landmarks, versus \qty{1.3}{\mm}/\qty{2.4}{\mm} for ASDIR and \qty{2.1}{\mm}/\qty{3.0}{\mm} for TM-MCD. On the MRI dataset, TM-prob achieved the median TRE of \qty{3.9}{\mm}/\qty{2.6}{\mm} and a mean DSC of 0.87, matching ASDIR (\qty{3.3}{\mm}/\qty{2.7}{\mm}, and DSC of 0.87) while outperforming TM-MCD (\qty{4.4}{\mm}/\qty{2.9}{\mm}, and 0.84). In uncertainty calibration, TM-prob achieved a LECE of \qty{1.74}{\mm}/\qty{0.30}{\mm} on MRI manual/algorithm-generated landmarks versus \qty{2.41}{\mm}/\qty{0.56}{\mm} for ASDIR and \qty{6.65}{\mm}/\qty{3.92}{\mm} for TM-MCD, and an average contour ECE of 5.8% versus 7.0% and 21.2%. Two patients with indistinct GTV boundaries exhibited substantially wider target D95 distributions, demonstrating that calibrated DDF uncertainty translates into clinically relevant dose-coverage uncertainty.

  Significance: TM-prob is an end-to-end DL model, achieving fast, well-calibrated, uncertainty-aware registration for lung cancer patients, enabling reliable DDF uncertainty propagation into dose accumulation for clinical decision-making in online adaptive radiotherapy.

  Journal IF-equivalent: 2.9 (OpenAlex 2-year mean citedness, value as of 2026-10-28, retrieved 2026-10-29; not the official Clarivate IF)
  Reference: Wei C, Radonic D, Klaar R, Hohmann N, Marschner S, Eze C, et al. An uncertainty-aware deep learning-based registration model for adaptive lung cancer radiotherapy. Phys Med Biol. 2026 Oct 30 [Epub ahead of print]. doi:10.1088/1361-6560/aebc09. PMID: 42962374.
  Checked: Abstract only

← Back to this issue