Citations

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence (AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: The deployment of the OCC system resulted in a 35.0% reduction in the false discovery rate, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs, improving contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation and reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVM hallucinations with ablation study; and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.

Abstract Purpose To describe the creation and clinical deployment of an integrated stand‐alone hybrid automated chart review platform that is comprised of a database, oncology information system (OIS) interfaces, and a user interface (UI). Methods A consensus checklist was developed to homogenize the practices of clinical physics staff and physics residents for all plan types. Critical review of the single checklist's items led to the creation of a new concept, the “plan attribute,” which permits specialization of the final checklist based on the characteristics of a particular plan. Only relevant and applicable tests are automatically populated to form a plan checklist based on plan attributes. Each populated checklist in this hybrid automation platform includes elements of full automation, steps or functions that use automation to augment a human input or effort, as well as steps completed by humans. Logging and categorizing of deficiencies found during the chart check was also implemented. Results Chart check data was analyzed for an over 4‐year time span starting from the clinical deployment of the tool in October 2020. This analysis included a total of 427 073 tests spread among 7882 initial chart checks. The recorded deficiencies at three triage levels showed 7116 minor errors, 679 major errors, and 71 plan rejections. The plan rejection level is the highest chart deficiency, which required the plan to be rejected and sent back for serious remediation and/or new plan generation. Conclusion This report describes the successful development and implementation of a hybrid‐automated chart checking program. The software leverages modern database and software design to improve the per case performance and experience of a multi‐user group. Chart check database permits high‐level review and improvement in all aspects of plan check and user performance.

The NCCN Guidelines for Thyroid Carcinoma address the management of different types of thyroid carcinoma, including papillary, follicular, oncocytic, medullary, and anaplastic carcinoma. The NCCN Thyroid Carcinoma Panel meets at least annually to review comments from reviewers within their institutions, examine relevant new data from publications and abstracts, and reevaluate and update their recommendations. These NCCN Guidelines Insights focus on the panel’s most recent recommendations regarding systemic therapies for thyroid carcinoma as well as the supporting clinical data.

AbstractBackgroundGastric cancer with synchronous peritoneal metastases is a debilitating disease with limited treatment options. This article describes an update of the 2018 Chicago Consensus guidelines addressing the management of gastric cancer with synchronous peritoneal metastases in line with the most recent evidence.MethodsA clinical management pathway was updated through two rounds of a Delphi consensus to assess agreement levels with pathway blocks. Supporting evidence underwent evaluation using a rapid literature review. Meta‐analyses were performed as appropriate.ResultsOverall, the level of evidence in this disease subset was low to moderate. Of 124 participants in the first round, 109 (88%) responded in the second round. Strong consensus (>90%) was achieved in six of eight blocks (75%) in rounds 1 and 2. A multidisciplinary preoperative assessment and diagnostic laparoscopy should be offered to all patients, whereas patients with a high burden of disease or progression should undergo nonsurgical management. Patients with stable/responsive disease and a low peritoneal carcinomatosis index should subsequently be offered treatment with regional therapeutic interventions and cytoreductive surgery. In patients who are cytology‐positive, systemic therapy can be used to convert them to cytology‐negative, with subsequent surgery offered according to the patient's goals of care. Meta‐analysis of observational and randomized control trials revealed a survival benefit with the addition of intraperitoneal chemotherapy to cytoreductive surgery (hazard ratio, 0.52).ConclusionsThe consensus‐driven clinical pathway for gastric cancer with synchronous peritoneal metastases offers vital clinical guidance for practitioners. There is a growing body of high‐quality evidence to support management strategies, and future clinical trials are eagerly awaited.

AbstractNeuroendocrine neoplasms (NENs) with peritoneal metastases (PM) represent a complex clinical challenge because of low incidence and heterogeneous phenotypes. This commentary describes the results of a national consensus aimed at addressing clinical management of patients with NENs and PM. An update of the 2018 Chicago consensus guidelines was conducted with a modified Delphi technique, which encompassed two rounds of voting. The levels of agreement for various pathway blocks were assessed, and key systemic therapy concepts were summarized by content experts. Supporting evidence was evaluated via a rapid literature review. Overall, the level of evidence for the management of PM in this disease was universally low. In total, 107 participants responded in the first round, with 88 of 107 (82%) participating in the second round. Strong consensus (>90%) was achieved in five of seven (71%) and seven of seven (100%) blocks in rounds 1 and 2, respectively. A multidisciplinary approach including psychosocial and wellness assessments received a strong positive recommendation. Management of NENs with PM was organized according to disease grade and symptom profiles. In grade 1 and 2 well‐differentiated NENs, cytoreductive surgery received strong support (>95%) after the management of functional syndromes (if present). For grade 3 well‐differentiated NENs, systemic therapy is the primary recommendation, with surgical resection considered in select cases. Given the limited evidence, the consensus‐driven clinical pathway offers vital clinical guidance for the management of NENs with PM. The need for high‐quality evidence remains critical to the field.

Abstract Purpose Lattice radiation therapy (LRT) is a form of spatially fractionated radiation therapy that allows increased total dose delivery aiming for improved treatment response without an increase in toxicities, commonly utilized for palliation of bulky tumors. The LRT treatment planning process is complex, while eligible patients often have an urgent need for expedited treatment start. In this study, we aimed to develop a simulation‐free workflow for volumetric modulated arc therapy (VMAT)‐based LRT planning via deep learning‐predicted synthetic CT (sCT) to expedite treatment initiation. Methods Two deep learning models were initially trained using 3D U‐Net architecture to generate sCT from diagnostic CTs (dCT) of the thoracic and abdomen regions using a training dataset of 50 patients. The models were then tested on an independent dataset of 15 patients using image similarity analysis assessing mean absolute error (MAE) and structural similarity index measure (SSIM) as metrics. VMAT‐based LRT plans were generated based on sCT and recalculated on the planning CT (pCT) for dosimetric accuracy comparison. Differences in dose volume histogram (DVH) metrics between pCT and sCT plans were assessed using the Wilcoxon signed‐rank test. Results The final sCT prediction model demonstrated high image similarity to pCT, with a MAE and SSIM of 38.93 ± 14.79 Hounsfield Units (HU) and 0.92 ± 0.05 for the thoracic region, and 73.60 ± 22.90 HU and 0.90 ± 0.03 for the abdominal region, respectively. There were no statistically significant differences between sCT and pCT plans in terms of organ‐at‐risk and target volume DVH parameters, including maximum dose (Dmax), mean dose (Dmean), dose delivered to 90% (D90%) and 50% (D50%) of target volume, except for minimum dose (Dmin) and (D10%). Conclusion With demonstrated high image similarity and adequate dose agreement between sCT and pCT, our study is a proof‐of‐concept for using deep learning predicted sCT for a simulation‐free treatment planning workflow for VMAT‐based LRT.

Background/Objectives: The accurate delineation of primary tumors (GTVp) and metastatic lymph nodes (GTVn) in head and neck (HN) cancers is essential for effective radiation treatment planning, yet remains a challenging and laborious task. This study aims to develop a deep-learning-based auto-segmentation (DLAS) model trained on external datasets with false-positive elimination using clinical diagnosis reports. Methods: The DLAS model was trained on a multi-institutional public dataset with 882 cases. Forty-four institutional cases were randomly selected as the external testing dataset. DLAS-generated GTVp and GTVn were validated against clinical diagnosis reports to identify false-positive and false-negative segmentation errors using two large language models: ChatGPT-4 and Llama-3. False-positive ruling out was conducted by matching the centroids of AI-generated contours with the slice locations or anatomical regions described in the reports. Performance was evaluated using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), and tumor detection precision. Results: ChatGPT-4 outperformed Llama-3 in accurately extracting tumor locations from the diagnostic reports. False-positive contours were identified in 15 out of 44 cases. The DSCmean of the DLAS contours for GTVp and GTVn increased from 0.68 to 0.75 and from 0.69 to 0.75, respectively, after the ruling-out process. Notably, the average HD95 value for GTVn decreased from 18.81 mm to 5.2 mm. Post ruling out, the model achieved 100% precision for GTVp and GTVn when compared with the results of physician-determined contours. Conclusions: The false-positive ruling-out approach based on diagnostic reports effectively enhances the precision of DLAS in the HN region. The model accurately identifies the tumor location and detects all false-negative errors.

Gastric cancer is the fifth leading cause of cancer-related deaths worldwide. Over 95% of gastric cancers are adenocarcinomas, which are typically classified based on anatomic location and histologic type. Gastric cancer generally carries a poor prognosis because it is often diagnosed at an advanced stage. Systemic therapy can provide palliation, improve survival, and enhance the quality of life in patients with locally advanced or metastatic disease. The implementation of biomarker testing has had a significant impact on clinical practice and patient care. Targeted therapies have demonstrated encouraging results in clinical trials for the treatment of patients with locally advanced or metastatic disease. This selection from the NCCN Clinical Practice Guidelines in Oncology for Gastric Cancer highlights recommendations for biomarker testing and discusses updates for the treatment of advanced disease, including peritoneal carcinoma as only disease and unresectable locally advanced, recurrent, or metastatic disease.

Objectives: Identifying patients’ advantageous radiotherapy modalities prior to CT simulation is challenging. This study aimed to develop a workflow using deep learning (DL)-predicted synthetic CT (sCT) for treatment modality comparison based solely on a diagnostic CT (dCT). Methods: A DL network, U-Net, was trained utilizing 46 thoracic cases from a public database to generate sCT images predicting planning CT (pCT) scans based on the latest dCT, and tested on 15 institutional patients. The sCT accuracy was evaluated against the corresponding pCT and a commercial algorithm deformed CT (MdCT) based on Mean Absolute Error (MAE) and Universal Quality Index (UQI). To determine advantageous treatment modality, clinical dose-volume histogram (DVH) metrics and Normal Tissue Complication Probability (NTCP) differences between proton and photon treatment plans were analyzed on the sCTs via concordance correlation coefficient (CCC). Results: The AI-generated sCTs closely resembled those of the commercial deformation algorithm in the tested cases. The differences in MAE and UQI values between the sCT-vs-pCT and MdCT-vs-pCT were 19.38 HU and 0.06, respectively. The mean absolute NTCP deviation between sCT and pCT was 1.54%, 0.21%, and 2.36% for esophagus perforation, lung pneumonitis, and heart pericarditis, respectively. The CCC between sCT and pCT was 0.90 for DVH metrics and 0.97 for NTCP, indicating moderate agreement for DVH metrics and substantial agreement. Conclusions: Radiation oncologists can potentially utilize this personalized sCT based approach as a clinical support tool to rapidly compare the treatment modality benefit during patient consultation and facilitate in-depth discussion on potential toxicities at a patient-specific level.

Background/Objectives: Exudative age-related macular degeneration (AMD) is a disease of choroidal neovascularization that causes blindness. Current treatments to preserve vision in this prevalent and blinding condition are repeat intraocular injections of anti-vascular endothelial growth factor medicines for a patient’s lifetime to preserve and prevent vision loss leading to blindness. Rifampicin, a small-molecule antibiotic, has previously been reported to exhibit anti-angiogenic properties and a topical safety profile that is well-tolerated. Based on this evidence, we investigated the feasibility of formulating rifamycin as an ophthalmic drop capable of delivering therapeutic concentrations to the posterior segment of the eye. Methods: Inhibition of neovascularization by administration of rifampicin was analyzed in the rat oxygen-induced retinopathy (OIR) and mouse laser-induced choroidal neovascularization (CNV) models. Pharmacokinetic (PK) studies were conducted in mice, rats, and rabbits by dosing various formulations containing rifampicin, and the compound was quantified by LC/MS analysis. Results: Results from dose escalation studies in the mouse laser-induced CNV model suggested the minimum effective dose of rifampicin required for inhibiting neovascularization in subretinal tissues to be 0.7 mg/kg, which is substantially lower than the 20 mg/kg dosage approved for infectious disease treatments. The previous studies did not report the minimum effective dose in the anti-angiogenesis effects. The effective area under the concentration-time curve (AUC) in the sub-retina was evaluated as 0.27 h·ng/mg. In rabbits, rifampicin was delivered to the sub-retina by a single topical application of various formulations in a dose-dependent manner. The topical application of the formulations containing 1% rifampicin, which was well-tolerated in clinical trials previously reported for ocular trachoma, achieved subretinal delivery approximately 2–32 times greater than the effective AUC. Plasma exposure of the compound by the topical application was evaluated to range approximately 0.5–10 ng/mL. Conclusions: Rifampicin was delivered to the sub-retina in rabbits with an efficiency greater than the effective dose required for inhibiting neovascularization. Limited amounts of plasma exposure by the topical application were detected. These results suggested the therapeutic potential of the rifampicin formulations for the topical treatment of exudative macular degeneration.