Delineation of clinical target volume for postoperative radiotherapy in stage IIIA-pN2 non-small-cell lung cancer

Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a first-line screening and diagnostic tool for prostate cancer, aiding in treatment selection and noninvasive radiotherapy guidance. However, the manual interpretation of MRI data is challenging and time-consuming, which may impact sensitivity and specificity. With recent technological advances, artificial intelligence (AI) in the form of computer-aided diagnosis (CAD) based on MRI data has been applied to prostate cancer diagnosis and treatment. Among AI techniques, deep learning involving convolutional neural networks contributes to detection, segmentation, scoring, grading, and prognostic evaluation of prostate cancer. CAD systems have automatic operation, rapid processing, and accuracy, incorporating multiple sequences of multiparametric MRI data of the prostate gland into the deep learning model. Thus, they have become a research direction of great interest, especially in smart healthcare. This review highlights the current progress of deep learning technology in MRI-based diagnosis and treatment of prostate cancer. The key elements of deep learning-based MRI image processing in CAD systems and radiotherapy of prostate cancer are briefly described, making it understandable not only for radiologists but also for general physicians without specialized imaging interpretation training. Deep learning technology enables lesion identification, detection, and segmentation, grading and scoring of prostate cancer, and prediction of postoperative recurrence and prognostic outcomes. The diagnostic accuracy of deep learning can be improved by optimizing models and algorithms, expanding medical database resources, and combining multi-omics data and comprehensive analysis of various morphological data. Deep learning has the potential to become the key diagnostic method in prostate cancer diagnosis and treatment in the future.

Supraclavicular Recurrence in Completely Resected (y)pN2 Non-Small Cell Lung Cancer: Implications for Postoperative Radiotherapy

Background: The clinical value and delineation of clinical target volume (CTV) of postoperative radiotherapy (PORT) in completely resected (y)pN2 non-small cell lung cancer (NSCLC) remain controversial. Investigations specifically focusing on the cumulative incidence and prognostic significance of initial disease recurrence at the supraclavicular region (SCR) in this disease population are seldom reported.

Methods: Consecutive patients with curatively resected (y)pN2 NSCLC who received adjuvant chemotherapy from January 2013 to December 2018 at our cancer center were retrospectively examined. Disease recurrence at the surgical margin, ipsilateral hilum, and/or mediastinum was defined as loco-regional recurrence (LRR). Disease recurrence beyond LRR and SCR, was defined as distant metastasis (DM). Overall survival (OS1 and OS2) were calculated from surgery and disease recurrence to death of any cause, in the entire cohort and in patients with recurrent disease, respectively.

Results: Among the 311 patients enrolled, PORT without elective supraclavicular nodal irradiation (ESRT) was performed in 94 patients and neoadjuvant chemotherapy was administered in 31 patients. With a median follow-up of 26 months, 203 patients developed recurrent disease, including 27 SCRs, among which 16 were without DM and 22 involved the ipsilateral supraclavicular region. The 1, 3, and 5-year cumulative incidence of SCR were 6.53, 13.0, and 24.7%, respectively. Chosen DM as a competing event, cN2, ypN2, not receiving lobectomy, and negative expression of CK7 were significantly associated with SCR using the univariate competing risk analysis, while ypN2 was identified as the only independent risk factor of SCR (p = 0.012). PORT significantly reduced LRR (p = 0.031) and prolonged OS1 (p = 0.018), but didn't impact SCR (p = 0.254). Pattern of failure analyses indicated that the majority of LRRs developed within the actuarial or virtual CTV of PORT, and 15 of the 22 ipsilateral SCRs could be covered by the virtual CTV of proposed ESRT. In terms of OS2, patients who developed SCR but without DM had intermediate prognosis, compared with those who had DM (p = 0.009) and those who had only LRR (p = 0.048).

Conclusions: SCR is not uncommon and has important prognostic significance in completely resected (y)pN2 NSCLC. The clinical value of PORT and ESRT in such patients need to be further investigated.