cs.CVOct 19, 2025

Click, Predict, Trust: Clinician-Guided and Clinician-Evaluated AI Segmentation for Lung Cancer CT-Based Prognosis within the Knowledge-to-Action Framework

Authors: Mohammad R. Salmanpour, Sonya Falahati, Amir Hossein Pouria, Amin Mousavi, Somayeh Sadat Mehrnia, Morteza Alizadeh, Arman Gorji, Zeinab Farsangi, 

Organizations: Department of Basic and Translational Research, BC Cancer Research Institute, Vancouver, BC, Canada · Department of Radiology, University of British Columbia, Vancouver, BC, Canada · Technological Virtual Collaboration (TECVICO Corp.), Vancouver, BC, Canada · Amirkabir University of Technology, Department of Computer Engineering, Tehran, Iran · 

Abstract

Lung cancer remains the leading cause of cancer mortality, with CT imaging central to screening, prognosis, and treatment. Manual segmentation is variable and time-intensive, while deep learning (DL) offers automation but faces barriers to clinical adoption. Guided by the Knowledge-to-Action framework, this study develops a clinician-in-the-loop DL pipeline to enhance reproducibility, prognostic accuracy, and clinical trust. Multi-center CT data from 999 patients across 12 public datasets were analyzed using five DL models (3D Attention U-Net, ResUNet, VNet, ReconNet, SAM-Med3D), benchmarked against expert contours on whole and click-point cropped images. Segmentation reproducibility was assessed using 497 PySERA-extracted radiomic features via Spearman correlation, ICC, Wilcoxon tests, and MANOVA, while prognostic modeling compared supervised (SL) and semi-supervised learning (SSL) across 38 dimensionality reduction strategies and 24 classifiers. Six physicians qualitatively evaluated masks across seven domains, including clinical meaningfulness, boundary quality, prognostic value, trust, and workflow integration. VNet achieved the best performance (Dice = 0.83, IoU = 0.71), radiomic stability (mean correlation = 0.76, ICC = 0.65), and predictive accuracy under SSL (accuracy = 0.88, F1 = 0.83). SSL consistently outperformed SL across models. Radiologists favored VNet for peritumoral representation and smoother boundaries, preferring AI-generated initial masks for refinement rather than replacement. These results demonstrate that integrating VNet with SSL yields accurate, reproducible, and clinically trusted CT-based lung cancer prognosis, highlighting a feasible path toward physician-centered AI translation.

Explore similar work

CardsList
  1. Trusting Right Predictions for Wrong Reasons: A LIME Based Analysis of Deep Learning Interpretability in Lung Cancer Diagnosis

    Jun 14, 2026Samarpan Poudel, Vladislav D VekslerExplainable Artificial IntelligenceExplanation Stability

  2. Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset

    Oct 13, 2025Nivea Roy, Son Tran, Atul Sajjanhar +4Medical Image ClassificationOncology

  3. Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation

    May 2, 2026Suraj Pai, Thibault Heintz, Cosmin Ciausu +3VLM RobustnessImage Segmentation