Citations

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

Objectives: Esophageal cancer (EC) often presents with dysphagia due to tumor obstruction. Esophageal stenting has the potential of palliating dysphagia, improving nutrition, preventing aspiration, and improving quality of life (QoL) but may be associated with risks. The present systematic review and guidelines are intended to assist treatment decision-making when considering stent placement in patients with EC based on the available evidence. Methods: Using the population, intervention, comparator, outcome, timing and study design framework, the evidence was assessed using Cochrane and PRISMA 2020 methodology. Eligible studies included prospective phase II-III trials and retrospective analyses published between January 1, 2010 and December 3, 2024 in the Ovid Medline database. These references were assessed by American Radium Society (ARS) Appropriate Use Criteria (AUC) methodology. RAND-UCLA consensus methodology was used to rate the appropriateness of the use of stents. Results: ARS AUC recommendations include (1) esophageal stenting is usually not appropriate in patients with early-stage EC in whom upfront surgery is planned; (2) esophageal stenting is usually not appropriate in patients with locally-advanced EC in whom neoadjuvant/perioperative therapy and esophagectomy or definitive chemoradiation is planned; (3) esophageal stenting may be appropriate in the setting of metastatic EC, especially in patients with short life expectancy with limited treatment options; (4) esophageal stenting is usually not appropriate for benign stricture following curative-intent therapy; (5) esophageal stenting is usually not appropriate for locally recurrent tumor in the setting of prior radiation; and (6) esophageal stenting is usually appropriate for management of tracheoesophageal fistula before curative-intent treatment. Conclusions: This ARS AUC summary provides guidelines for the use of esophageal stents in patients with EC provides based on available evidence.

ImportanceThere exists substantial heterogeneity in outcomes within T stages for patients with cutaneous squamous cell carcinoma (cSCC).ObjectiveTo determine whether a customized generative pretrained transformer model, trained on a comprehensive dataset with more than 1 trillion parameters and equipped with relevant focused context and retrieval augmented generation (RAG), could excel in aggregating and interpreting vast quantities of data to develop a novel class-based risk stratification system that outperforms the current standards.Design, Setting, and ParticipantsTo build the RAG knowledge base, a systematic review of the literature was conducted that addressed risk factors for poor outcomes in cSCC. Using the RAG-enabled generative pretrained transformer (GPT) model, we developed a novel class-based risk stratification system that assigned point values for risk factors, culminating in a GPT-based prognostication system called the artificial intelligence–derived risk score (AIRIS). The system’s performance was validated on a combined prospective and retrospective cohort of 2379 primary cSCC tumors (1996-2023) with at least 36 months of follow-up, against Brigham and Women’s Hospital (BWH) and American Joint Committee on Cancer Staging Manual, eighth edition (AJCC8) systems in stratifying risk for locoregional recurrence (LR), nodal metastasis (NM), distant metastasis (DM), and disease-specific death (DSD).Main Outcomes and MeasuresPerformance metrics evaluated included distinctiveness, homogeneity, and monotonicity, as defined by the AJCC8, as well as sensitivity, specificity, positive predictive value, negative predictive value, accuracy, the area under the receiver operating characteristic curve, and concordance.ResultsThe median age at diagnosis was 73 (IQR, 64-81) years, with 38.5% female patients and 61.5% male patients. The AIRIS prognostication system demonstrated superior sensitivity across all outcomes (LR, 49.1%; NM, 73.7%; DM, 82.5%; and DSD, 72.2%) and the highest area under the receiver operating characteristic curve values (LR, 0.69; NM, 0.81; DM, 0.85; and DSD, 0.80), indicating significantly enhanced discriminative capability compared with the BWH and AJCC8 systems. While all systems were comparably distinctive, the AIRIS prognostication system consistently demonstrated the lowest proportion of tumors exhibiting poor outcomes in low-risk categories, suggesting its improved homogeneity and monotonicity.Conclusions and RelevanceThe results of this diagnostic study suggest that the AIRIS system outperforms the existing BWH and AJCC8 prognostication systems, potentially providing a more effective tool for predicting poor outcomes in cSCC. This study illustrates the potential of large language models in refining prognostic tools, offering implications for treating patients with cancer.

This phase II trial of transoral surgery (TOS) with deintensified postoperative management in human papillomavirus (HPV)–associated oropharynx cancer (OPC) enrolled patients with resectable cT1-2 stage III/IV American Joint Committee on Cancer (AJCC) seventh edition p16+ OPC without matted neck nodes. Those with clear margins, 0-1 + nodes (LN), and no extranodal extension (ENE) were observed (arm A); those with clear margins, 2-4 + LN, or ENE ≤1 mm were randomly assigned to 50 Gy (arm B) or 60 Gy (arm C); and those with involved margins, >4 + LN, or >1 mm ENE received weekly cisplatin and 60-66 Gy (arm D). Among 359 evaluable patients, the 54-month progression-free (PFS) and overall survival (OS) were 90.6% (90% CI, 87.2% to 93.1%) and 95.3% (93.0% to 96.9%), respectively. The 54-month PFS by arm was A 93.2% (79.6% to 97.8%; all four recurrences among N1 patients), B 94.9% (89.7% to 97.5%), C 90.2% (82.7% to 94.6%), and D 85.5% (77.5% to 90.8%). The 54-month OS by arm was A 97.1% (85.7% to 99.4%), B 97.9% (93.5% to 99.3%), C 95.1% (90.1% to 97.6%), and D 92.5% (86.9% to 95.7%). PFS or OS did not differ by primary site or smoking history. TOS and neck dissection with deintensified postoperative management results in outstanding 54-month PFS and OS. Among patients with favorable pathologic characteristics, those with N1 disease are at risk of late recurrence without radiation.

BACKGROUND: Surgical intervention remains an important option in the management of vestibular schwannoma (VSs). Development of a systematic approach to choose the most appropriate route for this intervention, based on existing published evidence, is an important goal. OBJECTIVE: To review the literature published since the 2018 Congress of Neurological Surgeons Guideline on surgical intervention for patients with sporadic VSs and use this information to update that set of recommendations. METHODS: The literature in the PubMed and MEDLINE databases from January 2015 through May 20, 2022, was searched for manuscripts pertaining to surgical intervention for VSs. Those manuscripts meeting inclusion criteria were then analyzed for creation of recommendations in response to a set of updated questions. RESULTS: The resultant findings included a considerable amount of data that did not alter the recommendations form the 2018 publication on this topic. Thus, recommendations stating hearing preservation surgery through the middle fossa or retrosigmoid approach may be considered in individuals with good preoperative hearing as an alternative to simple observation remain. In addition, if microsurgical resection is necessary after stereotactic radiosurgery, it is recommended that patients be counseled that there is an increased likelihood of a subtotal resection and decreased facial nerve function. In some questions, insufficient data were present to create an answer and that is stated. CONCLUSION: This guideline demonstrates surgical intervention for VSs and represents a range of options, and the choice of the intervention depends on the specific aspects of the lesion and the individual that harbors them. Objective refinement of those choices will require thoughtful research design by investigations that wish to address those items for which we still have insufficient information. The full guideline can be seen online at https://www.cns.org/guidelines/treatment-adults-vestibular-schwannoma/7-surgical-resection-treatment-of-patients-with-ve-2

BACKGROUND: Given the increasing prevalence and shifting disease demographic of vestibular schwannoma toward smaller tumors in people with less advanced symptoms, increasing emphasis has been placed on functional hearing preservation. OBJECTIVE: To provide an update to the 2018 CNS Guideline on hearing preservation outcomes in patients with sporadic vestibular schwannoma. METHODS: Systematic review and clinical practice guideline summarizing data pertaining to hearing preservation outcomes within the first 10 years after contemporary stereotactic radiation, microsurgery, or observation with serial imaging. The analysis incorporates studies included in the 2018 guideline and additional literature published up to May 20, 2022, providing a comprehensive up-to-date review of published clinical outcome data over time. RESULTS: Pooled estimated rates of serviceable hearing preservation are presented for observation, radiosurgery, and microsurgery for adults with sporadic vestibular schwannoma who have documented serviceable hearing in the ipsilateral ear at the time of diagnosis. Overall estimated rates of maintaining serviceable hearing are 78% at 2 years, 59% at 5 years, and 47% at 10 years during observation; 71% at 2 years, 59% at 5 years, and 38% at 10 years after radiosurgery; and 48% at 2 years, 40% at 5 years, and 32% at 10 years after microsurgery. In addition, features portending hearing outcome among management modalities are reported to guide accurate patient counseling. CONCLUSION: Regardless of treatment modality, fewer than half of patients with sporadic vestibular schwannoma who present with serviceable hearing will maintain useful hearing by 10 years. Across all studies, microsurgery and radiosurgery seem to accelerate this decline over the natural history, although further research is needed given limitations of available evidence. The full guideline can be seen online at https://www.cns.org/guidelines/treatment-adults-vestibular-schwannoma/4-hearing-preservation-outcomes-in-patients-with-s

BACKGROUND: Intraoperative neuromonitoring (IONM) has become vital in the management of vestibular schwannoma (VS) with the paradigm shift from tumor eradication to functional preservation. Several facial nerve (FN) monitoring strategies have been explored over the past few decades ranging from free-running electromyography, direct nerve stimulation, continuous nerve stimulation, facial motor evoked potentials, blink reflex, and others. Hearing preservation surgery is guided primarily by far-field auditory brainstem response and real-time cochlear nerve action potentials. Given the heterogeneity in tumor and patient factors, it remains very difficult to accurately predict cranial nerve outcomes, regardless of the monitoring strategy. OBJECTIVE: To critically appraise literature regarding IONM during VS surgery and update the previous evidence-based clinical practice guideline. METHODS: This is a systematic review of the literature, incorporating articles from March 2015 to May 2022. Literature published before 2015 that would have been included in the previous Congress of Neurological Surgeons guideline was not searched again in this update. RESULTS: FN monitoring provides better functional outcomes compared with anatomic dissection alone and may guide the extent of tumor resection. While facial motor evoked potentials and free-running electromyography can provide continuous noninvasive FN monitoring, there are insufficient data to determine which more strongly correlates with facial function outcomes. Both electrophysiological data and tumor size correlate with facial function outcomes. The ideal hearing monitoring strategy remains unclear as there are insufficient data comparing cochlear nerve action potentials with far-field auditory brainstem response. All studies were graded as Class III evidence. CONCLUSION: IONM should be used in all VS cases. While the optimal FN and hearing monitoring strategy remains elusive, available data support the use of a combination of strategies, including preoperative tumor size, to maximize sensitivity and specificity. There remains a significant need for high-quality comparative studies to determine which intraoperative monitoring scheme can provide intraoperative guidance and predict postoperative outcome. The full guideline can be seen online at https://www.cns.org/guidelines/treatment-adults-vestibular-schwannoma/3-intraoperative-cranial-nerve-monitoring-in-manag