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.

Role of Chemoradiation in the Adjuvant Treatment of Radically Resected Pancreatic Cancer Patients: A Mono-Institutional Retrospective Analysis.

INTRODUCTION: Pancreatic cancer (PC) represents an unfavorable prognosis condition, even in patients with resectable disease. The aim of this series was to investigate the role of treatment intensification with adjuvant chemoradiation (CRT) in radically resected PC patients. METHODS: Data from PC patients who underwent radical surgery, adjuvant chemotherapy (CT), and CRT throughout a 20-year period were retrospectively collected. Actuarial local control (LC) and the overall survival (OS) were the primary endpoints, with disease-free survival and metastasis-free survival (MFS) representing secondary endpoints. RESULTS: The analysis included 108 PC patients treated with adjuvant CRT and CT from January 2000 to August 2019. Median age was 66 years (range: 40-83), and all patients underwent radical surgical resection with adjuvant CT (88, 81.5%) plus concomitant CRT (101, 93.5%) or radiotherapy alone (7, 6.5%). The median dose delivered to the tumor bed was 50.4 Gy (range: 45-50.6 Gy), while median dose to regional lymphatic drainage stations was 39.6 Gy (range 39.6-45 Gy). Concomitant CT was a gemcitabine-based regimen in the vast majority of patients (87, 80.6%). Median follow-up time was 21 months; the 2- and 5-year LC rates were 75.8% and 59.1%, respectively. Perineural invasion at pathological assessment was found significantly associated with LC (p = 0.028). Median OS was 40 months with 2- and 5-year OS rates of 73.9% and 41.6%, respectively. CONCLUSIONS: The outcomes of this series suggest to investigate the possible impact of adding adjuvant CRT to CT in PC patients. Timing and combination of modern CRT with new systemic therapies need to be further investigated to personalize therapy and optimize clinical advantages.

Does restaging MRI radiomics analysis improve pathological complete response prediction in rectal cancer patients? A prognostic model development.

PURPOSE: Our study investigated the contribution that the application of radiomics analysis on post-treatment magnetic resonance imaging can add to the assessments performed by an experienced disease-specific multidisciplinary tumor board (MTB) for the prediction of pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC). MATERIALS AND METHODS: This analysis included consecutively retrospective LARC patients who obtained a complete or near-complete response after nCRT and/or a pCR after surgery between January 2010 and September 2019. A three-step radiomics features selection was performed and three models were generated: a radiomics model (rRM), a multidisciplinary tumor board model (yMTB) and a combined model (CM). The predictive performance of models was quantified using the receiver operating characteristic (ROC) curve, evaluating the area under curve (AUC). RESULTS: The analysis involved 144 LARC patients; a total of 232 radiomics features were extracted from the MR images acquired post-nCRT. The yMTB, rRM and CM predicted pCR with an AUC of 0.82, 0.73 and 0.84, respectively. ROC comparison was not significant (p = 0.6) between yMTB and CM. CONCLUSION: Radiomics analysis showed good performance in identifying complete responders, which increased when combined with standard clinical evaluation; this increase was not statistically significant but did improve the prediction of clinical response.

Could the conservative approach be considered safe in the treatment of locally advanced rectal cancer in case of a clinical near-complete or complete response? A retrospective analysis.

BACKGROUND: Conservative approach has emerged as an option for the management of rectal cancer (RC) patients with a near or complete clinical response after neoadjuvant chemoradiotherapy (nCRT). The aim of this study is to assess the impact of the conservative approach by comparing patients' survival outcomes and quality of life with those who had surgical resection. METHODS: A single-institution and retrospective study including RC patients who reached a near complete or complete clinical response after nCRT from January 2010 to September 2019. Conservative approaches included local excision or watch and wait strategy; surgery approaches included anterior resection or abdominal-perineal resection.Local regrowth (LR), overall survival, disease free survival, metastasis free survival and colostomy free survival were evaluated through Kaplan-Meier curves and compared trough log-rank tests. Quality of life was measured by the following validated questionnaires: EORTC QLC30, EORTC QLQ - CR29 and Fecal Incontinence Quality of Life scale. RESULTS: Overall 157 patients were analyzed: 105 (66,9%) underwent radical surgery and 52 (33,1%) had a conservative approach. With a median follow-up of 51 months, 2 patients in the surgical group had a local recurrence and 8 in the conservative group had a LR, respectively. Distance metastasis occurred in 7 and 1 patients of surgical and conservative group, respectively. No differences were detected in terms of survival outcomes except for colostomy free survival (p: 0,01). The conservative group showed better intestinal (p < 0.01) and sexual (p: 0,04) function and emotional status (p: 0,02). CONCLUSIONS: Conservative approach seems to be safe in terms of survival outcomes with a significant advantage on quality of life in RC patients who achieved clinical complete response after nCRT.

Thoracic outlet syndrome: wide literature for few cases. Status of the art.

Despite its low prevalence and incidence, considerable debate exists in the literature on thoracic outlet syndrome (TOS). From literature analysis on nerve entrapments, we realized that TOS is the second most commonly published entrapment syndrome in the literature (after carpal tunnel syndrome) and that it is even more reported than ulnar neuropathy at elbow, which, instead, is very frequent. Despite the large amount of articles, there is still controversy regarding its classification, clinical picture, diagnostic objective findings, diagnostic modalities, therapeutical strategies and outcomes. While some experts believe that TOS is underrated, overlooked and very frequent, others even doubt its existence as a nosological entity. In the attempt to shed more light on this condition, we performed a systematic review of the literature and report evidence and opinions around this controversial subject. Only articles focused on neurogenic TOS were considered. Understanding the status of the art and the underlying reasons of doubts and weaknesses could help clinical practice and set the stage for future research.

Secondary posterior interosseous nerve lesions associated with humeral fractures.

INTRODUCTION: Radial nerve lesions associated with humeral shaft fractures are the most common traumatic nerve lesions observed with long bone fractures. Secondary indirect posterior interosseous nerve (PIN) lesions can be associated with traumatic radial nerve palsy. The aim of this study was to identify cases of traumatic double-site radial nerve involvement through ultrasound (US). METHODS: Patients with traumatic radial nerve lesions referred to our laboratory from January 2010 to January 2014 were evaluated. RESULTS: Of the 35 patients, 18 had US evidence of a radial nerve lesion at the fracture site associated with secondary PIN involvement at the arcade of Frohse. CONCLUSIONS: Multiple-site nerve lesions are difficult to demonstrate through electrodiagnostic tests. In our case series, half of the patients with traumatic radial nerve damage had US evidence of PIN injury. Prospective studies with follow-up are needed to determine the clinical and prognostic relevance of this finding and the best therapeutic approach.

Electrophysiological study of the bulbocavernosus reflex: normative data.

In the clinical setting the bulbocavernosus reflex (BCR) is elicited by squeezing the glans penis and digitally palpating the contraction of the bulbocavernosus (BC) muscle. In neurophysiology the BCR is obtained by stimulating the dorsal nerve of the penis or clitoris and by recording the response from BC muscle and it should be performed in selected patients with suspected urinary, bowel, or sexual neurogenic dysfunction. The BCR is considered one of the sacral neurophysiological tests of the greatest clinical utility. Previous normative data were obtained on small samples. The aim of this study was to determine normative values for the BCR in a large sample of men. We studied a large population (105 men; mean age 53 years, range 19-73 years) without central or peripheral neurological diseases. In each subject the sacral reflex was elicited by electrical stimulation of the base of the dorsum penis and recorded using a surface electrode from the BC muscle. We recorded the latency, calculated at onset, and the maximal amplitude of response, calculated peak to peak. We were able to detect the BCR in all the men. No correlation between BCR latency and age was found (r=0.136; p=0.160). The mean onset latency value was 33.0±4.85 ms (mean±2SD, range 26.8-39.4). The mean amplitude value was 16.53±12.21 µV (mean±2SD, range 4.2-43.6). Our normative data on the BCR were similar to previously published data.

Ultrasound study is useful to discriminate between axonotmesis and neurotmesis also in very small nerves: a case of sensory digital ulnar branch study.

Discrimination between axonotmesis and neurotmesis is crucial in traumatic nerve injury. We present the case of a 43-year-old woman which presented hypoesthesia in the fourth and fifth right fingers, started after surgery for Dupuytren syndrome. At ultrasound study, the ulnar digital sensory branch was identified. Before the division into the two terminal branches, a neuroma was observed, while neurotmesis was excluded. This case shows the utility of ultrasonography in peripheral nervous system examination and the possibility of visualization of very small nerves and their terminal branches.