Potential Role of Generative Adversarial Networks in Enhancing Brain Tumors.

PURPOSE: Contrast enhancement is necessary for visualizing, diagnosing, and treating brain tumors. Through this study, we aimed to examine the potential role of general adversarial neural networks in generating artificial intelligence-based enhancement of tumors using a lightweight model. PATIENTS AND METHODS: A retrospective study was conducted on magnetic resonance imaging scans of patients diagnosed with brain tumors between 2020 and 2023. A generative adversarial neural network was built to generate images that would mimic the real contrast enhancement of these tumors. The performance of the neural network was evaluated quantitatively by VGG-16, ResNet, binary cross-entropy loss, mean absolute error, mean squared error, and structural similarity index measures. Regarding the qualitative evaluation, nine cases were randomly selected from the test set and were used to build a short satisfaction survey for experienced medical professionals. RESULTS: One hundred twenty-nine patients with 156 scans were identified from the hospital database. The data were randomly split into a training set and validation set (90%) and a test set (10%). The VGG loss function for training, validation, and test sets were 2,049.8, 2,632.6, and 4,276.9, respectively. Additionally, the structural similarity index measured 0.366, 0.356, and 0.3192, respectively. At the time of submitting the article, 23 medical professionals responded to the survey. The median overall satisfaction score was 7 of 10. CONCLUSION: Our network would open the door for using lightweight models in performing artificial contrast enhancement. Further research is necessary in this field to reach the point of clinical practicality.

Can Machine Learning Predict Favorable Outcome After Radiofrequency Ablation of Hepatocellular Carcinoma?

PURPOSE: The standard practice for limited-stage hepatocellular carcinoma (HCC) is the resection or the use of local ablative techniques, such as radiofrequency ablation (RFA). The outcome after RFA depends on a complex interaction between the patient's general condition, hepatic function, and disease stage. In this study, we aimed to explore using a machine learning model to predict the response. PATIENTS AND METHODS: A retrospective study was conducted for patients with RFA for a localized HCC between 2018 and 2022. The collected clinical, radiologic, and laboratory data were explored using Python and XGBoost. They were split into a training set (70%) and a validation set (30%). The primary end point of this study was to predict the probability of achieving favorable outcomes 12 months after RFA. Favorable outcomes were defined as the patient was alive and HCC was controlled. RESULTS: One hundred and eleven patients were eligible for the study. Males were 78 (70.3%) with a median age of 57 (range of 43-81) years. Favorable outcome was seen in 62 (55.9%) of the patients. The 1-year survival rate and control rate were 94.6%, and 61.3%, respectively. The final model harbored an accuracy and an AUC of 90.6% and 0.95, respectively, for the training set, while they were 78.9% and 0.80, respectively, for the validation set. CONCLUSION: Machine learning can be a predictive tool for the outcome after RFA in patients with HCC. Further validation by a larger study is necessary.

Management of cranial chondroblastoma in adults; a pooled analysis.

OBJECTIVES: Chondroblastoma is a rare bone tumour that often affects children more than adults. The adult cranial affection is a unique presentation of the disease (less than 2%) that mandates specific management. Through this pooled-analysis, we aimed to examine this disease group and obtain reliable scientific conclusions. METHODS: The literature was searched for case-reports of cranial chondroblastoma. Afterwards, a pooled analysis was done for the selected articles. The data in question were the patient's age, gender, disease site, modalities of treatment, disease control, salvage treatment, and disease-specific survival. RESULTS: 122 case reports were retrieved from the literature. The median age at diagnosis was 38.5 years. Up to the moment, the standard of care remains complete resection. The relapse-free survival was 29.5 months, with a three-year relapse rate of 9% and disease-specific mortality of 0%. Most of the relapses were salvaged excellently with excision. The strongest predictor for relapse was the post-resection residual disease, with three-years relapse rates of 23.8% and 2.4% for positive and negative residuals, respectively. Adjuvant Radiotherapy failed to improve the relapse rates. CONCLUSION: Complete surgical excision is the standard of care. Post-surgical residual is the only adverse prognostic factor that predicts poor disease control.

Correction to: Risk stratification of pediatric high-grade glioma: a newly proposed prognostic score.

The original version of this article unfortunately contained an error. The author apologizes for having provided an incorrect name: "Mohamed S. Zaghluol" should be "Mohamed S. Zaghloul". Given in this article is the correct author name.

New insights inside the interdigitating dendritic cell sarcoma-pooled analysis and review of literature.

Interdigitating dendritic cell sarcoma is a rare haematological neoplasm with high debatable management protocols. The data extracted from 127 case reports published between 1981 and 2018 were analysed. The median age at diagnosis was 58 years with a male to female ratio of 1.65:1. The median OS and PFS of IDCS were 12 and 6 months, respectively, with a disease-specific mortality rate of 36.4%. Two-thirds of patients had a localised disease, while 30% had a disseminated form with 1-year mortality rates of 21.1% and 78.9%, respectively. Twenty per cent of cases were associated with other malignancies. Histologically, the proliferation of large spindle-shaped cells with fascicular growth was described in 84.3% of cases. Based on Cox-regression model, surgical resection was the only treatment modality linked to survival improvement with no recorded survival benefits of radiotherapy and chemotherapy. The 1-year mortality rates in resected and non-resected disease were 17.8% and 63.2%, respectively (P < 0.0001).

Risk stratification of pediatric high-grade glioma: a newly proposed prognostic score.

OBJECTIVES: High-grade glioma (HGG) is a clinical challenge. Radiation Therapy Oncology Group Recursive Partitioning Analysis (RTOG-RPA) for HGG remains the standard for assessing the prognosis of adult HGG. This study assesses the validity of the RTOG-RPA to be applied to pediatric HGG. METHODS: A retrospective study was conducted on 59 pediatric HGG treated in the Children's Cancer Hospital, Egypt (CCHE) between 2007 and 2016. Several factors were studied as predictors for the disease survival, including age, gender, increased intracranial hypertension, tumor characteristics and pathology, CSF seeding, performance status, post-surgical residual, and radiation dose. The statistically significant results were integrated into a Cox-regression model to develop a prognostic risk score. RESULTS: Kaplan-Meier statistics identified 13 factors that impacted the overall survival. However, Cox model showed that the histological grade IV [HR 14.2, 95%CI; (3.5-57), P < 0.0001], thalamic infiltration [HR 8.7; 95%CI; (2.9-25.9), P < 0.0001], PS ≥ 60 [HR 0.317; 95%CI; (0.13-0.776); P = 0.012], and maximum tumor dimension > 3.3 cm [HR 10.2; 95%CI; (1.58-65.89); P = 0.015] were the independent variables that predicted the overall survival. A risk score was proposed based on the presence of one or more of these factors. The median OS for the low risk (score 0-1), the intermediate-low risk (score 2), the intermediate-high risk (score 3), and the high risk (score 4) were 40, 18.5, 9.5, and 2.5 months, respectively, (P < 0.0001). CONCLUSION: The proposed model and risk score could stratify pediatric patients as the RTOG-RPA do for the adults.

Dermatofibrosarcoma of The Breast - Case Report and Review of Literature.

Dermatofibrosarcoma protuberans is a rare form of soft tissue sarcoma that tends to invade and recur locally. The most common site of this disease is head, neck and extremities; however, the involvement of the breast has been reported. We present a case with a dermatofibrosarcoma of the breast that is composed of low-grade spindle cells which are positive for CD43. She was treated by wide surgical excision followed by adjuvant external beam irradiation at a dose of 60 Gray. After a follow-up of 24 months, no local-regional or distant recurrence was detected.

59 years old male with local advanced adenoid cystic carcinoma of the hypopharynx - A case report and a review of the literature.

Minor Salivary Gland tumours are rare, representing 2% of the head and neck tumours and less than 1% of hypopharyngeal cancers. The most common subtype of minor salivary gland tumours is adenoid cystic carcinoma. Although there are several case reports discussed it, there are only two reports discussing hypopharyngeal presentation in the literature, and they were treated by surgical resection. Despite that, our case report still to be unique as it presents a case of irresectable locally advanced tumour subjected to a trial of induction therapy.