Machine learning model to preoperatively predict T2/T3 staging of laryngeal and hypopharyngeal cancer based on the CT radiomic signature

OBJECTIVES

To develop and assess a radiomics-based prediction model for distinguishing T2/T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma (LHSCC) METHODS: A total of 118 patients with pathologically proven LHSCC were enrolled in this retrospective study. We performed feature processing based on 851 radiomic features derived from contrast-enhanced CT images and established multiple radiomic models by combining three feature selection methods and seven machine learning classifiers. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the models. The radiomic signature obtained from the optimal model and statistically significant morphological image characteristics were incorporated into the predictive nomogram. The performance of the nomogram was assessed by calibration curve and decision curve analysis.

RESULTS

Using analysis of variance (ANOVA) feature selection and logistic regression (LR) classifier produced the best model. The AUCs of the training, validation, and test sets were 0.919, 0.857, and 0.817, respectively. A nomogram based on the model integrating the radiomic signature and a morphological imaging characteristic (suspicious thyroid cartilage invasion) exhibited C-indexes of 0.899 (95% confidence interval (CI) 0.843-0.955), fitting well in calibration curves (p > 0.05). Decision curve analysis further confirmed the clinical usefulness of the nomogram.

CONCLUSIONS

The nomogram based on the radiomics model derived from contrast-enhanced CT images had good diagnostic performance for distinguishing T2/T3 staging of LHSCC.

CLINICAL RELEVANCE STATEMENT

Accurate T2/T3 staging assessment of LHSCC aids in determining whether laryngectomy or laryngeal preservation therapy should be performed. The nomogram based on the radiomics model derived from contrast-enhanced CT images has the potential to predict the T2/T3 staging of LHSCC, which can provide a non-invasive and robust approach for guiding the optimization of clinical decision-making.

KEY POINTS

• Combining analysis of variance with logistic regression yielded the optimal radiomic model. • A nomogram based on the CT-radiomic signature has good performance for differentiating T2 from T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma. • It provides a non-invasive and robust approach for guiding the optimization of clinical decision-making.

Comparison of the eighth version of the American Joint Committee on Cancer manual to the seventh version for colorectal cancer: A retrospective review of our data

AIM

To analyze the survival trends in colorectal cancer (CRC) based on the different classifications recommended by the seventh and eighth editions of the American Joint Committee on Cancer staging system (AJCC-7^th and AJCC-8^th).

METHODS

The database from our institution was queried to identify patients with pathologically confirmed stage 0-IV CRC diagnosed between 2006 and 2012. Data from 2080 cases were collected and 1090 cases were evaluated through standardized inclusion and exclusion criteria. CRC was staged by AJCC-7^th and then restaged by AJCC-8^th. Five-year disease-free survival (DFS) and overall survival (OS) were compared. SPSS 21.0 software was used for all data. DFS and OS were compared and analyzed by Kaplan-Meier and Log-rank test.

RESULTS

Linear regression and automatic linear regression showed lymph node positive functional equations by tumor-node-metastasis staging from AJCC-7^th and tumor-node-metastasis staging from AJCC-8^th. Neurological invasion, venous infiltration, lymphatic infiltration, and tumor deposition put forward stricter requirements for pathological examination in AJCC-8^th compared to AJCC-7^th. After re-analyzing our cohort with AJCC-8^th, the percentage of stage IVB cases decreased from 2.8% to 0.8%. As a result 2% of the cases were classified under the new IVC staging. DFS and OS was significantly shorter (P = 0.012) in stage IVC patients compared to stage IVB patients.

CONCLUSION

The addition of stage IVC in AJCC-8^th has shown that peritoneal metastasis has a worse prognosis than distant organ metastasis in our institution’s CRC cohort. Additional datasets should be analyzed to confirm these findings.

Improvements to the gastric cancer tumor-node-metastasis staging system based on computer-aided unsupervised clustering

Background

The Union for International Cancer Control (UICC) tumor-node-metastasis (TNM) classification is a key gastric cancer prognosis system. This study aimed to create a new TNM system to provide a reference for the clinical diagnosis and treatment of gastric cancer.

Methods

A review of gastric cancer patients’ records was conducted in The First Hospital of China Medical University and the Liaoning Cancer Hospital and Institute. Based on patients’ prognoses data, computer-aided unsupervised clustering was performed for all possible TNM staging situations to create a new staging division system.

Results

The primary outcome measure was 5-year survival, analyzed according to TNM classifications. Computer-aided unsupervised clustering for all TNM staging situations was used to create TNM division criteria that were more consistent with clinical situations. Furthermore, unsupervised clustering for the number of lymph node metastasis in the N stage led to the formulation of a classification method that differs from the existing N stage criteria, and unsupervised clustering for tumor size provided an additional reference for prognosis estimates.

Conclusions

Finally, we developed a TNM staging system based on the computer-aided unsupervised clustering method; this system was more in line with clinical prognosis data when compared with the 7th edition of UICC gastric cancer TNM classification.

Surgical procedure determination based on tumor-node-metastasis staging of gallbladder cancer

AIM: To investigate the impact of surgical procedures on prognosis of gallbladder cancer patients classified with the latest tumor-node-metastasis (TNM) staging system.

METHODS: A retrospective study was performed by reviewing 152 patients with primary gallbladder carcinoma treated at Peking Union Medical College Hospital from January 2003 to June 2013. Postsurgical follow-up was performed by telephone and outpatient visits. Clinical records were reviewed and patients were grouped based on the new edition of TNM staging system (AJCC, seventh edition, 2010). Prognoses were analyzed and compared based on surgical operations including simple cholecystectomy, radical cholecystectomy (or extended radical cholecystectomy), and palliative surgery. Simple cholecystectomy is, by definition, resection of the gallbladder fossa. Radical cholecystectomy involves a wedge resection of the gallbladder fossa with 2 cm non-neoplastic liver tissue; resection of a suprapancreatic segment of the extrahepatic bile duct and extended portal lymph node dissection may also be considered based on the patient’s circumstance. Palliative surgery refers to cholecystectomy with biliary drainage. Data analysis was performed with SPSS 19.0 software. Kaplan-Meier survival analysis and Logrank test were used for survival rate comparison. P < 0.05 was considered statistically significant.

RESULTS: Patients were grouped based on the new 7^th edition of TNM staging system, including 8 cases of stage 0, 10 cases of stage I, 25 cases of stage II, 21 cases of stage IIIA, 21 cases of stage IIIB, 24 cases of stage IVA, 43 cases of stage IVB. Simple cholecystectomy was performed on 28 cases, radical cholecystectomy or expanded gallbladder radical resection on 57 cases, and palliative resection on 28 cases. Thirty-nine cases were not operated. Patients with stages 0 and I disease demonstrated no statistical significant difference in survival time between those receiving radical cholecystectomy and simple cholecystectomy (P = 0.826). The prognosis of stage II patients with radical cholecystectomy was better than that of simple cholecystectomy. For stage III patients, radical cholecystectomy was significantly superior to other surgical options (P < 0.05). For stage IVA patients, radical cholecystectomy was not better than palliative resection and non-surgical treatment. For stage IVB, patients who underwent palliative resection significantly outlived those with non-surgical treatment (P < 0.01)

CONCLUSION: For stages 0 and I patients, simple cholecystectomy is the optimal surgical procedure, while radical cholecystectomy should be actively operated for stages II and III patients.