Accuracy of deep neural learning models in the imaging prediction of pathological complete response after neoadjuvant chemoradiotherapy for locally advanced rectal cancer: a systematic review.

PURPOSE: Up to 15-27% of patients achieve pathologic complete response (pCR) following neoadjuvant chemoradiotherapy (CRT) for locally advanced rectal cancer (LARC). Deep neural learning (DL) algorithms have been suggested to be a useful adjunct to allow accurate prediction of pCR and to identify patients who could potentially avoid surgery. This systematic review aims to interrogate the accuracy of DL algorithms at predicting pCR. METHODS: Embase (PubMed, MEDLINE) databases and Google Scholar were searched to identify eligible English-language studies, with the search concluding in July 2022. Studies reporting on the accuracy of DL models in predicting pCR were selected for review and information pertaining to study characteristics and diagnostic measures was extracted from relevant studies. Risk of bias was evaluated using the Newcastle-Ottawa scale (NOS). RESULTS: Our search yielded 85 potential publications. Nineteen full texts were reviewed, and a total of 12 articles were included in this systematic review. There were six retrospective and six prospective cohort studies. The most common DL algorithm used was the Convolutional Neural Network (CNN). Performance comparison was carried out via single modality comparison. The median performance for each best-performing algorithm was an AUC of 0.845 (range 0.71-0.99) and Accuracy of 0.85 (0.83-0.98). CONCLUSIONS: There is a promising role for DL models in the prediction of pCR following neoadjuvant-CRT for LARC. Further studies are needed to provide a standardised comparison in order to allow for large-scale clinical application. PROPERO REGISTRATION: PROSPERO 2021 CRD42021269904 Available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021269904 .

Surgeon-performed ultrasound in a head and neck surgical oncology clinic: saving time and improving patient care.

INTRODUCTION: Surgeon-performed ultrasound (SUS) for head and neck masses is increasingly being performed by head and neck surgeons. This is the first study assessing its impact in a head and neck surgical oncology clinic, examining the effect on various parameters. METHODS: Retrospective analysis was conducted on a database, analysing and comparing all new patients reviewed 6 months prior to (pre-SUS group) and 6 months following (post-SUS group) the introduction of SUS to the outpatient head and neck surgical oncology clinic. The numbers of radiology imaging investigations (ordered through a medical imaging department), fine-needle aspirations (FNAs) performed, clinical appointments and time to definitive treatment decision were analysed and compared. RESULTS: A total of 365 patients were included: 169 in the pre-SUS group and 196 in the post-SUS group. There was a statistically significant difference in the number of total radiological imaging investigations performed (1.60 vs. 0.70, p < 0.00001), radiologist-performed FNAs (0.24 vs. 0.10, p = 0.0234), time for definitive treatment decision being made (16.4 days vs. 11.6 days, p = 0.04338), and number of clinical encounters (3.03 vs. 2.29, p < 0.00001). No statistically significant difference was observed in the number of head and neck surgical oncology clinic appointments (1.70 vs. 1.66, p = 0.6672). CONCLUSION: Surgeon-performed ultrasound reduces the number of radiological imaging investigations and FNAs performed, reduces time for definitive treatment decision being made, and reduces the number of clinical encounters for patients. This supports its use in head and neck cancer setting and has important implications for both patients and the health-care system.

Materials used for mastoid obliteration and its complications: a systematic review.

OBJECTIVE: The objectives of this review are to identify the types of materials with their associated complications and respective considerations when used to obliterate the mastoid cavity. METHODS: A systematic search was performed across PubMed, Embase, Medline and Cochrane databases from January 2009 to January 2020 for randomized controlled trials and observational studies of patients that underwent mastoid obliteration. Studies that fulfilled the inclusion criteria were screened and scored according to the MINORS and relevance scores to determine final inclusion. Types of complications were grouped into minor and major complications based on the Clavien-Dindo classification. RESULTS: Two thousand five hundred and seventy-eight ears were evaluated. There were a total of 165 (7.9%) minor and 142 (6.8%) major complications in the autologous group. Overall complication rate is 14.8%. The major complications were largely recurrent and residual disease requiring revision surgery. There were 10 (18.5%) minor complications and three (5.6%) major complications in the allogenic group. The cumulative complications risk is 24%. For the synthetic group, there were 39 (8.0%) minor and 34 (7.6%) major complications. The cumulative complication rate is 16.6%. CONCLUSION: Current evidence on materials for mastoid obliteration has been evolving. Each material has its strengths and limitations. The trend over the last decade favours the use of autologous materials. The principle of using a material remains being cautious of not reimplanting skin that can lead to the development of a cholesteatoma. The choice of materials is dependent on patient factors as well as the surgeons' preference and experience.