Surveillance imaging for patients with head and neck cancer treated with definitive radiotherapy: A partially observed Markov decision process model

Markov models for clinical decision-making in radiation oncology: A systematic review

The intrinsic stochasticity of patients' response to treatment is a major consideration for clinical decision-making in radiation therapy. Markov models are powerful tools to capture this stochasticity and render effective treatment decisions. This paper provides an overview of the Markov models for clinical decision analysis in radiation oncology. A comprehensive literature search was conducted within MEDLINE using PubMed, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Only studies published from 2000 to 2023 were considered. Selected publications were summarized in two categories: (i) studies that compare two (or more) fixed treatment policies using Monte Carlo simulation and (ii) studies that seek an optimal treatment policy through Markov Decision Processes (MDPs). Relevant to the scope of this study, 61 publications were selected for detailed review. The majority of these publications (n = 56) focused on comparative analysis of two or more fixed treatment policies using Monte Carlo simulation. Classifications based on cancer site, utility measures and the type of sensitivity analysis are presented. Five publications considered MDPs with the aim of computing an optimal treatment policy; a detailed statement of the analysis and results is provided for each work. As an extension of Markov model-based simulation analysis, MDP offers a flexible framework to identify an optimal treatment policy among a possibly large set of treatment policies. However, the applications of MDPs to oncological decision-making have been understudied, and the full capacity of this framework to render complex optimal treatment decisions warrants further consideration.

Review of reinforcement learning applications in segmentation, chemotherapy, and radiotherapy of cancer

Owing to early diagnosis and treatment of cancer as a prerequisite in recent times, the role of machine learning has been increased substantially. The mathematically powerful and optimized solutions for the detection and cure of cancer are constantly being explored and novel models based upon standard algorithms are also being developed. Leveraging one such solution is Reinforcement Learning (RL), which is a semi-supervised type of learning. The paper presents a detailed discussion on the various RL techniques, algorithms, and open issues, in addition to the review of literature for diagnosis and treatment of cancer. A smaller number of publications for diagnosis and treatment of cancer have been reported before 2011 but now after the success of Deep Learning (DL) and the advent of Deep Reinforcement Learning (DRL), the publications have grown in number from 2017 onwards. The scope of RL for cancer diagnosis and treatment is also demystified and provides the research community with the insights of how to formulate RL problem as a Cancer diagnostic problem. RL has been found successful for landmark detection in medical images and optimal control of drugs and radiations.

Post-treatment surveillance imaging in head and neck cancer: a systematic review

BACKGROUND

In patients treated for head and neck cancer, imaging studies are usually obtained within 3-6 months after treatment for assessment of treatment response. After 6 months, most guidelines advocate clinical follow-up, with imaging reserved for patients with clinically suspect or equivocal findings. However, some guidelines do recommend systematic imaging surveillance, and many clinicians tend to include some type of imaging in their follow-up schemes.

OBJECTIVES

This systematic review focuses on the usefulness of routine (systematic) post-treatment imaging surveillance of head and neck cancer beyond the first 3-6-month baseline imaging study.

METHODS

A systematic literature search was conducted using PubMed and Google Scholar. Additional studies were identified by reviewing reference lists. Only original studies and review papers were considered. Results obtained with systematic post-treatment surveillance imaging were compared to symptom-directed imaging and/or clinical finding-directed imaging.

RESULTS

Five hundred twenty-one records were identified through the database search, and 44 additional records were identified through other sources. Forty-eight articles were selected for the final review. Analysis of these records showed that almost half of cases of locoregional recurrences and/or metastases were only detected by imaging (40.9%), and the mean time of detection of recurrent or metastatic disease (11.5 months) was well beyond the period of the first post-treatment scan. Most authors reported superior results with PET-CT when compared to other imaging techniques.

CONCLUSION

Strong arguments were found in favor of systematic imaging surveillance in locoregional advanced head and neck cancer during at least one and preferably 2 years after treatment.

CRITICAL RELEVANCE STATEMENT

Analysis of the selected records showed that almost half of cases of locoregional recurrences and/or metastases were only detected by imaging. This systematic review suggests that imaging may currently be underused in the post-treatment surveillance of patients with head and neck cancer.

KEY POINTS

• This systematic review focuses on the usefulness of long-term systematic imaging surveillance in patients treated for head and neck cancer. • Analysis of 521 articles revealed that systematic imaging allowed the initial detection of locoregional recurrences and/or metastases in more than 40% of patients. • Imaging may currently be underused in the post-treatment surveillance of patients with advanced head and neck cancer.

Cost-Effectiveness Analysis of PET-CT Surveillance After Treatment of Human Papillomavirus-Positive Oropharyngeal Cancer

OBJECTIVE

To determine the cost-effectiveness of surveillance imaging with PET/CT scan among patients with human papillomavirus-positive oropharyngeal squamous cell carcinoma.

STUDY DESIGN

Cost-effectiveness analysis.

SETTING

Oncologic care centers in the United States with head and neck oncologic surgeons and physicians.

METHODS

We compared the cost-effectiveness of 2 posttreatment surveillance strategies: clinical surveillance with the addition of PET/CT scan versus clinical surveillance alone in human papillomavirus-positive oropharyngeal squamous cell carcinoma patients. We constructed a Markov decision model which was analyzed from a third-party payer's perspective using 1-year Markov cycles and a 30-year time horizon. Values for transition probabilities, costs, health care utilities, and their studied ranges were derived from the literature.

RESULTS

The incremental cost-effectiveness ratio for PET/CT with clinical surveillance versus clinical surveillance alone was $89,850 per quality-adjusted life year gained. Flexible fiberoptic scope exams during clinical surveillance would have to be over 51% sensitive or PET/CT scan cost would have to exceed $1678 for clinical surveillance alone to be more cost-effective. The willingness-to-pay threshold at which imaging surveillance was equally cost-effective to clinical surveillance was approximately $80,000/QALY.

CONCLUSION

Despite lower recurrence rates of human papillomavirus-positive oropharyngeal cancer, a single PET/CT scan within 6 months after primary treatment remains a cost-effective tool for routine surveillance when its cost does not exceed $1678. The cost-effectiveness of this strategy is also dependent on the clinical surveillance sensitivity (flexible fiberoptic pharyngoscopy), and willingness-to-pay thresholds which vary by country.

The Value of Surveillance Imaging of Oral Squamous Cell Carcinoma

The evaluation of surveillance imaging of OSCC patients is a difficult task physicians have to face daily. Multiple patients experience a recurrence of this disease, which underlines the importance of regular patient monitoring programs. Our study analysed the value of surveillance imaging, such as computed tomography (CT) and nuclear magnetic resonance imaging (NMRI), as a patient monitoring programme and its effectiveness in achieving improvement in early recurrence detection. The study comprised 125 patients, out of which 56 (n = 56) showed radiological and 69 (n = 69) showed clinical and radiological conspicuous patterns in domestic follow-ups, respectively. The use of CT and NMRI showed a significant dependence on the histological result (p = 0.03). However, the different groups showed no significant dependence on the histological result (p = 0.96). The distribution of the histological biopsies, which were taken due to radiological changes, were prone to wrong positive diagnoses (false positives) in 71 percent. To conclude, imaging modalities should be chosen for each patient individually to reduce false positives, improve the early detection of recurrence, and increase the cure rate.

Accuracy of fine-needle aspiration cytology in detecting cervical node metastasis after radiotherapy: Systematic review and meta-analysis

PURPOSE

To define the accuracy of fine-needle aspiration cytology (FNAC) in diagnosing persistent or recurrent neck metastases in previously irradiated patients.

METHODS

The study was performed according to the PRISMA-DTA guidelines.

RESULTS

A total of 382 FNACs were used for calculation of diagnostic accuracy parameters. The overall pooled sensitivity and specificity in detecting malignant nodes were 69.1% (95% CI: 56.3%-80.7%; I² = 79.5%) and 84.2% (95% CI: 71.8%-93.5%; I² = 87.0%), respectively. Cumulative diagnostic odds ratio (DOR) was 16.54 (95% CI: 4.89-38.99; I² = 65.8%), while cumulative positive and negative likelihood ratio (PLR and NLR) were 5.4 (95% CI: 2.3-11.2) and 0.37 (95% CI: 0.22-0.54), respectively.

CONCLUSIONS

FNAC alone could not guide the decision to perform a salvage neck dissection in previously irradiated patients, but its results should be assessed in relation to the specific clinical context.