Shuai Feng

Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.

UNSTRUCTURED Cancer diagnosis depends on data from radiology, digital pathology, molecular profiling, laboratory testing, and longitudinal clinical records. AI performs well in selected tasks, but most systems remain narrow and disconnected from the iterative reasoning required in oncology. This Viewpoint defines an AI agent as a feedback-driven system that maintains task state, selects among governed tools, observes results, and revises its plan under explicit safety constraints. This definition separates agents from multimodal foundation models, retrieval-augmented generation, and fixed workflow automation. We organize the discussion across multimodal data collection, preprocessing, fusion and representation learning, and diagnostic decision support. We distinguished agent-level evidence, component- or infrastructure-level evidence, and prospective propositions throughout. Clinical translation will require resilient failure handling, guideline version control, prospective evaluation, computational and workflow feasibility, and clinician authority over final decisions. The near-term opportunity is therefore transparent and traceable clinical decision support rather than autonomous cancer diagnosis.

Lung cancer is the leading cause of cancer deaths worldwide. Although several lung cancer diagnostic methods are available for lung nodule biopsy, there are limitations in terms of accuracy, safety, and invasiveness. Transbronchial needle aspiration (TBNA) is a common method for diagnosing and treating lung cancer that involves a robot-assisted medical flexible needle moving along a curved three-dimensional trajectory, avoiding anatomical barriers to achieve clinically meaningful goals in humans. Inspired by the puncture angle between the needle tip and the vessel in venipuncture, we suggest that different orientations of the medical flexible needle puncture path affect the cost of the puncture trajectory and propose an effective puncture region based on the optimal puncture direction, which is a strategy based on imposing geometric constraints on the search space of the puncture direction, and based on this, we focused on the improved implementation of RCS*. Planning within the TBNA-based lung environment was performed using the rapidly exploring random tree (RRT), resolution-complete search (RCS), and RCS* (a resolution-optimal version of RCS) within an effective puncture region. The experimental results show that the optimal puncture direction corresponding to the lowest cost puncture trajectory is consistent among the three algorithms and RCS* is more efficient for planning. The experiments verified the feasibility and practicality of our proposed minimum puncture angle and puncture effective region and facilitated the study of the puncture direction of flexible needle puncture.

Background: Whether neoadjuvant chemotherapy (NAC) followed by interval debulking surgery (IDS) against primary debulking surgery (PDS) has a differential effect on prognosis due to Breast Cancer Susceptibility Genes (BRCA)1/2 mutations has not been confirmed by current studies.Methods: All patients included in this retrospective study were admitted to Qilu Hospital of Shandong University between January 2009 and June 2020, and germline BRCA1/2 mutation were tested. Patients in stage IIIB, IIIC, and IV, re-staged by International Federation of Gynecology and Obstetrics (FIGO) 2014, were selected for analysis. All patients with NAC received 1-5 cycles of platinum-containing (carboplatin, cisplatin, or nedaplatin) chemotherapy. Patients who received maintenance therapy after chemotherapy were not eligible for this study. All relevant medical records were collected.Results: A total of 322 patients were enrolled, including 112 patients with BRCA1/2 mutations (BRCAmut), and 210 patients with BRCA1/2 wild-type (BRCAwt). In the two groups, 40 BRCAmut patients (35.7%) and 69 BRCAwt patients (32.9%) received NAC. The progression-free survival (PFS) of BRCAmut patients was significantly reduced after NAC (median: 14.9 vs. 18.5 months; p=0.023); however, there was no difference in overall survival (OS) (median: 75.1 vs. 72.8 months; p=0.798). Whether BRCAwt patients received NAC had no significant effect on PFS (median: 13.5 vs. 16.0 months; p=0.780) or OS (median: 54.0 vs. 56.4 months; p=0.323). Multivariate analyses in BRCAmut patients showed that the predictors of prolonged PFS were PDS (p=0.001), the absence of residual lesions (p=0.012), and FIGO III stage (p=0.020); Besides, PARP inhibitor was the independent predictor for prolonged OS in BRCAmut patients (p=0.000), for BRCAwt patients, the absence of residual lesions (p=0.041) and history of PARP inhibitors (p=0.000) were beneficial factors for OS prolongation.Conclusions: For ovarian cancer patients with FIGO IIIB, IIIC, and IV, NAC-IDS did not adversely affect survival outcomes due to different BRCA1/2 germline mutational status.