METHODS: External root resorption was simulated on 88 extracted premolar teeth using tungsten bur in different depths (0.5 mm, 1 mm, and 2 mm). All teeth were scanned using a Cone beam CT (Carestream Dental, Atlanta, GA). Afterward, a training (70%), validation (10%), and test (20%) dataset were established. The performance of four DLMs including Random Forest (RF) + Visual Geometry Group 16 (VGG), RF + EfficienNetB4 (EFNET), Support Vector Machine (SVM) + VGG, and SVM + EFNET) and four hybrid models (DLM + FST: (i) FS + RF + VGG, (ii) FS + RF + EFNET, (iii) FS + SVM + VGG and (iv) FS + SVM + EFNET) was compared. Five performance parameters were assessed: classification accuracy, F1-score, precision, specificity, and error rate. FST algorithms (Boruta and Recursive Feature Selection) were combined with the DLMs to assess their performance.

RESULTS: RF + VGG exhibited the highest performance in identifying ERR, followed by the other tested models. Similarly, FST combined with RF + VGG outperformed other models with classification accuracy, F1-score, precision, and specificity of 81.9%, weighted accuracy of 83%, and area under the curve (AUC) of 96%. Kruskal Wallis test revealed a significant difference (p = 0.008) in the prediction accuracy among the eight DLMs.

METHODS: Retrospective review of 119 consecutive paediatric patients referred for 18F-FDG-PET/CT at the Department of Nuclear Medicine of the National Cancer Institute, Putrajaya. All had DRE and underwent evaluation at the Paediatric Institute, Hospital Kuala Lumpur. Visually detected areas of 18F-FDG-PET/CT hypometabolism were correlated with clinical, MRI and VEM findings.

RESULTS: Hypometabolism was detected in 102/119 (86%) 18FFDG- PET/CT scans. The pattern of hypometabolism in 73 patients with normal MRI was focal unilobar in 16/73 (22%), multilobar unilateral in 8/73 (11%), bilateral in 27/73 (37%) and global in 5/73 (7%) of patients; whilst 17/73 (23%) showed normal metabolism. In 46 patients with lesions on MRI, 18F-FDG-PET/CT showed concordant localisation and lateralization of the EF in 30/46 (65%) patients, and bilateral or widespread hypometabolism in the rest. Addition of 18FFDG PET/CT impacted decision making in 66/119 (55%) of patients; 24/73 with non-lesional and 30/46 patients with lesional epilepsies were recommended for surgery or further surgical work up, whilst surgery was not recommended in 11/46 patients with lesional epilepsy due to bilateral or widespread hypometabolism. 25 patients subsequently underwent epilepsy surgery, with 16/25 becoming seizure free following surgery.

METHODS: A ball phantom was scanned using panoramic mode of the Planmeca ProMax 3D Mid CBCT unit (Planmeca, Helsinki, Finland) with standard exposure settings used in clinical practice (60 kV, 2 mA, and maximum FOV). An automated calculator algorithm was developed in MATLAB platform. Two parameters associated with panoramic image distortion such as balls diameter and distance between middle and tenth balls were measured. These automated measurements were compared with manual measurement using the Planmeca Romexis and ImageJ software.

METHODS: The 4-h our virtual meeting in October 2020 brought together 26 experts from 14 APAC countries to discuss APCCC 2019 recommendations. Presentations were prerecorded and viewed prior to the meeting. A postmeeting survey gathered views on current practice.

RESULTS: The meeting and survey highlighted several developments since APAC APCCC 2018. Increased access and use in the region of PSMA PET/CT imaging is providing additional diagnostic and staging information for advanced prostate cancer and influencing local and systemic therapy choices. Awareness of oligometastatic disease, although not clearly defined, is increasing. Novel androgen receptor pathway antagonists are expanding treatment options. Cost and access to contemporary treatments and technologies continue to be a significant factor influencing therapeutic decisions in the region. With treatment options increasing, multidisciplinary treatment planning, shared decision making, and informed choice remain critical. A discussion on the COVID-19 pandemic highlighted challenges for diagnosis, treatment, and clinical trials and new service delivery models that will continue beyond the pandemic.

METHODS: Positron emission tomography (PET) and computed tomography (CT) image data from 97 patients with LC and 77 patients with TB nodules were collected. One hundred radiomic features were extracted from both PET and CT imaging using the pyradiomics platform, and 2048 deep learning features were obtained through a residual neural network approach. Four models included traditional machine learning model with radiomic features as input (traditional radiomics), a deep learning model with separate input of image features (deep convolutional neural networks [DCNN]), a deep learning model with two inputs of radiomic features and deep learning features (radiomics-DCNN) and a deep learning model with inputs of radiomic features and deep learning features and clinical information (integrated model). The models were evaluated using area under the curve (AUC), sensitivity, accuracy, specificity, and F1-score metrics.

RESULTS: The results of the classification of TB nodules and LC showed that the integrated model achieved an AUC of 0.84 (0.82-0.88), sensitivity of 0.85 (0.80-0.88), and specificity of 0.84 (0.83-0.87), performing better than the other models.