AI decision support systems can assist clinicians in planning adaptive treatment strategies that can dynamically react to individuals’ cancer progression for effective personalized care. However, AI’s imperfections can lead to suboptimal therapeutics if clinicians over or under rely on AI. To investigate such collaborative decision-making process, we conducted a Human–AI interaction study on response-adaptive radiotherapy for non-small cell lung cancer and hepatocellular carcinoma. We investigated two levels of collaborative behavior: model-agnostic and model-specific; and found that Human–AI interaction is multifactorial and depends on the complex interrelationship between prior knowledge and preferences, patient’s state, disease site, treatment modality, model transparency, and AI’s learned behavior and biases. In summary, some clinicians may disregard AI recommendations due to skepticism; others will critically analyze AI recommendations on a case-by-case basis; clinicians will adjust their decisions if they find AI recommendations beneficial to patients; and clinician will disregard AI recommendations if deemed harmful or suboptimal and seek alternatives.

Gastric and esophageal tumors are diverse neoplasms that involve mucosal and submucosal tissue layers and include squamous cell carcinomas, adenocarcinomas, spindle cell neoplasms, neuroendocrine tumors, marginal B cell lymphomas, along with less common tumors. The worldwide burden of esophageal and gastric malignancies is significant, with esophageal and gastric cancer representing the ninth and fifth most common cancers, respectively. The approach to diagnosis and staging of these lesions is multimodal and includes a combination of gastrointestinal endoscopy, endoscopic ultrasound, and cross-sectional imaging. Likewise, therapy is multidisciplinary and combines therapeutic endoscopy, surgery, radiotherapy, and systemic chemotherapeutic tools. Future directions for diagnosis of esophageal and gastric malignancies are evolving rapidly and will involve advances in endoscopic and endosonographic techniques including tethered capsules, optical coherence tomography, along with targeted cytologic and serological analyses.

Contrast-enhanced breast MRI has an established role in aiding in the detection, evaluation, and management of breast cancer. This article discusses MRI sequences, the clinical utility of MRI, and how MRI has been evaluated for use in breast radiotherapy treatment planning. We highlight the contribution of MRI in the decision-making regarding selecting appropriate candidates for breast conservation therapy and review the emerging role of MRI-guided breast radiotherapy.

Purpose: Treatment options for pancreatic ductal adenocarcinoma (PDAC) are commonly limited for patients with advanced age due to medical comorbidities and/or poor performance status. These patients may not be candidates for more aggressive chemotherapy regimens and/or surgical resection leaving few, if any, other effective treatments. Ablative stereotactic MRI-guided adaptive radiation therapy (A-SMART) is both efficacious and safe for PDAC and can achieve excellent long-term local control, however, the appropriateness of A-SMART for elderly patients with inoperable PDAC is not well understood. Methods: A retrospective analysis was performed of inoperable non-metastatic PDAC patients aged 75 years or older treated on the MRIdian Linac at 2 institutions. Clinical outcomes of interest included overall survival (OS), progression-free survival (PFS), distant metastasis-free survival (DMFS), and locoregional (LRC). Toxicity was graded according to Common Terminology Criteria for Adverse Events (CTCAE, v5). Results: A total of 49 patients were evaluated with a median age of 81 years (range, 75-91) and a median follow-up of 14 months from diagnosis. PDAC was classified as locally advanced (46.9%), borderline resectable (36.7%), or medically inoperable (16.3%). Neoadjuvant chemotherapy was delivered to 84% of patients and all received A-SMART to a median 50 Gy (range, 40-50 Gy) in 5 fractions. 1 Year LRC, PFS, and OS were 88.9%, 53.8%, and 78.9%, respectively. Nine patients (18%) had resection after A-SMART and benefited from PFS improvement (26 vs 6 months, P = .01). ECOG PS <2 was the only predictor of improved OS on multivariate analysis. Acute and late grade 3 + toxicity rates were 8.2% and 4.1%, respectively. Conclusions: A-SMART is associated with encouraging LRC and OS in elderly patients with initially inoperable PDAC. This novel non-invasive treatment strategy appears to be well-tolerated in patients with advanced age and should be considered in this population that has limited treatment options.

Whether the therapeutic response of soft-tissue sarcoma to neoadjuvant treatment is predictive for clinical outcomes is unclear. Given the rarity of this disease and the confounding effects of chemotherapy, this study analyzes whether a favorable pathologic response (fPR) after neoadjuvant radiation therapy (RT) alone is associated with clinical benefits. An institutional review board-approved retrospective review was conducted on a database of patients with primary soft-tissue sarcoma treated at our institution between 1987 and 2015 with neoadjuvant RT alone followed by surgical resection. Time-to-event outcomes estimated with a Kaplan–Meier analysis included overall survival, progression-free survival (PFS), locoregional control, and distant control (DC). Cox regression analyses were performed to determine prognostic variables associated with clinical outcomes. Of the overall cohort of 315 patients, 181 patients (57%) were included in the primary analysis with documented pathologic necrosis (PN) rates (mean: 59%) and a median follow up from diagnosis of 48 months (range, 4-170 months). The median neoadjuvant RT dose was 50 Gy (range, 40-60 Gy), and the majority of patients had negative surgical margins (79%). Only 35 patients (19%) achieved a fPR (PN ≥95%), which was associated with a higher R0 resection rate (94% vs. 75%; P = .013), a significant 5-year PFS benefit (74% vs. 43%; P = .014), and a nonsignificant 5-year DC benefit (76% vs. 62%; P = .12) compared with PN <95%. On multivariable analysis, fPR was an independent predictor for PFS (hazard ratio: 0.47; 95% confidence interval, 0.25-0.90; P = .022). Achieving fPR with neoadjuvant RT alone is associated with a higher R0 resection rate and possible DC benefit, translating into a significant improvement in PFS. Further studies to improve pathologic response rates and prospectively validate this endpoint are warranted.