Explainable prediction model for the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma using CNN on CT images.

Several studies have emphasised how positive and negative human papillomavirus (HPV+ and HPV-, respectively) oropharyngeal squamous cell carcinoma (OPSCC) has distinct molecular profiles, tumor characteristics, and disease outcomes. Different radiomics-based prediction models have been proposed, by also using innovative techniques such as Convolutional Neural Networks (CNNs). Although some of these models reached encouraging predictive performances, there evidence explaining the role of radiomic features in achieving a specific outcome is scarce. In this paper, we propose some preliminary results related to an explainable CNN-based model to predict HPV status in OPSCC patients. We extracted the Gross Tumor Volume (GTV) of pre-treatment CT images related to 499 patients (356 HPV+ and 143 HPV-) included into the OPC-Radiomics public dataset to train an end-to-end Inception-V3 CNN architecture. We also collected a multicentric dataset consisting of 92 patients (43 HPV+ , 49 HPV-), which was employed as an independent test set. Finally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) technique to highlight the most informative areas with respect to the predicted outcome. The proposed model reached an AUC value of 73.50% on the independent test. As a result of the Grad-CAM algorithm, the most informative areas related to the correctly classified HPV+ patients were located into the intratumoral area. Conversely, the most important areas referred to the tumor edges. Finally, since the proposed model provided additional information with respect to the accuracy of the classification given by the visualization of the areas of greatest interest for predictive purposes for each case examined, it could contribute to increase confidence in using computer-based predictive models in the actual clinical practice.

Outcomes and toxicity following post-operative hypofractionated radiotherapy to the regional nodes and the breast or the chest wall in locally advanced breast cancer.

OBJECTIVES: We aimed to analyze the impact of a 3-week schedule of HypoFractionated (HF) radiotherapy (RT) after axillary dissection and breast surgery, in terms of safety and efficacy in patients with locally advanced breast cancer (BC). METHODS: Eligible patients were females with Stage IIA - IIIC BC who underwent axillary dissection and breast surgery, either quadrantectomy or mastectomy. HF RT was delivered in 15 or 16 fractions for a total dose of 40.05 Gy or 42.56 Gy, respectively, to the clavicular nodal region along with the whole breast (HF WBRT) or the chest wall (HF PMRT), according to the type of surgery. Locoregional recurrence (LRR), distant metastases-free survival (DMFS), overall survival (OS) and acute and late treatment-related toxicities were estimated. RESULTS: 57 patients with a median age of 60 years (32-85) were retrospectively analyzed. 34 (60%) of patients underwent breast conservative surgery in the form of quadrantectomy and 23 (40%) were offered radical mastectomy. All patients underwent hypofractionated regional nodal irradiation (HF RNI). 34 (60%) of them underwent HF WBRT, while 23 (40%) received HF PMRT.At a median follow-up of 80 months (30-113), the 7-year LRR-free survival was 93% (95% CI, 74%-95%). The same features for DMFS and OS were 76% (95% CI, 52%-78%) and 67% (95% CI, 50%-80%), respectively. Only one (2%) patient experienced G3 acute skin toxicity. No grade ≥2 late toxicity was observed. CONCLUSION: Our study shows that HF RNI with HF RT to the whole breast or the chest wall after breast surgery is safe and effective in patients with locally advanced BC. Longer follow-up is needed to strengthen further analyses on late toxicity and clinical outcomes. ADVANCES IN KNOWLEDGE: This paper adds to the evidence that post-operative RNI with WBRT or PMRT can be safely and effectively delivered with 3-week HF regimen. Locally advanced BC patients can be offered HF RT to the regional nodes and the breast or the chest wall regardless the type of surgery.